[test] tell Travis to install rtmpdump and add initial support to rtmp testing

.gitignore

@@ -11,7 +11,6 @@ MANIFEST
 README.txt
 youtube-dl.1
 youtube-dl.bash-completion
-youtube-dl.fish
 youtube-dl
 youtube-dl.exe
 youtube-dl.tar.gz
@@ -24,12 +23,6 @@ updates_key.pem
 *.vtt
 *.flv
 *.mp4
-*.m4a
-*.m4v
 *.part
-*.swp
 test/testdata
 .tox
-youtube-dl.zsh
-.idea
-.idea/*

.travis.yml

@@ -2,16 +2,16 @@ language: python
 python:
   - "2.6"
   - "2.7"
-  - "3.2"
   - "3.3"
-  - "3.4"
-  - "3.5"
-sudo: false
+before_install:
+  - sudo apt-get update -qq
+  - sudo apt-get install -qq rtmpdump
 script: nosetests test --verbose
 notifications:
   email:
     - filippo.valsorda@gmail.com
     - phihag@phihag.de
+    - jaime.marquinez.ferrandiz+travis@gmail.com
     - yasoob.khld@gmail.com
 #  irc:
 #    channels:

AUTHORS

@@ -1,146 +0,0 @@
-Ricardo Garcia Gonzalez
-Danny Colligan
-Benjamin Johnson
-Vasyl' Vavrychuk
-Witold Baryluk
-Paweł Paprota
-Gergely Imreh
-Rogério Brito
-Philipp Hagemeister
-Sören Schulze
-Kevin Ngo
-Ori Avtalion
-shizeeg
-Filippo Valsorda
-Christian Albrecht
-Dave Vasilevsky
-Jaime Marquínez Ferrándiz
-Jeff Crouse
-Osama Khalid
-Michael Walter
-M. Yasoob Ullah Khalid
-Julien Fraichard
-Johny Mo Swag
-Axel Noack
-Albert Kim
-Pierre Rudloff
-Huarong Huo
-Ismael Mejía
-Steffan 'Ruirize' James
-Andras Elso
-Jelle van der Waa
-Marcin Cieślak
-Anton Larionov
-Takuya Tsuchida
-Sergey M.
-Michael Orlitzky
-Chris Gahan
-Saimadhav Heblikar
-Mike Col
-Oleg Prutz
-pulpe
-Andreas Schmitz
-Michael Kaiser
-Niklas Laxström
-David Triendl
-Anthony Weems
-David Wagner
-Juan C. Olivares
-Mattias Harrysson
-phaer
-Sainyam Kapoor
-Nicolas Évrard
-Jason Normore
-Hoje Lee
-Adam Thalhammer
-Georg Jähnig
-Ralf Haring
-Koki Takahashi
-Ariset Llerena
-Adam Malcontenti-Wilson
-Tobias Bell
-Naglis Jonaitis
-Charles Chen
-Hassaan Ali
-Dobrosław Żybort
-David Fabijan
-Sebastian Haas
-Alexander Kirk
-Erik Johnson
-Keith Beckman
-Ole Ernst
-Aaron McDaniel (mcd1992)
-Magnus Kolstad
-Hari Padmanaban
-Carlos Ramos
-5moufl
-lenaten
-Dennis Scheiba
-Damon Timm
-winwon
-Xavier Beynon
-Gabriel Schubiner
-xantares
-Jan Matějka
-Mauroy Sébastien
-William Sewell
-Dao Hoang Son
-Oskar Jauch
-Matthew Rayfield
-t0mm0
-Tithen-Firion
-Zack Fernandes
-cryptonaut
-Adrian Kretz
-Mathias Rav
-Petr Kutalek
-Will Glynn
-Max Reimann
-Cédric Luthi
-Thijs Vermeir
-Joel Leclerc
-Christopher Krooss
-Ondřej Caletka
-Dinesh S
-Johan K. Jensen
-Yen Chi Hsuan
-Enam Mijbah Noor
-David Luhmer
-Shaya Goldberg
-Paul Hartmann
-Frans de Jonge
-Robin de Rooij
-Ryan Schmidt
-Leslie P. Polzer
-Duncan Keall
-Alexander Mamay
-Devin J. Pohly
-Eduardo Ferro Aldama
-Jeff Buchbinder
-Amish Bhadeshia
-Joram Schrijver
-Will W.
-Mohammad Teimori Pabandi
-Roman Le Négrate
-Matthias Küch
-Julian Richen
-Ping O.
-Mister Hat
-Peter Ding
-jackyzy823
-George Brighton
-Remita Amine
-Aurélio A. Heckert
-Bernhard Minks
-sceext
-Zach Bruggeman
-Tjark Saul
-slangangular
-Behrouz Abbasi
-ngld
-nyuszika7h
-Shaun Walbridge
-Lee Jenkins
-Anssi Hannula
-Lukáš Lalinský
-Qijiang Fan

CHANGELOG

@@ -0,0 +1,14 @@
+2013.01.02  Codename: GIULIA
+
+    * Add support for ComedyCentral clips <nto>
+    * Corrected Vimeo description fetching <Nick Daniels>
+    * Added the --no-post-overwrites argument <Barbu Paul - Gheorghe>
+    * --verbose offers more environment info
+    * New info_dict field: uploader_id
+    * New updates system, with signature checking
+    * New IEs: NBA, JustinTV, FunnyOrDie, TweetReel, Steam, Ustream
+    * Fixed IEs: BlipTv
+    * Fixed for Python 3 IEs: Xvideo, Youku, XNXX, Dailymotion, Vimeo, InfoQ
+    * Simplified IEs and test code
+    * Various (Python 3 and other) fixes
+    * Revamped and expanded tests

CONTRIBUTING.md

@@ -1,140 +0,0 @@
-**Please include the full output of youtube-dl when run with `-v`**.
-
-The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
-
-Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
-
-### Is the description of the issue itself sufficient?
-
-We often get issue reports that we cannot really decipher. While in most cases we eventually get the required information after asking back multiple times, this poses an unnecessary drain on our resources. Many contributors, including myself, are also not native speakers, so we may misread some parts.
-
-So please elaborate on what feature you are requesting, or what bug you want to be fixed. Make sure that it's obvious
-
-- What the problem is
-- How it could be fixed
-- How your proposed solution would look like
-
-If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
-
-For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
-
-If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
-
-**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
-
-###  Are you using the latest version?
-
-Before reporting any issue, type `youtube-dl -U`. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
-
-###  Is the issue already documented?
-
-Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
-
-###  Why are existing options not enough?
-
-Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
-
-###  Is there enough context in your bug report?
-
-People want to solve problems, and often think they do us a favor by breaking down their larger problems (e.g. wanting to skip already downloaded files) to a specific request (e.g. requesting us to look whether the file exists before downloading the info page). However, what often happens is that they break down the problem into two steps: One simple, and one impossible (or extremely complicated one).
-
-We are then presented with a very complicated request when the original problem could be solved far easier, e.g. by recording the downloaded video IDs in a separate file. To avoid this, you must include the greater context where it is non-obvious. In particular, every feature request that does not consist of adding support for a new site should contain a use case scenario that explains in what situation the missing feature would be useful.
-
-###  Does the issue involve one problem, and one problem only?
-
-Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
-
-In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
-
-###  Is anyone going to need the feature?
-
-Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
-
-###  Is your question about youtube-dl?
-
-It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
-
-# DEVELOPER INSTRUCTIONS
-
-Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
-
-To run youtube-dl as a developer, you don't need to build anything either. Simply execute
-
-    python -m youtube_dl
-
-To run the test, simply invoke your favorite test runner, or execute a test file directly; any of the following work:
-
-    python -m unittest discover
-    python test/test_download.py
-    nosetests
-
-If you want to create a build of youtube-dl yourself, you'll need
-
-* python
-* make
-* pandoc
-* zip
-* nosetests
-
-### Adding support for a new site
-
-If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
-
-1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
-2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
-3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
-4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
-    ```python
-    # coding: utf-8
-    from __future__ import unicode_literals
-
-    from .common import InfoExtractor
-
-
-    class YourExtractorIE(InfoExtractor):
-        _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
-        _TEST = {
-            'url': 'http://yourextractor.com/watch/42',
-            'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
-            'info_dict': {
-                'id': '42',
-                'ext': 'mp4',
-                'title': 'Video title goes here',
-                'thumbnail': 're:^https?://.*\.jpg$',
-                # TODO more properties, either as:
-                # * A value
-                # * MD5 checksum; start the string with md5:
-                # * A regular expression; start the string with re:
-                # * Any Python type (for example int or float)
-            }
-        }
-
-        def _real_extract(self, url):
-            video_id = self._match_id(url)
-            webpage = self._download_webpage(url, video_id)
-
-            # TODO more code goes here, for example ...
-            title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
-
-            return {
-                'id': video_id,
-                'title': title,
-                'description': self._og_search_description(webpage),
-                # TODO more properties (see youtube_dl/extractor/common.py)
-            }
-    ```
-5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
-6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
-7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
-8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
-9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
-
-        $ git add youtube_dl/extractor/__init__.py
-        $ git add youtube_dl/extractor/yourextractor.py
-        $ git commit -m '[yourextractor] Add new extractor'
-        $ git push origin yourextractor
-
-10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
-
-In any case, thank you very much for your contributions!
-

LATEST_VERSION

@@ -0,0 +1 @@
+2012.12.99

MANIFEST.in

@@ -2,6 +2,4 @@ include README.md
 include test/*.py
 include test/*.json
 include youtube-dl.bash-completion
-include youtube-dl.fish
 include youtube-dl.1
-recursive-include docs Makefile conf.py *.rst

Makefile

@@ -1,14 +1,15 @@
-all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
+all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
-	find . -name "*.pyc" -delete
+	rm -rf youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
 
-PREFIX ?= /usr/local
-BINDIR ?= $(PREFIX)/bin
-MANDIR ?= $(PREFIX)/man
-SHAREDIR ?= $(PREFIX)/share
-PYTHON ?= /usr/bin/env python
+cleanall: clean
+	rm -f youtube-dl youtube-dl.exe
+
+PREFIX=/usr/local
+BINDIR=$(PREFIX)/bin
+MANDIR=$(PREFIX)/man
+PYTHON=/usr/bin/env python
 
 # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
 ifeq ($(PREFIX),/usr)
@@ -21,36 +22,23 @@ else
 	endif
 endif
 
-install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
+install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
 	install -d $(DESTDIR)$(BINDIR)
 	install -m 755 youtube-dl $(DESTDIR)$(BINDIR)
 	install -d $(DESTDIR)$(MANDIR)/man1
 	install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1
 	install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
 	install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
-	install -d $(DESTDIR)$(SHAREDIR)/zsh/site-functions
-	install -m 644 youtube-dl.zsh $(DESTDIR)$(SHAREDIR)/zsh/site-functions/_youtube-dl
-	install -d $(DESTDIR)$(SYSCONFDIR)/fish/completions
-	install -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish
-
-codetest:
-	flake8 .
 
 test:
 	#nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
 	nosetests --verbose test
-	$(MAKE) codetest
-
-ot: offlinetest
-
-offlinetest: codetest
-	nosetests --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py
 
 tar: youtube-dl.tar.gz
 
-.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest supportedsites
+.PHONY: all clean install test tar bash-completion pypi-files
 
-pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
+pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1
 
 youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	zip --quiet youtube-dl youtube_dl/*.py youtube_dl/*/*.py
@@ -61,38 +49,20 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	chmod a+x youtube-dl
 
 README.md: youtube_dl/*.py youtube_dl/*/*.py
-	COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
-
-CONTRIBUTING.md: README.md
-	python devscripts/make_contributing.py README.md CONTRIBUTING.md
-
-supportedsites:
-	python devscripts/make_supportedsites.py docs/supportedsites.md
+	COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
 
 README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 
 youtube-dl.1: README.md
-	python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
-	pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
-	rm -f youtube-dl.1.temp.md
+	pandoc -s -f markdown -t man README.md -o youtube-dl.1
 
 youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
 	python devscripts/bash-completion.py
 
 bash-completion: youtube-dl.bash-completion
 
-youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
-	python devscripts/zsh-completion.py
-
-zsh-completion: youtube-dl.zsh
-
-youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
-	python devscripts/fish-completion.py
-
-fish-completion: youtube-dl.fish
-
-youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
+youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
 	@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \
 		--exclude '*.kate-swp' \
@@ -102,10 +72,8 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		--exclude '__pycache' \
 		--exclude '.git' \
 		--exclude 'testdata' \
-		--exclude 'docs/_build' \
 		-- \
-		bin devscripts test youtube_dl docs \
-		LICENSE README.md README.txt \
-		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
-		youtube-dl.zsh youtube-dl.fish setup.py \
+		bin devscripts test youtube_dl \
+		CHANGELOG LICENSE README.md README.txt \
+		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion setup.py \
 		youtube-dl

devscripts/bash-completion.in

@@ -1,21 +1,10 @@
 __youtube_dl()
 {
-    local cur prev opts fileopts diropts keywords
+    local cur prev opts
     COMPREPLY=()
     cur="${COMP_WORDS[COMP_CWORD]}"
-    prev="${COMP_WORDS[COMP_CWORD-1]}"
     opts="{{flags}}"
-    keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
-    fileopts="-a|--batch-file|--download-archive|--cookies|--load-info"
-    diropts="--cache-dir"
-
-    if [[ ${prev} =~ ${fileopts} ]]; then
-        COMPREPLY=( $(compgen -f -- ${cur}) )
-        return 0
-    elif [[ ${prev} =~ ${diropts} ]]; then
-        COMPREPLY=( $(compgen -d -- ${cur}) )
-        return 0
-    fi
+    keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater"
 
     if [[ ${cur} =~ : ]]; then
         COMPREPLY=( $(compgen -W "${keywords}" -- ${cur}) )

devscripts/bash-completion.py

@@ -1,27 +1,24 @@
 #!/usr/bin/env python
-from __future__ import unicode_literals
-
 import os
 from os.path import dirname as dirn
 import sys
 
-sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
+sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
 import youtube_dl
 
 BASH_COMPLETION_FILE = "youtube-dl.bash-completion"
 BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
 
-
 def build_completion(opt_parser):
     opts_flag = []
     for group in opt_parser.option_groups:
         for option in group.option_list:
-            # for every long flag
+            #for every long flag
             opts_flag.append(option.get_opt_string())
     with open(BASH_COMPLETION_TEMPLATE) as f:
         template = f.read()
     with open(BASH_COMPLETION_FILE, "w") as f:
-        # just using the special char
+        #just using the special char
         filled_template = template.replace("{{flags}}", " ".join(opts_flag))
         f.write(filled_template)
 

devscripts/buildserver.py

@@ -142,7 +142,7 @@ def win_service_set_status(handle, status_code):
 
 def win_service_main(service_name, real_main, argc, argv_raw):
     try:
-        # args = [argv_raw[i].value for i in range(argc)]
+        #args = [argv_raw[i].value for i in range(argc)]
         stop_event = threading.Event()
         handler = HandlerEx(functools.partial(stop_event, win_service_handler))
         h = advapi32.RegisterServiceCtrlHandlerExW(service_name, handler, None)
@@ -233,7 +233,6 @@ def rmtree(path):
 
 #==============================================================================
 
-
 class BuildError(Exception):
     def __init__(self, output, code=500):
         self.output = output
@@ -370,7 +369,7 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea
 
 
 class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
-    actionDict = {'build': Builder, 'download': Builder}  # They're the same, no more caching.
+    actionDict = { 'build': Builder, 'download': Builder } # They're the same, no more caching.
 
     def do_GET(self):
         path = urlparse.urlparse(self.path)

devscripts/check-porn.py

@@ -1,12 +1,8 @@
 #!/usr/bin/env python
-from __future__ import unicode_literals
 
 """
 This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
 if we are not 'age_limit' tagging some porn site
-
-A second approach implemented relies on a list of porn domains, to activate it
-pass the list filename as the only argument
 """
 
 # Allow direct execution
@@ -15,42 +11,25 @@ import sys
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import get_testcases
-from youtube_dl.utils import compat_urllib_parse_urlparse
 from youtube_dl.utils import compat_urllib_request
 
-if len(sys.argv) > 1:
-    METHOD = 'LIST'
-    LIST = open(sys.argv[1]).read().decode('utf8').strip()
-else:
-    METHOD = 'EURISTIC'
-
 for test in get_testcases():
-    if METHOD == 'EURISTIC':
-        try:
-            webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
-        except Exception:
-            print('\nFail: {0}'.format(test['name']))
-            continue
+    try:
+        webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
+    except:
+        print('\nFail: {0}'.format(test['name']))
+        continue
 
-        webpage = webpage.decode('utf8', 'replace')
+    webpage = webpage.decode('utf8', 'replace')
 
-        RESULT = 'porn' in webpage.lower()
-
-    elif METHOD == 'LIST':
-        domain = compat_urllib_parse_urlparse(test['url']).netloc
-        if not domain:
-            print('\nFail: {0}'.format(test['name']))
-            continue
-        domain = '.'.join(domain.split('.')[-2:])
-
-        RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
-
-    if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] or
-                   test['info_dict']['age_limit'] != 18):
+    if 'porn' in webpage.lower() and ('info_dict' not in test
+                                      or 'age_limit' not in test['info_dict']
+                                      or test['info_dict']['age_limit'] != 18):
         print('\nPotential missing age_limit check: {0}'.format(test['name']))
 
-    elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] and
-                         test['info_dict']['age_limit'] == 18):
+    elif 'porn' not in webpage.lower() and ('info_dict' in test and
+                                            'age_limit' in test['info_dict'] and
+                                            test['info_dict']['age_limit'] == 18):
         print('\nPotential false negative: {0}'.format(test['name']))
 
     else:

devscripts/fish-completion.in

@@ -1,5 +0,0 @@
-
-{{commands}}
-
-
-complete --command youtube-dl --arguments ":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"

devscripts/fish-completion.py

@@ -1,48 +0,0 @@
-#!/usr/bin/env python
-from __future__ import unicode_literals
-
-import optparse
-import os
-from os.path import dirname as dirn
-import sys
-
-sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
-import youtube_dl
-from youtube_dl.utils import shell_quote
-
-FISH_COMPLETION_FILE = 'youtube-dl.fish'
-FISH_COMPLETION_TEMPLATE = 'devscripts/fish-completion.in'
-
-EXTRA_ARGS = {
-    'recode-video': ['--arguments', 'mp4 flv ogg webm mkv', '--exclusive'],
-
-    # Options that need a file parameter
-    'download-archive': ['--require-parameter'],
-    'cookies': ['--require-parameter'],
-    'load-info': ['--require-parameter'],
-    'batch-file': ['--require-parameter'],
-}
-
-
-def build_completion(opt_parser):
-    commands = []
-
-    for group in opt_parser.option_groups:
-        for option in group.option_list:
-            long_option = option.get_opt_string().strip('-')
-            complete_cmd = ['complete', '--command', 'youtube-dl', '--long-option', long_option]
-            if option._short_opts:
-                complete_cmd += ['--short-option', option._short_opts[0].strip('-')]
-            if option.help != optparse.SUPPRESS_HELP:
-                complete_cmd += ['--description', option.help]
-            complete_cmd.extend(EXTRA_ARGS.get(long_option, []))
-            commands.append(shell_quote(complete_cmd))
-
-    with open(FISH_COMPLETION_TEMPLATE) as f:
-        template = f.read()
-    filled_template = template.replace('{{commands}}', '\n'.join(commands))
-    with open(FISH_COMPLETION_FILE, 'w') as f:
-        f.write(filled_template)
-
-parser = youtube_dl.parseOpts()[0]
-build_completion(parser)

devscripts/generate_aes_testdata.py

@@ -1,42 +0,0 @@
-from __future__ import unicode_literals
-
-import codecs
-import subprocess
-
-import os
-import sys
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from youtube_dl.utils import intlist_to_bytes
-from youtube_dl.aes import aes_encrypt, key_expansion
-
-secret_msg = b'Secret message goes here'
-
-
-def hex_str(int_list):
-    return codecs.encode(intlist_to_bytes(int_list), 'hex')
-
-
-def openssl_encode(algo, key, iv):
-    cmd = ['openssl', 'enc', '-e', '-' + algo, '-K', hex_str(key), '-iv', hex_str(iv)]
-    prog = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
-    out, _ = prog.communicate(secret_msg)
-    return out
-
-iv = key = [0x20, 0x15] + 14 * [0]
-
-r = openssl_encode('aes-128-cbc', key, iv)
-print('aes_cbc_decrypt')
-print(repr(r))
-
-password = key
-new_key = aes_encrypt(password, key_expansion(password))
-r = openssl_encode('aes-128-ctr', new_key, iv)
-print('aes_decrypt_text 16')
-print(repr(r))
-
-password = key + 16 * [0]
-new_key = aes_encrypt(password, key_expansion(password)) * (32 // 16)
-r = openssl_encode('aes-256-ctr', new_key, iv)
-print('aes_decrypt_text 32')
-print(repr(r))

devscripts/gh-pages/add-version.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-from __future__ import unicode_literals
 
 import json
 import sys

devscripts/gh-pages/generate-download.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
-from __future__ import unicode_literals
-
 import hashlib
+import shutil
+import subprocess
+import tempfile
 import urllib.request
 import json
 

devscripts/gh-pages/sign-versions.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-from __future__ import unicode_literals, with_statement
 
 import rsa
 import json
@@ -12,23 +11,22 @@ except NameError:
 
 versions_info = json.load(open('update/versions.json'))
 if 'signature' in versions_info:
-    del versions_info['signature']
+	del versions_info['signature']
 
 print('Enter the PKCS1 private key, followed by a blank line:')
 privkey = b''
 while True:
-    try:
-        line = input()
-    except EOFError:
-        break
-    if line == '':
-        break
-    privkey += line.encode('ascii') + b'\n'
+	try:
+		line = input()
+	except EOFError:
+		break
+	if line == '':
+		break
+	privkey += line.encode('ascii') + b'\n'
 privkey = rsa.PrivateKey.load_pkcs1(privkey)
 
 signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).encode('utf-8'), privkey, 'SHA-256')).decode()
 print('signature: ' + signature)
 
 versions_info['signature'] = signature
-with open('update/versions.json', 'w') as versionsf:
-    json.dump(versions_info, versionsf, indent=4, sort_keys=True)
+json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)

devscripts/gh-pages/update-copyright.py

@@ -1,11 +1,11 @@
 #!/usr/bin/env python
 # coding: utf-8
 
-from __future__ import with_statement, unicode_literals
+from __future__ import with_statement
 
 import datetime
 import glob
-import io  # For Python 2 compatibilty
+import io # For Python 2 compatibilty
 import os
 import re
 
@@ -13,7 +13,7 @@ year = str(datetime.datetime.now().year)
 for fn in glob.glob('*.html*'):
     with io.open(fn, encoding='utf-8') as f:
         content = f.read()
-    newc = re.sub(r'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', 'Copyright © 2006-' + year, content)
+    newc = re.sub(u'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', u'Copyright © 2006-' + year, content)
     if content != newc:
         tmpFn = fn + '.part'
         with io.open(tmpFn, 'wt', encoding='utf-8') as outf:

devscripts/gh-pages/update-feed.py

@@ -1,76 +1,56 @@
 #!/usr/bin/env python3
-from __future__ import unicode_literals
 
 import datetime
-import io
-import json
+
 import textwrap
 
+import json
 
-atom_template = textwrap.dedent("""\
-    <?xml version="1.0" encoding="utf-8"?>
-    <feed xmlns="http://www.w3.org/2005/Atom">
-        <link rel="self" href="http://rg3.github.io/youtube-dl/update/releases.atom" />
-        <title>youtube-dl releases</title>
-        <id>https://yt-dl.org/feed/youtube-dl-updates-feed</id>
-        <updated>@TIMESTAMP@</updated>
-        @ENTRIES@
-    </feed>""")
+atom_template=textwrap.dedent("""\
+								<?xml version='1.0' encoding='utf-8'?>
+								<atom:feed xmlns:atom="http://www.w3.org/2005/Atom">
+									<atom:title>youtube-dl releases</atom:title>
+									<atom:id>youtube-dl-updates-feed</atom:id>
+									<atom:updated>@TIMESTAMP@</atom:updated>
+									@ENTRIES@
+								</atom:feed>""")
 
-entry_template = textwrap.dedent("""
-    <entry>
-        <id>https://yt-dl.org/feed/youtube-dl-updates-feed/youtube-dl-@VERSION@</id>
-        <title>New version @VERSION@</title>
-        <link href="http://rg3.github.io/youtube-dl" />
-        <content type="xhtml">
-            <div xmlns="http://www.w3.org/1999/xhtml">
-                Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
-            </div>
-        </content>
-        <author>
-            <name>The youtube-dl maintainers</name>
-        </author>
-        <updated>@TIMESTAMP@</updated>
-    </entry>
-    """)
+entry_template=textwrap.dedent("""
+								<atom:entry>
+									<atom:id>youtube-dl-@VERSION@</atom:id>
+									<atom:title>New version @VERSION@</atom:title>
+									<atom:link href="http://rg3.github.io/youtube-dl" />
+									<atom:content type="xhtml">
+										<div xmlns="http://www.w3.org/1999/xhtml">
+											Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
+										</div>
+									</atom:content>
+									<atom:author>
+										<atom:name>The youtube-dl maintainers</atom:name>
+									</atom:author>
+									<atom:updated>@TIMESTAMP@</atom:updated>
+								</atom:entry>
+								""")
 
 now = datetime.datetime.now()
-now_iso = now.isoformat() + 'Z'
+now_iso = now.isoformat()
 
-atom_template = atom_template.replace('@TIMESTAMP@', now_iso)
+atom_template = atom_template.replace('@TIMESTAMP@',now_iso)
+
+entries=[]
 
 versions_info = json.load(open('update/versions.json'))
 versions = list(versions_info['versions'].keys())
 versions.sort()
 
-entries = []
 for v in versions:
-    fields = v.split('.')
-    year, month, day = map(int, fields[:3])
-    faked = 0
-    patchlevel = 0
-    while True:
-        try:
-            datetime.date(year, month, day)
-        except ValueError:
-            day -= 1
-            faked += 1
-            assert day > 0
-            continue
-        break
-    if len(fields) >= 4:
-        try:
-            patchlevel = int(fields[3])
-        except ValueError:
-            patchlevel = 1
-    timestamp = '%04d-%02d-%02dT00:%02d:%02dZ' % (year, month, day, faked, patchlevel)
-
-    entry = entry_template.replace('@TIMESTAMP@', timestamp)
-    entry = entry.replace('@VERSION@', v)
-    entries.append(entry)
+	entry = entry_template.replace('@TIMESTAMP@',v.replace('.','-'))
+	entry = entry.replace('@VERSION@',v)
+	entries.append(entry)
 
 entries_str = textwrap.indent(''.join(entries), '\t')
 atom_template = atom_template.replace('@ENTRIES@', entries_str)
 
-with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file:
-    atom_file.write(atom_template)
+with open('update/releases.atom','w',encoding='utf-8') as atom_file:
+	atom_file.write(atom_template)
+

devscripts/gh-pages/update-sites.py

@@ -1,29 +1,27 @@
 #!/usr/bin/env python3
-from __future__ import unicode_literals
 
 import sys
 import os
 import textwrap
 
 # We must be able to import youtube_dl
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
 
 import youtube_dl
 
-
 def main():
     with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf:
         template = tmplf.read()
 
     ie_htmls = []
-    for ie in youtube_dl.list_extractors(age_limit=None):
+    for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
         ie_html = '<b>{}</b>'.format(ie.IE_NAME)
         ie_desc = getattr(ie, 'IE_DESC', None)
         if ie_desc is False:
             continue
         elif ie_desc is not None:
             ie_html += ': {}'.format(ie.IE_DESC)
-        if not ie.working():
+        if ie.working() == False:
             ie_html += ' (Currently broken)'
         ie_htmls.append('<li>{}</li>'.format(ie_html))
 

devscripts/make_contributing.py

@@ -1,32 +0,0 @@
-#!/usr/bin/env python
-from __future__ import unicode_literals
-
-import io
-import optparse
-import re
-
-
-def main():
-    parser = optparse.OptionParser(usage='%prog INFILE OUTFILE')
-    options, args = parser.parse_args()
-    if len(args) != 2:
-        parser.error('Expected an input and an output filename')
-
-    infile, outfile = args
-
-    with io.open(infile, encoding='utf-8') as inf:
-        readme = inf.read()
-
-    bug_text = re.search(
-        r'(?s)#\s*BUGS\s*[^\n]*\s*(.*?)#\s*COPYRIGHT', readme).group(1)
-    dev_text = re.search(
-        r'(?s)(#\s*DEVELOPER INSTRUCTIONS.*?)#\s*EMBEDDING YOUTUBE-DL',
-        readme).group(1)
-
-    out = bug_text + dev_text
-
-    with io.open(outfile, 'w', encoding='utf-8') as outf:
-        outf.write(out)
-
-if __name__ == '__main__':
-    main()

devscripts/make_readme.py

@@ -1,26 +1,20 @@
-from __future__ import unicode_literals
-
-import io
 import sys
 import re
 
 README_FILE = 'README.md'
 helptext = sys.stdin.read()
 
-if isinstance(helptext, bytes):
-    helptext = helptext.decode('utf-8')
-
-with io.open(README_FILE, encoding='utf-8') as f:
+with open(README_FILE) as f:
     oldreadme = f.read()
 
 header = oldreadme[:oldreadme.index('# OPTIONS')]
 footer = oldreadme[oldreadme.index('# CONFIGURATION'):]
 
-options = helptext[helptext.index('  General Options:') + 19:]
-options = re.sub(r'(?m)^  (\w.+)$', r'## \1', options)
+options = helptext[helptext.index('  General Options:')+19:]
+options = re.sub(r'^  (\w.+)$', r'## \1', options, flags=re.M)
 options = '# OPTIONS\n' + options + '\n'
 
-with io.open(README_FILE, 'w', encoding='utf-8') as f:
+with open(README_FILE, 'w') as f:
     f.write(header)
     f.write(options)
     f.write(footer)

devscripts/make_supportedsites.py

@@ -1,45 +0,0 @@
-#!/usr/bin/env python
-from __future__ import unicode_literals
-
-import io
-import optparse
-import os
-import sys
-
-
-# Import youtube_dl
-ROOT_DIR = os.path.join(os.path.dirname(__file__), '..')
-sys.path.insert(0, ROOT_DIR)
-import youtube_dl
-
-
-def main():
-    parser = optparse.OptionParser(usage='%prog OUTFILE.md')
-    options, args = parser.parse_args()
-    if len(args) != 1:
-        parser.error('Expected an output filename')
-
-    outfile, = args
-
-    def gen_ies_md(ies):
-        for ie in ies:
-            ie_md = '**{0}**'.format(ie.IE_NAME)
-            ie_desc = getattr(ie, 'IE_DESC', None)
-            if ie_desc is False:
-                continue
-            if ie_desc is not None:
-                ie_md += ': {0}'.format(ie.IE_DESC)
-            if not ie.working():
-                ie_md += ' (Currently broken)'
-            yield ie_md
-
-    ies = sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower())
-    out = '# Supported sites\n' + ''.join(
-        ' - ' + md + '\n'
-        for md in gen_ies_md(ies))
-
-    with io.open(outfile, 'w', encoding='utf-8') as outf:
-        outf.write(out)
-
-if __name__ == '__main__':
-    main()

devscripts/prepare_manpage.py

@@ -1,63 +0,0 @@
-from __future__ import unicode_literals
-
-import io
-import os.path
-import sys
-import re
-
-ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
-README_FILE = os.path.join(ROOT_DIR, 'README.md')
-
-
-def filter_options(readme):
-    ret = ''
-    in_options = False
-    for line in readme.split('\n'):
-        if line.startswith('# '):
-            if line[2:].startswith('OPTIONS'):
-                in_options = True
-            else:
-                in_options = False
-
-        if in_options:
-            if line.lstrip().startswith('-'):
-                option, description = re.split(r'\s{2,}', line.lstrip())
-                split_option = option.split(' ')
-
-                if not split_option[-1].startswith('-'):  # metavar
-                    option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
-
-                # Pandoc's definition_lists. See http://pandoc.org/README.html
-                # for more information.
-                ret += '\n%s\n:   %s\n' % (option, description)
-            else:
-                ret += line.lstrip() + '\n'
-        else:
-            ret += line + '\n'
-
-    return ret
-
-with io.open(README_FILE, encoding='utf-8') as f:
-    readme = f.read()
-
-PREFIX = '''%YOUTUBE-DL(1)
-
-# NAME
-
-youtube\-dl \- download videos from youtube.com or other video platforms
-
-# SYNOPSIS
-
-**youtube-dl** \[OPTIONS\] URL [URL...]
-
-'''
-readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
-readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
-readme = PREFIX + readme
-
-readme = filter_options(readme)
-
-if sys.version_info < (3, 0):
-    print(readme.encode('utf-8'))
-else:
-    print(readme)

devscripts/release.sh

@@ -14,28 +14,20 @@
 
 set -e
 
-skip_tests=true
-if [ "$1" = '--run-tests' ]; then
-    skip_tests=false
+skip_tests=false
+if [ "$1" = '--skip-test' ]; then
+    skip_tests=true
     shift
 fi
 
 if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
 version="$1"
-major_version=$(echo "$version" | sed -n 's#^\([0-9]*\.[0-9]*\.[0-9]*\).*#\1#p')
-if test "$major_version" '!=' "$(date '+%Y.%m.%d')"; then
-    echo "$version does not start with today's date!"
-    exit 1
-fi
-
 if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi
 if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
-useless_files=$(find youtube_dl -type f -not -name '*.py')
-if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $useless_files"; exit 1; fi
 if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
 
 /bin/echo -e "\n### First of all, testing..."
-make clean
+make cleanall
 if $skip_tests ; then
     echo 'SKIPPING TESTS'
 else
@@ -45,9 +37,9 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 
-/bin/echo -e "\n### Committing documentation and youtube_dl/version.py..."
-make README.md CONTRIBUTING.md supportedsites
-git add README.md CONTRIBUTING.md docs/supportedsites.md youtube_dl/version.py
+/bin/echo -e "\n### Committing CHANGELOG README.md and youtube_dl/version.py..."
+make README.md
+git add CHANGELOG README.md youtube_dl/version.py
 git commit -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."
@@ -73,9 +65,10 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 (cd build/$version/ && sha1sum $RELEASE_FILES > SHA1SUMS)
 (cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
 (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
+git checkout HEAD -- youtube-dl youtube-dl.exe
 
 /bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
-for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
+for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
 scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
 ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
@@ -102,7 +95,7 @@ rm -rf build
 
 make pypi-files
 echo "Uploading to PyPi ..."
-python setup.py sdist bdist_wheel upload
+python setup.py sdist upload
 make clean
 
 /bin/echo -e "\n### DONE!"

devscripts/transition_helper.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python
+
+import sys, os
+
+try:
+    import urllib.request as compat_urllib_request
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_request
+
+sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
+sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
+sys.stderr.write(u'The new location of the binaries is https://github.com/rg3/youtube-dl/downloads, not the git repository.\n\n')
+
+try:
+	raw_input()
+except NameError: # Python 3
+	input()
+
+filename = sys.argv[0]
+
+API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
+BIN_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl"
+
+if not os.access(filename, os.W_OK):
+    sys.exit('ERROR: no write permissions on %s' % filename)
+
+try:
+    urlh = compat_urllib_request.urlopen(BIN_URL)
+    newcontent = urlh.read()
+    urlh.close()
+except (IOError, OSError) as err:
+    sys.exit('ERROR: unable to download latest version')
+
+try:
+    with open(filename, 'wb') as outf:
+        outf.write(newcontent)
+except (IOError, OSError) as err:
+    sys.exit('ERROR: unable to overwrite current version')
+
+sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

devscripts/transition_helper_exe/setup.py

@@ -0,0 +1,12 @@
+from distutils.core import setup
+import py2exe
+
+py2exe_options = {
+    "bundle_files": 1,
+    "compressed": 1,
+    "optimize": 2,
+    "dist_dir": '.',
+    "dll_excludes": ['w9xpopen.exe']
+}
+
+setup(console=['youtube-dl.py'], options={ "py2exe": py2exe_options }, zipfile=None)

devscripts/transition_helper_exe/youtube-dl.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python
+
+import sys, os
+import urllib2
+import json, hashlib
+
+def rsa_verify(message, signature, key):
+    from struct import pack
+    from hashlib import sha256
+    from sys import version_info
+    def b(x):
+        if version_info[0] == 2: return x
+        else: return x.encode('latin1')
+    assert(type(message) == type(b('')))
+    block_size = 0
+    n = key[0]
+    while n:
+        block_size += 1
+        n >>= 8
+    signature = pow(int(signature, 16), key[1], key[0])
+    raw_bytes = []
+    while signature:
+        raw_bytes.insert(0, pack("B", signature & 0xFF))
+        signature >>= 8
+    signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
+    if signature[0:2] != b('\x00\x01'): return False
+    signature = signature[2:]
+    if not b('\x00') in signature: return False
+    signature = signature[signature.index(b('\x00'))+1:]
+    if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
+    signature = signature[19:]
+    if signature != sha256(message).digest(): return False
+    return True
+
+sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
+sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
+sys.stderr.write(u'From now on, get the binaries from http://rg3.github.com/youtube-dl/download.html, not from the git repository.\n\n')
+
+raw_input()
+
+filename = sys.argv[0]
+
+UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
+VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
+JSON_URL = UPDATE_URL + 'versions.json'
+UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
+
+if not os.access(filename, os.W_OK):
+    sys.exit('ERROR: no write permissions on %s' % filename)
+
+exe = os.path.abspath(filename)
+directory = os.path.dirname(exe)
+if not os.access(directory, os.W_OK):
+    sys.exit('ERROR: no write permissions on %s' % directory)
+
+try:
+    versions_info = urllib2.urlopen(JSON_URL).read().decode('utf-8')
+    versions_info = json.loads(versions_info)
+except:
+    sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
+if not 'signature' in versions_info:
+    sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
+signature = versions_info['signature']
+del versions_info['signature']
+if not rsa_verify(json.dumps(versions_info, sort_keys=True), signature, UPDATES_RSA_KEY):
+    sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
+
+version = versions_info['versions'][versions_info['latest']]
+
+try:
+    urlh = urllib2.urlopen(version['exe'][0])
+    newcontent = urlh.read()
+    urlh.close()
+except (IOError, OSError) as err:
+    sys.exit('ERROR: unable to download latest version')
+
+newcontent_hash = hashlib.sha256(newcontent).hexdigest()
+if newcontent_hash != version['exe'][1]:
+    sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
+
+try:
+    with open(exe + '.new', 'wb') as outf:
+        outf.write(newcontent)
+except (IOError, OSError) as err:
+    sys.exit(u'ERROR: unable to write the new version')
+
+try:
+    bat = os.path.join(directory, 'youtube-dl-updater.bat')
+    b = open(bat, 'w')
+    b.write("""
+echo Updating youtube-dl...
+ping 127.0.0.1 -n 5 -w 1000 > NUL
+move /Y "%s.new" "%s"
+del "%s"
+    \n""" %(exe, exe, bat))
+    b.close()
+
+    os.startfile(bat)
+except (IOError, OSError) as err:
+    sys.exit('ERROR: unable to overwrite current version')
+
+sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

devscripts/zsh-completion.in

@@ -1,28 +0,0 @@
-#compdef youtube-dl
-
-__youtube_dl() {
-    local curcontext="$curcontext" fileopts diropts cur prev
-    typeset -A opt_args
-    fileopts="{{fileopts}}"
-    diropts="{{diropts}}"
-    cur=$words[CURRENT]
-    case $cur in
-        :)
-            _arguments '*: :(::ytfavorites ::ytrecommended ::ytsubscriptions ::ytwatchlater ::ythistory)'
-        ;;
-        *)
-            prev=$words[CURRENT-1]
-            if [[ ${prev} =~ ${fileopts} ]]; then
-                _path_files
-            elif [[ ${prev} =~ ${diropts} ]]; then
-                _path_files -/
-            elif [[ ${prev} == "--recode-video" ]]; then
-                _arguments '*: :(mp4 flv ogg webm mkv)'
-            else
-                _arguments '*: :({{flags}})'
-            fi
-        ;;
-    esac
-}
-
-__youtube_dl

devscripts/zsh-completion.py

@@ -1,48 +0,0 @@
-#!/usr/bin/env python
-from __future__ import unicode_literals
-
-import os
-from os.path import dirname as dirn
-import sys
-
-sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
-import youtube_dl
-
-ZSH_COMPLETION_FILE = "youtube-dl.zsh"
-ZSH_COMPLETION_TEMPLATE = "devscripts/zsh-completion.in"
-
-
-def build_completion(opt_parser):
-    opts = [opt for group in opt_parser.option_groups
-            for opt in group.option_list]
-    opts_file = [opt for opt in opts if opt.metavar == "FILE"]
-    opts_dir = [opt for opt in opts if opt.metavar == "DIR"]
-
-    fileopts = []
-    for opt in opts_file:
-        if opt._short_opts:
-            fileopts.extend(opt._short_opts)
-        if opt._long_opts:
-            fileopts.extend(opt._long_opts)
-
-    diropts = []
-    for opt in opts_dir:
-        if opt._short_opts:
-            diropts.extend(opt._short_opts)
-        if opt._long_opts:
-            diropts.extend(opt._long_opts)
-
-    flags = [opt.get_opt_string() for opt in opts]
-
-    with open(ZSH_COMPLETION_TEMPLATE) as f:
-        template = f.read()
-
-    template = template.replace("{{fileopts}}", "|".join(fileopts))
-    template = template.replace("{{diropts}}", "|".join(diropts))
-    template = template.replace("{{flags}}", " ".join(flags))
-
-    with open(ZSH_COMPLETION_FILE, "w") as f:
-        f.write(template)
-
-parser = youtube_dl.parseOpts()[0]
-build_completion(parser)

docs/.gitignore

@@ -1 +0,0 @@
-_build/

docs/Makefile

@@ -1,177 +0,0 @@
-# Makefile for Sphinx documentation
-#
-
-# You can set these variables from the command line.
-SPHINXOPTS    =
-SPHINXBUILD   = sphinx-build
-PAPER         =
-BUILDDIR      = _build
-
-# User-friendly check for sphinx-build
-ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
-$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
-endif
-
-# Internal variables.
-PAPEROPT_a4     = -D latex_paper_size=a4
-PAPEROPT_letter = -D latex_paper_size=letter
-ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
-# the i18n builder cannot share the environment and doctrees with the others
-I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
-
-.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
-
-help:
-	@echo "Please use \`make <target>' where <target> is one of"
-	@echo "  html       to make standalone HTML files"
-	@echo "  dirhtml    to make HTML files named index.html in directories"
-	@echo "  singlehtml to make a single large HTML file"
-	@echo "  pickle     to make pickle files"
-	@echo "  json       to make JSON files"
-	@echo "  htmlhelp   to make HTML files and a HTML help project"
-	@echo "  qthelp     to make HTML files and a qthelp project"
-	@echo "  devhelp    to make HTML files and a Devhelp project"
-	@echo "  epub       to make an epub"
-	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
-	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
-	@echo "  latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
-	@echo "  text       to make text files"
-	@echo "  man        to make manual pages"
-	@echo "  texinfo    to make Texinfo files"
-	@echo "  info       to make Texinfo files and run them through makeinfo"
-	@echo "  gettext    to make PO message catalogs"
-	@echo "  changes    to make an overview of all changed/added/deprecated items"
-	@echo "  xml        to make Docutils-native XML files"
-	@echo "  pseudoxml  to make pseudoxml-XML files for display purposes"
-	@echo "  linkcheck  to check all external links for integrity"
-	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
-
-clean:
-	rm -rf $(BUILDDIR)/*
-
-html:
-	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
-	@echo
-	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
-
-dirhtml:
-	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
-	@echo
-	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
-
-singlehtml:
-	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
-	@echo
-	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
-
-pickle:
-	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
-	@echo
-	@echo "Build finished; now you can process the pickle files."
-
-json:
-	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
-	@echo
-	@echo "Build finished; now you can process the JSON files."
-
-htmlhelp:
-	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
-	@echo
-	@echo "Build finished; now you can run HTML Help Workshop with the" \
-	      ".hhp project file in $(BUILDDIR)/htmlhelp."
-
-qthelp:
-	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
-	@echo
-	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
-	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
-	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/youtube-dl.qhcp"
-	@echo "To view the help file:"
-	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/youtube-dl.qhc"
-
-devhelp:
-	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
-	@echo
-	@echo "Build finished."
-	@echo "To view the help file:"
-	@echo "# mkdir -p $$HOME/.local/share/devhelp/youtube-dl"
-	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/youtube-dl"
-	@echo "# devhelp"
-
-epub:
-	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
-	@echo
-	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
-
-latex:
-	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
-	@echo
-	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
-	@echo "Run \`make' in that directory to run these through (pdf)latex" \
-	      "(use \`make latexpdf' here to do that automatically)."
-
-latexpdf:
-	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
-	@echo "Running LaTeX files through pdflatex..."
-	$(MAKE) -C $(BUILDDIR)/latex all-pdf
-	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
-
-latexpdfja:
-	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
-	@echo "Running LaTeX files through platex and dvipdfmx..."
-	$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
-	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
-
-text:
-	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
-	@echo
-	@echo "Build finished. The text files are in $(BUILDDIR)/text."
-
-man:
-	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
-	@echo
-	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
-
-texinfo:
-	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
-	@echo
-	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
-	@echo "Run \`make' in that directory to run these through makeinfo" \
-	      "(use \`make info' here to do that automatically)."
-
-info:
-	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
-	@echo "Running Texinfo files through makeinfo..."
-	make -C $(BUILDDIR)/texinfo info
-	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
-
-gettext:
-	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
-	@echo
-	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
-
-changes:
-	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
-	@echo
-	@echo "The overview file is in $(BUILDDIR)/changes."
-
-linkcheck:
-	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
-	@echo
-	@echo "Link check complete; look for any errors in the above output " \
-	      "or in $(BUILDDIR)/linkcheck/output.txt."
-
-doctest:
-	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
-	@echo "Testing of doctests in the sources finished, look at the " \
-	      "results in $(BUILDDIR)/doctest/output.txt."
-
-xml:
-	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
-	@echo
-	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
-
-pseudoxml:
-	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
-	@echo
-	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."

docs/conf.py

@@ -1,71 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# youtube-dl documentation build configuration file, created by
-# sphinx-quickstart on Fri Mar 14 21:05:43 2014.
-#
-# This file is execfile()d with the current directory set to its
-# containing dir.
-#
-# Note that not all possible configuration values are present in this
-# autogenerated file.
-#
-# All configuration values have a default; values that are commented out
-# serve to show the default.
-
-import sys
-import os
-# Allows to import youtube_dl
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-# -- General configuration ------------------------------------------------
-
-# Add any Sphinx extension module names here, as strings. They can be
-# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
-# ones.
-extensions = [
-    'sphinx.ext.autodoc',
-]
-
-# Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
-
-# The suffix of source filenames.
-source_suffix = '.rst'
-
-# The master toctree document.
-master_doc = 'index'
-
-# General information about the project.
-project = u'youtube-dl'
-copyright = u'2014, Ricardo Garcia Gonzalez'
-
-# The version info for the project you're documenting, acts as replacement for
-# |version| and |release|, also used in various other places throughout the
-# built documents.
-#
-# The short X.Y version.
-from youtube_dl.version import __version__
-version = __version__
-# The full version, including alpha/beta/rc tags.
-release = version
-
-# List of patterns, relative to source directory, that match files and
-# directories to ignore when looking for source files.
-exclude_patterns = ['_build']
-
-# The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'sphinx'
-
-# -- Options for HTML output ----------------------------------------------
-
-# The theme to use for HTML and HTML Help pages.  See the documentation for
-# a list of builtin themes.
-html_theme = 'default'
-
-# Add any paths that contain custom static files (such as style sheets) here,
-# relative to this directory. They are copied after the builtin static files,
-# so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
-
-# Output file base name for HTML help builder.
-htmlhelp_basename = 'youtube-dldoc'

docs/index.rst

@@ -1,23 +0,0 @@
-Welcome to youtube-dl's documentation!
-======================================
-
-*youtube-dl* is a command-line program to download videos from YouTube.com and more sites.
-It can also be used in Python code.
-
-Developer guide
----------------
-
-This section contains information for using *youtube-dl* from Python programs.
-
-.. toctree::
-    :maxdepth: 2
-
-    module_guide
-
-Indices and tables
-==================
-
-* :ref:`genindex`
-* :ref:`modindex`
-* :ref:`search`
-

docs/module_guide.rst

@@ -1,67 +0,0 @@
-Using the ``youtube_dl`` module
-===============================
-
-When using the ``youtube_dl`` module, you start by creating an instance of :class:`YoutubeDL` and adding all the available extractors:
-
-.. code-block:: python
-
-    >>> from youtube_dl import YoutubeDL
-    >>> ydl = YoutubeDL()
-    >>> ydl.add_default_info_extractors()
-
-Extracting video information
-----------------------------
-
-You use the :meth:`YoutubeDL.extract_info` method for getting the video information, which returns a dictionary:
-
-.. code-block:: python
-
-    >>> info = ydl.extract_info('http://www.youtube.com/watch?v=BaW_jenozKc', download=False)
-    [youtube] Setting language
-    [youtube] BaW_jenozKc: Downloading webpage
-    [youtube] BaW_jenozKc: Downloading video info webpage
-    [youtube] BaW_jenozKc: Extracting video information
-    >>> info['title']
-    'youtube-dl test video "\'/\\ä↭𝕐'
-    >>> info['height'], info['width']
-    (720, 1280)
-
-If you want to download or play the video you can get its url:
-
-.. code-block:: python
-
-    >>> info['url']
-    'https://...'
-
-Extracting playlist information
--------------------------------
-
-The playlist information is extracted in a similar way, but the dictionary is a bit different:
-
-.. code-block:: python
-
-    >>> playlist = ydl.extract_info('http://www.ted.com/playlists/13/open_source_open_world', download=False)
-    [TED] open_source_open_world: Downloading playlist webpage
-    ...
-    >>> playlist['title']
-    'Open-source, open world'
-
-
-
-You can access the videos in the playlist with the ``entries`` field:
-
-.. code-block:: python
-
-    >>> for video in playlist['entries']:
-    ...     print('Video #%d: %s' % (video['playlist_index'], video['title']))
-
-    Video #1: How Arduino is open-sourcing imagination
-    Video #2: The year open data went worldwide
-    Video #3: Massive-scale online collaboration
-    Video #4: The art of asking
-    Video #5: How cognitive surplus will change the world
-    Video #6: The birth of Wikipedia
-    Video #7: Coding a better government
-    Video #8: The era of open innovation
-    Video #9: The currency of the new economy is trust
-

docs/supportedsites.md

@@ -1,706 +0,0 @@
-# Supported sites
- - **1tv**: Первый канал
- - **1up.com**
- - **220.ro**
- - **22tracks:genre**
- - **22tracks:track**
- - **24video**
- - **3sat**
- - **4tube**
- - **56.com**
- - **5min**
- - **8tracks**
- - **91porn**
- - **9gag**
- - **abc.net.au**
- - **Abc7News**
- - **AcademicEarth:Course**
- - **AddAnime**
- - **AdobeTV**
- - **AdobeTVVideo**
- - **AdultSwim**
- - **Aftenposten**
- - **Aftonbladet**
- - **AirMozilla**
- - **AlJazeera**
- - **Allocine**
- - **AlphaPorno**
- - **anitube.se**
- - **AnySex**
- - **Aparat**
- - **AppleConnect**
- - **AppleDaily**: 臺灣蘋果日報
- - **AppleTrailers**
- - **archive.org**: archive.org videos
- - **ARD**
- - **ARD:mediathek**
- - **arte.tv**
- - **arte.tv:+7**
- - **arte.tv:concert**
- - **arte.tv:creative**
- - **arte.tv:ddc**
- - **arte.tv:embed**
- - **arte.tv:future**
- - **AtresPlayer**
- - **ATTTechChannel**
- - **audiomack**
- - **audiomack:album**
- - **Azubu**
- - **BaiduVideo**: 百度视频
- - **bambuser**
- - **bambuser:channel**
- - **Bandcamp**
- - **Bandcamp:album**
- - **bbc**: BBC
- - **bbc.co.uk**: BBC iPlayer
- - **BeatportPro**
- - **Beeg**
- - **BehindKink**
- - **Bet**
- - **Bild**: Bild.de
- - **BiliBili**
- - **blinkx**
- - **blip.tv:user**
- - **BlipTV**
- - **Bloomberg**
- - **Bpb**: Bundeszentrale für politische Bildung
- - **BR**: Bayerischer Rundfunk Mediathek
- - **Break**
- - **Brightcove**
- - **bt:article**: Bergens Tidende Articles
- - **bt:vestlendingen**: Bergens Tidende - Vestlendingen
- - **BuzzFeed**
- - **BYUtv**
- - **Camdemy**
- - **CamdemyFolder**
- - **Canal13cl**
- - **canalc2.tv**
- - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
- - **CBS**
- - **CBSNews**: CBS News
- - **CBSSports**
- - **CeskaTelevize**
- - **channel9**: Channel 9
- - **Chilloutzone**
- - **chirbit**
- - **chirbit:profile**
- - **Cinchcast**
- - **Cinemassacre**
- - **Clipfish**
- - **cliphunter**
- - **Clipsyndicate**
- - **Cloudy**
- - **Clubic**
- - **cmt.com**
- - **CNET**
- - **CNN**
- - **CNNArticle**
- - **CNNBlogs**
- - **CollegeHumor**
- - **CollegeRama**
- - **ComCarCoff**
- - **ComedyCentral**
- - **ComedyCentralShows**: The Daily Show / The Colbert Report
- - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
- - **Cracked**
- - **Criterion**
- - **CrooksAndLiars**
- - **Crunchyroll**
- - **crunchyroll:playlist**
- - **CSpan**: C-SPAN
- - **CtsNews**: 華視新聞
- - **culturebox.francetvinfo.fr**
- - **dailymotion**
- - **dailymotion:playlist**
- - **dailymotion:user**
- - **DailymotionCloud**
- - **daum.net**
- - **DBTV**
- - **DCN**
- - **DctpTv**
- - **DeezerPlaylist**
- - **defense.gouv.fr**
- - **DHM**: Filmarchiv - Deutsches Historisches Museum
- - **Discovery**
- - **Dotsub**
- - **DouyuTV**: 斗鱼
- - **dramafever**
- - **dramafever:series**
- - **DRBonanza**
- - **Dropbox**
- - **DrTuber**
- - **DRTV**
- - **Dump**
- - **Dumpert**
- - **dvtv**: http://video.aktualne.cz/
- - **EaglePlatform**
- - **EbaumsWorld**
- - **EchoMsk**
- - **eHow**
- - **Einthusan**
- - **eitb.tv**
- - **EllenTV**
- - **EllenTV:clips**
- - **ElPais**: El País
- - **Embedly**
- - **EMPFlix**
- - **Engadget**
- - **Eporner**
- - **EroProfile**
- - **Escapist**
- - **ESPN** (Currently broken)
- - **EsriVideo**
- - **Europa**
- - **EveryonesMixtape**
- - **exfm**: ex.fm
- - **ExpoTV**
- - **ExtremeTube**
- - **facebook**
- - **faz.net**
- - **fc2**
- - **fernsehkritik.tv**
- - **Firstpost**
- - **FiveTV**
- - **Flickr**
- - **Folketinget**: Folketinget (ft.dk; Danish parliament)
- - **FootyRoom**
- - **Foxgay**
- - **FoxNews**: Fox News and Fox Business Video
- - **FoxSports**
- - **france2.fr:generation-quoi**
- - **FranceCulture**
- - **FranceInter**
- - **francetv**: France 2, 3, 4, 5 and Ô
- - **francetvinfo.fr**
- - **Freesound**
- - **freespeech.org**
- - **FreeVideo**
- - **FunnyOrDie**
- - **Gamekings**
- - **GameOne**
- - **gameone:playlist**
- - **Gamersyde**
- - **GameSpot**
- - **GameStar**
- - **Gametrailers**
- - **Gazeta**
- - **GDCVault**
- - **generic**: Generic downloader that works on some sites
- - **Gfycat**
- - **GiantBomb**
- - **Giga**
- - **Glide**: Glide mobile video messages (glide.me)
- - **Globo**
- - **GodTube**
- - **GoldenMoustache**
- - **Golem**
- - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com
- - **Goshgay**
- - **Groupon**
- - **Hark**
- - **HearThisAt**
- - **Heise**
- - **HellPorno**
- - **Helsinki**: helsinki.fi
- - **HentaiStigma**
- - **HistoricFilms**
- - **History**
- - **hitbox**
- - **hitbox:live**
- - **HornBunny**
- - **HotNewHipHop**
- - **Howcast**
- - **HowStuffWorks**
- - **HuffPost**: Huffington Post
- - **Hypem**
- - **Iconosquare**
- - **ign.com**
- - **imdb**: Internet Movie Database trailers
- - **imdb:list**: Internet Movie Database lists
- - **Imgur**
- - **ImgurAlbum**
- - **Ina**
- - **Indavideo**
- - **IndavideoEmbed**
- - **InfoQ**
- - **Instagram**
- - **instagram:user**: Instagram user profile
- - **InternetVideoArchive**
- - **IPrima**
- - **iqiyi**: 爱奇艺
- - **Ir90Tv**
- - **ivi**: ivi.ru
- - **ivi:compilation**: ivi.ru compilations
- - **Izlesene**
- - **JadoreCettePub**
- - **JeuxVideo**
- - **Jove**
- - **jpopsuki.tv**
- - **Jukebox**
- - **Kaltura**
- - **KanalPlay**: Kanal 5/9/11 Play
- - **Kankan**
- - **Karaoketv**
- - **KarriereVideos**
- - **keek**
- - **KeezMovies**
- - **KhanAcademy**
- - **KickStarter**
- - **kontrtube**: KontrTube.ru - Труба зовёт
- - **KrasView**: Красвью
- - **Ku6**
- - **kuwo:album**: 酷我音乐 - 专辑
- - **kuwo:category**: 酷我音乐 - 分类
- - **kuwo:chart**: 酷我音乐 - 排行榜
- - **kuwo:mv**: 酷我音乐 - MV
- - **kuwo:singer**: 酷我音乐 - 歌手
- - **kuwo:song**: 酷我音乐
- - **la7.tv**
- - **Laola1Tv**
- - **Lecture2Go**
- - **Letv**: 乐视网
- - **LetvPlaylist**
- - **LetvTv**
- - **Libsyn**
- - **life:embed**
- - **lifenews**: LIFE | NEWS
- - **limelight**
- - **limelight:channel**
- - **limelight:channel_list**
- - **LiveLeak**
- - **livestream**
- - **livestream:original**
- - **LnkGo**
- - **lrt.lt**
- - **lynda**: lynda.com videos
- - **lynda:course**: lynda.com online courses
- - **m6**
- - **macgamestore**: MacGameStore trailers
- - **mailru**: Видео@Mail.Ru
- - **Malemotion**
- - **MDR**
- - **media.ccc.de**
- - **MegaVideoz**
- - **metacafe**
- - **Metacritic**
- - **Mgoon**
- - **Minhateca**
- - **MinistryGrid**
- - **miomio.tv**
- - **MiTele**: mitele.es
- - **mixcloud**
- - **MLB**
- - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
- - **Mofosex**
- - **Mojvideo**
- - **Moniker**: allmyvideos.net and vidspot.net
- - **mooshare**: Mooshare.biz
- - **Morningstar**: morningstar.com
- - **Motherless**
- - **Motorsport**: motorsport.com
- - **MovieClips**
- - **MovieFap**
- - **Moviezine**
- - **movshare**: MovShare
- - **MPORA**
- - **MSNBC**
- - **MTV**
- - **mtv.de**
- - **mtviggy.com**
- - **mtvservices:embedded**
- - **MuenchenTV**: münchen.tv
- - **MusicPlayOn**
- - **muzu.tv**
- - **Mwave**
- - **MySpace**
- - **MySpace:album**
- - **MySpass**
- - **Myvi**
- - **myvideo**
- - **MyVidster**
- - **n-tv.de**
- - **NationalGeographic**
- - **Naver**
- - **NBA**
- - **NBC**
- - **NBCNews**
- - **NBCSports**
- - **NBCSportsVPlayer**
- - **ndr**: NDR.de - Norddeutscher Rundfunk
- - **ndr:embed**
- - **ndr:embed:base**
- - **NDTV**
- - **NerdCubedFeed**
- - **Nerdist**
- - **netease:album**: 网易云音乐 - 专辑
- - **netease:djradio**: 网易云音乐 - 电台
- - **netease:mv**: 网易云音乐 - MV
- - **netease:playlist**: 网易云音乐 - 歌单
- - **netease:program**: 网易云音乐 - 电台节目
- - **netease:singer**: 网易云音乐 - 歌手
- - **netease:song**: 网易云音乐
- - **Netzkino**
- - **Newgrounds**
- - **Newstube**
- - **NextMedia**: 蘋果日報
- - **NextMediaActionNews**: 蘋果日報 - 動新聞
- - **nfb**: National Film Board of Canada
- - **nfl.com**
- - **nhl.com**
- - **nhl.com:news**: NHL news
- - **nhl.com:videocenter**: NHL videocenter category
- - **niconico**: ニコニコ動画
- - **NiconicoPlaylist**
- - **njoy**: N-JOY
- - **njoy:embed**
- - **Noco**
- - **Normalboots**
- - **NosVideo**
- - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
- - **novamov**: NovaMov
- - **nowness**
- - **nowness:playlist**
- - **nowness:series**
- - **NowTV**
- - **nowvideo**: NowVideo
- - **npo**: npo.nl and ntr.nl
- - **npo.nl:live**
- - **npo.nl:radio**
- - **npo.nl:radio:fragment**
- - **NRK**
- - **NRKPlaylist**
- - **NRKTV**: NRK TV and NRK Radio
- - **ntv.ru**
- - **Nuvid**
- - **NYTimes**
- - **NYTimesArticle**
- - **ocw.mit.edu**
- - **Odnoklassniki**
- - **OktoberfestTV**
- - **on.aol.com**
- - **OnionStudios**
- - **Ooyala**
- - **OoyalaExternal**
- - **orf:fm4**: radio FM4
- - **orf:iptv**: iptv.ORF.at
- - **orf:oe1**: Radio Österreich 1
- - **orf:tvthek**: ORF TVthek
- - **parliamentlive.tv**: UK parliament videos
- - **Patreon**
- - **PBS**
- - **Periscope**: Periscope
- - **PhilharmonieDeParis**: Philharmonie de Paris
- - **Phoenix**
- - **Photobucket**
- - **Pinkbike**
- - **Pladform**
- - **PlanetaPlay**
- - **play.fm**
- - **played.to**
- - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
- - **Playvid**
- - **Playwire**
- - **pluralsight**
- - **pluralsight:course**
- - **plus.google**: Google Plus
- - **pluzz.francetv.fr**
- - **podomatic**
- - **PornHd**
- - **PornHub**
- - **PornHubPlaylist**
- - **Pornotube**
- - **PornoVoisines**
- - **PornoXO**
- - **PrimeShareTV**
- - **PromptFile**
- - **prosiebensat1**: ProSiebenSat.1 Digital
- - **Puls4**
- - **Pyvideo**
- - **qqmusic**: QQ音乐
- - **qqmusic:album**: QQ音乐 - 专辑
- - **qqmusic:playlist**: QQ音乐 - 歌单
- - **qqmusic:singer**: QQ音乐 - 歌手
- - **qqmusic:toplist**: QQ音乐 - 排行榜
- - **Quickscope**: Quick Scope
- - **QuickVid**
- - **R7**
- - **radio.de**
- - **radiobremen**
- - **radiofrance**
- - **RadioJavan**
- - **Rai**
- - **RBMARadio**
- - **RDS**: RDS.ca
- - **RedTube**
- - **Restudy**
- - **ReverbNation**
- - **RingTV**
- - **RottenTomatoes**
- - **Roxwel**
- - **RTBF**
- - **Rte**
- - **rtl.nl**: rtl.nl and rtlxl.nl
- - **RTL2**
- - **RTP**
- - **RTS**: RTS.ch
- - **rtve.es:alacarta**: RTVE a la carta
- - **rtve.es:infantil**: RTVE infantil
- - **rtve.es:live**: RTVE.es live streams
- - **RTVNH**
- - **RUHD**
- - **rutube**: Rutube videos
- - **rutube:channel**: Rutube channels
- - **rutube:embed**: Rutube embedded videos
- - **rutube:movie**: Rutube movies
- - **rutube:person**: Rutube person videos
- - **RUTV**: RUTV.RU
- - **Ruutu**
- - **safari**: safaribooksonline.com online video
- - **safari:course**: safaribooksonline.com online courses
- - **Sandia**: Sandia National Laboratories
- - **Sapo**: SAPO Vídeos
- - **savefrom.net**
- - **SBS**: sbs.com.au
- - **SciVee**
- - **screen.yahoo:search**: Yahoo screen search
- - **Screencast**
- - **ScreencastOMatic**
- - **ScreenwaveMedia**
- - **SenateISVP**
- - **ServingSys**
- - **Sexu**
- - **SexyKarma**: Sexy Karma and Watch Indian Porn
- - **Shahid**
- - **Shared**: shared.sx and vivo.sx
- - **ShareSix**
- - **Sina**
- - **Slideshare**
- - **Slutload**
- - **smotri**: Smotri.com
- - **smotri:broadcast**: Smotri.com broadcasts
- - **smotri:community**: Smotri.com community videos
- - **smotri:user**: Smotri.com user videos
- - **SnagFilms**
- - **SnagFilmsEmbed**
- - **Snotr**
- - **Sohu**
- - **soompi**
- - **soompi:show**
- - **soundcloud**
- - **soundcloud:playlist**
- - **soundcloud:set**
- - **soundcloud:user**
- - **soundgasm**
- - **soundgasm:profile**
- - **southpark.cc.com**
- - **southpark.cc.com:español**
- - **southpark.de**
- - **southpark.nl**
- - **southparkstudios.dk**
- - **Space**
- - **SpankBang**
- - **Spankwire**
- - **Spiegel**
- - **Spiegel:Article**: Articles on spiegel.de
- - **Spiegeltv**
- - **Spike**
- - **Sport5**
- - **SportBox**
- - **SportBoxEmbed**
- - **SportDeutschland**
- - **Sportschau**
- - **Srf**
- - **SRMediathek**: Saarländischer Rundfunk
- - **SSA**
- - **stanfordoc**: Stanford Open ClassRoom
- - **Steam**
- - **streamcloud.eu**
- - **StreamCZ**
- - **StreetVoice**
- - **SunPorno**
- - **SVT**
- - **SVTPlay**: SVT Play and Öppet arkiv
- - **SWRMediathek**
- - **Syfy**
- - **SztvHu**
- - **Tagesschau**
- - **Tapely**
- - **Tass**
- - **teachertube**: teachertube.com videos
- - **teachertube:user:collection**: teachertube.com user and collection videos
- - **TeachingChannel**
- - **Teamcoco**
- - **TeamFour**
- - **TechTalks**
- - **techtv.mit.edu**
- - **ted**
- - **TeleBruxelles**
- - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
- - **Telegraaf**
- - **TeleMB**
- - **TeleTask**
- - **TenPlay**
- - **TestTube**
- - **TF1**
- - **TheOnion**
- - **ThePlatform**
- - **ThePlatformFeed**
- - **TheSixtyOne**
- - **ThisAmericanLife**
- - **ThisAV**
- - **THVideo**
- - **THVideoPlaylist**
- - **tinypic**: tinypic.com videos
- - **tlc.com**
- - **tlc.de**
- - **TMZ**
- - **TMZArticle**
- - **TNAFlix**
- - **tou.tv**
- - **Toypics**: Toypics user profile
- - **ToypicsUser**: Toypics user profile
- - **TrailerAddict** (Currently broken)
- - **Trilulilu**
- - **TruTube**
- - **Tube8**
- - **TubiTv**
- - **Tudou**
- - **Tumblr**
- - **TuneIn**
- - **Turbo**
- - **Tutv**
- - **tv.dfb.de**
- - **TV2**
- - **TV2Article**
- - **TV4**: tv4.se and tv4play.se
- - **TVC**
- - **TVCArticle**
- - **tvigle**: Интернет-телевидение Tvigle.ru
- - **tvp.pl**
- - **tvp.pl:Series**
- - **TVPlay**: TV3Play and related services
- - **Tweakers**
- - **twitch:bookmarks**
- - **twitch:chapter**
- - **twitch:past_broadcasts**
- - **twitch:profile**
- - **twitch:stream**
- - **twitch:video**
- - **twitch:vod**
- - **TwitterCard**
- - **Ubu**
- - **udemy**
- - **udemy:course**
- - **UDNEmbed**: 聯合影音
- - **Ultimedia**
- - **Unistra**
- - **Urort**: NRK P3 Urørt
- - **ustream**
- - **ustream:channel**
- - **Varzesh3**
- - **Vbox7**
- - **VeeHD**
- - **Veoh**
- - **Vessel**
- - **Vesti**: Вести.Ru
- - **Vevo**
- - **VGTV**: VGTV and BTTV
- - **vh1.com**
- - **Vice**
- - **Viddler**
- - **video.google:search**: Google Video search
- - **video.mit.edu**
- - **VideoDetective**
- - **videofy.me**
- - **videolectures.net**
- - **VideoMega**
- - **VideoPremium**
- - **VideoTt**: video.tt - Your True Tube
- - **videoweed**: VideoWeed
- - **Vidme**
- - **Vidzi**
- - **vier**
- - **vier:videos**
- - **Viewster**
- - **viki**
- - **viki:channel**
- - **vimeo**
- - **vimeo:album**
- - **vimeo:channel**
- - **vimeo:group**
- - **vimeo:likes**: Vimeo user likes
- - **vimeo:review**: Review pages on vimeo
- - **vimeo:user**
- - **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
- - **Vimple**: Vimple - one-click video hosting
- - **Vine**
- - **vine:user**
- - **vk**: VK
- - **vk:uservideos**: VK - User's Videos
- - **vlive**
- - **Vodlocker**
- - **VoiceRepublic**
- - **Vporn**
- - **vpro**: npo.nl and ntr.nl
- - **VRT**
- - **vube**: Vube.com
- - **VuClip**
- - **vulture.com**
- - **Walla**
- - **WashingtonPost**
- - **wat.tv**
- - **WayOfTheMaster**
- - **WDR**
- - **wdr:mobile**
- - **WDRMaus**: Sendung mit der Maus
- - **WebOfStories**
- - **WebOfStoriesPlaylist**
- - **Weibo**
- - **Wimp**
- - **Wistia**
- - **WNL**
- - **WorldStarHipHop**
- - **wrzuta.pl**
- - **WSJ**: Wall Street Journal
- - **XBef**
- - **XboxClips**
- - **XHamster**
- - **XHamsterEmbed**
- - **XMinus**
- - **XNXX**
- - **Xstream**
- - **XTube**
- - **XTubeUser**: XTube user profile
- - **Xuite**: 隨意窩Xuite影音
- - **XVideos**
- - **XXXYMovies**
- - **Yahoo**: Yahoo screen and movies
- - **Yam**: 蕃薯藤yam天空部落
- - **yandexmusic:album**: Яндекс.Музыка - Альбом
- - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
- - **yandexmusic:track**: Яндекс.Музыка - Трек
- - **YesJapan**
- - **yinyuetai:video**: 音悦Tai
- - **Ynet**
- - **YouJizz**
- - **youku**: 优酷
- - **YouPorn**
- - **YourUpload**
- - **youtube**: YouTube.com
- - **youtube:channel**: YouTube.com channels
- - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
- - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
- - **youtube:playlist**: YouTube.com playlists
- - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
- - **youtube:search**: YouTube.com searches
- - **youtube:search:date**: YouTube.com searches, newest videos first
- - **youtube:search_url**: YouTube.com search URLs
- - **youtube:show**: YouTube.com (multi-season) shows
- - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- - **Zapiks**
- - **ZDF**
- - **ZDFChannel**
- - **zingmp3:album**: mp3.zing.vn albums
- - **zingmp3:song**: mp3.zing.vn songs

setup.cfg

@@ -1,6 +0,0 @@
-[wheel]
-universal = True
-
-[flake8]
-exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build,.git
-ignore = E402,E501,E731

setup.py

@@ -3,8 +3,7 @@
 
 from __future__ import print_function
 
-import os.path
-import warnings
+import pkg_resources
 import sys
 
 try:
@@ -45,25 +44,12 @@ py2exe_params = {
 if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
     params = py2exe_params
 else:
-    files_spec = [
-        ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
-        ('etc/fish/completions', ['youtube-dl.fish']),
-        ('share/doc/youtube_dl', ['README.txt']),
-        ('share/man/man1', ['youtube-dl.1'])
-    ]
-    root = os.path.dirname(os.path.abspath(__file__))
-    data_files = []
-    for dirname, files in files_spec:
-        resfiles = []
-        for fn in files:
-            if not os.path.exists(fn):
-                warnings.warn('Skipping file %s since it is not present. Type  make  to build all automatically generated files.' % fn)
-            else:
-                resfiles.append(fn)
-        data_files.append((dirname, resfiles))
-
     params = {
-        'data_files': data_files,
+        'data_files': [  # Installing system-wide would require sudo...
+            ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
+            ('share/doc/youtube_dl', ['README.txt']),
+            ('share/man/man1', ['youtube-dl.1'])
+        ]
     }
     if setuptools_available:
         params['entry_points'] = {'console_scripts': ['youtube-dl = youtube_dl:main']}
@@ -85,10 +71,7 @@ setup(
     author_email='ytdl@yt-dl.org',
     maintainer='Philipp Hagemeister',
     maintainer_email='phihag@phihag.de',
-    packages=[
-        'youtube_dl',
-        'youtube_dl.extractor', 'youtube_dl.downloader',
-        'youtube_dl.postprocessor'],
+    packages=['youtube_dl', 'youtube_dl.extractor'],
 
     # Provokes warning on most systems (why?!)
     # test_suite = 'nose.collector',
@@ -102,9 +85,7 @@ setup(
         "Programming Language :: Python :: 2.6",
         "Programming Language :: Python :: 2.7",
         "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.2",
-        "Programming Language :: Python :: 3.3",
-        "Programming Language :: Python :: 3.4",
+        "Programming Language :: Python :: 3.3"
     ],
 
     **params

test/helper.py

@@ -1,5 +1,3 @@
-from __future__ import unicode_literals
-
 import errno
 import io
 import hashlib
@@ -11,11 +9,7 @@ import sys
 
 import youtube_dl.extractor
 from youtube_dl import YoutubeDL
-from youtube_dl.utils import (
-    compat_str,
-    preferredencoding,
-    write_string,
-)
+from youtube_dl.utils import preferredencoding
 
 
 def get_params(override=None):
@@ -43,10 +37,10 @@ def report_warning(message):
     If stderr is a tty file the 'WARNING:' will be colored
     '''
     if sys.stderr.isatty() and os.name != 'nt':
-        _msg_header = '\033[0;33mWARNING:\033[0m'
+        _msg_header = u'\033[0;33mWARNING:\033[0m'
     else:
-        _msg_header = 'WARNING:'
-    output = '%s %s\n' % (_msg_header, message)
+        _msg_header = u'WARNING:'
+    output = u'%s %s\n' % (_msg_header, message)
     if 'b' in getattr(sys.stderr, 'mode', '') or sys.version_info[0] < 3:
         output = output.encode(preferredencoding())
     sys.stderr.write(output)
@@ -57,9 +51,9 @@ class FakeYDL(YoutubeDL):
         # Different instances of the downloader can't share the same dictionary
         # some test set the "sublang" parameter, which would break the md5 checks.
         params = get_params(override=override)
-        super(FakeYDL, self).__init__(params, auto_init=False)
+        super(FakeYDL, self).__init__(params)
         self.result = []
-
+        
     def to_screen(self, s, skip_eol=None):
         print(s)
 
@@ -72,164 +66,20 @@ class FakeYDL(YoutubeDL):
     def expect_warning(self, regex):
         # Silence an expected warning matching a regex
         old_report_warning = self.report_warning
-
         def report_warning(self, message):
-            if re.match(regex, message):
-                return
+            if re.match(regex, message): return
             old_report_warning(message)
         self.report_warning = types.MethodType(report_warning, self)
 
-
-def gettestcases(include_onlymatching=False):
+def get_testcases():
     for ie in youtube_dl.extractor.gen_extractors():
-        for tc in ie.get_testcases(include_onlymatching):
-            yield tc
+        t = getattr(ie, '_TEST', None)
+        if t:
+            t['name'] = type(ie).__name__[:-len('IE')]
+            yield t
+        for t in getattr(ie, '_TESTS', []):
+            t['name'] = type(ie).__name__[:-len('IE')]
+            yield t
 
 
 md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
-
-
-def expect_value(self, got, expected, field):
-    if isinstance(expected, compat_str) and expected.startswith('re:'):
-        match_str = expected[len('re:'):]
-        match_rex = re.compile(match_str)
-
-        self.assertTrue(
-            isinstance(got, compat_str),
-            'Expected a %s object, but got %s for field %s' % (
-                compat_str.__name__, type(got).__name__, field))
-        self.assertTrue(
-            match_rex.match(got),
-            'field %s (value: %r) should match %r' % (field, got, match_str))
-    elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
-        start_str = expected[len('startswith:'):]
-        self.assertTrue(
-            isinstance(got, compat_str),
-            'Expected a %s object, but got %s for field %s' % (
-                compat_str.__name__, type(got).__name__, field))
-        self.assertTrue(
-            got.startswith(start_str),
-            'field %s (value: %r) should start with %r' % (field, got, start_str))
-    elif isinstance(expected, compat_str) and expected.startswith('contains:'):
-        contains_str = expected[len('contains:'):]
-        self.assertTrue(
-            isinstance(got, compat_str),
-            'Expected a %s object, but got %s for field %s' % (
-                compat_str.__name__, type(got).__name__, field))
-        self.assertTrue(
-            contains_str in got,
-            'field %s (value: %r) should contain %r' % (field, got, contains_str))
-    elif isinstance(expected, type):
-        self.assertTrue(
-            isinstance(got, expected),
-            'Expected type %r for field %s, but got value %r of type %r' % (expected, field, got, type(got)))
-    elif isinstance(expected, dict) and isinstance(got, dict):
-        expect_dict(self, got, expected)
-    elif isinstance(expected, list) and isinstance(got, list):
-        self.assertEqual(
-            len(expected), len(got),
-            'Expect a list of length %d, but got a list of length %d for field %s' % (
-                len(expected), len(got), field))
-        for index, (item_got, item_expected) in enumerate(zip(got, expected)):
-            type_got = type(item_got)
-            type_expected = type(item_expected)
-            self.assertEqual(
-                type_expected, type_got,
-                'Type mismatch for list item at index %d for field %s, expected %r, got %r' % (
-                    index, field, type_expected, type_got))
-            expect_value(self, item_got, item_expected, field)
-    else:
-        if isinstance(expected, compat_str) and expected.startswith('md5:'):
-            got = 'md5:' + md5(got)
-        elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
-            self.assertTrue(
-                isinstance(got, (list, dict)),
-                'Expected field %s to be a list or a dict, but it is of type %s' % (
-                    field, type(got).__name__))
-            expected_num = int(expected.partition(':')[2])
-            assertGreaterEqual(
-                self, len(got), expected_num,
-                'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got)))
-            return
-        self.assertEqual(
-            expected, got,
-            'Invalid value for field %s, expected %r, got %r' % (field, expected, got))
-
-
-def expect_dict(self, got_dict, expected_dict):
-    for info_field, expected in expected_dict.items():
-        got = got_dict.get(info_field)
-        expect_value(self, got, expected, info_field)
-
-
-def expect_info_dict(self, got_dict, expected_dict):
-    expect_dict(self, got_dict, expected_dict)
-    # Check for the presence of mandatory fields
-    if got_dict.get('_type') not in ('playlist', 'multi_video'):
-        for key in ('id', 'url', 'title', 'ext'):
-            self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
-    # Check for mandatory fields that are automatically set by YoutubeDL
-    for key in ['webpage_url', 'extractor', 'extractor_key']:
-        self.assertTrue(got_dict.get(key), 'Missing field: %s' % key)
-
-    # Are checkable fields missing from the test case definition?
-    test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
-                          for key, value in got_dict.items()
-                          if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location', 'age_limit'))
-    missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
-    if missing_keys:
-        def _repr(v):
-            if isinstance(v, compat_str):
-                return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
-            else:
-                return repr(v)
-        info_dict_str = ''
-        if len(missing_keys) != len(expected_dict):
-            info_dict_str += ''.join(
-                '    %s: %s,\n' % (_repr(k), _repr(v))
-                for k, v in test_info_dict.items() if k not in missing_keys)
-
-            if info_dict_str:
-                info_dict_str += '\n'
-        info_dict_str += ''.join(
-            '    %s: %s,\n' % (_repr(k), _repr(test_info_dict[k]))
-            for k in missing_keys)
-        write_string(
-            '\n\'info_dict\': {\n' + info_dict_str + '},\n', out=sys.stderr)
-        self.assertFalse(
-            missing_keys,
-            'Missing keys in test definition: %s' % (
-                ', '.join(sorted(missing_keys))))
-
-
-def assertRegexpMatches(self, text, regexp, msg=None):
-    if hasattr(self, 'assertRegexp'):
-        return self.assertRegexp(text, regexp, msg)
-    else:
-        m = re.match(regexp, text)
-        if not m:
-            note = 'Regexp didn\'t match: %r not found' % (regexp)
-            if len(text) < 1000:
-                note += ' in %r' % text
-            if msg is None:
-                msg = note
-            else:
-                msg = note + ', ' + msg
-            self.assertTrue(m, msg)
-
-
-def assertGreaterEqual(self, got, expected, msg=None):
-    if not (got >= expected):
-        if msg is None:
-            msg = '%r not greater than or equal to %r' % (got, expected)
-        self.assertTrue(got >= expected, msg)
-
-
-def expect_warnings(ydl, warnings_re):
-    real_warning = ydl.report_warning
-
-    def _report_warning(w):
-        if not any(re.search(w_re, w) for w_re in warnings_re):
-            real_warning(w)
-
-    ydl.report_warning = _report_warning

test/parameters.json

@@ -7,7 +7,8 @@
     "forcethumbnail": false, 
     "forcetitle": false, 
     "forceurl": false, 
-    "format": "best",
+    "format": null, 
+    "format_limit": null, 
     "ignoreerrors": false, 
     "listformats": null, 
     "logtostderr": false, 
@@ -26,8 +27,9 @@
     "rejecttitle": null, 
     "retries": 10, 
     "simulate": false, 
+    "skip_download": false, 
     "subtitleslang": null, 
-    "subtitlesformat": "best",
+    "subtitlesformat": "srt",
     "test": true, 
     "updatetime": true, 
     "usenetrc": false, 
@@ -37,7 +39,5 @@
     "writeinfojson": true, 
     "writesubtitles": false,
     "allsubtitles": false,
-    "listssubtitles": false,
-    "socket_timeout": 20,
-    "fixup": "never"
+    "listssubtitles": false
 }

test/swftests/.gitignore

@@ -1 +0,0 @@
-*.swf

test/swftests/ArrayAccess.as

@@ -1,19 +0,0 @@
-// input: [["a", "b", "c", "d"]]
-// output: ["c", "b", "a", "d"]
-
-package {
-public class ArrayAccess {
-    public static function main(ar:Array):Array {
-    	var aa:ArrayAccess = new ArrayAccess();
-    	return aa.f(ar, 2);
-    }
-
-    private function f(ar:Array, num:Number):Array{
-        var x:String = ar[0];
-        var y:String = ar[num % ar.length];
-        ar[0] = y;
-        ar[num] = x;
-        return ar;
-    }
-}
-}

test/swftests/ClassCall.as

@@ -1,17 +0,0 @@
-// input: []
-// output: 121
-
-package {
-public class ClassCall {
-    public static function main():int{
-    	var f:OtherClass = new OtherClass();
-        return f.func(100,20);
-    }
-}
-}
-
-class OtherClass {
-	public function func(x: int, y: int):int {
-		return x+y+1;
-	}
-}

test/swftests/ClassConstruction.as

@@ -1,15 +0,0 @@
-// input: []
-// output: 0
-
-package {
-public class ClassConstruction {
-    public static function main():int{
-    	var f:Foo = new Foo();
-        return 0;
-    }
-}
-}
-
-class Foo {
-
-}

test/swftests/ConstArrayAccess.as

@@ -1,18 +0,0 @@
-// input: []
-// output: 4
-
-package {
-public class ConstArrayAccess {
-	private static const x:int = 2;
-	private static const ar:Array = ["42", "3411"];
-
-    public static function main():int{
-        var c:ConstArrayAccess = new ConstArrayAccess();
-        return c.f();
-    }
-
-    public function f(): int {
-    	return ar[1].length;
-    }
-}
-}

test/swftests/ConstantInt.as

@@ -1,12 +0,0 @@
-// input: []
-// output: 2
-
-package {
-public class ConstantInt {
-	private static const x:int = 2;
-
-    public static function main():int{
-        return x;
-    }
-}
-}

test/swftests/DictCall.as

@@ -1,10 +0,0 @@
-// input: [{"x": 1, "y": 2}]
-// output: 3
-
-package {
-public class DictCall {
-    public static function main(d:Object):int{
-        return d.x + d.y;
-    }
-}
-}

test/swftests/EqualsOperator.as

@@ -1,10 +0,0 @@
-// input: []
-// output: false
-
-package {
-public class EqualsOperator {
-    public static function main():Boolean{
-        return 1 == 2;
-    }
-}
-}

test/swftests/LocalVars.as

@@ -1,13 +0,0 @@
-// input: [1, 2]
-// output: 3
-
-package {
-public class LocalVars {
-    public static function main(a:int, b:int):int{
-        var c:int = a + b + b;
-        var d:int = c - b;
-        var e:int = d;
-        return e;
-    }
-}
-}

test/swftests/MemberAssignment.as

@@ -1,22 +0,0 @@
-// input: [1]
-// output: 2
-
-package {
-public class MemberAssignment {
-    public var v:int;
-
-    public function g():int {
-        return this.v;
-    }
-
-    public function f(a:int):int{
-        this.v = a;
-        return this.v + this.g();
-    }
-
-    public static function main(a:int): int {
-        var v:MemberAssignment = new MemberAssignment();
-        return v.f(a);
-    }
-}
-}

test/swftests/NeOperator.as

@@ -1,24 +0,0 @@
-// input: []
-// output: 123
-
-package {
-public class NeOperator {
-    public static function main(): int {
-        var res:int = 0;
-        if (1 != 2) {
-            res += 3;
-        } else {
-            res += 4;
-        }
-        if (2 != 2) {
-            res += 10;
-        } else {
-            res += 20;
-        }
-        if (9 == 9) {
-            res += 100;
-        }
-        return res;
-    }
-}
-}

test/swftests/PrivateCall.as

@@ -1,21 +0,0 @@
-// input: []
-// output: 9
-
-package {
-public class PrivateCall {
-    public static function main():int{
-    	var f:OtherClass = new OtherClass();
-        return f.func();
-    }
-}
-}
-
-class OtherClass {
-	private function pf():int {
-		return 9;
-	}
-
-	public function func():int {
-		return this.pf();
-	}
-}

test/swftests/PrivateVoidCall.as

@@ -1,22 +0,0 @@
-// input: []
-// output: 9
-
-package {
-public class PrivateVoidCall {
-    public static function main():int{
-        var f:OtherClass = new OtherClass();
-        f.func();
-        return 9;
-    }
-}
-}
-
-class OtherClass {
-    private function pf():void {
-        ;
-    }
-
-    public function func():void {
-        this.pf();
-    }
-}

test/swftests/StaticAssignment.as

@@ -1,13 +0,0 @@
-// input: [1]
-// output: 1
-
-package {
-public class StaticAssignment {
-	public static var v:int;
-
-    public static function main(a:int):int{
-        v = a;
-        return v;
-    }
-}
-}

test/swftests/StaticRetrieval.as

@@ -1,16 +0,0 @@
-// input: []
-// output: 1
-
-package {
-public class StaticRetrieval {
-	public static var v:int;
-
-    public static function main():int{
-        if (v) {
-        	return 0;
-        } else {
-        	return 1;
-        }
-    }
-}
-}

test/swftests/StringBasics.as

@@ -1,11 +0,0 @@
-// input: []
-// output: 3
-
-package {
-public class StringBasics {
-    public static function main():int{
-        var s:String = "abc";
-        return s.length;
-    }
-}
-}

test/swftests/StringCharCodeAt.as

@@ -1,11 +0,0 @@
-// input: []
-// output: 9897
-
-package {
-public class StringCharCodeAt {
-    public static function main():int{
-        var s:String = "abc";
-        return s.charCodeAt(1) * 100 + s.charCodeAt();
-    }
-}
-}

test/swftests/StringConversion.as

@@ -1,11 +0,0 @@
-// input: []
-// output: 2
-
-package {
-public class StringConversion {
-    public static function main():int{
-        var s:String = String(99);
-        return s.length;
-    }
-}
-}

test/test_InfoExtractor.py

@@ -1,62 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from test.helper import FakeYDL
-from youtube_dl.extractor.common import InfoExtractor
-from youtube_dl.extractor import YoutubeIE, get_info_extractor
-
-
-class TestIE(InfoExtractor):
-    pass
-
-
-class TestInfoExtractor(unittest.TestCase):
-    def setUp(self):
-        self.ie = TestIE(FakeYDL())
-
-    def test_ie_key(self):
-        self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE)
-
-    def test_html_search_regex(self):
-        html = '<p id="foo">Watch this <a href="http://www.youtube.com/watch?v=BaW_jenozKc">video</a></p>'
-        search = lambda re, *args: self.ie._html_search_regex(re, html, *args)
-        self.assertEqual(search(r'<p id="foo">(.+?)</p>', 'foo'), 'Watch this video')
-
-    def test_opengraph(self):
-        ie = self.ie
-        html = '''
-            <meta name="og:title" content='Foo'/>
-            <meta content="Some video's description " name="og:description"/>
-            <meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
-            '''
-        self.assertEqual(ie._og_search_title(html), 'Foo')
-        self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
-        self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
-
-    def test_html_search_meta(self):
-        ie = self.ie
-        html = '''
-            <meta name="a" content="1" />
-            <meta name='b' content='2'>
-            <meta name="c" content='3'>
-            <meta name=d content='4'>
-            <meta property="e" content='5' >
-            <meta content="6" name="f">
-        '''
-
-        self.assertEqual(ie._html_search_meta('a', html), '1')
-        self.assertEqual(ie._html_search_meta('b', html), '2')
-        self.assertEqual(ie._html_search_meta('c', html), '3')
-        self.assertEqual(ie._html_search_meta('d', html), '4')
-        self.assertEqual(ie._html_search_meta('e', html), '5')
-        self.assertEqual(ie._html_search_meta('f', html), '6')
-
-if __name__ == '__main__':
-    unittest.main()

test/test_YoutubeDL.py

@@ -1,23 +1,12 @@
 #!/usr/bin/env python
 
-from __future__ import unicode_literals
-
 # Allow direct execution
 import os
 import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-import copy
-
-from test.helper import FakeYDL, assertRegexpMatches
-from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_str
-from youtube_dl.extractor import YoutubeIE
-from youtube_dl.postprocessor.common import PostProcessor
-from youtube_dl.utils import ExtractorError, match_filter_func
-
-TEST_URL = 'http://localhost/sample.mp4'
+from test.helper import FakeYDL
 
 
 class YDL(FakeYDL):
@@ -33,419 +22,111 @@ class YDL(FakeYDL):
         self.msgs.append(msg)
 
 
-def _make_result(formats, **kwargs):
-    res = {
-        'formats': formats,
-        'id': 'testid',
-        'title': 'testttitle',
-        'extractor': 'testex',
-    }
-    res.update(**kwargs)
-    return res
-
-
 class TestFormatSelection(unittest.TestCase):
     def test_prefer_free_formats(self):
         # Same resolution => download webm
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 460, 'url': TEST_URL},
-            {'ext': 'mp4', 'height': 460, 'url': TEST_URL},
+            {u'ext': u'webm', u'height': 460},
+            {u'ext': u'mp4',  u'height': 460},
         ]
-        info_dict = _make_result(formats)
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
+        info_dict = {u'formats': formats, u'extractor': u'test'}
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['ext'], 'webm')
+        self.assertEqual(downloaded[u'ext'], u'webm')
 
         # Different resolution => download best quality (mp4)
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
-            {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
+            {u'ext': u'webm', u'height': 720},
+            {u'ext': u'mp4', u'height': 1080},
         ]
-        info_dict['formats'] = formats
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
+        info_dict[u'formats'] = formats
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['ext'], 'mp4')
+        self.assertEqual(downloaded[u'ext'], u'mp4')
 
-        # No prefer_free_formats => prefer mp4 and flv for greater compatibility
+        # No prefer_free_formats => keep original formats order
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
-            {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
-            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
+            {u'ext': u'webm', u'height': 720},
+            {u'ext': u'flv', u'height': 720},
         ]
-        info_dict['formats'] = formats
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
+        info_dict[u'formats'] = formats
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['ext'], 'mp4')
+        self.assertEqual(downloaded[u'ext'], u'flv')
+
+    def test_format_limit(self):
+        formats = [
+            {u'format_id': u'meh', u'url': u'http://example.com/meh'},
+            {u'format_id': u'good', u'url': u'http://example.com/good'},
+            {u'format_id': u'great', u'url': u'http://example.com/great'},
+            {u'format_id': u'excellent', u'url': u'http://example.com/exc'},
+        ]
+        info_dict = {
+            u'formats': formats, u'extractor': u'test', 'id': 'testvid'}
 
         ydl = YDL()
-        ydl.params['prefer_free_formats'] = False
-        formats = [
-            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
-            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
-        ]
-        info_dict['formats'] = formats
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['ext'], 'flv')
+        self.assertEqual(downloaded[u'format_id'], u'excellent')
+
+        ydl = YDL({'format_limit': 'good'})
+        assert ydl.params['format_limit'] == 'good'
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded[u'format_id'], u'good')
+
+        ydl = YDL({'format_limit': 'great', 'format': 'all'})
+        ydl.process_ie_result(info_dict)
+        self.assertEqual(ydl.downloaded_info_dicts[0][u'format_id'], u'meh')
+        self.assertEqual(ydl.downloaded_info_dicts[1][u'format_id'], u'good')
+        self.assertEqual(ydl.downloaded_info_dicts[2][u'format_id'], u'great')
+        self.assertTrue('3' in ydl.msgs[0])
+
+        ydl = YDL()
+        ydl.params['format_limit'] = 'excellent'
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded[u'format_id'], u'excellent')
 
     def test_format_selection(self):
         formats = [
-            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
-            {'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL},
-            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
-            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
-            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
+            {u'format_id': u'35', u'ext': u'mp4'},
+            {u'format_id': u'45', u'ext': u'webm'},
+            {u'format_id': u'47', u'ext': u'webm'},
+            {u'format_id': u'2', u'ext': u'flv'},
         ]
-        info_dict = _make_result(formats)
+        info_dict = {u'formats': formats, u'extractor': u'test'}
 
-        ydl = YDL({'format': '20/47'})
-        ydl.process_ie_result(info_dict.copy())
+        ydl = YDL({'format': u'20/47'})
+        ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], '47')
+        self.assertEqual(downloaded['format_id'], u'47')
 
-        ydl = YDL({'format': '20/71/worst'})
-        ydl.process_ie_result(info_dict.copy())
+        ydl = YDL({'format': u'20/71/worst'})
+        ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], '35')
+        self.assertEqual(downloaded['format_id'], u'35')
 
         ydl = YDL()
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], '2')
-
-        ydl = YDL({'format': 'webm/mp4'})
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], '47')
-
-        ydl = YDL({'format': '3gp/40/mp4'})
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], '35')
-
-        ydl = YDL({'format': 'example-with-dashes'})
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'example-with-dashes')
-
-    def test_format_selection_audio(self):
-        formats = [
-            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
-            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
-            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
-        ]
-        info_dict = _make_result(formats)
-
-        ydl = YDL({'format': 'bestaudio'})
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'audio-high')
-
-        ydl = YDL({'format': 'worstaudio'})
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'audio-low')
-
-        formats = [
-            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
-            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
-        ]
-        info_dict = _make_result(formats)
-
-        ydl = YDL({'format': 'bestaudio/worstaudio/best'})
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'vid-high')
-
-    def test_format_selection_audio_exts(self):
-        formats = [
-            {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
-            {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
-            {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
-            {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
-            {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
-        ]
-
-        info_dict = _make_result(formats)
-        ydl = YDL({'format': 'best'})
-        ie = YoutubeIE(ydl)
-        ie._sort_formats(info_dict['formats'])
-        ydl.process_ie_result(copy.deepcopy(info_dict))
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'aac-64')
-
-        ydl = YDL({'format': 'mp3'})
-        ie = YoutubeIE(ydl)
-        ie._sort_formats(info_dict['formats'])
-        ydl.process_ie_result(copy.deepcopy(info_dict))
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'mp3-64')
-
-        ydl = YDL({'prefer_free_formats': True})
-        ie = YoutubeIE(ydl)
-        ie._sort_formats(info_dict['formats'])
-        ydl.process_ie_result(copy.deepcopy(info_dict))
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'ogg-64')
-
-    def test_format_selection_video(self):
-        formats = [
-            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
-            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
-        ]
-        info_dict = _make_result(formats)
-
-        ydl = YDL({'format': 'bestvideo'})
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'dash-video-high')
-
-        ydl = YDL({'format': 'worstvideo'})
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'dash-video-low')
-
-    def test_youtube_format_selection(self):
-        order = [
-            '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',
-            # Apple HTTP Live Streaming
-            '96', '95', '94', '93', '92', '132', '151',
-            # 3D
-            '85', '84', '102', '83', '101', '82', '100',
-            # Dash video
-            '137', '248', '136', '247', '135', '246',
-            '245', '244', '134', '243', '133', '242', '160',
-            # Dash audio
-            '141', '172', '140', '171', '139',
-        ]
-
-        def format_info(f_id):
-            info = YoutubeIE._formats[f_id].copy()
-            info['format_id'] = f_id
-            info['url'] = 'url:' + f_id
-            return info
-        formats_order = [format_info(f_id) for f_id in order]
-
-        info_dict = _make_result(list(formats_order), extractor='youtube')
-        ydl = YDL({'format': 'bestvideo+bestaudio'})
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], '137+141')
-        self.assertEqual(downloaded['ext'], 'mp4')
+        self.assertEqual(downloaded['format_id'], u'2')
 
-        info_dict = _make_result(list(formats_order), extractor='youtube')
-        ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'})
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
+        ydl = YDL({'format': u'webm/mp4'})
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], '38')
+        self.assertEqual(downloaded['format_id'], u'47')
 
-        info_dict = _make_result(list(formats_order), extractor='youtube')
-        ydl = YDL({'format': 'bestvideo/best,bestaudio'})
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
-        ydl.process_ie_result(info_dict)
-        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
-        self.assertEqual(downloaded_ids, ['137', '141'])
-
-        info_dict = _make_result(list(formats_order), extractor='youtube')
-        ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])+bestaudio'})
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
-        ydl.process_ie_result(info_dict)
-        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
-        self.assertEqual(downloaded_ids, ['137+141', '248+141'])
-
-        info_dict = _make_result(list(formats_order), extractor='youtube')
-        ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'})
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
-        ydl.process_ie_result(info_dict)
-        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
-        self.assertEqual(downloaded_ids, ['136+141', '247+141'])
-
-        info_dict = _make_result(list(formats_order), extractor='youtube')
-        ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'})
-        yie = YoutubeIE(ydl)
-        yie._sort_formats(info_dict['formats'])
-        ydl.process_ie_result(info_dict)
-        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
-        self.assertEqual(downloaded_ids, ['248+141'])
-
-        for f1, f2 in zip(formats_order, formats_order[1:]):
-            info_dict = _make_result([f1, f2], extractor='youtube')
-            ydl = YDL({'format': 'best/bestvideo'})
-            yie = YoutubeIE(ydl)
-            yie._sort_formats(info_dict['formats'])
-            ydl.process_ie_result(info_dict)
-            downloaded = ydl.downloaded_info_dicts[0]
-            self.assertEqual(downloaded['format_id'], f1['format_id'])
-
-            info_dict = _make_result([f2, f1], extractor='youtube')
-            ydl = YDL({'format': 'best/bestvideo'})
-            yie = YoutubeIE(ydl)
-            yie._sort_formats(info_dict['formats'])
-            ydl.process_ie_result(info_dict)
-            downloaded = ydl.downloaded_info_dicts[0]
-            self.assertEqual(downloaded['format_id'], f1['format_id'])
-
-    def test_invalid_format_specs(self):
-        def assert_syntax_error(format_spec):
-            ydl = YDL({'format': format_spec})
-            info_dict = _make_result([{'format_id': 'foo', 'url': TEST_URL}])
-            self.assertRaises(SyntaxError, ydl.process_ie_result, info_dict)
-
-        assert_syntax_error('bestvideo,,best')
-        assert_syntax_error('+bestaudio')
-        assert_syntax_error('bestvideo+')
-        assert_syntax_error('/')
-
-    def test_format_filtering(self):
-        formats = [
-            {'format_id': 'A', 'filesize': 500, 'width': 1000},
-            {'format_id': 'B', 'filesize': 1000, 'width': 500},
-            {'format_id': 'C', 'filesize': 1000, 'width': 400},
-            {'format_id': 'D', 'filesize': 2000, 'width': 600},
-            {'format_id': 'E', 'filesize': 3000},
-            {'format_id': 'F'},
-            {'format_id': 'G', 'filesize': 1000000},
-        ]
-        for f in formats:
-            f['url'] = 'http://_/'
-            f['ext'] = 'unknown'
-        info_dict = _make_result(formats)
-
-        ydl = YDL({'format': 'best[filesize<3000]'})
+        ydl = YDL({'format': u'3gp/40/mp4'})
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'D')
-
-        ydl = YDL({'format': 'best[filesize<=3000]'})
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'E')
-
-        ydl = YDL({'format': 'best[filesize <= ? 3000]'})
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'F')
-
-        ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'B')
-
-        ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'C')
-
-        ydl = YDL({'format': '[filesize>?1]'})
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'G')
-
-        ydl = YDL({'format': '[filesize<1M]'})
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'E')
-
-        ydl = YDL({'format': '[filesize<1MiB]'})
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'G')
-
-        ydl = YDL({'format': 'all[width>=400][width<=600]'})
-        ydl.process_ie_result(info_dict)
-        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
-        self.assertEqual(downloaded_ids, ['B', 'C', 'D'])
-
-        ydl = YDL({'format': 'best[height<40]'})
-        try:
-            ydl.process_ie_result(info_dict)
-        except ExtractorError:
-            pass
-        self.assertEqual(ydl.downloaded_info_dicts, [])
-
-
-class TestYoutubeDL(unittest.TestCase):
-    def test_subtitles(self):
-        def s_formats(lang, autocaption=False):
-            return [{
-                'ext': ext,
-                'url': 'http://localhost/video.%s.%s' % (lang, ext),
-                '_auto': autocaption,
-            } for ext in ['vtt', 'srt', 'ass']]
-        subtitles = dict((l, s_formats(l)) for l in ['en', 'fr', 'es'])
-        auto_captions = dict((l, s_formats(l, True)) for l in ['it', 'pt', 'es'])
-        info_dict = {
-            'id': 'test',
-            'title': 'Test',
-            'url': 'http://localhost/video.mp4',
-            'subtitles': subtitles,
-            'automatic_captions': auto_captions,
-            'extractor': 'TEST',
-        }
-
-        def get_info(params={}):
-            params.setdefault('simulate', True)
-            ydl = YDL(params)
-            ydl.report_warning = lambda *args, **kargs: None
-            return ydl.process_video_result(info_dict, download=False)
-
-        result = get_info()
-        self.assertFalse(result.get('requested_subtitles'))
-        self.assertEqual(result['subtitles'], subtitles)
-        self.assertEqual(result['automatic_captions'], auto_captions)
-
-        result = get_info({'writesubtitles': True})
-        subs = result['requested_subtitles']
-        self.assertTrue(subs)
-        self.assertEqual(set(subs.keys()), set(['en']))
-        self.assertTrue(subs['en'].get('data') is None)
-        self.assertEqual(subs['en']['ext'], 'ass')
-
-        result = get_info({'writesubtitles': True, 'subtitlesformat': 'foo/srt'})
-        subs = result['requested_subtitles']
-        self.assertEqual(subs['en']['ext'], 'srt')
-
-        result = get_info({'writesubtitles': True, 'subtitleslangs': ['es', 'fr', 'it']})
-        subs = result['requested_subtitles']
-        self.assertTrue(subs)
-        self.assertEqual(set(subs.keys()), set(['es', 'fr']))
-
-        result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
-        subs = result['requested_subtitles']
-        self.assertTrue(subs)
-        self.assertEqual(set(subs.keys()), set(['es', 'pt']))
-        self.assertFalse(subs['es']['_auto'])
-        self.assertTrue(subs['pt']['_auto'])
-
-        result = get_info({'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
-        subs = result['requested_subtitles']
-        self.assertTrue(subs)
-        self.assertEqual(set(subs.keys()), set(['es', 'pt']))
-        self.assertTrue(subs['es']['_auto'])
-        self.assertTrue(subs['pt']['_auto'])
+        self.assertEqual(downloaded['format_id'], u'35')
 
     def test_add_extra_info(self):
         test_dict = {
@@ -459,178 +140,6 @@ class TestYoutubeDL(unittest.TestCase):
         self.assertEqual(test_dict['extractor'], 'Foo')
         self.assertEqual(test_dict['playlist'], 'funny videos')
 
-    def test_prepare_filename(self):
-        info = {
-            'id': '1234',
-            'ext': 'mp4',
-            'width': None,
-        }
-
-        def fname(templ):
-            ydl = YoutubeDL({'outtmpl': templ})
-            return ydl.prepare_filename(info)
-        self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
-        self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
-        # Replace missing fields with 'NA'
-        self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
-
-    def test_format_note(self):
-        ydl = YoutubeDL()
-        self.assertEqual(ydl._format_note({}), '')
-        assertRegexpMatches(self, ydl._format_note({
-            'vbr': 10,
-        }), '^\s*10k$')
-
-    def test_postprocessors(self):
-        filename = 'post-processor-testfile.mp4'
-        audiofile = filename + '.mp3'
-
-        class SimplePP(PostProcessor):
-            def run(self, info):
-                with open(audiofile, 'wt') as f:
-                    f.write('EXAMPLE')
-                return [info['filepath']], info
-
-        def run_pp(params, PP):
-            with open(filename, 'wt') as f:
-                f.write('EXAMPLE')
-            ydl = YoutubeDL(params)
-            ydl.add_post_processor(PP())
-            ydl.post_process(filename, {'filepath': filename})
-
-        run_pp({'keepvideo': True}, SimplePP)
-        self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
-        self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
-        os.unlink(filename)
-        os.unlink(audiofile)
-
-        run_pp({'keepvideo': False}, SimplePP)
-        self.assertFalse(os.path.exists(filename), '%s exists' % filename)
-        self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
-        os.unlink(audiofile)
-
-        class ModifierPP(PostProcessor):
-            def run(self, info):
-                with open(info['filepath'], 'wt') as f:
-                    f.write('MODIFIED')
-                return [], info
-
-        run_pp({'keepvideo': False}, ModifierPP)
-        self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
-        os.unlink(filename)
-
-    def test_match_filter(self):
-        class FilterYDL(YDL):
-            def __init__(self, *args, **kwargs):
-                super(FilterYDL, self).__init__(*args, **kwargs)
-                self.params['simulate'] = True
-
-            def process_info(self, info_dict):
-                super(YDL, self).process_info(info_dict)
-
-            def _match_entry(self, info_dict, incomplete):
-                res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
-                if res is None:
-                    self.downloaded_info_dicts.append(info_dict)
-                return res
-
-        first = {
-            'id': '1',
-            'url': TEST_URL,
-            'title': 'one',
-            'extractor': 'TEST',
-            'duration': 30,
-            'filesize': 10 * 1024,
-        }
-        second = {
-            'id': '2',
-            'url': TEST_URL,
-            'title': 'two',
-            'extractor': 'TEST',
-            'duration': 10,
-            'description': 'foo',
-            'filesize': 5 * 1024,
-        }
-        videos = [first, second]
-
-        def get_videos(filter_=None):
-            ydl = FilterYDL({'match_filter': filter_})
-            for v in videos:
-                ydl.process_ie_result(v, download=True)
-            return [v['id'] for v in ydl.downloaded_info_dicts]
-
-        res = get_videos()
-        self.assertEqual(res, ['1', '2'])
-
-        def f(v):
-            if v['id'] == '1':
-                return None
-            else:
-                return 'Video id is not 1'
-        res = get_videos(f)
-        self.assertEqual(res, ['1'])
-
-        f = match_filter_func('duration < 30')
-        res = get_videos(f)
-        self.assertEqual(res, ['2'])
-
-        f = match_filter_func('description = foo')
-        res = get_videos(f)
-        self.assertEqual(res, ['2'])
-
-        f = match_filter_func('description =? foo')
-        res = get_videos(f)
-        self.assertEqual(res, ['1', '2'])
-
-        f = match_filter_func('filesize > 5KiB')
-        res = get_videos(f)
-        self.assertEqual(res, ['1'])
-
-    def test_playlist_items_selection(self):
-        entries = [{
-            'id': compat_str(i),
-            'title': compat_str(i),
-            'url': TEST_URL,
-        } for i in range(1, 5)]
-        playlist = {
-            '_type': 'playlist',
-            'id': 'test',
-            'entries': entries,
-            'extractor': 'test:playlist',
-            'extractor_key': 'test:playlist',
-            'webpage_url': 'http://example.com',
-        }
-
-        def get_ids(params):
-            ydl = YDL(params)
-            # make a copy because the dictionary can be modified
-            ydl.process_ie_result(playlist.copy())
-            return [int(v['id']) for v in ydl.downloaded_info_dicts]
-
-        result = get_ids({})
-        self.assertEqual(result, [1, 2, 3, 4])
-
-        result = get_ids({'playlistend': 10})
-        self.assertEqual(result, [1, 2, 3, 4])
-
-        result = get_ids({'playlistend': 2})
-        self.assertEqual(result, [1, 2])
-
-        result = get_ids({'playliststart': 10})
-        self.assertEqual(result, [])
-
-        result = get_ids({'playliststart': 2})
-        self.assertEqual(result, [2, 3, 4])
-
-        result = get_ids({'playlist_items': '2-4'})
-        self.assertEqual(result, [2, 3, 4])
-
-        result = get_ids({'playlist_items': '2,4'})
-        self.assertEqual(result, [2, 4])
-
-        result = get_ids({'playlist_items': '10'})
-        self.assertEqual(result, [])
-
 
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

@@ -1,55 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_decrypt_text
-from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
-import base64
-
-# the encrypted data can be generate with 'devscripts/generate_aes_testdata.py'
-
-
-class TestAES(unittest.TestCase):
-    def setUp(self):
-        self.key = self.iv = [0x20, 0x15] + 14 * [0]
-        self.secret_msg = b'Secret message goes here'
-
-    def test_encrypt(self):
-        msg = b'message'
-        key = list(range(16))
-        encrypted = aes_encrypt(bytes_to_intlist(msg), key)
-        decrypted = intlist_to_bytes(aes_decrypt(encrypted, key))
-        self.assertEqual(decrypted, msg)
-
-    def test_cbc_decrypt(self):
-        data = bytes_to_intlist(
-            b"\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6'\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd"
-        )
-        decrypted = intlist_to_bytes(aes_cbc_decrypt(data, self.key, self.iv))
-        self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
-
-    def test_decrypt_text(self):
-        password = intlist_to_bytes(self.key).decode('utf-8')
-        encrypted = base64.b64encode(
-            intlist_to_bytes(self.iv[:8]) +
-            b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
-        ).decode('utf-8')
-        decrypted = (aes_decrypt_text(encrypted, password, 16))
-        self.assertEqual(decrypted, self.secret_msg)
-
-        password = intlist_to_bytes(self.key).decode('utf-8')
-        encrypted = base64.b64encode(
-            intlist_to_bytes(self.iv[:8]) +
-            b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
-        ).decode('utf-8')
-        decrypted = (aes_decrypt_text(encrypted, password, 32))
-        self.assertEqual(decrypted, self.secret_msg)
-
-if __name__ == '__main__':
-    unittest.main()

test/test_age_restriction.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-from __future__ import unicode_literals
 
 # Allow direct execution
 import os
@@ -14,13 +13,13 @@ from youtube_dl import YoutubeDL
 
 
 def _download_restricted(url, filename, age):
-    """ Returns true if the file has been downloaded """
+    """ Returns true iff the file has been downloaded """
 
     params = {
         'age_limit': age,
         'skip_download': True,
         'writeinfojson': True,
-        'outtmpl': '%(id)s.%(ext)s',
+        "outtmpl": "%(id)s.%(ext)s",
     }
     ydl = YoutubeDL(params)
     ydl.add_default_info_extractors()
@@ -45,6 +44,11 @@ class TestAgeRestriction(unittest.TestCase):
             'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
             '505835.mp4', 2, old_age=25)
 
+    def test_pornotube(self):
+        self._assert_restricted(
+            'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
+            '1689755.flv', 13)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_all_urls.py

@@ -1,7 +1,5 @@
 #!/usr/bin/env python
 
-from __future__ import unicode_literals
-
 # Allow direct execution
 import os
 import sys
@@ -9,11 +7,11 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-from test.helper import gettestcases
+from test.helper import get_testcases
 
 from youtube_dl.extractor import (
-    FacebookIE,
     gen_extractors,
+    JustinTVIE,
     YoutubeIE,
 )
 
@@ -30,24 +28,21 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_youtube_playlist_matching(self):
         assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
-        assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q')  # 585
-        assertPlaylist('PL63F0C78739B09958')
-        assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
-        assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')  # 668
-        self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
-        # Top tracks
-        assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
+        assertPlaylist(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist(u'UUBABnxM4Ar9ten8Mdjj1j0Q') #585
+        assertPlaylist(u'PL63F0C78739B09958')
+        assertPlaylist(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+        assertPlaylist(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
+        assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
+        self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
 
     def test_youtube_matching(self):
-        self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
-        self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012'))  # 668
+        self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
+        self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
         self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
         self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
         self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
-        self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
 
     def test_youtube_channel_matching(self):
         assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
@@ -59,7 +54,7 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
 
     def test_youtube_feeds(self):
-        self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
+        self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
         self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
         self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
         self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
@@ -67,12 +62,24 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_youtube_show_matching(self):
         self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
 
-    def test_youtube_search_matching(self):
-        self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
-        self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
+    def test_justin_tv_channelid_matching(self):
+        self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"www.justin.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"www.twitch.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv/"))
+        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/"))
+
+    def test_justintv_videoid_matching(self):
+        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/b/328087483"))
+
+    def test_justin_tv_chapterid_matching(self):
+        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
 
     def test_youtube_extract(self):
-        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
+        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id)
         assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
@@ -80,21 +87,15 @@ class TestAllURLsMatching(unittest.TestCase):
         assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
         assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
 
-    def test_facebook_matching(self):
-        self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
-        self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
-
     def test_no_duplicates(self):
         ies = gen_extractors()
-        for tc in gettestcases(include_onlymatching=True):
+        for tc in get_testcases():
             url = tc['url']
             for ie in ies:
-                if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
+                if type(ie).__name__ in ['GenericIE', tc['name'] + 'IE']:
                     self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
                 else:
-                    self.assertFalse(
-                        ie.suitable(url),
-                        '%s should not match URL %r . That URL belongs to %s.' % (type(ie).__name__, url, tc['name']))
+                    self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
 
     def test_keywords(self):
         self.assertMatch(':ytsubs', ['youtube:subscriptions'])
@@ -102,33 +103,8 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':ythistory', ['youtube:history'])
         self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
         self.assertMatch(':tds', ['ComedyCentralShows'])
-
-    def test_vimeo_matching(self):
-        self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
-        self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
-        self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
-        self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
-        self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
-        self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
-
-    # https://github.com/rg3/youtube-dl/issues/1930
-    def test_soundcloud_not_matching_sets(self):
-        self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
-
-    def test_tumblr(self):
-        self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
-        self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
-
-    def test_pbs(self):
-        # https://github.com/rg3/youtube-dl/issues/2350
-        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
-        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
-
-    def test_yahoo_https(self):
-        # https://github.com/rg3/youtube-dl/issues/2701
-        self.assertMatch(
-            'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
-            ['Yahoo'])
+        self.assertMatch(':colbertreport', ['ComedyCentralShows'])
+        self.assertMatch(':cr', ['ComedyCentralShows'])
 
 
 if __name__ == '__main__':

test/test_cache.py

@@ -1,59 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-
-from __future__ import unicode_literals
-
-import shutil
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-
-from test.helper import FakeYDL
-from youtube_dl.cache import Cache
-
-
-def _is_empty(d):
-    return not bool(os.listdir(d))
-
-
-def _mkdir(d):
-    if not os.path.exists(d):
-        os.mkdir(d)
-
-
-class TestCache(unittest.TestCase):
-    def setUp(self):
-        TEST_DIR = os.path.dirname(os.path.abspath(__file__))
-        TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata')
-        _mkdir(TESTDATA_DIR)
-        self.test_dir = os.path.join(TESTDATA_DIR, 'cache_test')
-        self.tearDown()
-
-    def tearDown(self):
-        if os.path.exists(self.test_dir):
-            shutil.rmtree(self.test_dir)
-
-    def test_cache(self):
-        ydl = FakeYDL({
-            'cachedir': self.test_dir,
-        })
-        c = Cache(ydl)
-        obj = {'x': 1, 'y': ['ä', '\\a', True]}
-        self.assertEqual(c.load('test_cache', 'k.'), None)
-        c.store('test_cache', 'k.', obj)
-        self.assertEqual(c.load('test_cache', 'k2'), None)
-        self.assertFalse(_is_empty(self.test_dir))
-        self.assertEqual(c.load('test_cache', 'k.'), obj)
-        self.assertEqual(c.load('test_cache', 'y'), None)
-        self.assertEqual(c.load('test_cache2', 'k.'), None)
-        c.remove()
-        self.assertFalse(os.path.exists(self.test_dir))
-        self.assertEqual(c.load('test_cache', 'k.'), None)
-
-
-if __name__ == '__main__':
-    unittest.main()

test/test_compat.py

@@ -1,75 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-
-from youtube_dl.utils import get_filesystem_encoding
-from youtube_dl.compat import (
-    compat_getenv,
-    compat_expanduser,
-    compat_shlex_split,
-    compat_urllib_parse_unquote,
-    compat_urllib_parse_unquote_plus,
-)
-
-
-class TestCompat(unittest.TestCase):
-    def test_compat_getenv(self):
-        test_str = 'тест'
-        os.environ['YOUTUBE-DL-TEST'] = (
-            test_str if sys.version_info >= (3, 0)
-            else test_str.encode(get_filesystem_encoding()))
-        self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
-
-    def test_compat_expanduser(self):
-        old_home = os.environ.get('HOME')
-        test_str = 'C:\Documents and Settings\тест\Application Data'
-        os.environ['HOME'] = (
-            test_str if sys.version_info >= (3, 0)
-            else test_str.encode(get_filesystem_encoding()))
-        self.assertEqual(compat_expanduser('~'), test_str)
-        os.environ['HOME'] = old_home
-
-    def test_all_present(self):
-        import youtube_dl.compat
-        all_names = youtube_dl.compat.__all__
-        present_names = set(filter(
-            lambda c: '_' in c and not c.startswith('_'),
-            dir(youtube_dl.compat))) - set(['unicode_literals'])
-        self.assertEqual(all_names, sorted(present_names))
-
-    def test_compat_urllib_parse_unquote(self):
-        self.assertEqual(compat_urllib_parse_unquote('abc%20def'), 'abc def')
-        self.assertEqual(compat_urllib_parse_unquote('%7e/abc+def'), '~/abc+def')
-        self.assertEqual(compat_urllib_parse_unquote(''), '')
-        self.assertEqual(compat_urllib_parse_unquote('%'), '%')
-        self.assertEqual(compat_urllib_parse_unquote('%%'), '%%')
-        self.assertEqual(compat_urllib_parse_unquote('%%%'), '%%%')
-        self.assertEqual(compat_urllib_parse_unquote('%2F'), '/')
-        self.assertEqual(compat_urllib_parse_unquote('%2f'), '/')
-        self.assertEqual(compat_urllib_parse_unquote('%E6%B4%A5%E6%B3%A2'), '津波')
-        self.assertEqual(
-            compat_urllib_parse_unquote('''<meta property="og:description" content="%E2%96%81%E2%96%82%E2%96%83%E2%96%84%25%E2%96%85%E2%96%86%E2%96%87%E2%96%88" />
-%<a href="https://ar.wikipedia.org/wiki/%D8%AA%D8%B3%D9%88%D9%86%D8%A7%D9%85%D9%8A">%a'''),
-            '''<meta property="og:description" content="▁▂▃▄%▅▆▇█" />
-%<a href="https://ar.wikipedia.org/wiki/تسونامي">%a''')
-        self.assertEqual(
-            compat_urllib_parse_unquote('''%28%5E%E2%97%A3_%E2%97%A2%5E%29%E3%81%A3%EF%B8%BB%E3%83%87%E2%95%90%E4%B8%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%86%B6%I%Break%25Things%'''),
-            '''(^◣_◢^)っ︻デ═一    ⇀    ⇀    ⇀    ⇀    ⇀    ↶%I%Break%Things%''')
-
-    def test_compat_urllib_parse_unquote_plus(self):
-        self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
-        self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
-
-    def test_compat_shlex_split(self):
-        self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
-
-if __name__ == '__main__':
-    unittest.main()

test/test_download.py

@@ -1,7 +1,5 @@
 #!/usr/bin/env python
 
-from __future__ import unicode_literals
-
 # Allow direct execution
 import os
 import sys
@@ -9,13 +7,11 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
-    assertGreaterEqual,
-    expect_warnings,
     get_params,
-    gettestcases,
-    expect_info_dict,
+    get_testcases,
     try_rm,
-    report_warning,
+    md5,
+    report_warning
 )
 
 
@@ -25,105 +21,83 @@ import json
 import socket
 
 import youtube_dl.YoutubeDL
-from youtube_dl.compat import (
-    compat_http_client,
+from youtube_dl.utils import (
+    compat_str,
     compat_urllib_error,
     compat_HTTPError,
-)
-from youtube_dl.utils import (
     DownloadError,
     ExtractorError,
-    format_bytes,
     UnavailableVideoError,
 )
 from youtube_dl.extractor import get_info_extractor
 
 RETRIES = 3
 
-
 class YoutubeDL(youtube_dl.YoutubeDL):
     def __init__(self, *args, **kwargs):
         self.to_stderr = self.to_screen
         self.processed_info_dicts = []
         super(YoutubeDL, self).__init__(*args, **kwargs)
-
     def report_warning(self, message):
         # Don't accept warnings during tests
         raise ExtractorError(message)
-
     def process_info(self, info_dict):
         self.processed_info_dicts.append(info_dict)
         return super(YoutubeDL, self).process_info(info_dict)
 
-
 def _file_md5(fn):
     with open(fn, 'rb') as f:
         return hashlib.md5(f.read()).hexdigest()
 
-defs = gettestcases()
+defs = get_testcases()
 
 
 class TestDownload(unittest.TestCase):
     maxDiff = None
-
     def setUp(self):
         self.defs = defs
 
-# Dynamically generate tests
-
-
+### Dynamically generate tests
 def generator(test_case):
 
     def test_template(self):
         ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
         other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
-        is_playlist = any(k.startswith('playlist') for k in test_case)
-        test_cases = test_case.get(
-            'playlist', [] if is_playlist else [test_case])
-
         def print_skipping(reason):
             print('Skipping %s: %s' % (test_case['name'], reason))
         if not ie.working():
             print_skipping('IE marked as not _WORKING')
             return
-
-        for tc in test_cases:
-            info_dict = tc.get('info_dict', {})
-            if not (info_dict.get('id') and info_dict.get('ext')):
-                raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
-
+        if 'playlist' not in test_case:
+            info_dict = test_case.get('info_dict', {})
+            if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
+                print_skipping('The output file cannot be know, the "file" '
+                    'key is missing or the info_dict is incomplete')
+                return
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
             return
         for other_ie in other_ies:
             if not other_ie.working():
-                print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
+                print_skipping(u'test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
                 return
 
         params = get_params(test_case.get('params', {}))
-        if is_playlist and 'playlist' not in test_case:
-            params.setdefault('extract_flat', True)
-            params.setdefault('skip_download', True)
 
-        ydl = YoutubeDL(params, auto_init=False)
+        ydl = YoutubeDL(params)
         ydl.add_default_info_extractors()
         finished_hook_called = set()
-
         def _hook(status):
             if status['status'] == 'finished':
                 finished_hook_called.add(status['filename'])
-        ydl.add_progress_hook(_hook)
-        expect_warnings(ydl, test_case.get('expected_warnings', []))
+        ydl.fd.add_progress_hook(_hook)
 
         def get_tc_filename(tc):
-            return ydl.prepare_filename(tc.get('info_dict', {}))
+            return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
 
-        res_dict = None
-
-        def try_rm_tcs_files(tcs=None):
-            if tcs is None:
-                tcs = test_cases
-            for tc in tcs:
+        test_cases = test_case.get('playlist', [test_case])
+        def try_rm_tcs_files():
+            for tc in test_cases:
                 tc_filename = get_tc_filename(tc)
                 try_rm(tc_filename)
                 try_rm(tc_filename + '.part')
@@ -133,19 +107,14 @@ def generator(test_case):
             try_num = 1
             while True:
                 try:
-                    # We're not using .download here sine that is just a shim
-                    # for outside error handling, and returns the exit code
-                    # instead of the result dict.
-                    res_dict = ydl.extract_info(
-                        test_case['url'],
-                        force_generic_extractor=params.get('force_generic_extractor', False))
+                    ydl.download([test_case['url']])
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
-                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
+                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
                         raise
 
                     if try_num == RETRIES:
-                        report_warning('Failed due to network errors, skipping...')
+                        report_warning(u'Failed due to network errors, skipping...')
                         return
 
                     print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num))
@@ -154,78 +123,53 @@ def generator(test_case):
                 else:
                     break
 
-            if is_playlist:
-                self.assertTrue(res_dict['_type'] in ['playlist', 'multi_video'])
-                self.assertTrue('entries' in res_dict)
-                expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
-
-            if 'playlist_mincount' in test_case:
-                assertGreaterEqual(
-                    self,
-                    len(res_dict['entries']),
-                    test_case['playlist_mincount'],
-                    'Expected at least %d in playlist %s, but got only %d' % (
-                        test_case['playlist_mincount'], test_case['url'],
-                        len(res_dict['entries'])))
-            if 'playlist_count' in test_case:
-                self.assertEqual(
-                    len(res_dict['entries']),
-                    test_case['playlist_count'],
-                    'Expected %d entries in playlist %s, but got %d.' % (
-                        test_case['playlist_count'],
-                        test_case['url'],
-                        len(res_dict['entries']),
-                    ))
-            if 'playlist_duration_sum' in test_case:
-                got_duration = sum(e['duration'] for e in res_dict['entries'])
-                self.assertEqual(
-                    test_case['playlist_duration_sum'], got_duration)
-
             for tc in test_cases:
                 tc_filename = get_tc_filename(tc)
                 if not test_case.get('params', {}).get('skip_download', False):
                     self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
                     self.assertTrue(tc_filename in finished_hook_called)
-                    expected_minsize = tc.get('file_minsize', 10000)
-                    if expected_minsize is not None:
-                        if params.get('test'):
-                            expected_minsize = max(expected_minsize, 10000)
-                        got_fsize = os.path.getsize(tc_filename)
-                        assertGreaterEqual(
-                            self, got_fsize, expected_minsize,
-                            'Expected %s to be at least %s, but it\'s only %s ' %
-                            (tc_filename, format_bytes(expected_minsize),
-                                format_bytes(got_fsize)))
-                    if 'md5' in tc:
-                        md5_for_file = _file_md5(tc_filename)
-                        self.assertEqual(md5_for_file, tc['md5'])
                 info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
-                self.assertTrue(
-                    os.path.exists(info_json_fn),
-                    'Missing info file %s' % info_json_fn)
+                self.assertTrue(os.path.exists(info_json_fn))
+                if 'md5' in tc:
+                    md5_for_file = _file_md5(tc_filename)
+                    self.assertEqual(md5_for_file, tc['md5'])
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
+                for (info_field, expected) in tc.get('info_dict', {}).items():
+                    if isinstance(expected, compat_str) and expected.startswith('md5:'):
+                        got = 'md5:' + md5(info_dict.get(info_field))
+                    else:
+                        got = info_dict.get(info_field)
+                    self.assertEqual(expected, got,
+                        u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
-                expect_info_dict(self, info_dict, tc.get('info_dict', {}))
+                # If checkable fields are missing from the test case, print the info_dict
+                test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
+                    for key, value in info_dict.items()
+                    if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location'))
+                if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()):
+                    sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=2) + u'\n')
+
+                # Check for the presence of mandatory fields
+                for key in ('id', 'url', 'title', 'ext'):
+                    self.assertTrue(key in info_dict.keys() and info_dict[key])
+                # Check for mandatory fields that are automatically set by YoutubeDL
+                for key in ['webpage_url', 'extractor', 'extractor_key']:
+                    self.assertTrue(info_dict.get(key), u'Missing field: %s' % key)
         finally:
             try_rm_tcs_files()
-            if is_playlist and res_dict is not None and res_dict.get('entries'):
-                # Remove all other files that may have been extracted if the
-                # extractor returns full results even with extract_flat
-                res_tcs = [{'info_dict': e} for e in res_dict['entries']]
-                try_rm_tcs_files(res_tcs)
 
     return test_template
 
-# And add them to TestDownload
+### And add them to TestDownload
 for n, test_case in enumerate(defs):
     test_method = generator(test_case)
     tname = 'test_' + str(test_case['name'])
     i = 1
     while hasattr(TestDownload, tname):
-        tname = 'test_%s_%d' % (test_case['name'], i)
+        tname = 'test_'  + str(test_case['name']) + '_' + str(i)
         i += 1
-    test_method.__name__ = str(tname)
+    test_method.__name__ = tname
     setattr(TestDownload, test_method.__name__, test_method)
     del test_method
 

test/test_execution.py

@@ -1,43 +1,26 @@
-#!/usr/bin/env python
-# coding: utf-8
-
-from __future__ import unicode_literals
-
 import unittest
 
 import sys
 import os
 import subprocess
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from youtube_dl.utils import encodeArgument
 
 rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 
-
 try:
     _DEV_NULL = subprocess.DEVNULL
 except AttributeError:
     _DEV_NULL = open(os.devnull, 'wb')
 
-
 class TestExecution(unittest.TestCase):
     def test_import(self):
         subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir)
 
     def test_module_exec(self):
-        if sys.version_info >= (2, 7):  # Python 2.6 doesn't support package execution
+        if sys.version_info >= (2,7): # Python 2.6 doesn't support package execution
             subprocess.check_call([sys.executable, '-m', 'youtube_dl', '--version'], cwd=rootDir, stdout=_DEV_NULL)
 
     def test_main_exec(self):
         subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
 
-    def test_cmdline_umlauts(self):
-        p = subprocess.Popen(
-            [sys.executable, 'youtube_dl/__main__.py', encodeArgument('ä'), '--version'],
-            cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
-        _, stderr = p.communicate()
-        self.assertFalse(stderr)
-
 if __name__ == '__main__':
     unittest.main()

test/test_http.py

@@ -1,119 +0,0 @@
-#!/usr/bin/env python
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_http_server, compat_urllib_request
-import ssl
-import threading
-
-TEST_DIR = os.path.dirname(os.path.abspath(__file__))
-
-
-class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
-    def log_message(self, format, *args):
-        pass
-
-    def do_GET(self):
-        if self.path == '/video.html':
-            self.send_response(200)
-            self.send_header('Content-Type', 'text/html; charset=utf-8')
-            self.end_headers()
-            self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
-        elif self.path == '/vid.mp4':
-            self.send_response(200)
-            self.send_header('Content-Type', 'video/mp4')
-            self.end_headers()
-            self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
-        else:
-            assert False
-
-
-class FakeLogger(object):
-    def debug(self, msg):
-        pass
-
-    def warning(self, msg):
-        pass
-
-    def error(self, msg):
-        pass
-
-
-class TestHTTP(unittest.TestCase):
-    def setUp(self):
-        certfn = os.path.join(TEST_DIR, 'testcert.pem')
-        self.httpd = compat_http_server.HTTPServer(
-            ('localhost', 0), HTTPTestRequestHandler)
-        self.httpd.socket = ssl.wrap_socket(
-            self.httpd.socket, certfile=certfn, server_side=True)
-        self.port = self.httpd.socket.getsockname()[1]
-        self.server_thread = threading.Thread(target=self.httpd.serve_forever)
-        self.server_thread.daemon = True
-        self.server_thread.start()
-
-    def test_nocheckcertificate(self):
-        if sys.version_info >= (2, 7, 9):  # No certificate checking anyways
-            ydl = YoutubeDL({'logger': FakeLogger()})
-            self.assertRaises(
-                Exception,
-                ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
-
-        ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
-        r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
-        self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
-
-
-def _build_proxy_handler(name):
-    class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
-        proxy_name = name
-
-        def log_message(self, format, *args):
-            pass
-
-        def do_GET(self):
-            self.send_response(200)
-            self.send_header('Content-Type', 'text/plain; charset=utf-8')
-            self.end_headers()
-            self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode('utf-8'))
-    return HTTPTestRequestHandler
-
-
-class TestProxy(unittest.TestCase):
-    def setUp(self):
-        self.proxy = compat_http_server.HTTPServer(
-            ('localhost', 0), _build_proxy_handler('normal'))
-        self.port = self.proxy.socket.getsockname()[1]
-        self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
-        self.proxy_thread.daemon = True
-        self.proxy_thread.start()
-
-        self.cn_proxy = compat_http_server.HTTPServer(
-            ('localhost', 0), _build_proxy_handler('cn'))
-        self.cn_port = self.cn_proxy.socket.getsockname()[1]
-        self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever)
-        self.cn_proxy_thread.daemon = True
-        self.cn_proxy_thread.start()
-
-    def test_proxy(self):
-        cn_proxy = 'localhost:{0}'.format(self.cn_port)
-        ydl = YoutubeDL({
-            'proxy': 'localhost:{0}'.format(self.port),
-            'cn_verification_proxy': cn_proxy,
-        })
-        url = 'http://foo.com/bar'
-        response = ydl.urlopen(url).read().decode('utf-8')
-        self.assertEqual(response, 'normal: {0}'.format(url))
-
-        req = compat_urllib_request.Request(url)
-        req.add_header('Ytdl-request-proxy', cn_proxy)
-        response = ydl.urlopen(req).read().decode('utf-8')
-        self.assertEqual(response, 'cn: {0}'.format(url))
-
-if __name__ == '__main__':
-    unittest.main()

test/test_jsinterp.py

@@ -1,106 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from youtube_dl.jsinterp import JSInterpreter
-
-
-class TestJSInterpreter(unittest.TestCase):
-    def test_basic(self):
-        jsi = JSInterpreter('function x(){;}')
-        self.assertEqual(jsi.call_function('x'), None)
-
-        jsi = JSInterpreter('function x3(){return 42;}')
-        self.assertEqual(jsi.call_function('x3'), 42)
-
-    def test_calc(self):
-        jsi = JSInterpreter('function x4(a){return 2*a+1;}')
-        self.assertEqual(jsi.call_function('x4', 3), 7)
-
-    def test_empty_return(self):
-        jsi = JSInterpreter('function f(){return; y()}')
-        self.assertEqual(jsi.call_function('f'), None)
-
-    def test_morespace(self):
-        jsi = JSInterpreter('function x (a) { return 2 * a + 1 ; }')
-        self.assertEqual(jsi.call_function('x', 3), 7)
-
-        jsi = JSInterpreter('function f () { x =  2  ; return x; }')
-        self.assertEqual(jsi.call_function('f'), 2)
-
-    def test_strange_chars(self):
-        jsi = JSInterpreter('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }')
-        self.assertEqual(jsi.call_function('$_xY1', 20), 21)
-
-    def test_operators(self):
-        jsi = JSInterpreter('function f(){return 1 << 5;}')
-        self.assertEqual(jsi.call_function('f'), 32)
-
-        jsi = JSInterpreter('function f(){return 19 & 21;}')
-        self.assertEqual(jsi.call_function('f'), 17)
-
-        jsi = JSInterpreter('function f(){return 11 >> 2;}')
-        self.assertEqual(jsi.call_function('f'), 2)
-
-    def test_array_access(self):
-        jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
-        self.assertEqual(jsi.call_function('f'), [5, 2, 7])
-
-    def test_parens(self):
-        jsi = JSInterpreter('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}')
-        self.assertEqual(jsi.call_function('f'), 7)
-
-        jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
-        self.assertEqual(jsi.call_function('f'), 9)
-
-    def test_assignments(self):
-        jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
-        self.assertEqual(jsi.call_function('f'), 31)
-
-        jsi = JSInterpreter('function f(){var x = 20; x += 30 + 1; return x;}')
-        self.assertEqual(jsi.call_function('f'), 51)
-
-        jsi = JSInterpreter('function f(){var x = 20; x -= 30 + 1; return x;}')
-        self.assertEqual(jsi.call_function('f'), -11)
-
-    def test_comments(self):
-        'Skipping: Not yet fully implemented'
-        return
-        jsi = JSInterpreter('''
-        function x() {
-            var x = /* 1 + */ 2;
-            var y = /* 30
-            * 40 */ 50;
-            return x + y;
-        }
-        ''')
-        self.assertEqual(jsi.call_function('x'), 52)
-
-        jsi = JSInterpreter('''
-        function f() {
-            var x = "/*";
-            var y = 1 /* comment */ + 2;
-            return y;
-        }
-        ''')
-        self.assertEqual(jsi.call_function('f'), 3)
-
-    def test_precedence(self):
-        jsi = JSInterpreter('''
-        function x() {
-            var a = [10, 20, 30, 40, 50];
-            var b = 6;
-            a[0]=a[b%a.length];
-            return a;
-        }''')
-        self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
-
-
-if __name__ == '__main__':
-    unittest.main()

test/test_netrc.py

@@ -1,26 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-
-from youtube_dl.extractor import (
-    gen_extractors,
-)
-
-
-class TestNetRc(unittest.TestCase):
-    def test_netrc_present(self):
-        for ie in gen_extractors():
-            if not hasattr(ie, '_login'):
-                continue
-            self.assertTrue(
-                hasattr(ie, '_NETRC_MACHINE'),
-                'Extractor %s supports login, but is missing a _NETRC_MACHINE property' % ie.IE_NAME)
-
-
-if __name__ == '__main__':
-    unittest.main()

test/test_playlists.py

@@ -0,0 +1,115 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import FakeYDL
+
+
+from youtube_dl.extractor import (
+    DailymotionPlaylistIE,
+    DailymotionUserIE,
+    VimeoChannelIE,
+    UstreamChannelIE,
+    SoundcloudSetIE,
+    SoundcloudUserIE,
+    LivestreamIE,
+    NHLVideocenterIE,
+    BambuserChannelIE,
+    BandcampAlbumIE
+)
+
+
+class TestPlaylists(unittest.TestCase):
+    def assertIsPlaylist(self, info):
+        """Make sure the info has '_type' set to 'playlist'"""
+        self.assertEqual(info['_type'], 'playlist')
+
+    def test_dailymotion_playlist(self):
+        dl = FakeYDL()
+        ie = DailymotionPlaylistIE(dl)
+        result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'SPORT')
+        self.assertTrue(len(result['entries']) > 20)
+
+    def test_dailymotion_user(self):
+        dl = FakeYDL()
+        ie = DailymotionUserIE(dl)
+        result = ie.extract('http://www.dailymotion.com/user/generation-quoi/')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Génération Quoi')
+        self.assertTrue(len(result['entries']) >= 26)
+
+    def test_vimeo_channel(self):
+        dl = FakeYDL()
+        ie = VimeoChannelIE(dl)
+        result = ie.extract('http://vimeo.com/channels/tributes')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Vimeo Tributes')
+        self.assertTrue(len(result['entries']) > 24)
+
+    def test_ustream_channel(self):
+        dl = FakeYDL()
+        ie = UstreamChannelIE(dl)
+        result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'5124905')
+        self.assertTrue(len(result['entries']) >= 11)
+
+    def test_soundcloud_set(self):
+        dl = FakeYDL()
+        ie = SoundcloudSetIE(dl)
+        result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'The Royal Concept EP')
+        self.assertTrue(len(result['entries']) >= 6)
+
+    def test_soundcloud_user(self):
+        dl = FakeYDL()
+        ie = SoundcloudUserIE(dl)
+        result = ie.extract('https://soundcloud.com/the-concept-band')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'9615865')
+        self.assertTrue(len(result['entries']) >= 12)
+
+    def test_livestream_event(self):
+        dl = FakeYDL()
+        ie = LivestreamIE(dl)
+        result = ie.extract('http://new.livestream.com/tedx/cityenglish')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'TEDCity2.0 (English)')
+        self.assertTrue(len(result['entries']) >= 4)
+
+    def test_nhl_videocenter(self):
+        dl = FakeYDL()
+        ie = NHLVideocenterIE(dl)
+        result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'999')
+        self.assertEqual(result['title'], u'Highlights')
+        self.assertEqual(len(result['entries']), 12)
+
+    def test_bambuser_channel(self):
+        dl = FakeYDL()
+        ie = BambuserChannelIE(dl)
+        result = ie.extract('http://bambuser.com/channel/pixelversity')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'pixelversity')
+        self.assertTrue(len(result['entries']) >= 60)
+
+    def test_bandcamp_album(self):
+        dl = FakeYDL()
+        ie = BandcampAlbumIE(dl)
+        result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Nightmare Night EP')
+        self.assertTrue(len(result['entries']) >= 4)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_postprocessors.py

@@ -1,17 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from youtube_dl.postprocessor import MetadataFromTitlePP
-
-
-class TestMetadataFromTitle(unittest.TestCase):
-    def test_format_to_regex(self):
-        pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
-        self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)')

test/test_subtitles.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-from __future__ import unicode_literals
 
 # Allow direct execution
 import os
@@ -11,64 +10,57 @@ from test.helper import FakeYDL, md5
 
 
 from youtube_dl.extractor import (
-    BlipTVIE,
     YoutubeIE,
     DailymotionIE,
     TEDIE,
-    VimeoIE,
-    WallaIE,
-    CeskaTelevizeIE,
-    LyndaIE,
-    NPOIE,
-    ComedyCentralIE,
-    NRKTVIE,
-    RaiIE,
-    VikiIE,
-    ThePlatformIE,
-    ThePlatformFeedIE,
-    RTVEALaCartaIE,
-    FunnyOrDieIE,
 )
 
 
 class BaseTestSubtitles(unittest.TestCase):
     url = None
     IE = None
-
     def setUp(self):
         self.DL = FakeYDL()
-        self.ie = self.IE()
-        self.DL.add_info_extractor(self.ie)
+        self.ie = self.IE(self.DL)
 
     def getInfoDict(self):
-        info_dict = self.DL.extract_info(self.url, download=False)
+        info_dict = self.ie.extract(self.url)
         return info_dict
 
     def getSubtitles(self):
         info_dict = self.getInfoDict()
-        subtitles = info_dict['requested_subtitles']
-        if not subtitles:
-            return subtitles
-        for sub_info in subtitles.values():
-            if sub_info.get('data') is None:
-                uf = self.DL.urlopen(sub_info['url'])
-                sub_info['data'] = uf.read().decode('utf-8')
-        return dict((l, sub_info['data']) for l, sub_info in subtitles.items())
+        return info_dict['subtitles']
 
 
 class TestYoutubeSubtitles(BaseTestSubtitles):
     url = 'QRS8MkLhQmM'
     IE = YoutubeIE
 
+    def getSubtitles(self):
+        info_dict = self.getInfoDict()
+        return info_dict[0]['subtitles']
+
+    def test_youtube_no_writesubtitles(self):
+        self.DL.params['writesubtitles'] = False
+        subtitles = self.getSubtitles()
+        self.assertEqual(subtitles, None)
+
+    def test_youtube_subtitles(self):
+        self.DL.params['writesubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
+
+    def test_youtube_subtitles_lang(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitleslangs'] = ['it']
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
+
     def test_youtube_allsubtitles(self):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(len(subtitles.keys()), 13)
-        self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
-        self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
-        for lang in ['it', 'fr', 'de']:
-            self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
 
     def test_youtube_subtitles_sbv_format(self):
         self.DL.params['writesubtitles'] = True
@@ -80,7 +72,13 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
         self.DL.params['writesubtitles'] = True
         self.DL.params['subtitlesformat'] = 'vtt'
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
+        self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7')
+
+    def test_youtube_list_subtitles(self):
+        self.DL.expect_warning(u'Video doesn\'t have automatic captions')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
 
     def test_youtube_automatic_captions(self):
         self.url = '8YoUxe5ncPo'
@@ -89,262 +87,124 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
         subtitles = self.getSubtitles()
         self.assertTrue(subtitles['it'] is not None)
 
-    def test_youtube_translated_subtitles(self):
-        # This video has a subtitles track, which can be translated
-        self.url = 'Ky9eprVWzlI'
-        self.DL.params['writeautomaticsub'] = True
-        self.DL.params['subtitleslangs'] = ['it']
-        subtitles = self.getSubtitles()
-        self.assertTrue(subtitles['it'] is not None)
-
     def test_youtube_nosubtitles(self):
-        self.DL.expect_warning('video doesn\'t have subtitles')
-        self.url = 'n5BB19UTcdA'
+        self.DL.expect_warning(u'video doesn\'t have subtitles')
+        self.url = 'sAjKT8FhjI8'
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertFalse(subtitles)
+        self.assertEqual(len(subtitles), 0)
+
+    def test_youtube_multiple_langs(self):
+        self.url = 'QRS8MkLhQmM'
+        self.DL.params['writesubtitles'] = True
+        langs = ['it', 'fr', 'de']
+        self.DL.params['subtitleslangs'] = langs
+        subtitles = self.getSubtitles()
+        for lang in langs:
+            self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
 
 class TestDailymotionSubtitles(BaseTestSubtitles):
     url = 'http://www.dailymotion.com/video/xczg00'
     IE = DailymotionIE
 
+    def test_no_writesubtitles(self):
+        subtitles = self.getSubtitles()
+        self.assertEqual(subtitles, None)
+
+    def test_subtitles(self):
+        self.DL.params['writesubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
+
+    def test_subtitles_lang(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitleslangs'] = ['fr']
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
+
     def test_allsubtitles(self):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertTrue(len(subtitles.keys()) >= 6)
-        self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
-        self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
-        for lang in ['es', 'fr', 'de']:
-            self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
+        self.assertEqual(len(subtitles.keys()), 5)
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_automatic_captions(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslang'] = ['en']
+        subtitles = self.getSubtitles()
+        self.assertTrue(len(subtitles.keys()) == 0)
 
     def test_nosubtitles(self):
-        self.DL.expect_warning('video doesn\'t have subtitles')
+        self.DL.expect_warning(u'video doesn\'t have subtitles')
         self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertFalse(subtitles)
+        self.assertEqual(len(subtitles), 0)
+
+    def test_multiple_langs(self):
+        self.DL.params['writesubtitles'] = True
+        langs = ['es', 'fr', 'de']
+        self.DL.params['subtitleslangs'] = langs
+        subtitles = self.getSubtitles()
+        for lang in langs:
+            self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
 
 class TestTedSubtitles(BaseTestSubtitles):
     url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
     IE = TEDIE
 
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
+    def test_no_writesubtitles(self):
         subtitles = self.getSubtitles()
-        self.assertTrue(len(subtitles.keys()) >= 28)
-        self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
-        self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
-        for lang in ['es', 'fr', 'de']:
-            self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
+        self.assertEqual(subtitles, None)
 
+    def test_subtitles(self):
+        self.DL.params['writesubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '2154f31ff9b9f89a0aa671537559c21d')
 
-class TestBlipTVSubtitles(BaseTestSubtitles):
-    url = 'http://blip.tv/a/a-6603250'
-    IE = BlipTVIE
+    def test_subtitles_lang(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitleslangs'] = ['fr']
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['fr']), '7616cbc6df20ec2c1204083c83871cf6')
 
     def test_allsubtitles(self):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4')
+        self.assertEqual(len(subtitles.keys()), 28)
 
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
 
-class TestVimeoSubtitles(BaseTestSubtitles):
-    url = 'http://vimeo.com/76979871'
-    IE = VimeoIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
+    def test_automatic_captions(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslang'] = ['en']
         subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
-        self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
-        self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
+        self.assertTrue(len(subtitles.keys()) == 0)
 
-    def test_nosubtitles(self):
-        self.DL.expect_warning('video doesn\'t have subtitles')
-        self.url = 'http://vimeo.com/56015672'
+    def test_multiple_langs(self):
         self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
+        langs = ['es', 'fr', 'de']
+        self.DL.params['subtitleslangs'] = langs
         subtitles = self.getSubtitles()
-        self.assertFalse(subtitles)
-
-
-class TestWallaSubtitles(BaseTestSubtitles):
-    url = 'http://vod.walla.co.il/movie/2705958/the-yes-men'
-    IE = WallaIE
-
-    def test_allsubtitles(self):
-        self.DL.expect_warning('Automatic Captions not supported by this server')
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['heb']))
-        self.assertEqual(md5(subtitles['heb']), 'e758c5d7cb982f6bef14f377ec7a3920')
-
-    def test_nosubtitles(self):
-        self.DL.expect_warning('video doesn\'t have subtitles')
-        self.url = 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one'
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertFalse(subtitles)
-
-
-class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
-    url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
-    IE = CeskaTelevizeIE
-
-    def test_allsubtitles(self):
-        self.DL.expect_warning('Automatic Captions not supported by this server')
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['cs']))
-        self.assertTrue(len(subtitles['cs']) > 20000)
-
-    def test_nosubtitles(self):
-        self.DL.expect_warning('video doesn\'t have subtitles')
-        self.url = 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220'
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertFalse(subtitles)
-
-
-class TestLyndaSubtitles(BaseTestSubtitles):
-    url = 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html'
-    IE = LyndaIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), '09bbe67222259bed60deaa26997d73a7')
-
-
-class TestNPOSubtitles(BaseTestSubtitles):
-    url = 'http://www.npo.nl/nos-journaal/28-08-2014/POW_00722860'
-    IE = NPOIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['nl']))
-        self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4')
-
-
-class TestMTVSubtitles(BaseTestSubtitles):
-    url = 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother'
-    IE = ComedyCentralIE
-
-    def getInfoDict(self):
-        return super(TestMTVSubtitles, self).getInfoDict()['entries'][0]
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), 'b9f6ca22a6acf597ec76f61749765e65')
-
-
-class TestNRKSubtitles(BaseTestSubtitles):
-    url = 'http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1'
-    IE = NRKTVIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['no']))
-        self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2')
-
-
-class TestRaiSubtitles(BaseTestSubtitles):
-    url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
-    IE = RaiIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['it']))
-        self.assertEqual(md5(subtitles['it']), 'b1d90a98755126b61e667567a1f6680a')
-
-
-class TestVikiSubtitles(BaseTestSubtitles):
-    url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
-    IE = VikiIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), '53cb083a5914b2d84ef1ab67b880d18a')
-
-
-class TestThePlatformSubtitles(BaseTestSubtitles):
-    # from http://www.3playmedia.com/services-features/tools/integrations/theplatform/
-    # (see http://theplatform.com/about/partners/type/subtitles-closed-captioning/)
-    url = 'theplatform:JFUjUE1_ehvq'
-    IE = ThePlatformIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
-
-
-class TestThePlatformFeedSubtitles(BaseTestSubtitles):
-    url = 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207'
-    IE = ThePlatformFeedIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), '48649a22e82b2da21c9a67a395eedade')
-
-
-class TestRtveSubtitles(BaseTestSubtitles):
-    url = 'http://www.rtve.es/alacarta/videos/los-misterios-de-laura/misterios-laura-capitulo-32-misterio-del-numero-17-2-parte/2428621/'
-    IE = RTVEALaCartaIE
-
-    def test_allsubtitles(self):
-        print('Skipping, only available from Spain')
-        return
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['es']))
-        self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
-
-
-class TestFunnyOrDieSubtitles(BaseTestSubtitles):
-    url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
-    IE = FunnyOrDieIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
-
+        for lang in langs:
+            self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
 if __name__ == '__main__':
     unittest.main()

test/test_swfinterp.py

@@ -1,80 +0,0 @@
-#!/usr/bin/env python
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-
-import errno
-import io
-import json
-import re
-import subprocess
-
-from youtube_dl.swfinterp import SWFInterpreter
-
-
-TEST_DIR = os.path.join(
-    os.path.dirname(os.path.abspath(__file__)), 'swftests')
-
-
-class TestSWFInterpreter(unittest.TestCase):
-    pass
-
-
-def _make_testfunc(testfile):
-    m = re.match(r'^(.*)\.(as)$', testfile)
-    if not m:
-        return
-    test_id = m.group(1)
-
-    def test_func(self):
-        as_file = os.path.join(TEST_DIR, testfile)
-        swf_file = os.path.join(TEST_DIR, test_id + '.swf')
-        if ((not os.path.exists(swf_file)) or
-                os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
-            # Recompile
-            try:
-                subprocess.check_call([
-                    'mxmlc', '-output', swf_file,
-                    '-static-link-runtime-shared-libraries', as_file])
-            except OSError as ose:
-                if ose.errno == errno.ENOENT:
-                    print('mxmlc not found! Skipping test.')
-                    return
-                raise
-
-        with open(swf_file, 'rb') as swf_f:
-            swf_content = swf_f.read()
-        swfi = SWFInterpreter(swf_content)
-
-        with io.open(as_file, 'r', encoding='utf-8') as as_f:
-            as_content = as_f.read()
-
-        def _find_spec(key):
-            m = re.search(
-                r'(?m)^//\s*%s:\s*(.*?)\n' % re.escape(key), as_content)
-            if not m:
-                raise ValueError('Cannot find %s in %s' % (key, testfile))
-            return json.loads(m.group(1))
-
-        input_args = _find_spec('input')
-        output = _find_spec('output')
-
-        swf_class = swfi.extract_class(test_id)
-        func = swfi.extract_function(swf_class, 'main')
-        res = func(input_args)
-        self.assertEqual(res, output)
-
-    test_func.__name__ = str('test_swf_' + test_id)
-    setattr(TestSWFInterpreter, test_func.__name__, test_func)
-
-
-for testfile in os.listdir(TEST_DIR):
-    _make_testfunc(testfile)
-
-if __name__ == '__main__':
-    unittest.main()

test/test_unicode_literals.py

@@ -1,63 +0,0 @@
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-import io
-import re
-
-rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
-
-IGNORED_FILES = [
-    'setup.py',  # http://bugs.python.org/issue13943
-    'conf.py',
-    'buildserver.py',
-]
-
-IGNORED_DIRS = [
-    '.git',
-    '.tox',
-]
-
-from test.helper import assertRegexpMatches
-
-
-class TestUnicodeLiterals(unittest.TestCase):
-    def test_all_files(self):
-        for dirpath, dirnames, filenames in os.walk(rootDir):
-            for ignore_dir in IGNORED_DIRS:
-                if ignore_dir in dirnames:
-                    # If we remove the directory from dirnames os.walk won't
-                    # recurse into it
-                    dirnames.remove(ignore_dir)
-            for basename in filenames:
-                if not basename.endswith('.py'):
-                    continue
-                if basename in IGNORED_FILES:
-                    continue
-
-                fn = os.path.join(dirpath, basename)
-                with io.open(fn, encoding='utf-8') as inf:
-                    code = inf.read()
-
-                if "'" not in code and '"' not in code:
-                    continue
-                assertRegexpMatches(
-                    self,
-                    code,
-                    r'(?:(?:#.*?|\s*)\n)*from __future__ import (?:[a-z_]+,\s*)*unicode_literals',
-                    'unicode_literals import  missing in %s' % fn)
-
-                m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code)
-                if m is not None:
-                    self.assertTrue(
-                        m is None,
-                        'u present in %s, around %s' % (
-                            fn, code[m.start() - 10:m.end() + 10]))
-
-
-if __name__ == '__main__':
-    unittest.main()

test/test_utils.py

@@ -1,8 +1,6 @@
 #!/usr/bin/env python
 # coding: utf-8
 
-from __future__ import unicode_literals
-
 # Allow direct execution
 import os
 import sys
@@ -11,64 +9,30 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
 # Various small unit tests
-import io
-import json
 import xml.etree.ElementTree
 
+#from youtube_dl.utils import htmlentity_transform
 from youtube_dl.utils import (
-    age_restricted,
-    args_to_str,
-    clean_html,
-    DateRange,
-    detect_exe_version,
-    encodeFilename,
-    escape_rfc3986,
-    escape_url,
-    ExtractorError,
-    find_xpath_attr,
-    fix_xml_ampersands,
-    InAdvancePagedList,
-    intlist_to_bytes,
-    is_html,
-    js_to_json,
-    limit_length,
-    OnDemandPagedList,
-    orderedSet,
-    parse_duration,
-    parse_filesize,
-    parse_iso8601,
-    read_batch_urls,
-    sanitize_filename,
-    sanitize_path,
-    prepend_extension,
-    replace_extension,
-    shell_quote,
-    smuggle_url,
-    str_to_int,
-    strip_jsonp,
-    struct_unpack,
     timeconvert,
+    sanitize_filename,
     unescapeHTML,
+    orderedSet,
+    DateRange,
     unified_strdate,
-    unsmuggle_url,
-    uppercase_escape,
-    lowercase_escape,
-    url_basename,
-    urlencode_postdata,
-    version_tuple,
+    find_xpath_attr,
+    get_meta_content,
     xpath_with_ns,
-    xpath_element,
-    xpath_text,
-    xpath_attr,
-    render_table,
-    match_str,
-    parse_dfxp_time_expr,
-    dfxp2srt,
-    cli_option,
-    cli_valueless_option,
-    cli_bool_option,
+    smuggle_url,
+    unsmuggle_url,
+    shell_quote,
+    encodeFilename,
 )
 
+if sys.version_info < (3, 0):
+    _compat_str = lambda b: b.decode('unicode-escape')
+else:
+    _compat_str = lambda s: s
+
 
 class TestUtil(unittest.TestCase):
     def test_timeconvert(self):
@@ -90,20 +54,11 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('this - that', sanitize_filename('this: that'))
 
         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
-        aumlaut = 'ä'
+        aumlaut = _compat_str('\xe4')
         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
-        tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
+        tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
         self.assertEqual(sanitize_filename(tests), tests)
 
-        self.assertEqual(
-            sanitize_filename('New World record at 0:12:34'),
-            'New World record at 0_12_34')
-
-        self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
-        self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
-        self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
-        self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
-
         forbidden = '"\0\\/'
         for fc in forbidden:
             for fbc in forbidden:
@@ -123,9 +78,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 
-        tests = 'a\xe4b\u4e2d\u56fd\u7684c'
+        tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
-        self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
+        self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
 
         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
         for fc in forbidden:
@@ -133,8 +88,8 @@ class TestUtil(unittest.TestCase):
                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 
         # Handle a common case more neatly
-        self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
-        self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
+        self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
+        self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
         # .. but make sure the file name is never empty
         self.assertTrue(sanitize_filename('-', restricted=True) != '')
         self.assertTrue(sanitize_filename(':', restricted=True) != '')
@@ -144,74 +99,18 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 
-    def test_sanitize_path(self):
-        if sys.platform != 'win32':
-            return
-
-        self.assertEqual(sanitize_path('abc'), 'abc')
-        self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
-        self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
-        self.assertEqual(sanitize_path('abc|def'), 'abc#def')
-        self.assertEqual(sanitize_path('<>:"|?*'), '#######')
-        self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
-        self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
-
-        self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
-        self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
-
-        self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
-        self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
-        self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
-        self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
-
-        self.assertEqual(
-            sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
-            'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
-
-        self.assertEqual(
-            sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
-            'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
-        self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
-        self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
-        self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
-
-        self.assertEqual(sanitize_path('../abc'), '..\\abc')
-        self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
-        self.assertEqual(sanitize_path('./abc'), 'abc')
-        self.assertEqual(sanitize_path('./../abc'), '..\\abc')
-
-    def test_prepend_extension(self):
-        self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
-        self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
-        self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
-        self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
-        self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
-        self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
-
-    def test_replace_extension(self):
-        self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
-        self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
-        self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
-        self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
-        self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
-        self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
-
     def test_ordered_set(self):
         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
         self.assertEqual(orderedSet([]), [])
         self.assertEqual(orderedSet([1]), [1])
-        # keep the list ordered
+        #keep the list ordered
         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 
     def test_unescape_html(self):
-        self.assertEqual(unescapeHTML('%20;'), '%20;')
-        self.assertEqual(unescapeHTML('&#x2F;'), '/')
-        self.assertEqual(unescapeHTML('&#47;'), '/')
-        self.assertEqual(
-            unescapeHTML('&eacute;'), 'é')
-
+        self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
+        
     def test_daterange(self):
-        _20century = DateRange("19000101", "20000101")
+        _20century = DateRange("19000101","20000101")
         self.assertFalse("17890714" in _20century)
         _ac = DateRange("00010101")
         self.assertTrue("19690721" in _ac)
@@ -223,41 +122,33 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
-        self.assertEqual(unified_strdate('1968 12 10'), '19681210')
-        self.assertEqual(unified_strdate('1968-12-10'), '19681210')
-        self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
-        self.assertEqual(
-            unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
-            '20141126')
-        self.assertEqual(
-            unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
-            '20150202')
-        self.assertEqual(unified_strdate('25-09-2014'), '20140925')
 
     def test_find_xpath_attr(self):
-        testxml = '''<root>
+        testxml = u'''<root>
             <node/>
             <node x="a"/>
             <node x="a" y="c" />
             <node x="b" y="d" />
-            <node x="" />
         </root>'''
         doc = xml.etree.ElementTree.fromstring(testxml)
 
-        self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
-        self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
-        self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
-        self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
-        self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
-        self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
-        self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
-        self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
+
+    def test_meta_parser(self):
+        testhtml = u'''
+        <head>
+            <meta name="description" content="foo &amp; bar">
+            <meta content='Plato' name='author'/>
+        </head>
+        '''
+        get_meta = lambda name: get_meta_content(name, testhtml)
+        self.assertEqual(get_meta('description'), u'foo & bar')
+        self.assertEqual(get_meta('author'), 'Plato')
 
     def test_xpath_with_ns(self):
-        testxml = '''<root xmlns:media="http://example.com/">
+        testxml = u'''<root xmlns:media="http://example.com/">
             <media:song>
                 <media:author>The Author</media:author>
                 <url>http://server.com/download.mp3</url>
@@ -266,48 +157,11 @@ class TestUtil(unittest.TestCase):
         doc = xml.etree.ElementTree.fromstring(testxml)
         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
         self.assertTrue(find('media:song') is not None)
-        self.assertEqual(find('media:song/media:author').text, 'The Author')
-        self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
-
-    def test_xpath_element(self):
-        doc = xml.etree.ElementTree.Element('root')
-        div = xml.etree.ElementTree.SubElement(doc, 'div')
-        p = xml.etree.ElementTree.SubElement(div, 'p')
-        p.text = 'Foo'
-        self.assertEqual(xpath_element(doc, 'div/p'), p)
-        self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
-        self.assertTrue(xpath_element(doc, 'div/bar') is None)
-        self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
-
-    def test_xpath_text(self):
-        testxml = '''<root>
-            <div>
-                <p>Foo</p>
-            </div>
-        </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
-        self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
-        self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
-        self.assertTrue(xpath_text(doc, 'div/bar') is None)
-        self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
-
-    def test_xpath_attr(self):
-        testxml = '''<root>
-            <div>
-                <p x="a">Foo</p>
-            </div>
-        </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
-        self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
-        self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
-        self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
-        self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
-        self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
-        self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
-        self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
+        self.assertEqual(find('media:song/media:author').text, u'The Author')
+        self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
 
     def test_smuggle_url(self):
-        data = {"ö": "ö", "abc": [3]}
+        data = {u"ö": u"ö", u"abc": [3]}
         url = 'https://foo.bar/baz?x=y#a'
         smug_url = smuggle_url(url, data)
         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
@@ -319,408 +173,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(res_data, None)
 
     def test_shell_quote(self):
-        args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
-        self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
-
-    def test_str_to_int(self):
-        self.assertEqual(str_to_int('123,456'), 123456)
-        self.assertEqual(str_to_int('123.456'), 123456)
-
-    def test_url_basename(self):
-        self.assertEqual(url_basename('http://foo.de/'), '')
-        self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
-        self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
-        self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
-        self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
-        self.assertEqual(
-            url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
-            'trailer.mp4')
-
-    def test_parse_duration(self):
-        self.assertEqual(parse_duration(None), None)
-        self.assertEqual(parse_duration(False), None)
-        self.assertEqual(parse_duration('invalid'), None)
-        self.assertEqual(parse_duration('1'), 1)
-        self.assertEqual(parse_duration('1337:12'), 80232)
-        self.assertEqual(parse_duration('9:12:43'), 33163)
-        self.assertEqual(parse_duration('12:00'), 720)
-        self.assertEqual(parse_duration('00:01:01'), 61)
-        self.assertEqual(parse_duration('x:y'), None)
-        self.assertEqual(parse_duration('3h11m53s'), 11513)
-        self.assertEqual(parse_duration('3h 11m 53s'), 11513)
-        self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
-        self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
-        self.assertEqual(parse_duration('62m45s'), 3765)
-        self.assertEqual(parse_duration('6m59s'), 419)
-        self.assertEqual(parse_duration('49s'), 49)
-        self.assertEqual(parse_duration('0h0m0s'), 0)
-        self.assertEqual(parse_duration('0m0s'), 0)
-        self.assertEqual(parse_duration('0s'), 0)
-        self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
-        self.assertEqual(parse_duration('T30M38S'), 1838)
-        self.assertEqual(parse_duration('5 s'), 5)
-        self.assertEqual(parse_duration('3 min'), 180)
-        self.assertEqual(parse_duration('2.5 hours'), 9000)
-        self.assertEqual(parse_duration('02:03:04'), 7384)
-        self.assertEqual(parse_duration('01:02:03:04'), 93784)
-        self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
-        self.assertEqual(parse_duration('87 Min.'), 5220)
-
-    def test_fix_xml_ampersands(self):
-        self.assertEqual(
-            fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
-        self.assertEqual(
-            fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
-            '"&amp;x=y&amp;wrong;&amp;z=a')
-        self.assertEqual(
-            fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
-            '&amp;&apos;&gt;&lt;&quot;')
-        self.assertEqual(
-            fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
-        self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
-
-    def test_paged_list(self):
-        def testPL(size, pagesize, sliceargs, expected):
-            def get_page(pagenum):
-                firstid = pagenum * pagesize
-                upto = min(size, pagenum * pagesize + pagesize)
-                for i in range(firstid, upto):
-                    yield i
-
-            pl = OnDemandPagedList(get_page, pagesize)
-            got = pl.getslice(*sliceargs)
-            self.assertEqual(got, expected)
-
-            iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
-            got = iapl.getslice(*sliceargs)
-            self.assertEqual(got, expected)
-
-        testPL(5, 2, (), [0, 1, 2, 3, 4])
-        testPL(5, 2, (1,), [1, 2, 3, 4])
-        testPL(5, 2, (2,), [2, 3, 4])
-        testPL(5, 2, (4,), [4])
-        testPL(5, 2, (0, 3), [0, 1, 2])
-        testPL(5, 2, (1, 4), [1, 2, 3])
-        testPL(5, 2, (2, 99), [2, 3, 4])
-        testPL(5, 2, (20, 99), [])
-
-    def test_struct_unpack(self):
-        self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
-
-    def test_read_batch_urls(self):
-        f = io.StringIO('''\xef\xbb\xbf foo
-            bar\r
-            baz
-            # More after this line\r
-            ; or after this
-            bam''')
-        self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
-
-    def test_urlencode_postdata(self):
-        data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
-        self.assertTrue(isinstance(data, bytes))
-
-    def test_parse_iso8601(self):
-        self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
-        self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
-        self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
-        self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
-
-    def test_strip_jsonp(self):
-        stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
-        d = json.loads(stripped)
-        self.assertEqual(d, [{"id": "532cb", "x": 3}])
-
-        stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
-        d = json.loads(stripped)
-        self.assertEqual(d, {'STATUS': 'OK'})
-
-    def test_uppercase_escape(self):
-        self.assertEqual(uppercase_escape('aä'), 'aä')
-        self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
-
-    def test_lowercase_escape(self):
-        self.assertEqual(lowercase_escape('aä'), 'aä')
-        self.assertEqual(lowercase_escape('\\u0026'), '&')
-
-    def test_limit_length(self):
-        self.assertEqual(limit_length(None, 12), None)
-        self.assertEqual(limit_length('foo', 12), 'foo')
-        self.assertTrue(
-            limit_length('foo bar baz asd', 12).startswith('foo bar'))
-        self.assertTrue('...' in limit_length('foo bar baz asd', 12))
-
-    def test_escape_rfc3986(self):
-        reserved = "!*'();:@&=+$,/?#[]"
-        unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
-        self.assertEqual(escape_rfc3986(reserved), reserved)
-        self.assertEqual(escape_rfc3986(unreserved), unreserved)
-        self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
-        self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
-        self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
-        self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
-
-    def test_escape_url(self):
-        self.assertEqual(
-            escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
-            'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
-        )
-        self.assertEqual(
-            escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
-            'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
-        )
-        self.assertEqual(
-            escape_url('http://тест.рф/фрагмент'),
-            'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
-        )
-        self.assertEqual(
-            escape_url('http://тест.рф/абв?абв=абв#абв'),
-            'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
-        )
-        self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
-
-    def test_js_to_json_realworld(self):
-        inp = '''{
-            'clip':{'provider':'pseudo'}
-        }'''
-        self.assertEqual(js_to_json(inp), '''{
-            "clip":{"provider":"pseudo"}
-        }''')
-        json.loads(js_to_json(inp))
-
-        inp = '''{
-            'playlist':[{'controls':{'all':null}}]
-        }'''
-        self.assertEqual(js_to_json(inp), '''{
-            "playlist":[{"controls":{"all":null}}]
-        }''')
-
-        inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
-        json_code = js_to_json(inp)
-        self.assertEqual(json.loads(json_code), json.loads(inp))
-
-    def test_js_to_json_edgecases(self):
-        on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
-        self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
-
-        on = js_to_json('{"abc": true}')
-        self.assertEqual(json.loads(on), {'abc': True})
-
-        # Ignore JavaScript code as well
-        on = js_to_json('''{
-            "x": 1,
-            y: "a",
-            z: some.code
-        }''')
-        d = json.loads(on)
-        self.assertEqual(d['x'], 1)
-        self.assertEqual(d['y'], 'a')
-
-        on = js_to_json('["abc", "def",]')
-        self.assertEqual(json.loads(on), ['abc', 'def'])
-
-        on = js_to_json('{"abc": "def",}')
-        self.assertEqual(json.loads(on), {'abc': 'def'})
-
-    def test_clean_html(self):
-        self.assertEqual(clean_html('a:\nb'), 'a: b')
-        self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
-
-    def test_intlist_to_bytes(self):
-        self.assertEqual(
-            intlist_to_bytes([0, 1, 127, 128, 255]),
-            b'\x00\x01\x7f\x80\xff')
-
-    def test_args_to_str(self):
-        self.assertEqual(
-            args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
-            'foo ba/r -baz \'2 be\' \'\''
-        )
-
-    def test_parse_filesize(self):
-        self.assertEqual(parse_filesize(None), None)
-        self.assertEqual(parse_filesize(''), None)
-        self.assertEqual(parse_filesize('91 B'), 91)
-        self.assertEqual(parse_filesize('foobar'), None)
-        self.assertEqual(parse_filesize('2 MiB'), 2097152)
-        self.assertEqual(parse_filesize('5 GB'), 5000000000)
-        self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
-        self.assertEqual(parse_filesize('1,24 KB'), 1240)
-
-    def test_version_tuple(self):
-        self.assertEqual(version_tuple('1'), (1,))
-        self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
-        self.assertEqual(version_tuple('10.1-6'), (10, 1, 6))  # avconv style
-
-    def test_detect_exe_version(self):
-        self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
-built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
-configuration: --prefix=/usr --extra-'''), '1.2.1')
-        self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
-built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
-        self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
-Trying to open render node...
-Success at /dev/dri/renderD128.
-ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
-
-    def test_age_restricted(self):
-        self.assertFalse(age_restricted(None, 10))  # unrestricted content
-        self.assertFalse(age_restricted(1, None))  # unrestricted policy
-        self.assertFalse(age_restricted(8, 10))
-        self.assertTrue(age_restricted(18, 14))
-        self.assertFalse(age_restricted(18, 18))
-
-    def test_is_html(self):
-        self.assertFalse(is_html(b'\x49\x44\x43<html'))
-        self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
-        self.assertTrue(is_html(  # UTF-8 with BOM
-            b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
-        self.assertTrue(is_html(  # UTF-16-LE
-            b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
-        ))
-        self.assertTrue(is_html(  # UTF-16-BE
-            b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
-        ))
-        self.assertTrue(is_html(  # UTF-32-BE
-            b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
-        self.assertTrue(is_html(  # UTF-32-LE
-            b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
-
-    def test_render_table(self):
-        self.assertEqual(
-            render_table(
-                ['a', 'bcd'],
-                [[123, 4], [9999, 51]]),
-            'a    bcd\n'
-            '123  4\n'
-            '9999 51')
-
-    def test_match_str(self):
-        self.assertRaises(ValueError, match_str, 'xy>foobar', {})
-        self.assertFalse(match_str('xy', {'x': 1200}))
-        self.assertTrue(match_str('!xy', {'x': 1200}))
-        self.assertTrue(match_str('x', {'x': 1200}))
-        self.assertFalse(match_str('!x', {'x': 1200}))
-        self.assertTrue(match_str('x', {'x': 0}))
-        self.assertFalse(match_str('x>0', {'x': 0}))
-        self.assertFalse(match_str('x>0', {}))
-        self.assertTrue(match_str('x>?0', {}))
-        self.assertTrue(match_str('x>1K', {'x': 1200}))
-        self.assertFalse(match_str('x>2K', {'x': 1200}))
-        self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
-        self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
-        self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
-        self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
-        self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
-        self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
-        self.assertFalse(match_str(
-            'like_count > 100 & dislike_count <? 50 & description',
-            {'like_count': 90, 'description': 'foo'}))
-        self.assertTrue(match_str(
-            'like_count > 100 & dislike_count <? 50 & description',
-            {'like_count': 190, 'description': 'foo'}))
-        self.assertFalse(match_str(
-            'like_count > 100 & dislike_count <? 50 & description',
-            {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
-        self.assertFalse(match_str(
-            'like_count > 100 & dislike_count <? 50 & description',
-            {'like_count': 190, 'dislike_count': 10}))
-
-    def test_parse_dfxp_time_expr(self):
-        self.assertEqual(parse_dfxp_time_expr(None), 0.0)
-        self.assertEqual(parse_dfxp_time_expr(''), 0.0)
-        self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
-        self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
-        self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
-        self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
-
-    def test_dfxp2srt(self):
-        dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
-            <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
-            <body>
-                <div xml:lang="en">
-                    <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
-                    <p begin="1" end="2">第二行<br/>♪♪</p>
-                    <p begin="2" dur="1"><span>Third<br/>Line</span></p>
-                </div>
-            </body>
-            </tt>'''
-        srt_data = '''1
-00:00:00,000 --> 00:00:01,000
-The following line contains Chinese characters and special symbols
-
-2
-00:00:01,000 --> 00:00:02,000
-第二行
-♪♪
-
-3
-00:00:02,000 --> 00:00:03,000
-Third
-Line
-
-'''
-        self.assertEqual(dfxp2srt(dfxp_data), srt_data)
-
-        dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
-            <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
-            <body>
-                <div xml:lang="en">
-                    <p begin="0" end="1">The first line</p>
-                </div>
-            </body>
-            </tt>'''
-        srt_data = '''1
-00:00:00,000 --> 00:00:01,000
-The first line
-
-'''
-        self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
-
-    def test_cli_option(self):
-        self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
-        self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
-        self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
-
-    def test_cli_valueless_option(self):
-        self.assertEqual(cli_valueless_option(
-            {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
-        self.assertEqual(cli_valueless_option(
-            {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
-        self.assertEqual(cli_valueless_option(
-            {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
-        self.assertEqual(cli_valueless_option(
-            {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
-        self.assertEqual(cli_valueless_option(
-            {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
-        self.assertEqual(cli_valueless_option(
-            {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
-
-    def test_cli_bool_option(self):
-        self.assertEqual(
-            cli_bool_option(
-                {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
-            ['--no-check-certificate', 'true'])
-        self.assertEqual(
-            cli_bool_option(
-                {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
-            ['--no-check-certificate=true'])
-        self.assertEqual(
-            cli_bool_option(
-                {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
-            ['--check-certificate', 'false'])
-        self.assertEqual(
-            cli_bool_option(
-                {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
-            ['--check-certificate=false'])
-        self.assertEqual(
-            cli_bool_option(
-                {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
-            ['--check-certificate', 'true'])
-        self.assertEqual(
-            cli_bool_option(
-                {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
-            ['--check-certificate=true'])
+        args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
+        self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 
 
 if __name__ == '__main__':

test/test_write_annotations.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python
 # coding: utf-8
-from __future__ import unicode_literals
 
 # Allow direct execution
 import os
@@ -32,18 +31,19 @@ params = get_params({
 })
 
 
-TEST_ID = 'gr51aVj-mLg'
-ANNOTATIONS_FILE = TEST_ID + '.annotations.xml'
-EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
 
+TEST_ID = 'gr51aVj-mLg'
+ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
+EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
 
 class TestAnnotations(unittest.TestCase):
     def setUp(self):
         # Clear old files
         self.tearDown()
 
+
     def test_info_json(self):
-        expected = list(EXPECTED_ANNOTATIONS)  # Two annotations could have the same text.
+        expected = list(EXPECTED_ANNOTATIONS) #Two annotations could have the same text.
         ie = youtube_dl.extractor.YoutubeIE()
         ydl = YoutubeDL(params)
         ydl.add_info_extractor(ie)
@@ -51,7 +51,7 @@ class TestAnnotations(unittest.TestCase):
         self.assertTrue(os.path.exists(ANNOTATIONS_FILE))
         annoxml = None
         with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
-            annoxml = xml.etree.ElementTree.parse(annof)
+                annoxml = xml.etree.ElementTree.parse(annof)
         self.assertTrue(annoxml is not None, 'Failed to parse annotations XML')
         root = annoxml.getroot()
         self.assertEqual(root.tag, 'document')
@@ -59,17 +59,18 @@ class TestAnnotations(unittest.TestCase):
         self.assertEqual(annotationsTag.tag, 'annotations')
         annotations = annotationsTag.findall('annotation')
 
-        # Not all the annotations have TEXT children and the annotations are returned unsorted.
+        #Not all the annotations have TEXT children and the annotations are returned unsorted.
         for a in annotations:
-            self.assertEqual(a.tag, 'annotation')
-            if a.get('type') == 'text':
-                textTag = a.find('TEXT')
-                text = textTag.text
-                self.assertTrue(text in expected)  # assertIn only added in python 2.7
-                # remove the first occurance, there could be more than one annotation with the same text
-                expected.remove(text)
-        # We should have seen (and removed) all the expected annotation texts.
+                self.assertEqual(a.tag, 'annotation')
+                if a.get('type') == 'text':
+                        textTag = a.find('TEXT')
+                        text = textTag.text
+                        self.assertTrue(text in expected) #assertIn only added in python 2.7
+                        #remove the first occurance, there could be more than one annotation with the same text
+                        expected.remove(text)
+        #We should have seen (and removed) all the expected annotation texts.
         self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')
+        
 
     def tearDown(self):
         try_rm(ANNOTATIONS_FILE)

test/test_write_info_json.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import get_params
+
+
+import io
+import json
+
+import youtube_dl.YoutubeDL
+import youtube_dl.extractor
+
+
+class YoutubeDL(youtube_dl.YoutubeDL):
+    def __init__(self, *args, **kwargs):
+        super(YoutubeDL, self).__init__(*args, **kwargs)
+        self.to_stderr = self.to_screen
+
+params = get_params({
+    'writeinfojson': True,
+    'skip_download': True,
+    'writedescription': True,
+})
+
+
+TEST_ID = 'BaW_jenozKc'
+INFO_JSON_FILE = TEST_ID + '.info.json'
+DESCRIPTION_FILE = TEST_ID + '.mp4.description'
+EXPECTED_DESCRIPTION = u'''test chars:  "'/\ä↭𝕐
+
+This is a test video for youtube-dl.
+
+For more information, contact phihag@phihag.de .'''
+
+
+class TestInfoJSON(unittest.TestCase):
+    def setUp(self):
+        # Clear old files
+        self.tearDown()
+
+    def test_info_json(self):
+        ie = youtube_dl.extractor.YoutubeIE()
+        ydl = YoutubeDL(params)
+        ydl.add_info_extractor(ie)
+        ydl.download([TEST_ID])
+        self.assertTrue(os.path.exists(INFO_JSON_FILE))
+        with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf:
+            jd = json.load(jsonf)
+        self.assertEqual(jd['upload_date'], u'20121002')
+        self.assertEqual(jd['description'], EXPECTED_DESCRIPTION)
+        self.assertEqual(jd['id'], TEST_ID)
+        self.assertEqual(jd['extractor'], 'youtube')
+        self.assertEqual(jd['title'], u'''youtube-dl test video "'/\ä↭𝕐''')
+        self.assertEqual(jd['uploader'], 'Philipp Hagemeister')
+
+        self.assertTrue(os.path.exists(DESCRIPTION_FILE))
+        with io.open(DESCRIPTION_FILE, 'r', encoding='utf-8') as descf:
+            descr = descf.read()
+        self.assertEqual(descr, EXPECTED_DESCRIPTION)
+
+    def tearDown(self):
+        if os.path.exists(INFO_JSON_FILE):
+            os.remove(INFO_JSON_FILE)
+        if os.path.exists(DESCRIPTION_FILE):
+            os.remove(DESCRIPTION_FILE)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_youtube_lists.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-from __future__ import unicode_literals
 
 # Allow direct execution
 import os
@@ -11,8 +10,11 @@ from test.helper import FakeYDL
 
 
 from youtube_dl.extractor import (
+    YoutubeUserIE,
     YoutubePlaylistIE,
     YoutubeIE,
+    YoutubeChannelIE,
+    YoutubeShowIE,
 )
 
 
@@ -21,13 +23,51 @@ class TestYoutubeLists(unittest.TestCase):
         """Make sure the info has '_type' set to 'playlist'"""
         self.assertEqual(info['_type'], 'playlist')
 
+    def test_youtube_playlist(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], 'ytdl test PL')
+        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
+
     def test_youtube_playlist_noplaylist(self):
         dl = FakeYDL()
         dl.params['noplaylist'] = True
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertEqual(result['_type'], 'url')
-        self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
+        self.assertEqual(YoutubeIE()._extract_id(result['url']), 'FXxLjLQi3Fg')
+
+    def test_issue_673(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('PLBB231211A4F62143')
+        self.assertTrue(len(result['entries']) > 25)
+
+    def test_youtube_playlist_long(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+        self.assertIsPlaylist(result)
+        self.assertTrue(len(result['entries']) >= 799)
+
+    def test_youtube_playlist_with_deleted(self):
+        #651
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
+        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        self.assertFalse('pElCt5oNDuI' in ytie_results)
+        self.assertFalse('KdPEApIVdWM' in ytie_results)
+        
+    def test_youtube_playlist_empty(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')
+        self.assertIsPlaylist(result)
+        self.assertEqual(len(result['entries']), 0)
 
     def test_youtube_course(self):
         dl = FakeYDL()
@@ -35,27 +75,37 @@ class TestYoutubeLists(unittest.TestCase):
         # TODO find a > 100 (paginating?) videos course
         result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
         entries = result['entries']
-        self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
+        self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs')
         self.assertEqual(len(entries), 25)
-        self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
+        self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0')
 
-    def test_youtube_mix(self):
+    def test_youtube_channel(self):
+        dl = FakeYDL()
+        ie = YoutubeChannelIE(dl)
+        #test paginated channel
+        result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')
+        self.assertTrue(len(result['entries']) > 90)
+        #test autogenerated channel
+        result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
+        self.assertTrue(len(result['entries']) >= 18)
+
+    def test_youtube_user(self):
+        dl = FakeYDL()
+        ie = YoutubeUserIE(dl)
+        result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')
+        self.assertTrue(len(result['entries']) >= 320)
+
+    def test_youtube_safe_search(self):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
-        entries = result['entries']
-        self.assertTrue(len(entries) >= 20)
-        original_video = entries[0]
-        self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
+        result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')
+        self.assertEqual(len(result['entries']), 2)
 
-    def test_youtube_toptracks(self):
-        print('Skipping: The playlist page gives error 500')
-        return
+    def test_youtube_show(self):
         dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
-        entries = result['entries']
-        self.assertEqual(len(entries), 100)
+        ie = YoutubeShowIE(dl)
+        result = ie.extract('http://www.youtube.com/show/airdisasters')
+        self.assertTrue(len(result) >= 3)
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -1,76 +1,38 @@
 #!/usr/bin/env python
 
-from __future__ import unicode_literals
-
 # Allow direct execution
 import os
 import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
+
 import io
 import re
 import string
 
-from test.helper import FakeYDL
 from youtube_dl.extractor import YoutubeIE
-from youtube_dl.compat import compat_str, compat_urlretrieve
+from youtube_dl.utils import compat_str, compat_urlretrieve
 
 _TESTS = [
     (
-        'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
-        'js',
+        u'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
+        u'js',
         86,
-        '>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
+        u'>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
     ),
     (
-        'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
-        'js',
+        u'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
+        u'js',
         85,
-        '3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
+        u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
     ),
     (
-        'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
-        'js',
-        90,
-        ']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
+        u'https://s.ytimg.com/yts/swfbin/watch_as3-vflg5GhxU.swf',
+        u'swf',
+        82,
+        u':/.-,+*)=\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBAzyxw>utsrqponmlkjihgfedcba987654321'
     ),
-    (
-        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
-        'js',
-        84,
-        'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
-    ),
-    (
-        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
-        'js',
-        '2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
-        'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
-    ),
-    (
-        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
-        'js',
-        84,
-        '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
-    ),
-    (
-        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
-        'js',
-        83,
-        '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
-    ),
-    (
-        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
-        'js',
-        '4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
-        '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
-    ),
-    (
-        'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
-        'js',
-        '312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
-        '112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
-    )
 ]
 
 
@@ -82,20 +44,19 @@ class TestSignature(unittest.TestCase):
             os.mkdir(self.TESTDATA_DIR)
 
 
-def make_tfunc(url, stype, sig_input, expected_sig):
-    m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$', url)
-    assert m, '%r should follow URL format' % url
+def make_tfunc(url, stype, sig_length, expected_sig):
+    basename = url.rpartition('/')[2]
+    m = re.match(r'.*-([a-zA-Z0-9_-]+)\.[a-z]+$', basename)
+    assert m, '%r should follow URL format' % basename
     test_id = m.group(1)
 
     def test_func(self):
-        basename = 'player-%s.%s' % (test_id, stype)
         fn = os.path.join(self.TESTDATA_DIR, basename)
 
         if not os.path.exists(fn):
             compat_urlretrieve(url, fn)
 
-        ydl = FakeYDL()
-        ie = YoutubeIE(ydl)
+        ie = YoutubeIE()
         if stype == 'js':
             with io.open(fn, encoding='utf-8') as testf:
                 jscode = testf.read()
@@ -105,9 +66,7 @@ def make_tfunc(url, stype, sig_input, expected_sig):
             with open(fn, 'rb') as testf:
                 swfcode = testf.read()
             func = ie._parse_sig_swf(swfcode)
-        src_sig = (
-            compat_str(string.printable[:sig_input])
-            if isinstance(sig_input, int) else sig_input)
+        src_sig = compat_str(string.printable[:sig_length])
         got_sig = func(src_sig)
         self.assertEqual(got_sig, expected_sig)
 

test/testcert.pem

@@ -1,52 +0,0 @@
------BEGIN PRIVATE KEY-----
-MIIEvQIBADANBgkqhkiG9w0BAQEFAASCBKcwggSjAgEAAoIBAQDMF0bAzaHAdIyB
-HRmnIp4vv40lGqEePmWqicCl0QZ0wsb5dNysSxSa7330M2QeQopGfdaUYF1uTcNp
-Qx6ECgBSfg+RrOBI7r/u4F+sKX8MUXVaf/5QoBUrGNGSn/pp7HMGOuQqO6BVg4+h
-A1ySSwUG8mZItLRry1ISyErmW8b9xlqfd97uLME/5tX+sMelRFjUbAx8A4CK58Ev
-mMguHVTlXzx5RMdYcf1VScYcjlV/qA45uzP8zwI5aigfcmUD+tbGuQRhKxUhmw0J
-aobtOR6+JSOAULW5gYa/egE4dWLwbyM6b6eFbdnjlQzEA1EW7ChMPAW/Mo83KyiP
-tKMCSQulAgMBAAECggEALCfBDAexPjU5DNoh6bIorUXxIJzxTNzNHCdvgbCGiA54
-BBKPh8s6qwazpnjT6WQWDIg/O5zZufqjE4wM9x4+0Zoqfib742ucJO9wY4way6x4
-Clt0xzbLPabB+MoZ4H7ip+9n2+dImhe7pGdYyOHoNYeOL57BBi1YFW42Hj6u/8pd
-63YCXisto3Rz1YvRQVjwsrS+cRKZlzAFQRviL30jav7Wh1aWEfcXxjj4zhm8pJdk
-ITGtq6howz57M0NtX6hZnfe8ywzTnDFIGKIMA2cYHuYJcBh9bc4tCGubTvTKK9UE
-8fM+f6UbfGqfpKCq1mcgs0XMoFDSzKS9+mSJn0+5JQKBgQD+OCKaeH3Yzw5zGnlw
-XuQfMJGNcgNr+ImjmvzUAC2fAZUJLAcQueE5kzMv5Fmd+EFE2CEX1Vit3tg0SXvA
-G+bq609doILHMA03JHnV1npO/YNIhG3AAtJlKYGxQNfWH9mflYj9mEui8ZFxG52o
-zWhHYuifOjjZszUR+/eio6NPzwKBgQDNhUBTrT8LIX4SE/EFUiTlYmWIvOMgXYvN
-8Cm3IRNQ/yyphZaXEU0eJzfX5uCDfSVOgd6YM/2pRah+t+1Hvey4H8e0GVTu5wMP
-gkkqwKPGIR1YOmlw6ippqwvoJD7LuYrm6Q4D6e1PvkjwCq6lEndrOPmPrrXNd0JJ
-XO60y3U2SwKBgQDLkyZarryQXxcCI6Q10Tc6pskYDMIit095PUbTeiUOXNT9GE28
-Hi32ziLCakk9kCysNasii81MxtQ54tJ/f5iGbNMMddnkKl2a19Hc5LjjAm4cJzg/
-98KGEhvyVqvAo5bBDZ06/rcrD+lZOzUglQS5jcIcqCIYa0LHWQ/wJLxFzwKBgFcZ
-1SRhdSmDfUmuF+S4ZpistflYjC3IV5rk4NkS9HvMWaJS0nqdw4A3AMzItXgkjq4S
-DkOVLTkTI5Do5HAWRv/VwC5M2hkR4NMu1VGAKSisGiKtRsirBWSZMEenLNHshbjN
-Jrpz5rZ4H7NT46ZkCCZyFBpX4gb9NyOedjA7Via3AoGARF8RxbYjnEGGFuhnbrJB
-FTPR0vaL4faY3lOgRZ8jOG9V2c9Hzi/y8a8TU4C11jnJSDqYCXBTd5XN28npYxtD
-pjRsCwy6ze+yvYXPO7C978eMG3YRyj366NXUxnXN59ibwe/lxi2OD9z8J1LEdF6z
-VJua1Wn8HKxnXMI61DhTCSo=
------END PRIVATE KEY-----
------BEGIN CERTIFICATE-----
-MIIEEzCCAvugAwIBAgIJAK1haYi6gmSKMA0GCSqGSIb3DQEBCwUAMIGeMQswCQYD
-VQQGEwJERTEMMAoGA1UECAwDTlJXMRQwEgYDVQQHDAtEdWVzc2VsZG9yZjEbMBkG
-A1UECgwSeW91dHViZS1kbCBwcm9qZWN0MRkwFwYDVQQLDBB5b3V0dWJlLWRsIHRl
-c3RzMRIwEAYDVQQDDAlsb2NhbGhvc3QxHzAdBgkqhkiG9w0BCQEWEHBoaWhhZ0Bw
-aGloYWcuZGUwIBcNMTUwMTMwMDExNTA4WhgPMjExNTAxMDYwMTE1MDhaMIGeMQsw
-CQYDVQQGEwJERTEMMAoGA1UECAwDTlJXMRQwEgYDVQQHDAtEdWVzc2VsZG9yZjEb
-MBkGA1UECgwSeW91dHViZS1kbCBwcm9qZWN0MRkwFwYDVQQLDBB5b3V0dWJlLWRs
-IHRlc3RzMRIwEAYDVQQDDAlsb2NhbGhvc3QxHzAdBgkqhkiG9w0BCQEWEHBoaWhh
-Z0BwaGloYWcuZGUwggEiMA0GCSqGSIb3DQEBAQUAA4IBDwAwggEKAoIBAQDMF0bA
-zaHAdIyBHRmnIp4vv40lGqEePmWqicCl0QZ0wsb5dNysSxSa7330M2QeQopGfdaU
-YF1uTcNpQx6ECgBSfg+RrOBI7r/u4F+sKX8MUXVaf/5QoBUrGNGSn/pp7HMGOuQq
-O6BVg4+hA1ySSwUG8mZItLRry1ISyErmW8b9xlqfd97uLME/5tX+sMelRFjUbAx8
-A4CK58EvmMguHVTlXzx5RMdYcf1VScYcjlV/qA45uzP8zwI5aigfcmUD+tbGuQRh
-KxUhmw0JaobtOR6+JSOAULW5gYa/egE4dWLwbyM6b6eFbdnjlQzEA1EW7ChMPAW/
-Mo83KyiPtKMCSQulAgMBAAGjUDBOMB0GA1UdDgQWBBTBUZoqhQkzHQ6xNgZfFxOd
-ZEVt8TAfBgNVHSMEGDAWgBTBUZoqhQkzHQ6xNgZfFxOdZEVt8TAMBgNVHRMEBTAD
-AQH/MA0GCSqGSIb3DQEBCwUAA4IBAQCUOCl3T/J9B08Z+ijfOJAtkbUaEHuVZb4x
-5EpZSy2ZbkLvtsftMFieHVNXn9dDswQc5qjYStCC4o60LKw4M6Y63FRsAZ/DNaqb
-PY3jyCyuugZ8/sNf50vHYkAcF7SQYqOQFQX4TQsNUk2xMJIt7H0ErQFmkf/u3dg6
-cy89zkT462IwxzSG7NNhIlRkL9o5qg+Y1mF9eZA1B0rcL6hO24PPTHOd90HDChBu
-SZ6XMi/LzYQSTf0Vg2R+uMIVlzSlkdcZ6sqVnnqeLL8dFyIa4e9sj/D4ZCYP8Mqe
-Z73H5/NNhmwCHRqVUTgm307xblQaWGhwAiDkaRvRW2aJQ0qGEdZK
------END CERTIFICATE-----

tox.ini

@@ -1,13 +1,8 @@
 [tox]
-envlist = py26,py27,py33,py34,py35
+envlist = py26,py27,py33
 [testenv]
 deps =
    nose
    coverage
-# We need a valid $HOME for test_compat_expanduser
-passenv = HOME
-defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
-    --exclude test_subtitles.py --exclude test_write_annotations.py
-    --exclude test_youtube_lists.py
-commands = nosetests --verbose {posargs:{[testenv]defaultargs}}  # --with-coverage --cover-package=youtube_dl --cover-html
+commands = nosetests --verbose {posargs:test}  # --with-coverage --cover-package=youtube_dl --cover-html
                                                # test.test_download:TestDownload.test_NowVideo

youtube-dl

@@ -0,0 +1,89 @@
+#!/usr/bin/env python
+
+import sys, os
+import json, hashlib
+
+try:
+    import urllib.request as compat_urllib_request
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_request
+
+def rsa_verify(message, signature, key):
+    from struct import pack
+    from hashlib import sha256
+    from sys import version_info
+    def b(x):
+        if version_info[0] == 2: return x
+        else: return x.encode('latin1')
+    assert(type(message) == type(b('')))
+    block_size = 0
+    n = key[0]
+    while n:
+        block_size += 1
+        n >>= 8
+    signature = pow(int(signature, 16), key[1], key[0])
+    raw_bytes = []
+    while signature:
+        raw_bytes.insert(0, pack("B", signature & 0xFF))
+        signature >>= 8
+    signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
+    if signature[0:2] != b('\x00\x01'): return False
+    signature = signature[2:]
+    if not b('\x00') in signature: return False
+    signature = signature[signature.index(b('\x00'))+1:]
+    if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
+    signature = signature[19:]
+    if signature != sha256(message).digest(): return False
+    return True
+
+sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
+sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
+sys.stderr.write(u'From now on, get the binaries from http://rg3.github.io/youtube-dl/download.html, not from the git repository.\n\n')
+
+try:
+	raw_input()
+except NameError: # Python 3
+	input()
+
+filename = sys.argv[0]
+
+UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
+VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
+JSON_URL = UPDATE_URL + 'versions.json'
+UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
+
+if not os.access(filename, os.W_OK):
+    sys.exit('ERROR: no write permissions on %s' % filename)
+
+try:
+    versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8')
+    versions_info = json.loads(versions_info)
+except:
+    sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
+if not 'signature' in versions_info:
+    sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
+signature = versions_info['signature']
+del versions_info['signature']
+if not rsa_verify(json.dumps(versions_info, sort_keys=True).encode('utf-8'), signature, UPDATES_RSA_KEY):
+    sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
+
+version = versions_info['versions'][versions_info['latest']]
+
+try:
+    urlh = compat_urllib_request.urlopen(version['bin'][0])
+    newcontent = urlh.read()
+    urlh.close()
+except (IOError, OSError) as err:
+    sys.exit('ERROR: unable to download latest version')
+
+newcontent_hash = hashlib.sha256(newcontent).hexdigest()
+if newcontent_hash != version['bin'][1]:
+    sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
+
+try:
+    with open(filename, 'wb') as outf:
+        outf.write(newcontent)
+except (IOError, OSError) as err:
+    sys.exit('ERROR: unable to overwrite current version')
+
+sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

youtube-dl.plugin.zsh

@@ -1,24 +0,0 @@
-# This allows the youtube-dl command to be installed in ZSH using antigen.
-# Antigen is a bundle manager. It allows you to enhance the functionality of
-# your zsh session by installing bundles and themes easily.
-
-# Antigen documentation:
-# http://antigen.sharats.me/
-# https://github.com/zsh-users/antigen
-
-# Install youtube-dl:
-# antigen bundle rg3/youtube-dl
-# Bundles installed by antigen are available for use immediately.
-
-# Update youtube-dl (and all other antigen bundles):
-# antigen update
-
-# The antigen command will download the git repository to a folder and then
-# execute an enabling script (this file). The complete process for loading the
-# code is documented here:
-# https://github.com/zsh-users/antigen#notes-on-writing-plugins
-
-# This specific script just aliases youtube-dl to the python script that this
-# library provides. This requires updating the PYTHONPATH to ensure that the
-# full set of code can be located.
-alias youtube-dl="PYTHONPATH=$(dirname $0) $(dirname $0)/bin/youtube-dl"

youtube_dl/FileDownloader.py

@@ -0,0 +1,683 @@
+import os
+import re
+import subprocess
+import sys
+import time
+
+from .utils import (
+    compat_urllib_error,
+    compat_urllib_request,
+    ContentTooShortError,
+    determine_ext,
+    encodeFilename,
+    format_bytes,
+    sanitize_open,
+    timeconvert,
+)
+
+
+class FileDownloader(object):
+    """File Downloader class.
+
+    File downloader objects are the ones responsible of downloading the
+    actual video file and writing it to disk.
+
+    File downloaders accept a lot of parameters. In order not to saturate
+    the object constructor with arguments, it receives a dictionary of
+    options instead.
+
+    Available options:
+
+    verbose:           Print additional info to stdout.
+    quiet:             Do not print messages to stdout.
+    ratelimit:         Download speed limit, in bytes/sec.
+    retries:           Number of times to retry for HTTP error 5xx
+    buffersize:        Size of download buffer in bytes.
+    noresizebuffer:    Do not automatically resize the download buffer.
+    continuedl:        Try to continue downloads if possible.
+    noprogress:        Do not print the progress bar.
+    logtostderr:       Log messages to stderr instead of stdout.
+    consoletitle:      Display progress in console window's titlebar.
+    nopart:            Do not use temporary .part files.
+    updatetime:        Use the Last-modified header to set output file timestamps.
+    test:              Download only first bytes to test the downloader.
+    min_filesize:      Skip files smaller than this size
+    max_filesize:      Skip files larger than this size
+    """
+
+    params = None
+
+    def __init__(self, ydl, params):
+        """Create a FileDownloader object with the given options."""
+        self.ydl = ydl
+        self._progress_hooks = []
+        self.params = params
+
+    @staticmethod
+    def format_seconds(seconds):
+        (mins, secs) = divmod(seconds, 60)
+        (hours, mins) = divmod(mins, 60)
+        if hours > 99:
+            return '--:--:--'
+        if hours == 0:
+            return '%02d:%02d' % (mins, secs)
+        else:
+            return '%02d:%02d:%02d' % (hours, mins, secs)
+
+    @staticmethod
+    def calc_percent(byte_counter, data_len):
+        if data_len is None:
+            return None
+        return float(byte_counter) / float(data_len) * 100.0
+
+    @staticmethod
+    def format_percent(percent):
+        if percent is None:
+            return '---.-%'
+        return '%6s' % ('%3.1f%%' % percent)
+
+    @staticmethod
+    def calc_eta(start, now, total, current):
+        if total is None:
+            return None
+        dif = now - start
+        if current == 0 or dif < 0.001: # One millisecond
+            return None
+        rate = float(current) / dif
+        return int((float(total) - float(current)) / rate)
+
+    @staticmethod
+    def format_eta(eta):
+        if eta is None:
+            return '--:--'
+        return FileDownloader.format_seconds(eta)
+
+    @staticmethod
+    def calc_speed(start, now, bytes):
+        dif = now - start
+        if bytes == 0 or dif < 0.001: # One millisecond
+            return None
+        return float(bytes) / dif
+
+    @staticmethod
+    def format_speed(speed):
+        if speed is None:
+            return '%10s' % '---b/s'
+        return '%10s' % ('%s/s' % format_bytes(speed))
+
+    @staticmethod
+    def best_block_size(elapsed_time, bytes):
+        new_min = max(bytes / 2.0, 1.0)
+        new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
+        if elapsed_time < 0.001:
+            return int(new_max)
+        rate = bytes / elapsed_time
+        if rate > new_max:
+            return int(new_max)
+        if rate < new_min:
+            return int(new_min)
+        return int(rate)
+
+    @staticmethod
+    def parse_bytes(bytestr):
+        """Parse a string indicating a byte quantity into an integer."""
+        matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
+        if matchobj is None:
+            return None
+        number = float(matchobj.group(1))
+        multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
+        return int(round(number * multiplier))
+
+    def to_screen(self, *args, **kargs):
+        self.ydl.to_screen(*args, **kargs)
+
+    def to_stderr(self, message):
+        self.ydl.to_screen(message)
+
+    def to_console_title(self, message):
+        self.ydl.to_console_title(message)
+
+    def trouble(self, *args, **kargs):
+        self.ydl.trouble(*args, **kargs)
+
+    def report_warning(self, *args, **kargs):
+        self.ydl.report_warning(*args, **kargs)
+
+    def report_error(self, *args, **kargs):
+        self.ydl.report_error(*args, **kargs)
+
+    def slow_down(self, start_time, byte_counter):
+        """Sleep if the download speed is over the rate limit."""
+        rate_limit = self.params.get('ratelimit', None)
+        if rate_limit is None or byte_counter == 0:
+            return
+        now = time.time()
+        elapsed = now - start_time
+        if elapsed <= 0.0:
+            return
+        speed = float(byte_counter) / elapsed
+        if speed > rate_limit:
+            time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
+
+    def temp_name(self, filename):
+        """Returns a temporary filename for the given filename."""
+        if self.params.get('nopart', False) or filename == u'-' or \
+                (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
+            return filename
+        return filename + u'.part'
+
+    def undo_temp_name(self, filename):
+        if filename.endswith(u'.part'):
+            return filename[:-len(u'.part')]
+        return filename
+
+    def try_rename(self, old_filename, new_filename):
+        try:
+            if old_filename == new_filename:
+                return
+            os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
+        except (IOError, OSError):
+            self.report_error(u'unable to rename file')
+
+    def try_utime(self, filename, last_modified_hdr):
+        """Try to set the last-modified time of the given file."""
+        if last_modified_hdr is None:
+            return
+        if not os.path.isfile(encodeFilename(filename)):
+            return
+        timestr = last_modified_hdr
+        if timestr is None:
+            return
+        filetime = timeconvert(timestr)
+        if filetime is None:
+            return filetime
+        # Ignore obviously invalid dates
+        if filetime == 0:
+            return
+        try:
+            os.utime(filename, (time.time(), filetime))
+        except:
+            pass
+        return filetime
+
+    def report_destination(self, filename):
+        """Report destination filename."""
+        self.to_screen(u'[download] Destination: ' + filename)
+
+    def report_progress(self, percent, data_len_str, speed, eta):
+        """Report download progress."""
+        if self.params.get('noprogress', False):
+            return
+        clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
+        if eta is not None:
+            eta_str = self.format_eta(eta)
+        else:
+            eta_str = 'Unknown ETA'
+        if percent is not None:
+            percent_str = self.format_percent(percent)
+        else:
+            percent_str = 'Unknown %'
+        speed_str = self.format_speed(speed)
+        if self.params.get('progress_with_newline', False):
+            self.to_screen(u'[download] %s of %s at %s ETA %s' %
+                (percent_str, data_len_str, speed_str, eta_str))
+        else:
+            self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' %
+                (clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+        self.to_console_title(u'youtube-dl - %s of %s at %s ETA %s' %
+                (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
+
+    def report_resuming_byte(self, resume_len):
+        """Report attempt to resume at given byte."""
+        self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
+
+    def report_retry(self, count, retries):
+        """Report retry in case of HTTP error 5xx"""
+        self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
+
+    def report_file_already_downloaded(self, file_name):
+        """Report file has already been fully downloaded."""
+        try:
+            self.to_screen(u'[download] %s has already been downloaded' % file_name)
+        except UnicodeEncodeError:
+            self.to_screen(u'[download] The file has already been downloaded')
+
+    def report_unable_to_resume(self):
+        """Report it was impossible to resume download."""
+        self.to_screen(u'[download] Unable to resume')
+
+    def report_finish(self, data_len_str, tot_time):
+        """Report download finished."""
+        if self.params.get('noprogress', False):
+            self.to_screen(u'[download] Download completed')
+        else:
+            clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
+            self.to_screen(u'\r%s[download] 100%% of %s in %s' %
+                (clear_line, data_len_str, self.format_seconds(tot_time)))
+
+    def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url, live):
+        def run_rtmpdump(args):
+            start = time.time()
+            resume_percent = None
+            resume_downloaded_data_len = None
+            proc = subprocess.Popen(args, stderr=subprocess.PIPE)
+            cursor_in_new_line = True
+            proc_stderr_closed = False
+            while not proc_stderr_closed:
+                # read line from stderr
+                line = u''
+                while True:
+                    char = proc.stderr.read(1)
+                    if not char:
+                        proc_stderr_closed = True
+                        break
+                    if char in [b'\r', b'\n']:
+                        break
+                    line += char.decode('ascii', 'replace')
+                if not line:
+                    # proc_stderr_closed is True
+                    continue
+                mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
+                if mobj:
+                    downloaded_data_len = int(float(mobj.group(1))*1024)
+                    percent = float(mobj.group(2))
+                    if not resume_percent:
+                        resume_percent = percent
+                        resume_downloaded_data_len = downloaded_data_len
+                    eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent)
+                    speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_downloaded_data_len)
+                    data_len = None
+                    if percent > 0:
+                        data_len = int(downloaded_data_len * 100 / percent)
+                    data_len_str = u'~' + format_bytes(data_len)
+                    self.report_progress(percent, data_len_str, speed, eta)
+                    cursor_in_new_line = False
+                    self._hook_progress({
+                        'downloaded_bytes': downloaded_data_len,
+                        'total_bytes': data_len,
+                        'tmpfilename': tmpfilename,
+                        'filename': filename,
+                        'status': 'downloading',
+                        'eta': eta,
+                        'speed': speed,
+                    })
+                elif self.params.get('verbose', False):
+                    if not cursor_in_new_line:
+                        self.to_screen(u'')
+                    cursor_in_new_line = True
+                    self.to_screen(u'[rtmpdump] '+line)
+            proc.wait()
+            if not cursor_in_new_line:
+                self.to_screen(u'')
+            return proc.returncode
+
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+        test = self.params.get('test', False)
+
+        # Check for rtmpdump first
+        try:
+            subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+        except (OSError, IOError):
+            self.report_error(u'RTMP download detected but "rtmpdump" could not be run')
+            return False
+
+        # Download using rtmpdump. rtmpdump returns exit code 2 when
+        # the connection was interrumpted and resuming appears to be
+        # possible. This is part of rtmpdump's normal usage, AFAIK.
+        basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename]
+        if player_url is not None:
+            basic_args += ['--swfVfy', player_url]
+        if page_url is not None:
+            basic_args += ['--pageUrl', page_url]
+        if play_path is not None:
+            basic_args += ['--playpath', play_path]
+        if tc_url is not None:
+            basic_args += ['--tcUrl', url]
+        if test:
+            basic_args += ['--stop', '1']
+        if live:
+            basic_args += ['--live']
+        args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)]
+
+        if sys.platform == 'win32' and sys.version_info < (3, 0):
+            # Windows subprocess module does not actually support Unicode
+            # on Python 2.x
+            # See http://stackoverflow.com/a/9951851/35070
+            subprocess_encoding = sys.getfilesystemencoding()
+            args = [a.encode(subprocess_encoding, 'ignore') for a in args]
+        else:
+            subprocess_encoding = None
+
+        if self.params.get('verbose', False):
+            if subprocess_encoding:
+                str_args = [
+                    a.decode(subprocess_encoding) if isinstance(a, bytes) else a
+                    for a in args]
+            else:
+                str_args = args
+            try:
+                import pipes
+                shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
+            except ImportError:
+                shell_quote = repr
+            self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(str_args))
+
+        retval = run_rtmpdump(args)
+
+        while (retval == 2 or retval == 1) and not test:
+            prevsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'[rtmpdump] %s bytes' % prevsize)
+            time.sleep(5.0) # This seems to be needed
+            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+            cursize = os.path.getsize(encodeFilename(tmpfilename))
+            if prevsize == cursize and retval == 1:
+                break
+             # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
+            if prevsize == cursize and retval == 2 and cursize > 1024:
+                self.to_screen(u'[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+                retval = 0
+                break
+        if retval == 0 or (test and retval == 2):
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'[rtmpdump] %s bytes' % fsize)
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr(u"\n")
+            self.report_error(u'rtmpdump exited with code %d' % retval)
+            return False
+
+    def _download_with_mplayer(self, filename, url):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url]
+        # Check for mplayer first
+        try:
+            subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+        except (OSError, IOError):
+            self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0] )
+            return False
+
+        # Download using mplayer. 
+        retval = subprocess.call(args)
+        if retval == 0:
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr(u"\n")
+            self.report_error(u'mplayer exited with code %d' % retval)
+            return False
+
+    def _download_m3u8_with_ffmpeg(self, filename, url):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        args = ['-y', '-i', url, '-f', 'mp4', '-c', 'copy',
+            '-bsf:a', 'aac_adtstoasc', tmpfilename]
+
+        for program in ['avconv', 'ffmpeg']:
+            try:
+                subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+                break
+            except (OSError, IOError):
+                pass
+        else:
+            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found')
+        cmd = [program] + args
+
+        retval = subprocess.call(cmd)
+        if retval == 0:
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr(u"\n")
+            self.report_error(u'ffmpeg exited with code %d' % retval)
+            return False
+
+
+    def _do_download(self, filename, info_dict):
+        url = info_dict['url']
+
+        # Check file already present
+        if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
+            self.report_file_already_downloaded(filename)
+            self._hook_progress({
+                'filename': filename,
+                'status': 'finished',
+                'total_bytes': os.path.getsize(encodeFilename(filename)),
+            })
+            return True
+
+        # Attempt to download using rtmpdump
+        if url.startswith('rtmp'):
+            return self._download_with_rtmpdump(filename, url,
+                                                info_dict.get('player_url', None),
+                                                info_dict.get('page_url', None),
+                                                info_dict.get('play_path', None),
+                                                info_dict.get('tc_url', None),
+                                                info_dict.get('rtmp_live', False))
+
+        # Attempt to download using mplayer
+        if url.startswith('mms') or url.startswith('rtsp'):
+            return self._download_with_mplayer(filename, url)
+
+        # m3u8 manifest are downloaded with ffmpeg
+        if determine_ext(url) == u'm3u8':
+            return self._download_m3u8_with_ffmpeg(filename, url)
+
+        tmpfilename = self.temp_name(filename)
+        stream = None
+
+        # Do not include the Accept-Encoding header
+        headers = {'Youtubedl-no-compression': 'True'}
+        if 'user_agent' in info_dict:
+            headers['Youtubedl-user-agent'] = info_dict['user_agent']
+        basic_request = compat_urllib_request.Request(url, None, headers)
+        request = compat_urllib_request.Request(url, None, headers)
+
+        if self.params.get('test', False):
+            request.add_header('Range','bytes=0-10240')
+
+        # Establish possible resume length
+        if os.path.isfile(encodeFilename(tmpfilename)):
+            resume_len = os.path.getsize(encodeFilename(tmpfilename))
+        else:
+            resume_len = 0
+
+        open_mode = 'wb'
+        if resume_len != 0:
+            if self.params.get('continuedl', False):
+                self.report_resuming_byte(resume_len)
+                request.add_header('Range','bytes=%d-' % resume_len)
+                open_mode = 'ab'
+            else:
+                resume_len = 0
+
+        count = 0
+        retries = self.params.get('retries', 0)
+        while count <= retries:
+            # Establish connection
+            try:
+                if count == 0 and 'urlhandle' in info_dict:
+                    data = info_dict['urlhandle']
+                data = compat_urllib_request.urlopen(request)
+                break
+            except (compat_urllib_error.HTTPError, ) as err:
+                if (err.code < 500 or err.code >= 600) and err.code != 416:
+                    # Unexpected HTTP error
+                    raise
+                elif err.code == 416:
+                    # Unable to resume (requested range not satisfiable)
+                    try:
+                        # Open the connection again without the range header
+                        data = compat_urllib_request.urlopen(basic_request)
+                        content_length = data.info()['Content-Length']
+                    except (compat_urllib_error.HTTPError, ) as err:
+                        if err.code < 500 or err.code >= 600:
+                            raise
+                    else:
+                        # Examine the reported length
+                        if (content_length is not None and
+                                (resume_len - 100 < int(content_length) < resume_len + 100)):
+                            # The file had already been fully downloaded.
+                            # Explanation to the above condition: in issue #175 it was revealed that
+                            # YouTube sometimes adds or removes a few bytes from the end of the file,
+                            # changing the file size slightly and causing problems for some users. So
+                            # I decided to implement a suggested change and consider the file
+                            # completely downloaded if the file size differs less than 100 bytes from
+                            # the one in the hard drive.
+                            self.report_file_already_downloaded(filename)
+                            self.try_rename(tmpfilename, filename)
+                            self._hook_progress({
+                                'filename': filename,
+                                'status': 'finished',
+                            })
+                            return True
+                        else:
+                            # The length does not match, we start the download over
+                            self.report_unable_to_resume()
+                            open_mode = 'wb'
+                            break
+            # Retry
+            count += 1
+            if count <= retries:
+                self.report_retry(count, retries)
+
+        if count > retries:
+            self.report_error(u'giving up after %s retries' % retries)
+            return False
+
+        data_len = data.info().get('Content-length', None)
+        if data_len is not None:
+            data_len = int(data_len) + resume_len
+            min_data_len = self.params.get("min_filesize", None)
+            max_data_len =  self.params.get("max_filesize", None)
+            if min_data_len is not None and data_len < min_data_len:
+                self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
+                return False
+            if max_data_len is not None and data_len > max_data_len:
+                self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
+                return False
+
+        data_len_str = format_bytes(data_len)
+        byte_counter = 0 + resume_len
+        block_size = self.params.get('buffersize', 1024)
+        start = time.time()
+        while True:
+            # Download and write
+            before = time.time()
+            data_block = data.read(block_size)
+            after = time.time()
+            if len(data_block) == 0:
+                break
+            byte_counter += len(data_block)
+
+            # Open file just in time
+            if stream is None:
+                try:
+                    (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
+                    assert stream is not None
+                    filename = self.undo_temp_name(tmpfilename)
+                    self.report_destination(filename)
+                except (OSError, IOError) as err:
+                    self.report_error(u'unable to open for writing: %s' % str(err))
+                    return False
+            try:
+                stream.write(data_block)
+            except (IOError, OSError) as err:
+                self.to_stderr(u"\n")
+                self.report_error(u'unable to write data: %s' % str(err))
+                return False
+            if not self.params.get('noresizebuffer', False):
+                block_size = self.best_block_size(after - before, len(data_block))
+
+            # Progress message
+            speed = self.calc_speed(start, time.time(), byte_counter - resume_len)
+            if data_len is None:
+                eta = percent = None
+            else:
+                percent = self.calc_percent(byte_counter, data_len)
+                eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+            self.report_progress(percent, data_len_str, speed, eta)
+
+            self._hook_progress({
+                'downloaded_bytes': byte_counter,
+                'total_bytes': data_len,
+                'tmpfilename': tmpfilename,
+                'filename': filename,
+                'status': 'downloading',
+                'eta': eta,
+                'speed': speed,
+            })
+
+            # Apply rate limit
+            self.slow_down(start, byte_counter - resume_len)
+
+        if stream is None:
+            self.to_stderr(u"\n")
+            self.report_error(u'Did not get any data blocks')
+            return False
+        stream.close()
+        self.report_finish(data_len_str, (time.time() - start))
+        if data_len is not None and byte_counter != data_len:
+            raise ContentTooShortError(byte_counter, int(data_len))
+        self.try_rename(tmpfilename, filename)
+
+        # Update file modification time
+        if self.params.get('updatetime', True):
+            info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
+
+        self._hook_progress({
+            'downloaded_bytes': byte_counter,
+            'total_bytes': byte_counter,
+            'filename': filename,
+            'status': 'finished',
+        })
+
+        return True
+
+    def _hook_progress(self, status):
+        for ph in self._progress_hooks:
+            ph(status)
+
+    def add_progress_hook(self, ph):
+        """ ph gets called on download progress, with a dictionary with the entries
+        * filename: The final filename
+        * status: One of "downloading" and "finished"
+
+        It can also have some of the following entries:
+
+        * downloaded_bytes: Bytes on disks
+        * total_bytes: Total bytes, None if unknown
+        * tmpfilename: The filename we're currently writing to
+        * eta: The estimated time in seconds, None if unknown
+        * speed: The download speed in bytes/second, None if unknown
+
+        Hooks are guaranteed to be called at least once (with status "finished")
+        if the download is successful.
+        """
+        self._progress_hooks.append(ph)

youtube_dl/InfoExtractors.py

@@ -0,0 +1,4 @@
+# Legacy file for backwards compatibility, use youtube_dl.extractor instead!
+
+from .extractor.common import InfoExtractor, SearchInfoExtractor
+from .extractor import gen_extractors, get_info_extractor

youtube_dl/PostProcessor.py

@@ -0,0 +1,511 @@
+import os
+import subprocess
+import sys
+import time
+
+
+from .utils import (
+    compat_subprocess_get_DEVNULL,
+    encodeFilename,
+    PostProcessingError,
+    shell_quote,
+    subtitles_filename,
+)
+
+
+class PostProcessor(object):
+    """Post Processor class.
+
+    PostProcessor objects can be added to downloaders with their
+    add_post_processor() method. When the downloader has finished a
+    successful download, it will take its internal chain of PostProcessors
+    and start calling the run() method on each one of them, first with
+    an initial argument and then with the returned value of the previous
+    PostProcessor.
+
+    The chain will be stopped if one of them ever returns None or the end
+    of the chain is reached.
+
+    PostProcessor objects follow a "mutual registration" process similar
+    to InfoExtractor objects.
+    """
+
+    _downloader = None
+
+    def __init__(self, downloader=None):
+        self._downloader = downloader
+
+    def set_downloader(self, downloader):
+        """Sets the downloader for this PP."""
+        self._downloader = downloader
+
+    def run(self, information):
+        """Run the PostProcessor.
+
+        The "information" argument is a dictionary like the ones
+        composed by InfoExtractors. The only difference is that this
+        one has an extra field called "filepath" that points to the
+        downloaded file.
+
+        This method returns a tuple, the first element of which describes
+        whether the original file should be kept (i.e. not deleted - None for
+        no preference), and the second of which is the updated information.
+
+        In addition, this method may raise a PostProcessingError
+        exception if post processing fails.
+        """
+        return None, information # by default, keep file and do nothing
+
+class FFmpegPostProcessorError(PostProcessingError):
+    pass
+
+class AudioConversionError(PostProcessingError):
+    pass
+
+class FFmpegPostProcessor(PostProcessor):
+    def __init__(self,downloader=None):
+        PostProcessor.__init__(self, downloader)
+        self._exes = self.detect_executables()
+
+    @staticmethod
+    def detect_executables():
+        def executable(exe):
+            try:
+                subprocess.Popen([exe, '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
+            except OSError:
+                return False
+            return exe
+        programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
+        return dict((program, executable(program)) for program in programs)
+
+    def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
+        if not self._exes['ffmpeg'] and not self._exes['avconv']:
+            raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')
+
+        files_cmd = []
+        for path in input_paths:
+            files_cmd.extend(['-i', encodeFilename(path)])
+        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y'] + files_cmd
+               + opts +
+               [encodeFilename(self._ffmpeg_filename_argument(out_path))])
+
+        if self._downloader.params.get('verbose', False):
+            self._downloader.to_screen(u'[debug] ffmpeg command line: %s' % shell_quote(cmd))
+        p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        stdout,stderr = p.communicate()
+        if p.returncode != 0:
+            stderr = stderr.decode('utf-8', 'replace')
+            msg = stderr.strip().split('\n')[-1]
+            raise FFmpegPostProcessorError(msg)
+
+    def run_ffmpeg(self, path, out_path, opts):
+        self.run_ffmpeg_multiple_files([path], out_path, opts)
+
+    def _ffmpeg_filename_argument(self, fn):
+        # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
+        if fn.startswith(u'-'):
+            return u'./' + fn
+        return fn
+
+class FFmpegExtractAudioPP(FFmpegPostProcessor):
+    def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, nopostoverwrites=False):
+        FFmpegPostProcessor.__init__(self, downloader)
+        if preferredcodec is None:
+            preferredcodec = 'best'
+        self._preferredcodec = preferredcodec
+        self._preferredquality = preferredquality
+        self._nopostoverwrites = nopostoverwrites
+
+    def get_audio_codec(self, path):
+        if not self._exes['ffprobe'] and not self._exes['avprobe']:
+            raise PostProcessingError(u'ffprobe or avprobe not found. Please install one.')
+        try:
+            cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', encodeFilename(self._ffmpeg_filename_argument(path))]
+            handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE)
+            output = handle.communicate()[0]
+            if handle.wait() != 0:
+                return None
+        except (IOError, OSError):
+            return None
+        audio_codec = None
+        for line in output.decode('ascii', 'ignore').split('\n'):
+            if line.startswith('codec_name='):
+                audio_codec = line.split('=')[1].strip()
+            elif line.strip() == 'codec_type=audio' and audio_codec is not None:
+                return audio_codec
+        return None
+
+    def run_ffmpeg(self, path, out_path, codec, more_opts):
+        if not self._exes['ffmpeg'] and not self._exes['avconv']:
+            raise AudioConversionError('ffmpeg or avconv not found. Please install one.')
+        if codec is None:
+            acodec_opts = []
+        else:
+            acodec_opts = ['-acodec', codec]
+        opts = ['-vn'] + acodec_opts + more_opts
+        try:
+            FFmpegPostProcessor.run_ffmpeg(self, path, out_path, opts)
+        except FFmpegPostProcessorError as err:
+            raise AudioConversionError(err.msg)
+
+    def run(self, information):
+        path = information['filepath']
+
+        filecodec = self.get_audio_codec(path)
+        if filecodec is None:
+            raise PostProcessingError(u'WARNING: unable to obtain file audio codec with ffprobe')
+
+        more_opts = []
+        if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
+            if filecodec == 'aac' and self._preferredcodec in ['m4a', 'best']:
+                # Lossless, but in another container
+                acodec = 'copy'
+                extension = 'm4a'
+                more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
+            elif filecodec in ['aac', 'mp3', 'vorbis', 'opus']:
+                # Lossless if possible
+                acodec = 'copy'
+                extension = filecodec
+                if filecodec == 'aac':
+                    more_opts = ['-f', 'adts']
+                if filecodec == 'vorbis':
+                    extension = 'ogg'
+            else:
+                # MP3 otherwise.
+                acodec = 'libmp3lame'
+                extension = 'mp3'
+                more_opts = []
+                if self._preferredquality is not None:
+                    if int(self._preferredquality) < 10:
+                        more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
+                    else:
+                        more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
+        else:
+            # We convert the audio (lossy)
+            acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'opus': 'opus', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
+            extension = self._preferredcodec
+            more_opts = []
+            if self._preferredquality is not None:
+                # The opus codec doesn't support the -aq option
+                if int(self._preferredquality) < 10 and extension != 'opus':
+                    more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
+                else:
+                    more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
+            if self._preferredcodec == 'aac':
+                more_opts += ['-f', 'adts']
+            if self._preferredcodec == 'm4a':
+                more_opts += [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
+            if self._preferredcodec == 'vorbis':
+                extension = 'ogg'
+            if self._preferredcodec == 'wav':
+                extension = 'wav'
+                more_opts += ['-f', 'wav']
+
+        prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
+        new_path = prefix + sep + extension
+
+        # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
+        if new_path == path:
+            self._nopostoverwrites = True
+
+        try:
+            if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)):
+                self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path)
+            else:
+                self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
+                self.run_ffmpeg(path, new_path, acodec, more_opts)
+        except:
+            etype,e,tb = sys.exc_info()
+            if isinstance(e, AudioConversionError):
+                msg = u'audio conversion failed: ' + e.msg
+            else:
+                msg = u'error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')
+            raise PostProcessingError(msg)
+
+        # Try to update the date time for extracted audio file.
+        if information.get('filetime') is not None:
+            try:
+                os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
+            except:
+                self._downloader.report_warning(u'Cannot update utime of audio file')
+
+        information['filepath'] = new_path
+        return self._nopostoverwrites,information
+
+class FFmpegVideoConvertor(FFmpegPostProcessor):
+    def __init__(self, downloader=None,preferedformat=None):
+        super(FFmpegVideoConvertor, self).__init__(downloader)
+        self._preferedformat=preferedformat
+
+    def run(self, information):
+        path = information['filepath']
+        prefix, sep, ext = path.rpartition(u'.')
+        outpath = prefix + sep + self._preferedformat
+        if information['ext'] == self._preferedformat:
+            self._downloader.to_screen(u'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
+            return True,information
+        self._downloader.to_screen(u'['+'ffmpeg'+'] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) +outpath)
+        self.run_ffmpeg(path, outpath, [])
+        information['filepath'] = outpath
+        information['format'] = self._preferedformat
+        information['ext'] = self._preferedformat
+        return False,information
+
+
+class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
+    # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
+    _lang_map = {
+        'aa': 'aar',
+        'ab': 'abk',
+        'ae': 'ave',
+        'af': 'afr',
+        'ak': 'aka',
+        'am': 'amh',
+        'an': 'arg',
+        'ar': 'ara',
+        'as': 'asm',
+        'av': 'ava',
+        'ay': 'aym',
+        'az': 'aze',
+        'ba': 'bak',
+        'be': 'bel',
+        'bg': 'bul',
+        'bh': 'bih',
+        'bi': 'bis',
+        'bm': 'bam',
+        'bn': 'ben',
+        'bo': 'bod',
+        'br': 'bre',
+        'bs': 'bos',
+        'ca': 'cat',
+        'ce': 'che',
+        'ch': 'cha',
+        'co': 'cos',
+        'cr': 'cre',
+        'cs': 'ces',
+        'cu': 'chu',
+        'cv': 'chv',
+        'cy': 'cym',
+        'da': 'dan',
+        'de': 'deu',
+        'dv': 'div',
+        'dz': 'dzo',
+        'ee': 'ewe',
+        'el': 'ell',
+        'en': 'eng',
+        'eo': 'epo',
+        'es': 'spa',
+        'et': 'est',
+        'eu': 'eus',
+        'fa': 'fas',
+        'ff': 'ful',
+        'fi': 'fin',
+        'fj': 'fij',
+        'fo': 'fao',
+        'fr': 'fra',
+        'fy': 'fry',
+        'ga': 'gle',
+        'gd': 'gla',
+        'gl': 'glg',
+        'gn': 'grn',
+        'gu': 'guj',
+        'gv': 'glv',
+        'ha': 'hau',
+        'he': 'heb',
+        'hi': 'hin',
+        'ho': 'hmo',
+        'hr': 'hrv',
+        'ht': 'hat',
+        'hu': 'hun',
+        'hy': 'hye',
+        'hz': 'her',
+        'ia': 'ina',
+        'id': 'ind',
+        'ie': 'ile',
+        'ig': 'ibo',
+        'ii': 'iii',
+        'ik': 'ipk',
+        'io': 'ido',
+        'is': 'isl',
+        'it': 'ita',
+        'iu': 'iku',
+        'ja': 'jpn',
+        'jv': 'jav',
+        'ka': 'kat',
+        'kg': 'kon',
+        'ki': 'kik',
+        'kj': 'kua',
+        'kk': 'kaz',
+        'kl': 'kal',
+        'km': 'khm',
+        'kn': 'kan',
+        'ko': 'kor',
+        'kr': 'kau',
+        'ks': 'kas',
+        'ku': 'kur',
+        'kv': 'kom',
+        'kw': 'cor',
+        'ky': 'kir',
+        'la': 'lat',
+        'lb': 'ltz',
+        'lg': 'lug',
+        'li': 'lim',
+        'ln': 'lin',
+        'lo': 'lao',
+        'lt': 'lit',
+        'lu': 'lub',
+        'lv': 'lav',
+        'mg': 'mlg',
+        'mh': 'mah',
+        'mi': 'mri',
+        'mk': 'mkd',
+        'ml': 'mal',
+        'mn': 'mon',
+        'mr': 'mar',
+        'ms': 'msa',
+        'mt': 'mlt',
+        'my': 'mya',
+        'na': 'nau',
+        'nb': 'nob',
+        'nd': 'nde',
+        'ne': 'nep',
+        'ng': 'ndo',
+        'nl': 'nld',
+        'nn': 'nno',
+        'no': 'nor',
+        'nr': 'nbl',
+        'nv': 'nav',
+        'ny': 'nya',
+        'oc': 'oci',
+        'oj': 'oji',
+        'om': 'orm',
+        'or': 'ori',
+        'os': 'oss',
+        'pa': 'pan',
+        'pi': 'pli',
+        'pl': 'pol',
+        'ps': 'pus',
+        'pt': 'por',
+        'qu': 'que',
+        'rm': 'roh',
+        'rn': 'run',
+        'ro': 'ron',
+        'ru': 'rus',
+        'rw': 'kin',
+        'sa': 'san',
+        'sc': 'srd',
+        'sd': 'snd',
+        'se': 'sme',
+        'sg': 'sag',
+        'si': 'sin',
+        'sk': 'slk',
+        'sl': 'slv',
+        'sm': 'smo',
+        'sn': 'sna',
+        'so': 'som',
+        'sq': 'sqi',
+        'sr': 'srp',
+        'ss': 'ssw',
+        'st': 'sot',
+        'su': 'sun',
+        'sv': 'swe',
+        'sw': 'swa',
+        'ta': 'tam',
+        'te': 'tel',
+        'tg': 'tgk',
+        'th': 'tha',
+        'ti': 'tir',
+        'tk': 'tuk',
+        'tl': 'tgl',
+        'tn': 'tsn',
+        'to': 'ton',
+        'tr': 'tur',
+        'ts': 'tso',
+        'tt': 'tat',
+        'tw': 'twi',
+        'ty': 'tah',
+        'ug': 'uig',
+        'uk': 'ukr',
+        'ur': 'urd',
+        'uz': 'uzb',
+        've': 'ven',
+        'vi': 'vie',
+        'vo': 'vol',
+        'wa': 'wln',
+        'wo': 'wol',
+        'xh': 'xho',
+        'yi': 'yid',
+        'yo': 'yor',
+        'za': 'zha',
+        'zh': 'zho',
+        'zu': 'zul',
+    }
+
+    def __init__(self, downloader=None, subtitlesformat='srt'):
+        super(FFmpegEmbedSubtitlePP, self).__init__(downloader)
+        self._subformat = subtitlesformat
+
+    @classmethod
+    def _conver_lang_code(cls, code):
+        """Convert language code from ISO 639-1 to ISO 639-2/T"""
+        return cls._lang_map.get(code[:2])
+
+    def run(self, information):
+        if information['ext'] != u'mp4':
+            self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
+            return True, information
+        if not information.get('subtitles'):
+            self._downloader.to_screen(u'[ffmpeg] There aren\'t any subtitles to embed') 
+            return True, information
+
+        sub_langs = [key for key in information['subtitles']]
+        filename = information['filepath']
+        input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs]
+
+        opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy']
+        for (i, lang) in enumerate(sub_langs):
+            opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text'])
+            lang_code = self._conver_lang_code(lang)
+            if lang_code is not None:
+                opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
+        opts.extend(['-f', 'mp4'])
+
+        temp_filename = filename + u'.temp'
+        self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename)
+        self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
+        os.remove(encodeFilename(filename))
+        os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+
+        return True, information
+
+
+class FFmpegMetadataPP(FFmpegPostProcessor):
+    def run(self, info):
+        metadata = {}
+        if info.get('title') is not None:
+            metadata['title'] = info['title']
+        if info.get('upload_date') is not None:
+            metadata['date'] = info['upload_date']
+        if info.get('uploader') is not None:
+            metadata['artist'] = info['uploader']
+        elif info.get('uploader_id') is not None:
+            metadata['artist'] = info['uploader_id']
+
+        if not metadata:
+            self._downloader.to_screen(u'[ffmpeg] There isn\'t any metadata to add')
+            return True, info
+
+        filename = info['filepath']
+        ext = os.path.splitext(filename)[1][1:]
+        temp_filename = filename + u'.temp'
+
+        options = ['-c', 'copy']
+        for (name, value) in metadata.items():
+            options.extend(['-metadata', '%s=%s' % (name, value)])
+        options.extend(['-f', ext])
+
+        self._downloader.to_screen(u'[ffmpeg] Adding metadata to \'%s\'' % filename)
+        self.run_ffmpeg(filename, temp_filename, options)
+        os.remove(encodeFilename(filename))
+        os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+        return True, info

youtube_dl/__init__.py

@@ -1,59 +1,447 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-from __future__ import unicode_literals
+__authors__  = (
+    'Ricardo Garcia Gonzalez',
+    'Danny Colligan',
+    'Benjamin Johnson',
+    'Vasyl\' Vavrychuk',
+    'Witold Baryluk',
+    'Paweł Paprota',
+    'Gergely Imreh',
+    'Rogério Brito',
+    'Philipp Hagemeister',
+    'Sören Schulze',
+    'Kevin Ngo',
+    'Ori Avtalion',
+    'shizeeg',
+    'Filippo Valsorda',
+    'Christian Albrecht',
+    'Dave Vasilevsky',
+    'Jaime Marquínez Ferrándiz',
+    'Jeff Crouse',
+    'Osama Khalid',
+    'Michael Walter',
+    'M. Yasoob Ullah Khalid',
+    'Julien Fraichard',
+    'Johny Mo Swag',
+    'Axel Noack',
+    'Albert Kim',
+    'Pierre Rudloff',
+    'Huarong Huo',
+    'Ismael Mejía',
+    'Steffan \'Ruirize\' James',
+    'Andras Elso',
+    'Jelle van der Waa',
+    'Marcin Cieślak',
+    'Anton Larionov',
+    'Takuya Tsuchida',
+)
 
 __license__ = 'Public Domain'
 
 import codecs
-import io
+import getpass
+import optparse
 import os
 import random
+import re
+import shlex
+import subprocess
 import sys
 
 
-from .options import (
-    parseOpts,
-)
-from .compat import (
-    compat_expanduser,
-    compat_getpass,
-    compat_print,
-    compat_shlex_split,
-    workaround_optparse_bug9161,
-)
 from .utils import (
+    compat_print,
     DateRange,
     decodeOption,
-    DEFAULT_OUTTMPL,
+    determine_ext,
     DownloadError,
-    match_filter_func,
+    get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
-    read_batch_urls,
     SameFileError,
-    setproctitle,
     std_headers,
     write_string,
 )
 from .update import update_self
-from .downloader import (
+from .FileDownloader import (
     FileDownloader,
 )
-from .extractor import gen_extractors, list_extractors
+from .extractor import gen_extractors
+from .version import __version__
 from .YoutubeDL import YoutubeDL
+from .PostProcessor import (
+    FFmpegMetadataPP,
+    FFmpegVideoConvertor,
+    FFmpegExtractAudioPP,
+    FFmpegEmbedSubtitlePP,
+)
 
 
+def parseOpts(overrideArguments=None):
+    def _readOptions(filename_bytes):
+        try:
+            optionf = open(filename_bytes)
+        except IOError:
+            return [] # silently skip if file is not present
+        try:
+            res = []
+            for l in optionf:
+                res += shlex.split(l, comments=True)
+        finally:
+            optionf.close()
+        return res
+
+    def _format_option_string(option):
+        ''' ('-o', '--option') -> -o, --format METAVAR'''
+
+        opts = []
+
+        if option._short_opts:
+            opts.append(option._short_opts[0])
+        if option._long_opts:
+            opts.append(option._long_opts[0])
+        if len(opts) > 1:
+            opts.insert(1, ', ')
+
+        if option.takes_value(): opts.append(' %s' % option.metavar)
+
+        return "".join(opts)
+
+    def _comma_separated_values_options_callback(option, opt_str, value, parser):
+        setattr(parser.values, option.dest, value.split(','))
+
+    def _find_term_columns():
+        columns = os.environ.get('COLUMNS', None)
+        if columns:
+            return int(columns)
+
+        try:
+            sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+            out,err = sp.communicate()
+            return int(out.split()[1])
+        except:
+            pass
+        return None
+
+    def _hide_login_info(opts):
+        opts = list(opts)
+        for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
+            try:
+                i = opts.index(private_opt)
+                opts[i+1] = '<PRIVATE>'
+            except ValueError:
+                pass
+        return opts
+
+    max_width = 80
+    max_help_position = 80
+
+    # No need to wrap help messages if we're on a wide console
+    columns = _find_term_columns()
+    if columns: max_width = columns
+
+    fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
+    fmt.format_option_strings = _format_option_string
+
+    kw = {
+        'version'   : __version__,
+        'formatter' : fmt,
+        'usage' : '%prog [options] url [url...]',
+        'conflict_handler' : 'resolve',
+    }
+
+    parser = optparse.OptionParser(**kw)
+
+    # option groups
+    general        = optparse.OptionGroup(parser, 'General Options')
+    selection      = optparse.OptionGroup(parser, 'Video Selection')
+    authentication = optparse.OptionGroup(parser, 'Authentication Options')
+    video_format   = optparse.OptionGroup(parser, 'Video Format Options')
+    subtitles      = optparse.OptionGroup(parser, 'Subtitle Options')
+    downloader     = optparse.OptionGroup(parser, 'Download Options')
+    postproc       = optparse.OptionGroup(parser, 'Post-processing Options')
+    filesystem     = optparse.OptionGroup(parser, 'Filesystem Options')
+    verbosity      = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
+
+    general.add_option('-h', '--help',
+            action='help', help='print this help text and exit')
+    general.add_option('-v', '--version',
+            action='version', help='print program version and exit')
+    general.add_option('-U', '--update',
+            action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
+    general.add_option('-i', '--ignore-errors',
+            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to to skip unavailable videos in a playlist', default=False)
+    general.add_option('--abort-on-error',
+            action='store_false', dest='ignoreerrors',
+            help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')
+    general.add_option('--dump-user-agent',
+            action='store_true', dest='dump_user_agent',
+            help='display the current browser identification', default=False)
+    general.add_option('--user-agent',
+            dest='user_agent', help='specify a custom user agent', metavar='UA')
+    general.add_option('--referer',
+            dest='referer', help='specify a custom referer, use if the video access is restricted to one domain',
+            metavar='REF', default=None)
+    general.add_option('--list-extractors',
+            action='store_true', dest='list_extractors',
+            help='List all supported extractors and the URLs they would handle', default=False)
+    general.add_option('--extractor-descriptions',
+            action='store_true', dest='list_extractor_descriptions',
+            help='Output descriptions of all supported extractors', default=False)
+    general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
+    general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
+    general.add_option(
+        '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
+        help='Location in the filesystem where youtube-dl can store downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl .')
+    general.add_option(
+        '--no-cache-dir', action='store_const', const=None, dest='cachedir',
+        help='Disable filesystem caching')
+
+
+    selection.add_option('--playlist-start',
+            dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1)
+    selection.add_option('--playlist-end',
+            dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+    selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
+    selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
+    selection.add_option('--max-downloads', metavar='NUMBER',
+                         dest='max_downloads', type=int, default=None,
+                         help='Abort after downloading NUMBER files')
+    selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None)
+    selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None)
+    selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
+    selection.add_option('--datebefore', metavar='DATE', dest='datebefore', help='download only videos uploaded before this date', default=None)
+    selection.add_option('--dateafter', metavar='DATE', dest='dateafter', help='download only videos uploaded after this date', default=None)
+    selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False)
+    selection.add_option('--age-limit', metavar='YEARS', dest='age_limit',
+                         help='download only videos suitable for the given age',
+                         default=None, type=int)
+    selection.add_option('--download-archive', metavar='FILE',
+                         dest='download_archive',
+                         help='Download only videos not present in the archive file. Record all downloaded videos in it.')
+
+
+    authentication.add_option('-u', '--username',
+            dest='username', metavar='USERNAME', help='account username')
+    authentication.add_option('-p', '--password',
+            dest='password', metavar='PASSWORD', help='account password')
+    authentication.add_option('-n', '--netrc',
+            action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
+    authentication.add_option('--video-password',
+            dest='videopassword', metavar='PASSWORD', help='video password (vimeo only)')
+
+
+    video_format.add_option('-f', '--format',
+            action='store', dest='format', metavar='FORMAT', default='best',
+            help='video format code, specifiy the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
+    video_format.add_option('--all-formats',
+            action='store_const', dest='format', help='download all available video formats', const='all')
+    video_format.add_option('--prefer-free-formats',
+            action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested')
+    video_format.add_option('--max-quality',
+            action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
+    video_format.add_option('-F', '--list-formats',
+            action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
+
+    subtitles.add_option('--write-sub', '--write-srt',
+            action='store_true', dest='writesubtitles',
+            help='write subtitle file', default=False)
+    subtitles.add_option('--write-auto-sub', '--write-automatic-sub',
+            action='store_true', dest='writeautomaticsub',
+            help='write automatic subtitle file (youtube only)', default=False)
+    subtitles.add_option('--all-subs',
+            action='store_true', dest='allsubtitles',
+            help='downloads all the available subtitles of the video', default=False)
+    subtitles.add_option('--list-subs',
+            action='store_true', dest='listsubtitles',
+            help='lists all available subtitles for the video', default=False)
+    subtitles.add_option('--sub-format',
+            action='store', dest='subtitlesformat', metavar='FORMAT',
+            help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
+    subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
+            action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
+            default=[], callback=_comma_separated_values_options_callback,
+            help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
+
+    downloader.add_option('-r', '--rate-limit',
+            dest='ratelimit', metavar='LIMIT', help='maximum download rate in bytes per second (e.g. 50K or 4.2M)')
+    downloader.add_option('-R', '--retries',
+            dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
+    downloader.add_option('--buffer-size',
+            dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16K) (default is %default)', default="1024")
+    downloader.add_option('--no-resize-buffer',
+            action='store_true', dest='noresizebuffer',
+            help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
+    downloader.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
+
+    verbosity.add_option('-q', '--quiet',
+            action='store_true', dest='quiet', help='activates quiet mode', default=False)
+    verbosity.add_option('-s', '--simulate',
+            action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
+    verbosity.add_option('--skip-download',
+            action='store_true', dest='skip_download', help='do not download the video', default=False)
+    verbosity.add_option('-g', '--get-url',
+            action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
+    verbosity.add_option('-e', '--get-title',
+            action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+    verbosity.add_option('--get-id',
+            action='store_true', dest='getid', help='simulate, quiet but print id', default=False)
+    verbosity.add_option('--get-thumbnail',
+            action='store_true', dest='getthumbnail',
+            help='simulate, quiet but print thumbnail URL', default=False)
+    verbosity.add_option('--get-description',
+            action='store_true', dest='getdescription',
+            help='simulate, quiet but print video description', default=False)
+    verbosity.add_option('--get-filename',
+            action='store_true', dest='getfilename',
+            help='simulate, quiet but print output filename', default=False)
+    verbosity.add_option('--get-format',
+            action='store_true', dest='getformat',
+            help='simulate, quiet but print output format', default=False)
+    verbosity.add_option('-j', '--dump-json',
+            action='store_true', dest='dumpjson',
+            help='simulate, quiet but print JSON information', default=False)
+    verbosity.add_option('--newline',
+            action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
+    verbosity.add_option('--no-progress',
+            action='store_true', dest='noprogress', help='do not print progress bar', default=False)
+    verbosity.add_option('--console-title',
+            action='store_true', dest='consoletitle',
+            help='display progress in console titlebar', default=False)
+    verbosity.add_option('-v', '--verbose',
+            action='store_true', dest='verbose', help='print various debugging information', default=False)
+    verbosity.add_option('--dump-intermediate-pages',
+            action='store_true', dest='dump_intermediate_pages', default=False,
+            help='print downloaded pages to debug problems(very verbose)')
+    verbosity.add_option('--write-pages',
+            action='store_true', dest='write_pages', default=False,
+            help='Write downloaded pages to files in the current directory')
+    verbosity.add_option('--youtube-print-sig-code',
+            action='store_true', dest='youtube_print_sig_code', default=False,
+            help=optparse.SUPPRESS_HELP)
+
+
+    filesystem.add_option('-t', '--title',
+            action='store_true', dest='usetitle', help='use title in file name (default)', default=False)
+    filesystem.add_option('--id',
+            action='store_true', dest='useid', help='use only video ID in file name', default=False)
+    filesystem.add_option('-l', '--literal',
+            action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
+    filesystem.add_option('-A', '--auto-number',
+            action='store_true', dest='autonumber',
+            help='number downloaded files starting from 00000', default=False)
+    filesystem.add_option('-o', '--output',
+            dest='outtmpl', metavar='TEMPLATE',
+            help=('output filename template. Use %(title)s to get the title, '
+                  '%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, '
+                  '%(autonumber)s to get an automatically incremented number, '
+                  '%(ext)s for the filename extension, '
+                  '%(format)s for the format description (like "22 - 1280x720" or "HD"),'
+                  '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"),'
+                  '%(upload_date)s for the upload date (YYYYMMDD), '
+                  '%(extractor)s for the provider (youtube, metacafe, etc), '
+                  '%(id)s for the video id , %(playlist)s for the playlist the video is in, '
+                  '%(playlist_index)s for the position in the playlist and %% for a literal percent. '
+                  'Use - to output to stdout. Can also be used to download to a different directory, '
+                  'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
+    filesystem.add_option('--autonumber-size',
+            dest='autonumber_size', metavar='NUMBER',
+            help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
+    filesystem.add_option('--restrict-filenames',
+            action='store_true', dest='restrictfilenames',
+            help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
+    filesystem.add_option('-a', '--batch-file',
+            dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
+    filesystem.add_option('-w', '--no-overwrites',
+            action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+    filesystem.add_option('-c', '--continue',
+            action='store_true', dest='continue_dl', help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.', default=True)
+    filesystem.add_option('--no-continue',
+            action='store_false', dest='continue_dl',
+            help='do not resume partially downloaded files (restart from beginning)')
+    filesystem.add_option('--cookies',
+            dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
+    filesystem.add_option('--no-part',
+            action='store_true', dest='nopart', help='do not use .part files', default=False)
+    filesystem.add_option('--no-mtime',
+            action='store_false', dest='updatetime',
+            help='do not use the Last-modified header to set the file modification time', default=True)
+    filesystem.add_option('--write-description',
+            action='store_true', dest='writedescription',
+            help='write video description to a .description file', default=False)
+    filesystem.add_option('--write-info-json',
+            action='store_true', dest='writeinfojson',
+            help='write video metadata to a .info.json file', default=False)
+    filesystem.add_option('--write-annotations',
+            action='store_true', dest='writeannotations',
+            help='write video annotations to a .annotation file', default=False)
+    filesystem.add_option('--write-thumbnail',
+            action='store_true', dest='writethumbnail',
+            help='write thumbnail image to disk', default=False)
+
+
+    postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
+            help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
+    postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
+            help='"best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; best by default')
+    postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5',
+            help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
+    postproc.add_option('--recode-video', metavar='FORMAT', dest='recodevideo', default=None,
+            help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm)')
+    postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
+            help='keeps the video file on disk after the post-processing; the video is erased by default')
+    postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
+            help='do not overwrite post-processed files; the post-processed files are overwritten by default')
+    postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
+            help='embed subtitles in the video (only for mp4 videos)')
+    postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False,
+            help='add metadata to the files')
+
+
+    parser.add_option_group(general)
+    parser.add_option_group(selection)
+    parser.add_option_group(downloader)
+    parser.add_option_group(filesystem)
+    parser.add_option_group(verbosity)
+    parser.add_option_group(video_format)
+    parser.add_option_group(subtitles)
+    parser.add_option_group(authentication)
+    parser.add_option_group(postproc)
+
+    if overrideArguments is not None:
+        opts, args = parser.parse_args(overrideArguments)
+        if opts.verbose:
+            write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
+    else:
+        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
+        if xdg_config_home:
+            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
+            if not os.path.isfile(userConfFile):
+                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
+        else:
+            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
+            if not os.path.isfile(userConfFile):
+                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
+        systemConf = _readOptions('/etc/youtube-dl.conf')
+        userConf = _readOptions(userConfFile)
+        commandLineConf = sys.argv[1:]
+        argv = systemConf + userConf + commandLineConf
+        opts, args = parser.parse_args(argv)
+        if opts.verbose:
+            write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
+            write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
+            write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
+
+    return parser, opts, args
+
 def _real_main(argv=None):
     # Compatibility fixes for Windows
     if sys.platform == 'win32':
         # https://github.com/rg3/youtube-dl/issues/820
         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
 
-    workaround_optparse_bug9161()
-
-    setproctitle('youtube-dl')
-
     parser, opts, args = parseOpts(argv)
 
     # Set user agent
@@ -64,242 +452,165 @@ def _real_main(argv=None):
     if opts.referer is not None:
         std_headers['Referer'] = opts.referer
 
-    # Custom HTTP headers
-    if opts.headers is not None:
-        for h in opts.headers:
-            if h.find(':', 1) < 0:
-                parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
-            key, value = h.split(':', 2)
-            if opts.verbose:
-                write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
-            std_headers[key] = value
-
     # Dump user agent
     if opts.dump_user_agent:
         compat_print(std_headers['User-Agent'])
         sys.exit(0)
 
     # Batch file verification
-    batch_urls = []
+    batchurls = []
     if opts.batchfile is not None:
         try:
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
-                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
-            batch_urls = read_batch_urls(batchfd)
+                batchfd = open(opts.batchfile, 'r')
+            batchurls = batchfd.readlines()
+            batchurls = [x.strip() for x in batchurls]
+            batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
             if opts.verbose:
-                write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
+                write_string(u'[debug] Batch file urls: ' + repr(batchurls) + u'\n')
         except IOError:
-            sys.exit('ERROR: batch file could not be read')
-    all_urls = batch_urls + args
+            sys.exit(u'ERROR: batch file could not be read')
+    all_urls = batchurls + args
     all_urls = [url.strip() for url in all_urls]
-    _enc = preferredencoding()
-    all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
+
+    extractors = gen_extractors()
 
     if opts.list_extractors:
-        for ie in list_extractors(opts.age_limit):
+        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
             compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
+            all_urls = [url for url in all_urls if url not in matchedUrls]
             for mu in matchedUrls:
-                compat_print('  ' + mu)
+                compat_print(u'  ' + mu)
         sys.exit(0)
     if opts.list_extractor_descriptions:
-        for ie in list_extractors(opts.age_limit):
+        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
             if not ie._WORKING:
                 continue
             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
             if desc is False:
                 continue
             if hasattr(ie, 'SEARCH_KEY'):
-                _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
-                _COUNTS = ('', '5', '10', 'all')
-                desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
+                _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise')
+                _COUNTS = (u'', u'5', u'10', u'all')
+                desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
             compat_print(desc)
         sys.exit(0)
 
+
     # Conflicting, missing and erroneous options
     if opts.usenetrc and (opts.username is not None or opts.password is not None):
-        parser.error('using .netrc conflicts with giving username/password')
+        parser.error(u'using .netrc conflicts with giving username/password')
     if opts.password is not None and opts.username is None:
-        parser.error('account username missing\n')
+        parser.error(u' account username missing\n')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
-        parser.error('using output template conflicts with using title, video ID or auto number')
+        parser.error(u'using output template conflicts with using title, video ID or auto number')
     if opts.usetitle and opts.useid:
-        parser.error('using title conflicts with using video ID')
+        parser.error(u'using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
-        opts.password = compat_getpass('Type account password and press [Return]: ')
+        opts.password = getpass.getpass(u'Type account password and press return:')
     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:
-            parser.error('invalid rate limit specified')
+            parser.error(u'invalid rate limit specified')
         opts.ratelimit = numeric_limit
     if opts.min_filesize is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
         if numeric_limit is None:
-            parser.error('invalid min_filesize specified')
+            parser.error(u'invalid min_filesize specified')
         opts.min_filesize = numeric_limit
     if opts.max_filesize is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
         if numeric_limit is None:
-            parser.error('invalid max_filesize specified')
+            parser.error(u'invalid max_filesize specified')
         opts.max_filesize = numeric_limit
     if opts.retries is not None:
-        if opts.retries in ('inf', 'infinite'):
-            opts_retries = float('inf')
-        else:
-            try:
-                opts_retries = int(opts.retries)
-            except (TypeError, ValueError):
-                parser.error('invalid retry count specified')
+        try:
+            opts.retries = int(opts.retries)
+        except (TypeError, ValueError):
+            parser.error(u'invalid retry count specified')
     if opts.buffersize is not None:
         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
         if numeric_buffersize is None:
-            parser.error('invalid buffer size specified')
+            parser.error(u'invalid buffer size specified')
         opts.buffersize = numeric_buffersize
-    if opts.playliststart <= 0:
-        raise ValueError('Playlist start must be positive')
-    if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
-        raise ValueError('Playlist end must be greater than playlist start')
+    try:
+        opts.playliststart = int(opts.playliststart)
+        if opts.playliststart <= 0:
+            raise ValueError(u'Playlist start must be positive')
+    except (TypeError, ValueError):
+        parser.error(u'invalid playlist start number specified')
+    try:
+        opts.playlistend = int(opts.playlistend)
+        if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
+            raise ValueError(u'Playlist end must be greater than playlist start')
+    except (TypeError, ValueError):
+        parser.error(u'invalid playlist end number specified')
     if opts.extractaudio:
         if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
-            parser.error('invalid audio format specified')
+            parser.error(u'invalid audio format specified')
     if opts.audioquality:
         opts.audioquality = opts.audioquality.strip('k').strip('K')
         if not opts.audioquality.isdigit():
-            parser.error('invalid audio quality specified')
+            parser.error(u'invalid audio quality specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
-            parser.error('invalid video recode format specified')
-    if opts.convertsubtitles is not None:
-        if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
-            parser.error('invalid subtitle format specified')
-
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg']:
+            parser.error(u'invalid video recode format specified')
     if opts.date is not None:
         date = DateRange.day(opts.date)
     else:
         date = DateRange(opts.dateafter, opts.datebefore)
 
-    # Do not download videos when there are audio-only formats
-    if opts.extractaudio and not opts.keepvideo and opts.format is None:
-        opts.format = 'bestaudio/best'
-
     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
     # this was the old behaviour if only --all-sub was given.
-    if opts.allsubtitles and not opts.writeautomaticsub:
+    if opts.allsubtitles and (opts.writeautomaticsub == False):
         opts.writesubtitles = True
 
-    outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
-               (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
-               (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
-               (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
-               (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
-               (opts.useid and '%(id)s.%(ext)s') or
-               (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
-               DEFAULT_OUTTMPL)
-    if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
-        parser.error('Cannot download a video and extract audio into the same'
-                     ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
-                     ' template'.format(outtmpl))
-
-    any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
-    any_printing = opts.print_json
-    download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
-
-    # PostProcessors
-    postprocessors = []
-    # Add the metadata pp first, the other pps will copy it
-    if opts.metafromtitle:
-        postprocessors.append({
-            'key': 'MetadataFromTitle',
-            'titleformat': opts.metafromtitle
-        })
-    if opts.addmetadata:
-        postprocessors.append({'key': 'FFmpegMetadata'})
-    if opts.extractaudio:
-        postprocessors.append({
-            'key': 'FFmpegExtractAudio',
-            'preferredcodec': opts.audioformat,
-            'preferredquality': opts.audioquality,
-            'nopostoverwrites': opts.nopostoverwrites,
-        })
-    if opts.recodevideo:
-        postprocessors.append({
-            'key': 'FFmpegVideoConvertor',
-            'preferedformat': opts.recodevideo,
-        })
-    if opts.convertsubtitles:
-        postprocessors.append({
-            'key': 'FFmpegSubtitlesConvertor',
-            'format': opts.convertsubtitles,
-        })
-    if opts.embedsubtitles:
-        postprocessors.append({
-            'key': 'FFmpegEmbedSubtitle',
-        })
-    if opts.xattrs:
-        postprocessors.append({'key': 'XAttrMetadata'})
-    if opts.embedthumbnail:
-        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
-        postprocessors.append({
-            'key': 'EmbedThumbnail',
-            'already_have_thumbnail': already_have_thumbnail
-        })
-        if not already_have_thumbnail:
-            opts.writethumbnail = True
-    # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
-    # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
-    if opts.exec_cmd:
-        postprocessors.append({
-            'key': 'ExecAfterDownload',
-            'exec_cmd': opts.exec_cmd,
-        })
-    if opts.xattr_set_filesize:
-        try:
-            import xattr
-            xattr  # Confuse flake8
-        except ImportError:
-            parser.error('setting filesize xattr requested but python-xattr is not available')
-    external_downloader_args = None
-    if opts.external_downloader_args:
-        external_downloader_args = compat_shlex_split(opts.external_downloader_args)
-    postprocessor_args = None
-    if opts.postprocessor_args:
-        postprocessor_args = compat_shlex_split(opts.postprocessor_args)
-    match_filter = (
-        None if opts.match_filter is None
-        else match_filter_func(opts.match_filter))
+    if sys.version_info < (3,):
+        # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
+        if opts.outtmpl is not None:
+            opts.outtmpl = opts.outtmpl.decode(preferredencoding())
+    outtmpl =((opts.outtmpl is not None and opts.outtmpl)
+            or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s')
+            or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
+            or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
+            or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
+            or (opts.useid and u'%(id)s.%(ext)s')
+            or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
+            or u'%(title)s-%(id)s.%(ext)s')
+    if '%(ext)s' not in outtmpl and opts.extractaudio:
+        parser.error(u'Cannot download a video and extract audio into the same'
+                     u' file! Use "%%(ext)s" instead of %r' %
+                     determine_ext(outtmpl, u''))
 
     ydl_opts = {
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
-        'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
-        'quiet': (opts.quiet or any_getting or any_printing),
-        'no_warnings': opts.no_warnings,
+        'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.dumpjson),
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
         'forceid': opts.getid,
         'forcethumbnail': opts.getthumbnail,
         'forcedescription': opts.getdescription,
-        'forceduration': opts.getduration,
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,
-        'forcejson': opts.dumpjson or opts.print_json,
-        'dump_single_json': opts.dump_single_json,
-        'simulate': opts.simulate or any_getting,
-        'skip_download': opts.skip_download,
+        'forcejson': opts.dumpjson,
+        'simulate': opts.simulate,
+        'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.dumpjson),
         'format': opts.format,
+        'format_limit': opts.format_limit,
         'listformats': opts.listformats,
         'outtmpl': outtmpl,
         'autonumber_size': opts.autonumber_size,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
-        'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
-        'retries': opts_retries,
+        'retries': opts.retries,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,
@@ -307,7 +618,6 @@ def _real_main(argv=None):
         'progress_with_newline': opts.progress_with_newline,
         'playliststart': opts.playliststart,
         'playlistend': opts.playlistend,
-        'playlistreverse': opts.playlist_reverse,
         'noplaylist': opts.noplaylist,
         'logtostderr': opts.outtmpl == '-',
         'consoletitle': opts.consoletitle,
@@ -317,7 +627,6 @@ def _real_main(argv=None):
         'writeannotations': opts.writeannotations,
         'writeinfojson': opts.writeinfojson,
         'writethumbnail': opts.writethumbnail,
-        'write_all_thumbnails': opts.write_all_thumbnails,
         'writesubtitles': opts.writesubtitles,
         'writeautomaticsub': opts.writeautomaticsub,
         'allsubtitles': opts.allsubtitles,
@@ -335,71 +644,45 @@ def _real_main(argv=None):
         'keepvideo': opts.keepvideo,
         'min_filesize': opts.min_filesize,
         'max_filesize': opts.max_filesize,
-        'min_views': opts.min_views,
-        'max_views': opts.max_views,
         'daterange': date,
         'cachedir': opts.cachedir,
         'youtube_print_sig_code': opts.youtube_print_sig_code,
         'age_limit': opts.age_limit,
-        'download_archive': download_archive_fn,
+        'download_archive': opts.download_archive,
         'cookiefile': opts.cookiefile,
         'nocheckcertificate': opts.no_check_certificate,
-        'prefer_insecure': opts.prefer_insecure,
-        'proxy': opts.proxy,
-        'socket_timeout': opts.socket_timeout,
-        'bidi_workaround': opts.bidi_workaround,
-        'debug_printtraffic': opts.debug_printtraffic,
-        'prefer_ffmpeg': opts.prefer_ffmpeg,
-        'include_ads': opts.include_ads,
-        'default_search': opts.default_search,
-        'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
-        'encoding': opts.encoding,
-        'extract_flat': opts.extract_flat,
-        'merge_output_format': opts.merge_output_format,
-        'postprocessors': postprocessors,
-        'fixup': opts.fixup,
-        'source_address': opts.source_address,
-        'call_home': opts.call_home,
-        'sleep_interval': opts.sleep_interval,
-        'external_downloader': opts.external_downloader,
-        'list_thumbnails': opts.list_thumbnails,
-        'playlist_items': opts.playlist_items,
-        'xattr_set_filesize': opts.xattr_set_filesize,
-        'match_filter': match_filter,
-        'no_color': opts.no_color,
-        'ffmpeg_location': opts.ffmpeg_location,
-        'hls_prefer_native': opts.hls_prefer_native,
-        'external_downloader_args': external_downloader_args,
-        'postprocessor_args': postprocessor_args,
-        'cn_verification_proxy': opts.cn_verification_proxy,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
+        ydl.print_debug_header()
+        ydl.add_default_info_extractors()
+
+        # PostProcessors
+        # Add the metadata pp first, the other pps will copy it
+        if opts.addmetadata:
+            ydl.add_post_processor(FFmpegMetadataPP())
+        if opts.extractaudio:
+            ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
+        if opts.recodevideo:
+            ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
+        if opts.embedsubtitles:
+            ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
+
         # Update version
         if opts.update_self:
             update_self(ydl.to_screen, opts.verbose)
 
-        # Remove cache dir
-        if opts.rm_cachedir:
-            ydl.cache.remove()
-
         # Maybe do nothing
-        if (len(all_urls) < 1) and (opts.load_info_filename is None):
-            if opts.update_self or opts.rm_cachedir:
+        if len(all_urls) < 1:
+            if not opts.update_self:
+                parser.error(u'you must provide at least one URL')
+            else:
                 sys.exit()
 
-            ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
-            parser.error(
-                'You must provide at least one URL.\n'
-                'Type youtube-dl --help to see a list of all options.')
-
         try:
-            if opts.load_info_filename is not None:
-                retcode = ydl.download_with_info_file(opts.load_info_filename)
-            else:
-                retcode = ydl.download(all_urls)
+            retcode = ydl.download(all_urls)
         except MaxDownloadsReached:
-            ydl.to_screen('--max-download limit reached, aborting.')
+            ydl.to_screen(u'--max-download limit reached, aborting.')
             retcode = 101
 
     sys.exit(retcode)
@@ -411,8 +694,6 @@ def main(argv=None):
     except DownloadError:
         sys.exit(1)
     except SameFileError:
-        sys.exit('ERROR: fixed output name but more than one file to download')
+        sys.exit(u'ERROR: fixed output name but more than one file to download')
     except KeyboardInterrupt:
-        sys.exit('\nERROR: Interrupted by user')
-
-__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']
+        sys.exit(u'\nERROR: Interrupted by user')

youtube_dl/__main__.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-from __future__ import unicode_literals
 
 # Execute with
 # $ python youtube_dl/__main__.py (2.6+)
@@ -11,7 +10,7 @@ if __package__ is None and not hasattr(sys, "frozen"):
     # direct call of __main__.py
     import os.path
     path = os.path.realpath(os.path.abspath(__file__))
-    sys.path.insert(0, os.path.dirname(os.path.dirname(path)))
+    sys.path.append(os.path.dirname(os.path.dirname(path)))
 
 import youtube_dl
 

youtube_dl/aes.py

@@ -1,4 +1,4 @@
-from __future__ import unicode_literals
+__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_decrypt_text']
 
 import base64
 from math import ceil
@@ -7,11 +7,10 @@ from .utils import bytes_to_intlist, intlist_to_bytes
 
 BLOCK_SIZE_BYTES = 16
 
-
 def aes_ctr_decrypt(data, key, counter):
     """
     Decrypt with aes in counter mode
-
+    
     @param {int[]} data        cipher
     @param {int[]} key         16/24/32-Byte cipher key
     @param {instance} counter  Instance whose next_value function (@returns {int[]}  16-Byte block)
@@ -20,123 +19,73 @@ def aes_ctr_decrypt(data, key, counter):
     """
     expanded_key = key_expansion(key)
     block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
-
-    decrypted_data = []
+    
+    decrypted_data=[]
     for i in range(block_count):
         counter_block = counter.next_value()
-        block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
-        block += [0] * (BLOCK_SIZE_BYTES - len(block))
-
+        block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]
+        block += [0]*(BLOCK_SIZE_BYTES - len(block))
+        
         cipher_counter_block = aes_encrypt(counter_block, expanded_key)
         decrypted_data += xor(block, cipher_counter_block)
     decrypted_data = decrypted_data[:len(data)]
-
+    
     return decrypted_data
 
-
-def aes_cbc_decrypt(data, key, iv):
-    """
-    Decrypt with aes in CBC mode
-
-    @param {int[]} data        cipher
-    @param {int[]} key         16/24/32-Byte cipher key
-    @param {int[]} iv          16-Byte IV
-    @returns {int[]}           decrypted data
-    """
-    expanded_key = key_expansion(key)
-    block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
-
-    decrypted_data = []
-    previous_cipher_block = iv
-    for i in range(block_count):
-        block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
-        block += [0] * (BLOCK_SIZE_BYTES - len(block))
-
-        decrypted_block = aes_decrypt(block, expanded_key)
-        decrypted_data += xor(decrypted_block, previous_cipher_block)
-        previous_cipher_block = block
-    decrypted_data = decrypted_data[:len(data)]
-
-    return decrypted_data
-
-
 def key_expansion(data):
     """
     Generate key schedule
-
+    
     @param {int[]} data  16/24/32-Byte cipher key
-    @returns {int[]}     176/208/240-Byte expanded key
+    @returns {int[]}     176/208/240-Byte expanded key 
     """
-    data = data[:]  # copy
+    data = data[:] # copy
     rcon_iteration = 1
     key_size_bytes = len(data)
     expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES
-
+    
     while len(data) < expanded_key_size_bytes:
         temp = data[-4:]
         temp = key_schedule_core(temp, rcon_iteration)
         rcon_iteration += 1
-        data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
-
+        data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
         for _ in range(3):
             temp = data[-4:]
-            data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
-
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
         if key_size_bytes == 32:
             temp = data[-4:]
             temp = sub_bytes(temp)
-            data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
-
-        for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0):
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
+        for _ in range(3 if key_size_bytes == 32  else 2 if key_size_bytes == 24 else 0):
             temp = data[-4:]
-            data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
     data = data[:expanded_key_size_bytes]
-
+    
     return data
 
-
 def aes_encrypt(data, expanded_key):
     """
     Encrypt one block with aes
-
+    
     @param {int[]} data          16-Byte state
-    @param {int[]} expanded_key  176/208/240-Byte expanded key
+    @param {int[]} expanded_key  176/208/240-Byte expanded key 
     @returns {int[]}             16-Byte cipher
     """
     rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
-
+    
     data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
-    for i in range(1, rounds + 1):
+    for i in range(1, rounds+1):
         data = sub_bytes(data)
         data = shift_rows(data)
         if i != rounds:
             data = mix_columns(data)
-        data = xor(data, expanded_key[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES])
-
+        data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
+    
     return data
 
-
-def aes_decrypt(data, expanded_key):
-    """
-    Decrypt one block with aes
-
-    @param {int[]} data          16-Byte cipher
-    @param {int[]} expanded_key  176/208/240-Byte expanded key
-    @returns {int[]}             16-Byte state
-    """
-    rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
-
-    for i in range(rounds, 0, -1):
-        data = xor(data, expanded_key[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES])
-        if i != rounds:
-            data = mix_columns_inv(data)
-        data = shift_rows_inv(data)
-        data = sub_bytes_inv(data)
-    data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
-
-    return data
-
-
 def aes_decrypt_text(data, password, key_size_bytes):
     """
     Decrypt text
@@ -144,34 +93,33 @@ def aes_decrypt_text(data, password, key_size_bytes):
     - The cipher key is retrieved by encrypting the first 16 Byte of 'password'
       with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's)
     - Mode of operation is 'counter'
-
+    
     @param {str} data                    Base64 encoded string
     @param {str,unicode} password        Password (will be encoded with utf-8)
     @param {int} key_size_bytes          Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit
     @returns {str}                       Decrypted data
     """
     NONCE_LENGTH_BYTES = 8
-
-    data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
+    
+    data = bytes_to_intlist(base64.b64decode(data))
     password = bytes_to_intlist(password.encode('utf-8'))
-
-    key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password))
+    
+    key = password[:key_size_bytes] + [0]*(key_size_bytes - len(password))
     key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES)
-
+    
     nonce = data[:NONCE_LENGTH_BYTES]
     cipher = data[NONCE_LENGTH_BYTES:]
-
+    
     class Counter:
-        __value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
-
+        __value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
         def next_value(self):
             temp = self.__value
             self.__value = inc(self.__value)
             return temp
-
+    
     decrypted_data = aes_ctr_decrypt(cipher, key, Counter())
     plaintext = intlist_to_bytes(decrypted_data)
-
+    
     return plaintext
 
 RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
@@ -191,141 +139,64 @@ SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B,
         0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
         0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
         0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16)
-SBOX_INV = (0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
-            0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
-            0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
-            0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
-            0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
-            0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
-            0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
-            0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
-            0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
-            0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
-            0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
-            0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
-            0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
-            0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
-            0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
-            0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d)
-MIX_COLUMN_MATRIX = ((0x2, 0x3, 0x1, 0x1),
-                     (0x1, 0x2, 0x3, 0x1),
-                     (0x1, 0x1, 0x2, 0x3),
-                     (0x3, 0x1, 0x1, 0x2))
-MIX_COLUMN_MATRIX_INV = ((0xE, 0xB, 0xD, 0x9),
-                         (0x9, 0xE, 0xB, 0xD),
-                         (0xD, 0x9, 0xE, 0xB),
-                         (0xB, 0xD, 0x9, 0xE))
-RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35,
-                      0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA,
-                      0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31,
-                      0x53, 0xF5, 0x04, 0x0C, 0x14, 0x3C, 0x44, 0xCC, 0x4F, 0xD1, 0x68, 0xB8, 0xD3, 0x6E, 0xB2, 0xCD,
-                      0x4C, 0xD4, 0x67, 0xA9, 0xE0, 0x3B, 0x4D, 0xD7, 0x62, 0xA6, 0xF1, 0x08, 0x18, 0x28, 0x78, 0x88,
-                      0x83, 0x9E, 0xB9, 0xD0, 0x6B, 0xBD, 0xDC, 0x7F, 0x81, 0x98, 0xB3, 0xCE, 0x49, 0xDB, 0x76, 0x9A,
-                      0xB5, 0xC4, 0x57, 0xF9, 0x10, 0x30, 0x50, 0xF0, 0x0B, 0x1D, 0x27, 0x69, 0xBB, 0xD6, 0x61, 0xA3,
-                      0xFE, 0x19, 0x2B, 0x7D, 0x87, 0x92, 0xAD, 0xEC, 0x2F, 0x71, 0x93, 0xAE, 0xE9, 0x20, 0x60, 0xA0,
-                      0xFB, 0x16, 0x3A, 0x4E, 0xD2, 0x6D, 0xB7, 0xC2, 0x5D, 0xE7, 0x32, 0x56, 0xFA, 0x15, 0x3F, 0x41,
-                      0xC3, 0x5E, 0xE2, 0x3D, 0x47, 0xC9, 0x40, 0xC0, 0x5B, 0xED, 0x2C, 0x74, 0x9C, 0xBF, 0xDA, 0x75,
-                      0x9F, 0xBA, 0xD5, 0x64, 0xAC, 0xEF, 0x2A, 0x7E, 0x82, 0x9D, 0xBC, 0xDF, 0x7A, 0x8E, 0x89, 0x80,
-                      0x9B, 0xB6, 0xC1, 0x58, 0xE8, 0x23, 0x65, 0xAF, 0xEA, 0x25, 0x6F, 0xB1, 0xC8, 0x43, 0xC5, 0x54,
-                      0xFC, 0x1F, 0x21, 0x63, 0xA5, 0xF4, 0x07, 0x09, 0x1B, 0x2D, 0x77, 0x99, 0xB0, 0xCB, 0x46, 0xCA,
-                      0x45, 0xCF, 0x4A, 0xDE, 0x79, 0x8B, 0x86, 0x91, 0xA8, 0xE3, 0x3E, 0x42, 0xC6, 0x51, 0xF3, 0x0E,
-                      0x12, 0x36, 0x5A, 0xEE, 0x29, 0x7B, 0x8D, 0x8C, 0x8F, 0x8A, 0x85, 0x94, 0xA7, 0xF2, 0x0D, 0x17,
-                      0x39, 0x4B, 0xDD, 0x7C, 0x84, 0x97, 0xA2, 0xFD, 0x1C, 0x24, 0x6C, 0xB4, 0xC7, 0x52, 0xF6, 0x01)
-RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7, 0x1b, 0x68, 0x33, 0xee, 0xdf, 0x03,
-                      0x64, 0x04, 0xe0, 0x0e, 0x34, 0x8d, 0x81, 0xef, 0x4c, 0x71, 0x08, 0xc8, 0xf8, 0x69, 0x1c, 0xc1,
-                      0x7d, 0xc2, 0x1d, 0xb5, 0xf9, 0xb9, 0x27, 0x6a, 0x4d, 0xe4, 0xa6, 0x72, 0x9a, 0xc9, 0x09, 0x78,
-                      0x65, 0x2f, 0x8a, 0x05, 0x21, 0x0f, 0xe1, 0x24, 0x12, 0xf0, 0x82, 0x45, 0x35, 0x93, 0xda, 0x8e,
-                      0x96, 0x8f, 0xdb, 0xbd, 0x36, 0xd0, 0xce, 0x94, 0x13, 0x5c, 0xd2, 0xf1, 0x40, 0x46, 0x83, 0x38,
-                      0x66, 0xdd, 0xfd, 0x30, 0xbf, 0x06, 0x8b, 0x62, 0xb3, 0x25, 0xe2, 0x98, 0x22, 0x88, 0x91, 0x10,
-                      0x7e, 0x6e, 0x48, 0xc3, 0xa3, 0xb6, 0x1e, 0x42, 0x3a, 0x6b, 0x28, 0x54, 0xfa, 0x85, 0x3d, 0xba,
-                      0x2b, 0x79, 0x0a, 0x15, 0x9b, 0x9f, 0x5e, 0xca, 0x4e, 0xd4, 0xac, 0xe5, 0xf3, 0x73, 0xa7, 0x57,
-                      0xaf, 0x58, 0xa8, 0x50, 0xf4, 0xea, 0xd6, 0x74, 0x4f, 0xae, 0xe9, 0xd5, 0xe7, 0xe6, 0xad, 0xe8,
-                      0x2c, 0xd7, 0x75, 0x7a, 0xeb, 0x16, 0x0b, 0xf5, 0x59, 0xcb, 0x5f, 0xb0, 0x9c, 0xa9, 0x51, 0xa0,
-                      0x7f, 0x0c, 0xf6, 0x6f, 0x17, 0xc4, 0x49, 0xec, 0xd8, 0x43, 0x1f, 0x2d, 0xa4, 0x76, 0x7b, 0xb7,
-                      0xcc, 0xbb, 0x3e, 0x5a, 0xfb, 0x60, 0xb1, 0x86, 0x3b, 0x52, 0xa1, 0x6c, 0xaa, 0x55, 0x29, 0x9d,
-                      0x97, 0xb2, 0x87, 0x90, 0x61, 0xbe, 0xdc, 0xfc, 0xbc, 0x95, 0xcf, 0xcd, 0x37, 0x3f, 0x5b, 0xd1,
-                      0x53, 0x39, 0x84, 0x3c, 0x41, 0xa2, 0x6d, 0x47, 0x14, 0x2a, 0x9e, 0x5d, 0x56, 0xf2, 0xd3, 0xab,
-                      0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
-                      0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07)
-
+MIX_COLUMN_MATRIX = ((2,3,1,1),
+                     (1,2,3,1),
+                     (1,1,2,3),
+                     (3,1,1,2))
 
 def sub_bytes(data):
     return [SBOX[x] for x in data]
 
-
-def sub_bytes_inv(data):
-    return [SBOX_INV[x] for x in data]
-
-
 def rotate(data):
     return data[1:] + [data[0]]
 
-
 def key_schedule_core(data, rcon_iteration):
     data = rotate(data)
     data = sub_bytes(data)
     data[0] = data[0] ^ RCON[rcon_iteration]
-
+    
     return data
 
-
 def xor(data1, data2):
-    return [x ^ y for x, y in zip(data1, data2)]
+    return [x^y for x, y in zip(data1, data2)]
 
-
-def rijndael_mul(a, b):
-    if(a == 0 or b == 0):
-        return 0
-    return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]
-
-
-def mix_column(data, matrix):
+def mix_column(data):
     data_mixed = []
     for row in range(4):
         mixed = 0
         for column in range(4):
-            # xor is (+) and (-)
-            mixed ^= rijndael_mul(data[column], matrix[row][column])
+            addend = data[column]
+            if MIX_COLUMN_MATRIX[row][column] in (2,3):
+                addend <<= 1
+                if addend > 0xff:
+                    addend &= 0xff
+                    addend ^= 0x1b
+                if MIX_COLUMN_MATRIX[row][column] == 3:
+                    addend ^= data[column]
+            mixed ^= addend & 0xff
         data_mixed.append(mixed)
     return data_mixed
 
-
-def mix_columns(data, matrix=MIX_COLUMN_MATRIX):
+def mix_columns(data):
     data_mixed = []
     for i in range(4):
-        column = data[i * 4: (i + 1) * 4]
-        data_mixed += mix_column(column, matrix)
+        column = data[i*4 : (i+1)*4]
+        data_mixed += mix_column(column)
     return data_mixed
 
-
-def mix_columns_inv(data):
-    return mix_columns(data, MIX_COLUMN_MATRIX_INV)
-
-
 def shift_rows(data):
     data_shifted = []
     for column in range(4):
         for row in range(4):
-            data_shifted.append(data[((column + row) & 0b11) * 4 + row])
+            data_shifted.append( data[((column + row) & 0b11) * 4 + row] )
     return data_shifted
 
-
-def shift_rows_inv(data):
-    data_shifted = []
-    for column in range(4):
-        for row in range(4):
-            data_shifted.append(data[((column - row) & 0b11) * 4 + row])
-    return data_shifted
-
-
 def inc(data):
-    data = data[:]  # copy
-    for i in range(len(data) - 1, -1, -1):
+    data = data[:] # copy
+    for i in range(len(data)-1,-1,-1):
         if data[i] == 255:
             data[i] = 0
         else:
             data[i] = data[i] + 1
             break
     return data
-
-__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']

youtube_dl/cache.py

@@ -1,93 +0,0 @@
-from __future__ import unicode_literals
-
-import errno
-import io
-import json
-import os
-import re
-import shutil
-import traceback
-
-from .compat import compat_expanduser, compat_getenv
-from .utils import write_json_file
-
-
-class Cache(object):
-    def __init__(self, ydl):
-        self._ydl = ydl
-
-    def _get_root_dir(self):
-        res = self._ydl.params.get('cachedir')
-        if res is None:
-            cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
-            res = os.path.join(cache_root, 'youtube-dl')
-        return compat_expanduser(res)
-
-    def _get_cache_fn(self, section, key, dtype):
-        assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \
-            'invalid section %r' % section
-        assert re.match(r'^[a-zA-Z0-9_.-]+$', key), 'invalid key %r' % key
-        return os.path.join(
-            self._get_root_dir(), section, '%s.%s' % (key, dtype))
-
-    @property
-    def enabled(self):
-        return self._ydl.params.get('cachedir') is not False
-
-    def store(self, section, key, data, dtype='json'):
-        assert dtype in ('json',)
-
-        if not self.enabled:
-            return
-
-        fn = self._get_cache_fn(section, key, dtype)
-        try:
-            try:
-                os.makedirs(os.path.dirname(fn))
-            except OSError as ose:
-                if ose.errno != errno.EEXIST:
-                    raise
-            write_json_file(data, fn)
-        except Exception:
-            tb = traceback.format_exc()
-            self._ydl.report_warning(
-                'Writing cache to %r failed: %s' % (fn, tb))
-
-    def load(self, section, key, dtype='json', default=None):
-        assert dtype in ('json',)
-
-        if not self.enabled:
-            return default
-
-        cache_fn = self._get_cache_fn(section, key, dtype)
-        try:
-            try:
-                with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
-                    return json.load(cachef)
-            except ValueError:
-                try:
-                    file_size = os.path.getsize(cache_fn)
-                except (OSError, IOError) as oe:
-                    file_size = str(oe)
-                self._ydl.report_warning(
-                    'Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
-        except IOError:
-            pass  # No cache available
-
-        return default
-
-    def remove(self):
-        if not self.enabled:
-            self._ydl.to_screen('Cache is disabled (Did you combine --no-cache-dir and --rm-cache-dir?)')
-            return
-
-        cachedir = self._get_root_dir()
-        if not any((term in cachedir) for term in ('cache', 'tmp')):
-            raise Exception('Not removing directory %s - this does not look like a cache dir' % cachedir)
-
-        self._ydl.to_screen(
-            'Removing cache dir %s .' % cachedir, skip_eol=True)
-        if os.path.exists(cachedir):
-            self._ydl.to_screen('.', skip_eol=True)
-            shutil.rmtree(cachedir)
-        self._ydl.to_screen('.')

youtube_dl/compat.py

@@ -1,498 +0,0 @@
-from __future__ import unicode_literals
-
-import collections
-import getpass
-import optparse
-import os
-import re
-import shlex
-import shutil
-import socket
-import subprocess
-import sys
-import itertools
-
-
-try:
-    import urllib.request as compat_urllib_request
-except ImportError:  # Python 2
-    import urllib2 as compat_urllib_request
-
-try:
-    import urllib.error as compat_urllib_error
-except ImportError:  # Python 2
-    import urllib2 as compat_urllib_error
-
-try:
-    import urllib.parse as compat_urllib_parse
-except ImportError:  # Python 2
-    import urllib as compat_urllib_parse
-
-try:
-    from urllib.parse import urlparse as compat_urllib_parse_urlparse
-except ImportError:  # Python 2
-    from urlparse import urlparse as compat_urllib_parse_urlparse
-
-try:
-    import urllib.parse as compat_urlparse
-except ImportError:  # Python 2
-    import urlparse as compat_urlparse
-
-try:
-    import http.cookiejar as compat_cookiejar
-except ImportError:  # Python 2
-    import cookielib as compat_cookiejar
-
-try:
-    import http.cookies as compat_cookies
-except ImportError:  # Python 2
-    import Cookie as compat_cookies
-
-try:
-    import html.entities as compat_html_entities
-except ImportError:  # Python 2
-    import htmlentitydefs as compat_html_entities
-
-try:
-    import http.client as compat_http_client
-except ImportError:  # Python 2
-    import httplib as compat_http_client
-
-try:
-    from urllib.error import HTTPError as compat_HTTPError
-except ImportError:  # Python 2
-    from urllib2 import HTTPError as compat_HTTPError
-
-try:
-    from urllib.request import urlretrieve as compat_urlretrieve
-except ImportError:  # Python 2
-    from urllib import urlretrieve as compat_urlretrieve
-
-
-try:
-    from subprocess import DEVNULL
-    compat_subprocess_get_DEVNULL = lambda: DEVNULL
-except ImportError:
-    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
-
-try:
-    import http.server as compat_http_server
-except ImportError:
-    import BaseHTTPServer as compat_http_server
-
-try:
-    compat_str = unicode  # Python 2
-except NameError:
-    compat_str = str
-
-try:
-    from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
-    from urllib.parse import unquote as compat_urllib_parse_unquote
-    from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
-except ImportError:  # Python 2
-    _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
-                else re.compile('([\x00-\x7f]+)'))
-
-    # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
-    # implementations from cpython 3.4.3's stdlib. Python 2's version
-    # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244)
-
-    def compat_urllib_parse_unquote_to_bytes(string):
-        """unquote_to_bytes('abc%20def') -> b'abc def'."""
-        # Note: strings are encoded as UTF-8. This is only an issue if it contains
-        # unescaped non-ASCII characters, which URIs should not.
-        if not string:
-            # Is it a string-like object?
-            string.split
-            return b''
-        if isinstance(string, compat_str):
-            string = string.encode('utf-8')
-        bits = string.split(b'%')
-        if len(bits) == 1:
-            return string
-        res = [bits[0]]
-        append = res.append
-        for item in bits[1:]:
-            try:
-                append(compat_urllib_parse._hextochr[item[:2]])
-                append(item[2:])
-            except KeyError:
-                append(b'%')
-                append(item)
-        return b''.join(res)
-
-    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
-        """Replace %xx escapes by their single-character equivalent. The optional
-        encoding and errors parameters specify how to decode percent-encoded
-        sequences into Unicode characters, as accepted by the bytes.decode()
-        method.
-        By default, percent-encoded sequences are decoded with UTF-8, and invalid
-        sequences are replaced by a placeholder character.
-
-        unquote('abc%20def') -> 'abc def'.
-        """
-        if '%' not in string:
-            string.split
-            return string
-        if encoding is None:
-            encoding = 'utf-8'
-        if errors is None:
-            errors = 'replace'
-        bits = _asciire.split(string)
-        res = [bits[0]]
-        append = res.append
-        for i in range(1, len(bits), 2):
-            append(compat_urllib_parse_unquote_to_bytes(bits[i]).decode(encoding, errors))
-            append(bits[i + 1])
-        return ''.join(res)
-
-    def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace'):
-        """Like unquote(), but also replace plus signs by spaces, as required for
-        unquoting HTML form values.
-
-        unquote_plus('%7e/abc+def') -> '~/abc def'
-        """
-        string = string.replace('+', ' ')
-        return compat_urllib_parse_unquote(string, encoding, errors)
-
-try:
-    compat_basestring = basestring  # Python 2
-except NameError:
-    compat_basestring = str
-
-try:
-    compat_chr = unichr  # Python 2
-except NameError:
-    compat_chr = chr
-
-try:
-    from xml.etree.ElementTree import ParseError as compat_xml_parse_error
-except ImportError:  # Python 2.6
-    from xml.parsers.expat import ExpatError as compat_xml_parse_error
-
-
-try:
-    from urllib.parse import parse_qs as compat_parse_qs
-except ImportError:  # Python 2
-    # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
-    # Python 2's version is apparently totally broken
-
-    def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
-                   encoding='utf-8', errors='replace'):
-        qs, _coerce_result = qs, compat_str
-        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
-        r = []
-        for name_value in pairs:
-            if not name_value and not strict_parsing:
-                continue
-            nv = name_value.split('=', 1)
-            if len(nv) != 2:
-                if strict_parsing:
-                    raise ValueError("bad query field: %r" % (name_value,))
-                # Handle case of a control-name with no equal sign
-                if keep_blank_values:
-                    nv.append('')
-                else:
-                    continue
-            if len(nv[1]) or keep_blank_values:
-                name = nv[0].replace('+', ' ')
-                name = compat_urllib_parse_unquote(
-                    name, encoding=encoding, errors=errors)
-                name = _coerce_result(name)
-                value = nv[1].replace('+', ' ')
-                value = compat_urllib_parse_unquote(
-                    value, encoding=encoding, errors=errors)
-                value = _coerce_result(value)
-                r.append((name, value))
-        return r
-
-    def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
-                        encoding='utf-8', errors='replace'):
-        parsed_result = {}
-        pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
-                           encoding=encoding, errors=errors)
-        for name, value in pairs:
-            if name in parsed_result:
-                parsed_result[name].append(value)
-            else:
-                parsed_result[name] = [value]
-        return parsed_result
-
-try:
-    from shlex import quote as shlex_quote
-except ImportError:  # Python < 3.3
-    def shlex_quote(s):
-        if re.match(r'^[-_\w./]+$', s):
-            return s
-        else:
-            return "'" + s.replace("'", "'\"'\"'") + "'"
-
-
-if sys.version_info >= (2, 7, 3):
-    compat_shlex_split = shlex.split
-else:
-    # Working around shlex issue with unicode strings on some python 2
-    # versions (see http://bugs.python.org/issue1548891)
-    def compat_shlex_split(s, comments=False, posix=True):
-        if isinstance(s, compat_str):
-            s = s.encode('utf-8')
-        return shlex.split(s, comments, posix)
-
-
-def compat_ord(c):
-    if type(c) is int:
-        return c
-    else:
-        return ord(c)
-
-
-if sys.version_info >= (3, 0):
-    compat_getenv = os.getenv
-    compat_expanduser = os.path.expanduser
-else:
-    # Environment variables should be decoded with filesystem encoding.
-    # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
-
-    def compat_getenv(key, default=None):
-        from .utils import get_filesystem_encoding
-        env = os.getenv(key, default)
-        if env:
-            env = env.decode(get_filesystem_encoding())
-        return env
-
-    # HACK: The default implementations of os.path.expanduser from cpython do not decode
-    # environment variables with filesystem encoding. We will work around this by
-    # providing adjusted implementations.
-    # The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
-    # for different platforms with correct environment variables decoding.
-
-    if os.name == 'posix':
-        def compat_expanduser(path):
-            """Expand ~ and ~user constructions.  If user or $HOME is unknown,
-            do nothing."""
-            if not path.startswith('~'):
-                return path
-            i = path.find('/', 1)
-            if i < 0:
-                i = len(path)
-            if i == 1:
-                if 'HOME' not in os.environ:
-                    import pwd
-                    userhome = pwd.getpwuid(os.getuid()).pw_dir
-                else:
-                    userhome = compat_getenv('HOME')
-            else:
-                import pwd
-                try:
-                    pwent = pwd.getpwnam(path[1:i])
-                except KeyError:
-                    return path
-                userhome = pwent.pw_dir
-            userhome = userhome.rstrip('/')
-            return (userhome + path[i:]) or '/'
-    elif os.name == 'nt' or os.name == 'ce':
-        def compat_expanduser(path):
-            """Expand ~ and ~user constructs.
-
-            If user or $HOME is unknown, do nothing."""
-            if path[:1] != '~':
-                return path
-            i, n = 1, len(path)
-            while i < n and path[i] not in '/\\':
-                i = i + 1
-
-            if 'HOME' in os.environ:
-                userhome = compat_getenv('HOME')
-            elif 'USERPROFILE' in os.environ:
-                userhome = compat_getenv('USERPROFILE')
-            elif 'HOMEPATH' not in os.environ:
-                return path
-            else:
-                try:
-                    drive = compat_getenv('HOMEDRIVE')
-                except KeyError:
-                    drive = ''
-                userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
-
-            if i != 1:  # ~user
-                userhome = os.path.join(os.path.dirname(userhome), path[1:i])
-
-            return userhome + path[i:]
-    else:
-        compat_expanduser = os.path.expanduser
-
-
-if sys.version_info < (3, 0):
-    def compat_print(s):
-        from .utils import preferredencoding
-        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
-else:
-    def compat_print(s):
-        assert isinstance(s, compat_str)
-        print(s)
-
-
-try:
-    subprocess_check_output = subprocess.check_output
-except AttributeError:
-    def subprocess_check_output(*args, **kwargs):
-        assert 'input' not in kwargs
-        p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
-        output, _ = p.communicate()
-        ret = p.poll()
-        if ret:
-            raise subprocess.CalledProcessError(ret, p.args, output=output)
-        return output
-
-if sys.version_info < (3, 0) and sys.platform == 'win32':
-    def compat_getpass(prompt, *args, **kwargs):
-        if isinstance(prompt, compat_str):
-            from .utils import preferredencoding
-            prompt = prompt.encode(preferredencoding())
-        return getpass.getpass(prompt, *args, **kwargs)
-else:
-    compat_getpass = getpass.getpass
-
-# Old 2.6 and 2.7 releases require kwargs to be bytes
-try:
-    def _testfunc(x):
-        pass
-    _testfunc(**{'x': 0})
-except TypeError:
-    def compat_kwargs(kwargs):
-        return dict((bytes(k), v) for k, v in kwargs.items())
-else:
-    compat_kwargs = lambda kwargs: kwargs
-
-
-if sys.version_info < (2, 7):
-    def compat_socket_create_connection(address, timeout, source_address=None):
-        host, port = address
-        err = None
-        for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
-            af, socktype, proto, canonname, sa = res
-            sock = None
-            try:
-                sock = socket.socket(af, socktype, proto)
-                sock.settimeout(timeout)
-                if source_address:
-                    sock.bind(source_address)
-                sock.connect(sa)
-                return sock
-            except socket.error as _:
-                err = _
-                if sock is not None:
-                    sock.close()
-        if err is not None:
-            raise err
-        else:
-            raise socket.error("getaddrinfo returns an empty list")
-else:
-    compat_socket_create_connection = socket.create_connection
-
-
-# Fix https://github.com/rg3/youtube-dl/issues/4223
-# See http://bugs.python.org/issue9161 for what is broken
-def workaround_optparse_bug9161():
-    op = optparse.OptionParser()
-    og = optparse.OptionGroup(op, 'foo')
-    try:
-        og.add_option('-t')
-    except TypeError:
-        real_add_option = optparse.OptionGroup.add_option
-
-        def _compat_add_option(self, *args, **kwargs):
-            enc = lambda v: (
-                v.encode('ascii', 'replace') if isinstance(v, compat_str)
-                else v)
-            bargs = [enc(a) for a in args]
-            bkwargs = dict(
-                (k, enc(v)) for k, v in kwargs.items())
-            return real_add_option(self, *bargs, **bkwargs)
-        optparse.OptionGroup.add_option = _compat_add_option
-
-if hasattr(shutil, 'get_terminal_size'):  # Python >= 3.3
-    compat_get_terminal_size = shutil.get_terminal_size
-else:
-    _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
-
-    def compat_get_terminal_size(fallback=(80, 24)):
-        columns = compat_getenv('COLUMNS')
-        if columns:
-            columns = int(columns)
-        else:
-            columns = None
-        lines = compat_getenv('LINES')
-        if lines:
-            lines = int(lines)
-        else:
-            lines = None
-
-        if columns is None or lines is None or columns <= 0 or lines <= 0:
-            try:
-                sp = subprocess.Popen(
-                    ['stty', 'size'],
-                    stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-                out, err = sp.communicate()
-                _columns, _lines = map(int, out.split())
-            except Exception:
-                _columns, _lines = _terminal_size(*fallback)
-
-            if columns is None or columns <= 0:
-                columns = _columns
-            if lines is None or lines <= 0:
-                lines = _lines
-        return _terminal_size(columns, lines)
-
-try:
-    itertools.count(start=0, step=1)
-    compat_itertools_count = itertools.count
-except TypeError:  # Python 2.6
-    def compat_itertools_count(start=0, step=1):
-        n = start
-        while True:
-            yield n
-            n += step
-
-if sys.version_info >= (3, 0):
-    from tokenize import tokenize as compat_tokenize_tokenize
-else:
-    from tokenize import generate_tokens as compat_tokenize_tokenize
-
-__all__ = [
-    'compat_HTTPError',
-    'compat_basestring',
-    'compat_chr',
-    'compat_cookiejar',
-    'compat_cookies',
-    'compat_expanduser',
-    'compat_get_terminal_size',
-    'compat_getenv',
-    'compat_getpass',
-    'compat_html_entities',
-    'compat_http_client',
-    'compat_http_server',
-    'compat_itertools_count',
-    'compat_kwargs',
-    'compat_ord',
-    'compat_parse_qs',
-    'compat_print',
-    'compat_shlex_split',
-    'compat_socket_create_connection',
-    'compat_str',
-    'compat_subprocess_get_DEVNULL',
-    'compat_tokenize_tokenize',
-    'compat_urllib_error',
-    'compat_urllib_parse',
-    'compat_urllib_parse_unquote',
-    'compat_urllib_parse_unquote_plus',
-    'compat_urllib_parse_unquote_to_bytes',
-    'compat_urllib_parse_urlparse',
-    'compat_urllib_request',
-    'compat_urlparse',
-    'compat_urlretrieve',
-    'compat_xml_parse_error',
-    'shlex_quote',
-    'subprocess_check_output',
-    'workaround_optparse_bug9161',
-]

youtube_dl/downloader/__init__.py

@@ -1,48 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import FileDownloader
-from .external import get_external_downloader
-from .f4m import F4mFD
-from .hls import HlsFD
-from .hls import NativeHlsFD
-from .http import HttpFD
-from .rtsp import RtspFD
-from .rtmp import RtmpFD
-from .dash import DashSegmentsFD
-
-from ..utils import (
-    determine_protocol,
-)
-
-PROTOCOL_MAP = {
-    'rtmp': RtmpFD,
-    'm3u8_native': NativeHlsFD,
-    'm3u8': HlsFD,
-    'mms': RtspFD,
-    'rtsp': RtspFD,
-    'f4m': F4mFD,
-    'http_dash_segments': DashSegmentsFD,
-}
-
-
-def get_suitable_downloader(info_dict, params={}):
-    """Get the downloader class that can handle the info dict."""
-    protocol = determine_protocol(info_dict)
-    info_dict['protocol'] = protocol
-
-    external_downloader = params.get('external_downloader')
-    if external_downloader is not None:
-        ed = get_external_downloader(external_downloader)
-        if ed.supports(info_dict):
-            return ed
-
-    if protocol == 'm3u8' and params.get('hls_prefer_native'):
-        return NativeHlsFD
-
-    return PROTOCOL_MAP.get(protocol, HttpFD)
-
-
-__all__ = [
-    'get_suitable_downloader',
-    'FileDownloader',
-]

youtube_dl/downloader/common.py

@@ -1,372 +0,0 @@
-from __future__ import division, unicode_literals
-
-import os
-import re
-import sys
-import time
-
-from ..compat import compat_str
-from ..utils import (
-    encodeFilename,
-    decodeArgument,
-    format_bytes,
-    timeconvert,
-)
-
-
-class FileDownloader(object):
-    """File Downloader class.
-
-    File downloader objects are the ones responsible of downloading the
-    actual video file and writing it to disk.
-
-    File downloaders accept a lot of parameters. In order not to saturate
-    the object constructor with arguments, it receives a dictionary of
-    options instead.
-
-    Available options:
-
-    verbose:            Print additional info to stdout.
-    quiet:              Do not print messages to stdout.
-    ratelimit:          Download speed limit, in bytes/sec.
-    retries:            Number of times to retry for HTTP error 5xx
-    buffersize:         Size of download buffer in bytes.
-    noresizebuffer:     Do not automatically resize the download buffer.
-    continuedl:         Try to continue downloads if possible.
-    noprogress:         Do not print the progress bar.
-    logtostderr:        Log messages to stderr instead of stdout.
-    consoletitle:       Display progress in console window's titlebar.
-    nopart:             Do not use temporary .part files.
-    updatetime:         Use the Last-modified header to set output file timestamps.
-    test:               Download only first bytes to test the downloader.
-    min_filesize:       Skip files smaller than this size
-    max_filesize:       Skip files larger than this size
-    xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
-                        (experimenatal)
-    external_downloader_args:  A list of additional command-line arguments for the
-                        external downloader.
-
-    Subclasses of this one must re-define the real_download method.
-    """
-
-    _TEST_FILE_SIZE = 10241
-    params = None
-
-    def __init__(self, ydl, params):
-        """Create a FileDownloader object with the given options."""
-        self.ydl = ydl
-        self._progress_hooks = []
-        self.params = params
-        self.add_progress_hook(self.report_progress)
-
-    @staticmethod
-    def format_seconds(seconds):
-        (mins, secs) = divmod(seconds, 60)
-        (hours, mins) = divmod(mins, 60)
-        if hours > 99:
-            return '--:--:--'
-        if hours == 0:
-            return '%02d:%02d' % (mins, secs)
-        else:
-            return '%02d:%02d:%02d' % (hours, mins, secs)
-
-    @staticmethod
-    def calc_percent(byte_counter, data_len):
-        if data_len is None:
-            return None
-        return float(byte_counter) / float(data_len) * 100.0
-
-    @staticmethod
-    def format_percent(percent):
-        if percent is None:
-            return '---.-%'
-        return '%6s' % ('%3.1f%%' % percent)
-
-    @staticmethod
-    def calc_eta(start, now, total, current):
-        if total is None:
-            return None
-        if now is None:
-            now = time.time()
-        dif = now - start
-        if current == 0 or dif < 0.001:  # One millisecond
-            return None
-        rate = float(current) / dif
-        return int((float(total) - float(current)) / rate)
-
-    @staticmethod
-    def format_eta(eta):
-        if eta is None:
-            return '--:--'
-        return FileDownloader.format_seconds(eta)
-
-    @staticmethod
-    def calc_speed(start, now, bytes):
-        dif = now - start
-        if bytes == 0 or dif < 0.001:  # One millisecond
-            return None
-        return float(bytes) / dif
-
-    @staticmethod
-    def format_speed(speed):
-        if speed is None:
-            return '%10s' % '---b/s'
-        return '%10s' % ('%s/s' % format_bytes(speed))
-
-    @staticmethod
-    def best_block_size(elapsed_time, bytes):
-        new_min = max(bytes / 2.0, 1.0)
-        new_max = min(max(bytes * 2.0, 1.0), 4194304)  # Do not surpass 4 MB
-        if elapsed_time < 0.001:
-            return int(new_max)
-        rate = bytes / elapsed_time
-        if rate > new_max:
-            return int(new_max)
-        if rate < new_min:
-            return int(new_min)
-        return int(rate)
-
-    @staticmethod
-    def parse_bytes(bytestr):
-        """Parse a string indicating a byte quantity into an integer."""
-        matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
-        if matchobj is None:
-            return None
-        number = float(matchobj.group(1))
-        multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
-        return int(round(number * multiplier))
-
-    def to_screen(self, *args, **kargs):
-        self.ydl.to_screen(*args, **kargs)
-
-    def to_stderr(self, message):
-        self.ydl.to_screen(message)
-
-    def to_console_title(self, message):
-        self.ydl.to_console_title(message)
-
-    def trouble(self, *args, **kargs):
-        self.ydl.trouble(*args, **kargs)
-
-    def report_warning(self, *args, **kargs):
-        self.ydl.report_warning(*args, **kargs)
-
-    def report_error(self, *args, **kargs):
-        self.ydl.report_error(*args, **kargs)
-
-    def slow_down(self, start_time, now, byte_counter):
-        """Sleep if the download speed is over the rate limit."""
-        rate_limit = self.params.get('ratelimit', None)
-        if rate_limit is None or byte_counter == 0:
-            return
-        if now is None:
-            now = time.time()
-        elapsed = now - start_time
-        if elapsed <= 0.0:
-            return
-        speed = float(byte_counter) / elapsed
-        if speed > rate_limit:
-            time.sleep(max((byte_counter // rate_limit) - elapsed, 0))
-
-    def temp_name(self, filename):
-        """Returns a temporary filename for the given filename."""
-        if self.params.get('nopart', False) or filename == '-' or \
-                (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
-            return filename
-        return filename + '.part'
-
-    def undo_temp_name(self, filename):
-        if filename.endswith('.part'):
-            return filename[:-len('.part')]
-        return filename
-
-    def try_rename(self, old_filename, new_filename):
-        try:
-            if old_filename == new_filename:
-                return
-            os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
-        except (IOError, OSError) as err:
-            self.report_error('unable to rename file: %s' % compat_str(err))
-
-    def try_utime(self, filename, last_modified_hdr):
-        """Try to set the last-modified time of the given file."""
-        if last_modified_hdr is None:
-            return
-        if not os.path.isfile(encodeFilename(filename)):
-            return
-        timestr = last_modified_hdr
-        if timestr is None:
-            return
-        filetime = timeconvert(timestr)
-        if filetime is None:
-            return filetime
-        # Ignore obviously invalid dates
-        if filetime == 0:
-            return
-        try:
-            os.utime(filename, (time.time(), filetime))
-        except Exception:
-            pass
-        return filetime
-
-    def report_destination(self, filename):
-        """Report destination filename."""
-        self.to_screen('[download] Destination: ' + filename)
-
-    def _report_progress_status(self, msg, is_last_line=False):
-        fullmsg = '[download] ' + msg
-        if self.params.get('progress_with_newline', False):
-            self.to_screen(fullmsg)
-        else:
-            if os.name == 'nt':
-                prev_len = getattr(self, '_report_progress_prev_line_length',
-                                   0)
-                if prev_len > len(fullmsg):
-                    fullmsg += ' ' * (prev_len - len(fullmsg))
-                self._report_progress_prev_line_length = len(fullmsg)
-                clear_line = '\r'
-            else:
-                clear_line = ('\r\x1b[K' if sys.stderr.isatty() else '\r')
-            self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
-        self.to_console_title('youtube-dl ' + msg)
-
-    def report_progress(self, s):
-        if s['status'] == 'finished':
-            if self.params.get('noprogress', False):
-                self.to_screen('[download] Download completed')
-            else:
-                s['_total_bytes_str'] = format_bytes(s['total_bytes'])
-                if s.get('elapsed') is not None:
-                    s['_elapsed_str'] = self.format_seconds(s['elapsed'])
-                    msg_template = '100%% of %(_total_bytes_str)s in %(_elapsed_str)s'
-                else:
-                    msg_template = '100%% of %(_total_bytes_str)s'
-                self._report_progress_status(
-                    msg_template % s, is_last_line=True)
-
-        if self.params.get('noprogress'):
-            return
-
-        if s['status'] != 'downloading':
-            return
-
-        if s.get('eta') is not None:
-            s['_eta_str'] = self.format_eta(s['eta'])
-        else:
-            s['_eta_str'] = 'Unknown ETA'
-
-        if s.get('total_bytes') and s.get('downloaded_bytes') is not None:
-            s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes'])
-        elif s.get('total_bytes_estimate') and s.get('downloaded_bytes') is not None:
-            s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes_estimate'])
-        else:
-            if s.get('downloaded_bytes') == 0:
-                s['_percent_str'] = self.format_percent(0)
-            else:
-                s['_percent_str'] = 'Unknown %'
-
-        if s.get('speed') is not None:
-            s['_speed_str'] = self.format_speed(s['speed'])
-        else:
-            s['_speed_str'] = 'Unknown speed'
-
-        if s.get('total_bytes') is not None:
-            s['_total_bytes_str'] = format_bytes(s['total_bytes'])
-            msg_template = '%(_percent_str)s of %(_total_bytes_str)s at %(_speed_str)s ETA %(_eta_str)s'
-        elif s.get('total_bytes_estimate') is not None:
-            s['_total_bytes_estimate_str'] = format_bytes(s['total_bytes_estimate'])
-            msg_template = '%(_percent_str)s of ~%(_total_bytes_estimate_str)s at %(_speed_str)s ETA %(_eta_str)s'
-        else:
-            if s.get('downloaded_bytes') is not None:
-                s['_downloaded_bytes_str'] = format_bytes(s['downloaded_bytes'])
-                if s.get('elapsed'):
-                    s['_elapsed_str'] = self.format_seconds(s['elapsed'])
-                    msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s (%(_elapsed_str)s)'
-                else:
-                    msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s'
-            else:
-                msg_template = '%(_percent_str)s % at %(_speed_str)s ETA %(_eta_str)s'
-
-        self._report_progress_status(msg_template % s)
-
-    def report_resuming_byte(self, resume_len):
-        """Report attempt to resume at given byte."""
-        self.to_screen('[download] Resuming download at byte %s' % resume_len)
-
-    def report_retry(self, count, retries):
-        """Report retry in case of HTTP error 5xx"""
-        self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
-
-    def report_file_already_downloaded(self, file_name):
-        """Report file has already been fully downloaded."""
-        try:
-            self.to_screen('[download] %s has already been downloaded' % file_name)
-        except UnicodeEncodeError:
-            self.to_screen('[download] The file has already been downloaded')
-
-    def report_unable_to_resume(self):
-        """Report it was impossible to resume download."""
-        self.to_screen('[download] Unable to resume')
-
-    def download(self, filename, info_dict):
-        """Download to a filename using the info from info_dict
-        Return True on success and False otherwise
-        """
-
-        nooverwrites_and_exists = (
-            self.params.get('nooverwrites', False) and
-            os.path.exists(encodeFilename(filename))
-        )
-
-        continuedl_and_exists = (
-            self.params.get('continuedl', True) and
-            os.path.isfile(encodeFilename(filename)) and
-            not self.params.get('nopart', False)
-        )
-
-        # Check file already present
-        if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
-            self.report_file_already_downloaded(filename)
-            self._hook_progress({
-                'filename': filename,
-                'status': 'finished',
-                'total_bytes': os.path.getsize(encodeFilename(filename)),
-            })
-            return True
-
-        sleep_interval = self.params.get('sleep_interval')
-        if sleep_interval:
-            self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
-            time.sleep(sleep_interval)
-
-        return self.real_download(filename, info_dict)
-
-    def real_download(self, filename, info_dict):
-        """Real download process. Redefine in subclasses."""
-        raise NotImplementedError('This method must be implemented by subclasses')
-
-    def _hook_progress(self, status):
-        for ph in self._progress_hooks:
-            ph(status)
-
-    def add_progress_hook(self, ph):
-        # See YoutubeDl.py (search for progress_hooks) for a description of
-        # this interface
-        self._progress_hooks.append(ph)
-
-    def _debug_cmd(self, args, exe=None):
-        if not self.params.get('verbose', False):
-            return
-
-        str_args = [decodeArgument(a) for a in args]
-
-        if exe is None:
-            exe = os.path.basename(str_args[0])
-
-        try:
-            import pipes
-            shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
-        except ImportError:
-            shell_quote = repr
-        self.to_screen('[debug] %s command line: %s' % (
-            exe, shell_quote(str_args)))

youtube_dl/downloader/dash.py

@@ -1,66 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import FileDownloader
-from ..compat import compat_urllib_request
-
-
-class DashSegmentsFD(FileDownloader):
-    """
-    Download segments in a DASH manifest
-    """
-    def real_download(self, filename, info_dict):
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
-        base_url = info_dict['url']
-        segment_urls = info_dict['segment_urls']
-
-        is_test = self.params.get('test', False)
-        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
-        byte_counter = 0
-
-        def append_url_to_file(outf, target_url, target_name, remaining_bytes=None):
-            self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name))
-            req = compat_urllib_request.Request(target_url)
-            if remaining_bytes is not None:
-                req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
-
-            data = self.ydl.urlopen(req).read()
-
-            if remaining_bytes is not None:
-                data = data[:remaining_bytes]
-
-            outf.write(data)
-            return len(data)
-
-        def combine_url(base_url, target_url):
-            if re.match(r'^https?://', target_url):
-                return target_url
-            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
-
-        with open(tmpfilename, 'wb') as outf:
-            append_url_to_file(
-                outf, combine_url(base_url, info_dict['initialization_url']),
-                'initialization segment')
-            for i, segment_url in enumerate(segment_urls):
-                segment_len = append_url_to_file(
-                    outf, combine_url(base_url, segment_url),
-                    'segment %d / %d' % (i + 1, len(segment_urls)),
-                    remaining_bytes)
-                byte_counter += segment_len
-                if remaining_bytes is not None:
-                    remaining_bytes -= segment_len
-                    if remaining_bytes <= 0:
-                        break
-
-        self.try_rename(tmpfilename, filename)
-
-        self._hook_progress({
-            'downloaded_bytes': byte_counter,
-            'total_bytes': byte_counter,
-            'filename': filename,
-            'status': 'finished',
-        })
-
-        return True

youtube_dl/downloader/external.py

@@ -1,155 +0,0 @@
-from __future__ import unicode_literals
-
-import os.path
-import subprocess
-
-from .common import FileDownloader
-from ..utils import (
-    cli_option,
-    cli_valueless_option,
-    cli_bool_option,
-    cli_configuration_args,
-    encodeFilename,
-    encodeArgument,
-)
-
-
-class ExternalFD(FileDownloader):
-    def real_download(self, filename, info_dict):
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
-
-        retval = self._call_downloader(tmpfilename, info_dict)
-        if retval == 0:
-            fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
-            self.try_rename(tmpfilename, filename)
-            self._hook_progress({
-                'downloaded_bytes': fsize,
-                'total_bytes': fsize,
-                'filename': filename,
-                'status': 'finished',
-            })
-            return True
-        else:
-            self.to_stderr('\n')
-            self.report_error('%s exited with code %d' % (
-                self.get_basename(), retval))
-            return False
-
-    @classmethod
-    def get_basename(cls):
-        return cls.__name__[:-2].lower()
-
-    @property
-    def exe(self):
-        return self.params.get('external_downloader')
-
-    @classmethod
-    def supports(cls, info_dict):
-        return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
-
-    def _option(self, command_option, param):
-        return cli_option(self.params, command_option, param)
-
-    def _bool_option(self, command_option, param, true_value='true', false_value='false', separator=None):
-        return cli_bool_option(self.params, command_option, param, true_value, false_value, separator)
-
-    def _valueless_option(self, command_option, param, expected_value=True):
-        return cli_valueless_option(self.params, command_option, param, expected_value)
-
-    def _configuration_args(self, default=[]):
-        return cli_configuration_args(self.params, 'external_downloader_args', default)
-
-    def _call_downloader(self, tmpfilename, info_dict):
-        """ Either overwrite this or implement _make_cmd """
-        cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
-
-        self._debug_cmd(cmd)
-
-        p = subprocess.Popen(
-            cmd, stderr=subprocess.PIPE)
-        _, stderr = p.communicate()
-        if p.returncode != 0:
-            self.to_stderr(stderr)
-        return p.returncode
-
-
-class CurlFD(ExternalFD):
-    def _make_cmd(self, tmpfilename, info_dict):
-        cmd = [self.exe, '--location', '-o', tmpfilename]
-        for key, val in info_dict['http_headers'].items():
-            cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._option('--interface', 'source_address')
-        cmd += self._option('--proxy', 'proxy')
-        cmd += self._valueless_option('--insecure', 'nocheckcertificate')
-        cmd += self._configuration_args()
-        cmd += ['--', info_dict['url']]
-        return cmd
-
-
-class AxelFD(ExternalFD):
-    def _make_cmd(self, tmpfilename, info_dict):
-        cmd = [self.exe, '-o', tmpfilename]
-        for key, val in info_dict['http_headers'].items():
-            cmd += ['-H', '%s: %s' % (key, val)]
-        cmd += self._configuration_args()
-        cmd += ['--', info_dict['url']]
-        return cmd
-
-
-class WgetFD(ExternalFD):
-    def _make_cmd(self, tmpfilename, info_dict):
-        cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
-        for key, val in info_dict['http_headers'].items():
-            cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._option('--bind-address', 'source_address')
-        cmd += self._option('--proxy', 'proxy')
-        cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')
-        cmd += self._configuration_args()
-        cmd += ['--', info_dict['url']]
-        return cmd
-
-
-class Aria2cFD(ExternalFD):
-    def _make_cmd(self, tmpfilename, info_dict):
-        cmd = [self.exe, '-c']
-        cmd += self._configuration_args([
-            '--min-split-size', '1M', '--max-connection-per-server', '4'])
-        dn = os.path.dirname(tmpfilename)
-        if dn:
-            cmd += ['--dir', dn]
-        cmd += ['--out', os.path.basename(tmpfilename)]
-        for key, val in info_dict['http_headers'].items():
-            cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._option('--interface', 'source_address')
-        cmd += self._option('--all-proxy', 'proxy')
-        cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
-        cmd += ['--', info_dict['url']]
-        return cmd
-
-
-class HttpieFD(ExternalFD):
-    def _make_cmd(self, tmpfilename, info_dict):
-        cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
-        for key, val in info_dict['http_headers'].items():
-            cmd += ['%s:%s' % (key, val)]
-        return cmd
-
-_BY_NAME = dict(
-    (klass.get_basename(), klass)
-    for name, klass in globals().items()
-    if name.endswith('FD') and name != 'ExternalFD'
-)
-
-
-def list_external_downloaders():
-    return sorted(_BY_NAME.keys())
-
-
-def get_external_downloader(external_downloader):
-    """ Given the name of the executable, see whether we support the given
-        downloader . """
-    # Drop .exe extension on Windows
-    bn = os.path.splitext(os.path.basename(external_downloader))[0]
-    return _BY_NAME[bn]