Release 2012.12.11

The new shiny build system

.gitignore

@@ -0,0 +1,15 @@
+*.pyc
+*.pyo
+*~
+wine-py2exe/
+py2exe.log
+*.kate-swp
+build/
+dist/
+MANIFEST
+README.txt
+youtube-dl.1
+youtube-dl.bash-completion
+youtube-dl
+youtube-dl.exe
+youtube-dl.tar.gz

.travis.yml

@@ -0,0 +1,13 @@
+language: python
+python:
+  - "2.6"
+  - "2.7"
+#  - "3.3"
+script: nosetests test --verbose
+notifications:
+  email:
+    - filippo.valsorda@gmail.com
+  irc:
+    channels:
+      - "irc.freenode.org#youtube-dl"
+    skip_join: true

LATEST_VERSION

@@ -1 +1 @@
-2010.10.24
+9999.99.99

MANIFEST.in

@@ -0,0 +1,3 @@
+include README.md
+include test/*.py
+include test/*.json

Makefile

@@ -0,0 +1,48 @@
+all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
+
+clean:
+	rm -rf youtube-dl youtube-dl.exe youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/
+
+PREFIX=/usr/local
+BINDIR=$(PREFIX)/bin
+MANDIR=$(PREFIX)/man
+SYSCONFDIR=/etc
+
+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
+
+test:
+	nosetests2 --nocapture test
+
+.PHONY: all clean install test
+
+youtube-dl: youtube_dl/*.py
+	zip --quiet youtube-dl youtube_dl/*.py
+	zip --quiet --junk-paths youtube-dl youtube_dl/__main__.py
+	echo '#!/usr/bin/env python' > youtube-dl
+	cat youtube-dl.zip >> youtube-dl
+	rm youtube-dl.zip
+	chmod a+x youtube-dl
+
+README.md: youtube_dl/*.py
+	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
+	pandoc -s -f markdown -t man README.md -o youtube-dl.1
+
+youtube-dl.bash-completion: youtube_dl/*.py devscripts/bash-completion.template
+	python devscripts/bash-completion.py
+
+youtube-dl.tar.gz: all
+	tar -czf youtube-dl.tar.gz -s "|^./|./youtube-dl/|" \
+		--exclude="*.pyc" --exclude="*.pyo" --exclude="*~" --exclude="youtube-dl.exe" \
+		--exclude="wine-py2exe/" --exclude="py2exe.log" --exclude="*.kate-swp" \
+		--exclude="build/" --exclude="dist/" --exclude="MANIFEST" --exclude=".git/" .

README.md

@@ -0,0 +1,201 @@
+% YOUTUBE-DL(1)
+
+# NAME
+youtube-dl
+
+# SYNOPSIS
+**youtube-dl** [OPTIONS] URL [URL...]
+
+# DESCRIPTION
+**youtube-dl** is a small command-line program to download videos from
+YouTube.com and a few more sites. It requires the Python interpreter, version
+2.x (x being at least 6), and it is not platform specific. It should work in
+your Unix box, in Windows or in Mac OS X. It is released to the public domain,
+which means you can modify it, redistribute it or use it however you like.
+
+# OPTIONS
+    -h, --help               print this help text and exit
+    --version                print program version and exit
+    -U, --update             update this program to latest version
+    -i, --ignore-errors      continue on download errors
+    -r, --rate-limit LIMIT   download rate limit (e.g. 50k or 44.6m)
+    -R, --retries RETRIES    number of retries (default is 10)
+    --buffer-size SIZE       size of download buffer (e.g. 1024 or 16k) (default
+                             is 1024)
+    --no-resize-buffer       do not automatically adjust the buffer size. By
+                             default, the buffer size is automatically resized
+                             from an initial value of SIZE.
+    --dump-user-agent        display the current browser identification
+    --user-agent UA          specify a custom user agent
+    --list-extractors        List all supported extractors and the URLs they
+                             would handle
+
+## Video Selection:
+    --playlist-start NUMBER  playlist video to start at (default is 1)
+    --playlist-end NUMBER    playlist video to end at (default is last)
+    --match-title REGEX      download only matching titles (regex or caseless
+                             sub-string)
+    --reject-title REGEX     skip download for matching titles (regex or
+                             caseless sub-string)
+    --max-downloads NUMBER   Abort after downloading NUMBER files
+
+## Filesystem Options:
+    -t, --title              use title in file name
+    --id                     use video ID in file name
+    -l, --literal            [deprecated] alias of --title
+    -A, --auto-number        number downloaded files starting from 00000
+    -o, --output TEMPLATE    output filename template. Use %(title)s to get the
+                             title, %(uploader)s for the uploader name,
+                             %(autonumber)s to get an automatically incremented
+                             number, %(ext)s for the filename extension,
+                             %(upload_date)s for the upload date (YYYYMMDD),
+                             %(extractor)s for the provider (youtube, metacafe,
+                             etc), %(id)s for the video id 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' .
+    --restrict-filenames     Restrict filenames to only ASCII characters, and
+                             avoid "&" and spaces in filenames
+    -a, --batch-file FILE    file containing URLs to download ('-' for stdin)
+    -w, --no-overwrites      do not overwrite files
+    -c, --continue           resume partially downloaded files
+    --no-continue            do not resume partially downloaded files (restart
+                             from beginning)
+    --cookies FILE           file to read cookies from and dump cookie jar in
+    --no-part                do not use .part files
+    --no-mtime               do not use the Last-modified header to set the file
+                             modification time
+    --write-description      write video description to a .description file
+    --write-info-json        write video metadata to a .info.json file
+
+## Verbosity / Simulation Options:
+    -q, --quiet              activates quiet mode
+    -s, --simulate           do not download the video and do not write anything
+                             to disk
+    --skip-download          do not download the video
+    -g, --get-url            simulate, quiet but print URL
+    -e, --get-title          simulate, quiet but print title
+    --get-thumbnail          simulate, quiet but print thumbnail URL
+    --get-description        simulate, quiet but print video description
+    --get-filename           simulate, quiet but print output filename
+    --get-format             simulate, quiet but print output format
+    --no-progress            do not print progress bar
+    --console-title          display progress in console titlebar
+    -v, --verbose            print various debugging information
+
+## Video Format Options:
+    -f, --format FORMAT      video format code
+    --all-formats            download all available video formats
+    --prefer-free-formats    prefer free video formats unless a specific one is
+                             requested
+    --max-quality FORMAT     highest quality format to download
+    -F, --list-formats       list all available formats (currently youtube only)
+    --write-srt              write video closed captions to a .srt file
+                             (currently youtube only)
+    --srt-lang LANG          language of the closed captions to download
+                             (optional) use IETF language tags like 'en'
+
+## Authentication Options:
+    -u, --username USERNAME  account username
+    -p, --password PASSWORD  account password
+    -n, --netrc              use .netrc authentication data
+
+## Post-processing Options:
+    -x, --extract-audio      convert video files to audio-only files (requires
+                             ffmpeg or avconv and ffprobe or avprobe)
+    --audio-format FORMAT    "best", "aac", "vorbis", "mp3", "m4a", or "wav";
+                             best by default
+    --audio-quality QUALITY  ffmpeg/avconv audio quality specification, insert a
+                             value between 0 (better) and 9 (worse) for VBR or a
+                             specific bitrate like 128K (default 5)
+    -k, --keep-video         keeps the video file on disk after the post-
+                             processing; the video is erased by default
+
+# CONFIGURATION
+
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.local/config/youtube-dl.conf`.
+
+# OUTPUT TEMPLATE
+
+The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are:
+
+ - `id`: The sequence will be replaced by the video identifier.
+ - `url`: The sequence will be replaced by the video URL.
+ - `uploader`: The sequence will be replaced by the nickname of the person who uploaded the video.
+ - `upload_date`: The sequence will be replaced by the upload date in YYYYMMDD format.
+ - `title`: The sequence will be replaced by the video title.
+ - `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4).
+ - `epoch`: The sequence will be replaced by the Unix epoch when creating the file.
+ - `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
+
+The current default template is `%(id)s.%(ext)s`, but that will be switchted to `%(title)s-%(id)s.%(ext)s` (which can be requested with `-t` at the moment).
+
+In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
+
+    $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc
+    youtube-dl test video ''_ä↭𝕐.mp4    # All kinds of weird characters
+    $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
+    youtube-dl_test_video_.mp4          # A simple file name
+
+# FAQ
+
+### Can you please put the -b option back?
+
+Most people asking this question are not aware that youtube-dl now defaults to downloading the highest available quality as reported by YouTube, which will be 1080p or 720p in some cases, so you no longer need the -b option. For some specific videos, maybe YouTube does not report them to be available in a specific high quality format you''re interested in. In that case, simply request it with the -f option and youtube-dl will try to download it.
+
+### I get HTTP error 402 when trying to download a video. What's this?
+
+Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We''re [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a webbrowser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
+
+### I have downloaded a video but how can I play it?
+
+Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
+
+### The links provided by youtube-dl -g are not working anymore
+
+The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
+
+### ERROR: no fmt_url_map or conn information found in video info
+
+youtube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`.
+
+### ERROR: unable to download video ###
+
+youtube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`.
+
+### SyntaxError: Non-ASCII character ###
+
+The error
+
+    File "youtube-dl", line 2
+    SyntaxError: Non-ASCII character '\x93' ...
+
+means you're using an outdated version of Python. Please update to Python 2.6 or 2.7.
+
+### What is this binary file? Where has the code gone?
+
+Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
+
+### The exe throws a *Runtime error from Visual C++*
+
+To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
+
+# COPYRIGHT
+
+youtube-dl is released into the public domain by the copyright holders.
+
+This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain.
+
+# BUGS
+
+Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>
+
+Please include:
+
+* Your exact command line, like `youtube-dl -t "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"`. A common mistake is not to escape the `&`. Putting URLs in quotes should solve this problem.
+* The output of `youtube-dl --version`
+* The output of `python --version`
+* The name and version of your Operating System ("Ubuntu 11.04 x64" or "Windows 7 x64" is usually enough).
+
+For discussions, join us in the irc channel #youtube-dl on freenode.

bin/youtube-dl

@@ -0,0 +1,6 @@
+#!/usr/bin/env python
+
+import youtube_dl
+
+if __name__ == '__main__':
+    youtube_dl.main()

devscripts/bash-completion.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python
+import os
+from os.path import dirname as dirn
+import sys
+
+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.template"
+
+def build_completion(opt_parser):
+    opts_flag = []
+    for group in opt_parser.option_groups:
+        for option in group.option_list:
+            #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
+        filled_template = template.replace("{{flags}}", " ".join(opts_flag))
+        f.write(filled_template)
+
+parser = youtube_dl.parseOpts()[0]
+build_completion(parser)

devscripts/bash-completion.template

@@ -0,0 +1,14 @@
+__youtube-dl()
+{
+    local cur prev opts
+    COMPREPLY=()
+    cur="${COMP_WORDS[COMP_CWORD]}"
+    opts="{{flags}}"
+
+    if [[ ${cur} == * ]] ; then
+        COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
+        return 0
+    fi
+}
+
+complete -F __youtube-dl youtube-dl

devscripts/make_readme.py

@@ -0,0 +1,20 @@
+import sys
+import re
+
+README_FILE = 'README.md'
+helptext = sys.stdin.read()
+
+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'^  (\w.+)$', r'## \1', options, flags=re.M)
+options = '# OPTIONS\n' + options + '\n'
+
+with open(README_FILE, 'w') as f:
+    f.write(header)
+    f.write(options)
+    f.write(footer)

devscripts/posix-locale.sh

@@ -0,0 +1,6 @@
+
+# source this file in your shell to get a POSIX locale (which will break many programs, but that's kind of the point)
+
+export LC_ALL=POSIX
+export LANG=POSIX
+export LANGUAGE=POSIX

devscripts/release.sh

@@ -0,0 +1,11 @@
+#!/bin/sh
+
+if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
+version="$1"
+if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi
+if [ ! -z "`git status --porcelain`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
+sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/__init__.py
+make all
+git add -A
+git commit -m "release $version"
+git tag -m "Release $version" "$version"

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 +1,49 @@
+#!/usr/bin/env python
+
+import sys, os
+import urllib2
+
+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')
+
+raw_input()
+
+filename = sys.argv[0]
+
+API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
+EXE_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl.exe"
+
+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:
+    urlh = urllib2.urlopen(EXE_URL)
+    newcontent = urlh.read()
+    urlh.close()
+    with open(exe + '.new', 'wb') as outf:
+        outf.write(newcontent)
+except (IOError, OSError) as err:
+    sys.exit('ERROR: unable to download latest 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/wine-py2exe.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+
+# Run with as parameter a setup.py that works in the current directory
+# e.g. no os.chdir()
+# It will run twice, the first time will crash
+
+set -e
+
+SCRIPT_DIR="$( cd "$( dirname "$0" )" && pwd )"
+
+if [ ! -d wine-py2exe ]; then
+
+    sudo apt-get install wine1.3 axel bsdiff
+
+    mkdir wine-py2exe
+    cd wine-py2exe
+    export WINEPREFIX=`pwd`
+
+    axel -a "http://www.python.org/ftp/python/2.7/python-2.7.msi"
+    axel -a "http://downloads.sourceforge.net/project/py2exe/py2exe/0.6.9/py2exe-0.6.9.win32-py2.7.exe"
+    #axel -a "http://winetricks.org/winetricks"
+
+    # http://appdb.winehq.org/objectManager.php?sClass=version&iId=21957
+    echo "Follow python setup on screen"
+    wine msiexec /i python-2.7.msi
+    
+    echo "Follow py2exe setup on screen"
+    wine py2exe-0.6.9.win32-py2.7.exe
+    
+    #echo "Follow Microsoft Visual C++ 2008 Redistributable Package setup on screen"
+    #bash winetricks vcrun2008
+
+    rm py2exe-0.6.9.win32-py2.7.exe
+    rm python-2.7.msi
+    #rm winetricks
+    
+    # http://bugs.winehq.org/show_bug.cgi?id=3591
+    
+    mv drive_c/Python27/Lib/site-packages/py2exe/run.exe drive_c/Python27/Lib/site-packages/py2exe/run.exe.backup
+    bspatch drive_c/Python27/Lib/site-packages/py2exe/run.exe.backup drive_c/Python27/Lib/site-packages/py2exe/run.exe "$SCRIPT_DIR/SizeOfImage.patch"
+    mv drive_c/Python27/Lib/site-packages/py2exe/run_w.exe drive_c/Python27/Lib/site-packages/py2exe/run_w.exe.backup
+    bspatch drive_c/Python27/Lib/site-packages/py2exe/run_w.exe.backup drive_c/Python27/Lib/site-packages/py2exe/run_w.exe "$SCRIPT_DIR/SizeOfImage_w.patch"
+
+    cd -
+    
+else
+
+    export WINEPREFIX="$( cd wine-py2exe && pwd )"
+
+fi
+
+wine "C:\\Python27\\python.exe" "$1" py2exe > "py2exe.log" 2>&1 || true
+echo '# Copying python27.dll' >> "py2exe.log"
+cp "$WINEPREFIX/drive_c/windows/system32/python27.dll" build/bdist.win32/winexe/bundle-2.7/
+wine "C:\\Python27\\python.exe" "$1" py2exe >> "py2exe.log" 2>&1
+

setup.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from __future__ import print_function
+from distutils.core import setup
+import pkg_resources
+import sys
+
+try:
+    import py2exe
+    """This will create an exe that needs Microsoft Visual C++ 2008 Redistributable Package"""
+except ImportError:
+    if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
+        print("Cannot import py2exe", file=sys.stderr)
+        exit(1)
+
+py2exe_options = {
+    "bundle_files": 1,
+    "compressed": 1,
+    "optimize": 2,
+    "dist_dir": '.',
+    "dll_excludes": ['w9xpopen.exe']
+}
+py2exe_console = [{
+    "script": "./youtube_dl/__main__.py",
+    "dest_base": "youtube-dl",
+}]
+py2exe_params = {
+    'console': py2exe_console,
+    'options': { "py2exe": py2exe_options },
+    'zipfile': None
+}
+
+if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
+    params = py2exe_params
+else:
+    params = {
+        'scripts': ['bin/youtube-dl'],
+        'data_files': [('etc/bash_completion.d', ['youtube-dl.bash-completion']), # Installing system-wide would require sudo...
+                       ('share/doc/youtube_dl', ['README.txt']),
+                       ('share/man/man1/', ['youtube-dl.1'])]
+    }
+
+# Get the version from youtube_dl/version.py without importing the package
+exec(compile(open('youtube_dl/version.py').read(), 'youtube_dl/version.py', 'exec'))
+
+setup(
+    name = 'youtube_dl',
+    version = __version__,
+    description = 'YouTube video downloader',
+    long_description = 'Small command-line program to download videos from YouTube.com and other video sites.',
+    url = 'https://github.com/rg3/youtube-dl',
+    author = 'Ricardo Garcia',
+    maintainer = 'Philipp Hagemeister',
+    maintainer_email = 'phihag@phihag.de',
+    packages = ['youtube_dl'],
+
+    # Provokes warning on most systems (why?!)
+    #test_suite = 'nose.collector',
+    #test_requires = ['nosetest'],
+
+    classifiers = [
+        "Topic :: Multimedia :: Video",
+        "Development Status :: 5 - Production/Stable",
+        "Environment :: Console",
+        "License :: Public Domain",
+        "Programming Language :: Python :: 2.6",
+        "Programming Language :: Python :: 2.7",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.3"
+    ],
+
+    **params
+)

test/gentests.py

@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+import io  # for python 2
+import json
+import os
+import sys
+import unittest
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import youtube_dl.InfoExtractors
+
+HEADER = u'''#!/usr/bin/env python
+
+# DO NOT EDIT THIS FILE BY HAND!
+# It is auto-generated from tests.json and gentests.py.
+
+import hashlib
+import io
+import os
+import json
+import unittest
+import sys
+import socket
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import youtube_dl.FileDownloader
+import youtube_dl.InfoExtractors
+from youtube_dl.utils import *
+
+# General configuration (from __init__, not very elegant...)
+jar = compat_cookiejar.CookieJar()
+cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
+proxy_handler = compat_urllib_request.ProxyHandler()
+opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+compat_urllib_request.install_opener(opener)
+socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+class FileDownloader(youtube_dl.FileDownloader):
+    def __init__(self, *args, **kwargs):
+        youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
+        self.to_stderr = self.to_screen
+
+def _file_md5(fn):
+    with open(fn, 'rb') as f:
+        return hashlib.md5(f.read()).hexdigest()
+try:
+    _skip_unless = unittest.skipUnless
+except AttributeError: # Python 2.6
+    def _skip_unless(cond, reason='No reason given'):
+        def resfunc(f):
+            # Start the function name with test to appease nosetests-2.6
+            def test_wfunc(*args, **kwargs):
+                if cond:
+                    return f(*args, **kwargs)
+                else:
+                    print('Skipped test')
+                    return
+            return test_wfunc
+        return resfunc
+_skip = lambda *args, **kwargs: _skip_unless(False, *args, **kwargs)
+
+class DownloadTest(unittest.TestCase):
+    PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+
+    def setUp(self):
+        # Clear old files
+        self.tearDown()
+
+        with io.open(self.PARAMETERS_FILE, encoding='utf-8') as pf:
+            self.parameters = json.load(pf)
+'''
+
+FOOTER = u'''
+
+if __name__ == '__main__':
+    unittest.main()
+'''
+
+DEF_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tests.json')
+TEST_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'test_download.py')
+
+def gentests():
+    with io.open(DEF_FILE, encoding='utf-8') as deff:
+        defs = json.load(deff)
+    with io.open(TEST_FILE, 'w', encoding='utf-8') as testf:
+        testf.write(HEADER)
+        spaces = ' ' * 4
+        write = lambda l: testf.write(spaces + l + u'\n')
+
+        for d in defs:
+            name = d['name']
+            ie = getattr(youtube_dl.InfoExtractors, name + 'IE')
+            testf.write(u'\n')
+            write('@_skip_unless(youtube_dl.InfoExtractors.' + name + 'IE._WORKING, "IE marked as not _WORKING")')
+            if not d['file']:
+                write('@_skip("No output file specified")')
+            elif 'skip' in d:
+                write('@_skip(' + repr(d['skip']) + ')')
+            write('def test_' + name + '(self):')
+            write('    filename = ' + repr(d['file']))
+            write('    params = self.parameters')
+            for p in d.get('params', {}):
+                write('    params["' + p + '"] = ' + repr(d['params'][p]))
+            write('    fd = FileDownloader(params)')
+            write('    fd.add_info_extractor(youtube_dl.InfoExtractors.' + name + 'IE())')
+            for ien in d.get('addIEs', []):
+                write('    fd.add_info_extractor(youtube_dl.InfoExtractors.' + ien + 'IE())')
+            write('    fd.download([' + repr(d['url']) + '])')
+            write('    self.assertTrue(os.path.exists(filename))')
+            if 'md5' in d:
+                write('    md5_for_file = _file_md5(filename)')
+                write('    self.assertEqual(md5_for_file, ' + repr(d['md5']) + ')')
+
+        testf.write(u'\n\n')
+        write('def tearDown(self):')
+        for d in defs:
+            if d['file']:
+                write('    if os.path.exists(' + repr(d['file']) + '):')
+                write('        os.remove(' + repr(d['file']) + ')')
+            else:
+                write('    # No file specified for ' + d['name'])
+        testf.write(u'\n')
+        testf.write(FOOTER)
+
+if __name__ == '__main__':
+    gentests()

test/parameters.json

@@ -0,0 +1,40 @@
+{
+    "consoletitle": false, 
+    "continuedl": true, 
+    "forcedescription": false, 
+    "forcefilename": false, 
+    "forceformat": false, 
+    "forcethumbnail": false, 
+    "forcetitle": false, 
+    "forceurl": false, 
+    "format": null, 
+    "format_limit": null, 
+    "ignoreerrors": false, 
+    "listformats": null, 
+    "logtostderr": false, 
+    "matchtitle": null, 
+    "max_downloads": null, 
+    "nooverwrites": false, 
+    "nopart": false, 
+    "noprogress": false, 
+    "outtmpl": "%(id)s.%(ext)s", 
+    "password": null, 
+    "playlistend": -1, 
+    "playliststart": 1, 
+    "prefer_free_formats": false, 
+    "quiet": false, 
+    "ratelimit": null, 
+    "rejecttitle": null, 
+    "retries": 10, 
+    "simulate": false, 
+    "skip_download": false, 
+    "subtitleslang": null, 
+    "test": true, 
+    "updatetime": true, 
+    "usenetrc": false, 
+    "username": null, 
+    "verbose": true, 
+    "writedescription": false, 
+    "writeinfojson": false, 
+    "writesubtitles": false
+}

test/test_download.py

@@ -0,0 +1,198 @@
+#!/usr/bin/env python
+
+# DO NOT EDIT THIS FILE BY HAND!
+# It is auto-generated from tests.json and gentests.py.
+
+import hashlib
+import io
+import os
+import json
+import unittest
+import sys
+import socket
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import youtube_dl.FileDownloader
+import youtube_dl.InfoExtractors
+from youtube_dl.utils import *
+
+# General configuration (from __init__, not very elegant...)
+jar = compat_cookiejar.CookieJar()
+cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
+proxy_handler = compat_urllib_request.ProxyHandler()
+opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+compat_urllib_request.install_opener(opener)
+socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+class FileDownloader(youtube_dl.FileDownloader):
+    def __init__(self, *args, **kwargs):
+        youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
+        self.to_stderr = self.to_screen
+
+def _file_md5(fn):
+    with open(fn, 'rb') as f:
+        return hashlib.md5(f.read()).hexdigest()
+try:
+    _skip_unless = unittest.skipUnless
+except AttributeError: # Python 2.6
+    def _skip_unless(cond, reason='No reason given'):
+        def resfunc(f):
+            # Start the function name with test to appease nosetests-2.6
+            def test_wfunc(*args, **kwargs):
+                if cond:
+                    return f(*args, **kwargs)
+                else:
+                    print('Skipped test')
+                    return
+            return test_wfunc
+        return resfunc
+_skip = lambda *args, **kwargs: _skip_unless(False, *args, **kwargs)
+
+class DownloadTest(unittest.TestCase):
+    PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+
+    def setUp(self):
+        # Clear old files
+        self.tearDown()
+
+        with io.open(self.PARAMETERS_FILE, encoding='utf-8') as pf:
+            self.parameters = json.load(pf)
+
+    @_skip_unless(youtube_dl.InfoExtractors.YoutubeIE._WORKING, "IE marked as not _WORKING")
+    def test_Youtube(self):
+        filename = u'BaW_jenozKc.mp4'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.YoutubeIE())
+        fd.download([u'http://www.youtube.com/watch?v=BaW_jenozKc'])
+        self.assertTrue(os.path.exists(filename))
+
+    @_skip_unless(youtube_dl.InfoExtractors.DailymotionIE._WORKING, "IE marked as not _WORKING")
+    def test_Dailymotion(self):
+        filename = u'x33vw9.mp4'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.DailymotionIE())
+        fd.download([u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech'])
+        self.assertTrue(os.path.exists(filename))
+        md5_for_file = _file_md5(filename)
+        self.assertEqual(md5_for_file, u'392c4b85a60a90dc4792da41ce3144eb')
+
+    @_skip_unless(youtube_dl.InfoExtractors.MetacafeIE._WORKING, "IE marked as not _WORKING")
+    def test_Metacafe(self):
+        filename = u'_aUehQsCQtM.flv'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.MetacafeIE())
+        fd.add_info_extractor(youtube_dl.InfoExtractors.YoutubeIE())
+        fd.download([u'http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/'])
+        self.assertTrue(os.path.exists(filename))
+
+    @_skip_unless(youtube_dl.InfoExtractors.BlipTVIE._WORKING, "IE marked as not _WORKING")
+    def test_BlipTV(self):
+        filename = u'5779306.m4v'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.BlipTVIE())
+        fd.download([u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352'])
+        self.assertTrue(os.path.exists(filename))
+        md5_for_file = _file_md5(filename)
+        self.assertEqual(md5_for_file, u'b2d849efcf7ee18917e4b4d9ff37cafe')
+
+    @_skip_unless(youtube_dl.InfoExtractors.XVideosIE._WORKING, "IE marked as not _WORKING")
+    def test_XVideos(self):
+        filename = u'939581.flv'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.XVideosIE())
+        fd.download([u'http://www.xvideos.com/video939581/funny_porns_by_s_-1'])
+        self.assertTrue(os.path.exists(filename))
+        md5_for_file = _file_md5(filename)
+        self.assertEqual(md5_for_file, u'1d0c835822f0a71a7bf011855db929d0')
+
+    @_skip_unless(youtube_dl.InfoExtractors.VimeoIE._WORKING, "IE marked as not _WORKING")
+    def test_Vimeo(self):
+        filename = u'14160053.mp4'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.VimeoIE())
+        fd.download([u'http://vimeo.com/14160053'])
+        self.assertTrue(os.path.exists(filename))
+        md5_for_file = _file_md5(filename)
+        self.assertEqual(md5_for_file, u'60540a4ec7cc378ec84b919c0aed5023')
+
+    @_skip_unless(youtube_dl.InfoExtractors.SoundcloudIE._WORKING, "IE marked as not _WORKING")
+    def test_Soundcloud(self):
+        filename = u'62986583.mp3'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.SoundcloudIE())
+        fd.download([u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy'])
+        self.assertTrue(os.path.exists(filename))
+        md5_for_file = _file_md5(filename)
+        self.assertEqual(md5_for_file, u'ebef0a451b909710ed1d7787dddbf0d7')
+
+    @_skip_unless(youtube_dl.InfoExtractors.StanfordOpenClassroomIE._WORKING, "IE marked as not _WORKING")
+    def test_StanfordOpenClassroom(self):
+        filename = u'PracticalUnix_intro-environment.mp4'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.StanfordOpenClassroomIE())
+        fd.download([u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100'])
+        self.assertTrue(os.path.exists(filename))
+        md5_for_file = _file_md5(filename)
+        self.assertEqual(md5_for_file, u'544a9468546059d4e80d76265b0443b8')
+
+    @_skip_unless(youtube_dl.InfoExtractors.XNXXIE._WORKING, "IE marked as not _WORKING")
+    def test_XNXX(self):
+        filename = u'1135332.flv'
+        params = self.parameters
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.XNXXIE())
+        fd.download([u'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_'])
+        self.assertTrue(os.path.exists(filename))
+        md5_for_file = _file_md5(filename)
+        self.assertEqual(md5_for_file, u'0831677e2b4761795f68d417e0b7b445')
+
+    @_skip_unless(youtube_dl.InfoExtractors.YoukuIE._WORKING, "IE marked as not _WORKING")
+    def test_Youku(self):
+        filename = u'XNDgyMDQ2NTQw_part00.flv'
+        params = self.parameters
+        params["test"] = False
+        fd = FileDownloader(params)
+        fd.add_info_extractor(youtube_dl.InfoExtractors.YoukuIE())
+        fd.download([u'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html'])
+        self.assertTrue(os.path.exists(filename))
+        md5_for_file = _file_md5(filename)
+        self.assertEqual(md5_for_file, u'ffe3f2e435663dc2d1eea34faeff5b5b')
+
+
+    def tearDown(self):
+        if os.path.exists(u'BaW_jenozKc.mp4'):
+            os.remove(u'BaW_jenozKc.mp4')
+        if os.path.exists(u'x33vw9.mp4'):
+            os.remove(u'x33vw9.mp4')
+        if os.path.exists(u'_aUehQsCQtM.flv'):
+            os.remove(u'_aUehQsCQtM.flv')
+        if os.path.exists(u'5779306.m4v'):
+            os.remove(u'5779306.m4v')
+        if os.path.exists(u'939581.flv'):
+            os.remove(u'939581.flv')
+        if os.path.exists(u'14160053.mp4'):
+            os.remove(u'14160053.mp4')
+        if os.path.exists(u'62986583.mp3'):
+            os.remove(u'62986583.mp3')
+        if os.path.exists(u'PracticalUnix_intro-environment.mp4'):
+            os.remove(u'PracticalUnix_intro-environment.mp4')
+        if os.path.exists(u'1135332.flv'):
+            os.remove(u'1135332.flv')
+        if os.path.exists(u'XNDgyMDQ2NTQw_part00.flv'):
+            os.remove(u'XNDgyMDQ2NTQw_part00.flv')
+
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_execution.py

@@ -0,0 +1,26 @@
+import unittest
+
+import sys
+import os
+import subprocess
+
+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
+            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)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_utils.py

@@ -0,0 +1,100 @@
+#!/usr/bin/env python
+
+# Various small unit tests
+
+import sys
+import unittest
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+#from youtube_dl.utils import htmlentity_transform
+from youtube_dl.utils import timeconvert
+from youtube_dl.utils import sanitize_filename
+from youtube_dl.utils import unescapeHTML
+from youtube_dl.utils import orderedSet
+
+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):
+        self.assertTrue(timeconvert('') is None)
+        self.assertTrue(timeconvert('bougrg') is None)
+
+    def test_sanitize_filename(self):
+        self.assertEqual(sanitize_filename('abc'), 'abc')
+        self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
+
+        self.assertEqual(sanitize_filename('123'), '123')
+
+        self.assertEqual('abc_de', sanitize_filename('abc/de'))
+        self.assertFalse('/' in sanitize_filename('abc/de///'))
+
+        self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
+        self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
+        self.assertEqual('yes no', sanitize_filename('yes? no'))
+        self.assertEqual('this - that', sanitize_filename('this: that'))
+
+        self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
+        aumlaut = _compat_str('\xe4')
+        self.assertEqual(sanitize_filename(aumlaut), aumlaut)
+        tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
+        self.assertEqual(sanitize_filename(tests), tests)
+
+        forbidden = '"\0\\/'
+        for fc in forbidden:
+            for fbc in forbidden:
+                self.assertTrue(fbc not in sanitize_filename(fc))
+
+    def test_sanitize_filename_restricted(self):
+        self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
+        self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
+
+        self.assertEqual(sanitize_filename('123', restricted=True), '123')
+
+        self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
+        self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
+
+        self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
+        self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
+        self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
+        self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
+
+        tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
+        self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
+        self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
+
+        forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
+        for fc in forbidden:
+            for fbc in forbidden:
+                self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
+
+        # Handle a common case more neatly
+        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) != '')
+
+    def test_sanitize_ids(self):
+        self.assertEquals(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
+        self.assertEquals(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
+        self.assertEquals(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
+
+    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
+        self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
+
+    def test_unescape_html(self):
+        self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
+
+if __name__ == '__main__':
+    unittest.main()

test/test_youtube_lists.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python
+
+import sys
+import unittest
+import socket
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.InfoExtractors import YoutubePlaylistIE
+from youtube_dl.utils import *
+
+# General configuration (from __init__, not very elegant...)
+jar = compat_cookiejar.CookieJar()
+cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
+proxy_handler = compat_urllib_request.ProxyHandler()
+opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+compat_urllib_request.install_opener(opener)
+socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+class FakeDownloader(object):
+    def __init__(self):
+        self.result = []
+        self.params = {}
+    def to_screen(self, s):
+        print(s)
+    def trouble(self, s):
+        raise Exception(s)
+    def download(self, x):
+        self.result.append(x)
+
+class TestYoutubeLists(unittest.TestCase):
+    def test_youtube_playlist(self):
+        DL = FakeDownloader()
+        IE = YoutubePlaylistIE(DL)
+        IE.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
+        self.assertEqual(DL.result, [
+            ['http://www.youtube.com/watch?v=bV9L5Ht9LgY'],
+            ['http://www.youtube.com/watch?v=FXxLjLQi3Fg'],
+            ['http://www.youtube.com/watch?v=tU3Bgo5qJZE']
+        ])
+
+    def test_youtube_playlist_long(self):
+        DL = FakeDownloader()
+        IE = YoutubePlaylistIE(DL)
+        IE.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+        self.assertTrue(len(DL.result) >= 799)
+
+    def test_youtube_course(self):
+        DL = FakeDownloader()
+        IE = YoutubePlaylistIE(DL)
+        # TODO find a > 100 (paginating?) videos course
+        IE.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        self.assertEqual(DL.result[0], ['http://www.youtube.com/watch?v=j9WZyLZCBzs'])
+        self.assertEqual(len(DL.result), 25)
+        self.assertEqual(DL.result[-1], ['http://www.youtube.com/watch?v=rYefUsYuEp0'])
+
+    def test_youtube_channel(self):
+        """I give up, please find a channel that does paginate and test this like test_youtube_playlist_long"""
+        pass # TODO
+
+    def test_youtube_user(self):
+        DL = FakeDownloader()
+        IE = YoutubePlaylistIE(DL)
+        IE.extract('https://www.youtube.com/user/TheLinuxFoundation')
+        self.assertTrue(len(DL.result) >= 320)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_youtube_playlist_ids.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+
+import sys
+import unittest
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE
+
+class TestYoutubePlaylistMatching(unittest.TestCase):
+    def test_playlist_matching(self):
+        self.assertTrue(YoutubePlaylistIE().suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
+        self.assertTrue(YoutubePlaylistIE().suitable(u'PL63F0C78739B09958'))
+        self.assertFalse(YoutubePlaylistIE().suitable(u'PLtS2H6bU1M'))
+
+    def test_youtube_matching(self):
+        self.assertTrue(YoutubeIE().suitable(u'PLtS2H6bU1M'))
+
+if __name__ == '__main__':
+    unittest.main()

test/tests.json

@@ -0,0 +1,62 @@
+[
+  {
+    "name": "Youtube",
+    "url":  "http://www.youtube.com/watch?v=BaW_jenozKc",
+    "file":  "BaW_jenozKc.mp4"
+  },
+  {
+    "name": "Dailymotion",
+    "md5":  "392c4b85a60a90dc4792da41ce3144eb",
+    "url":  "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech",
+    "file":  "x33vw9.mp4"
+  },
+  {
+    "name": "Metacafe",
+    "addIEs": ["Youtube"],
+    "url":  "http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
+    "file":  "_aUehQsCQtM.flv"
+  },
+  {
+    "name": "BlipTV",
+    "md5":  "b2d849efcf7ee18917e4b4d9ff37cafe",
+    "url":  "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352",
+    "file":  "5779306.m4v"
+  },
+  {
+    "name": "XVideos",
+    "md5":  "1d0c835822f0a71a7bf011855db929d0",
+    "url":  "http://www.xvideos.com/video939581/funny_porns_by_s_-1",
+    "file":  "939581.flv"
+  },
+  {
+    "name": "Vimeo",
+    "md5":  "60540a4ec7cc378ec84b919c0aed5023",
+    "url":  "http://vimeo.com/14160053",
+    "file": "14160053.mp4"
+  },
+  {
+    "name": "Soundcloud",
+    "md5":  "ebef0a451b909710ed1d7787dddbf0d7",
+    "url":  "http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy",
+    "file":  "62986583.mp3"
+  },
+  {
+    "name": "StanfordOpenClassroom",
+    "md5":  "544a9468546059d4e80d76265b0443b8",
+    "url":  "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100",
+    "file":  "PracticalUnix_intro-environment.mp4"
+  },
+  {
+    "name": "XNXX",
+    "md5":  "0831677e2b4761795f68d417e0b7b445",
+    "url":  "http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_",
+    "file":  "1135332.flv"
+  },
+  {
+    "name": "Youku",
+    "url": "http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
+    "file": "XNDgyMDQ2NTQw_part00.flv",
+    "md5": "ffe3f2e435663dc2d1eea34faeff5b5b",
+    "params": { "test": false }
+  }
+]

youtube_dl/FileDownloader.py

@@ -0,0 +1,728 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+
+import math
+import os
+import re
+import socket
+import subprocess
+import sys
+import time
+import traceback
+
+if os.name == 'nt':
+    import ctypes
+
+from .utils import *
+
+
+class FileDownloader(object):
+    """File Downloader class.
+
+    File downloader objects are the ones responsible of downloading the
+    actual video file and writing it to disk if the user has requested
+    it, among some other tasks. In most cases there should be one per
+    program. As, given a video URL, the downloader doesn't know how to
+    extract all the needed information, task that InfoExtractors do, it
+    has to pass the URL to one of them.
+
+    For this, file downloader objects have a method that allows
+    InfoExtractors to be registered in a given order. When it is passed
+    a URL, the file downloader handles it to the first InfoExtractor it
+    finds that reports being able to handle it. The InfoExtractor extracts
+    all the information about the video or videos the URL refers to, and
+    asks the FileDownloader to process the video information, possibly
+    downloading the video.
+
+    File downloaders accept a lot of parameters. In order not to saturate
+    the object constructor with arguments, it receives a dictionary of
+    options instead. These options are available through the params
+    attribute for the InfoExtractors to use. The FileDownloader also
+    registers itself as the downloader in charge for the InfoExtractors
+    that are added to it, so this is a "mutual registration".
+
+    Available options:
+
+    username:          Username for authentication purposes.
+    password:          Password for authentication purposes.
+    usenetrc:          Use netrc for authentication instead.
+    quiet:             Do not print messages to stdout.
+    forceurl:          Force printing final URL.
+    forcetitle:        Force printing title.
+    forcethumbnail:    Force printing thumbnail URL.
+    forcedescription:  Force printing description.
+    forcefilename:     Force printing final filename.
+    simulate:          Do not download the video files.
+    format:            Video format code.
+    format_limit:      Highest quality format to try.
+    outtmpl:           Template for output names.
+    restrictfilenames: Do not allow "&" and spaces in file names
+    ignoreerrors:      Do not stop on download errors.
+    ratelimit:         Download speed limit, in bytes/sec.
+    nooverwrites:      Prevent overwriting files.
+    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.
+    playliststart:     Playlist item to start at.
+    playlistend:       Playlist item to end at.
+    matchtitle:        Download only matching titles.
+    rejecttitle:       Reject downloads for matching titles.
+    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.
+    writedescription:  Write the video description to a .description file
+    writeinfojson:     Write the video description to a .info.json file
+    writesubtitles:    Write the video subtitles to a .srt file
+    subtitleslang:     Language of the subtitles to download
+    test:              Download only first bytes to test the downloader.
+    """
+
+    params = None
+    _ies = []
+    _pps = []
+    _download_retcode = None
+    _num_downloads = None
+    _screen_file = None
+
+    def __init__(self, params):
+        """Create a FileDownloader object with the given options."""
+        self._ies = []
+        self._pps = []
+        self._download_retcode = 0
+        self._num_downloads = 0
+        self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
+        self.params = params
+
+        if '%(stitle)s' in self.params['outtmpl']:
+            self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
+
+    @staticmethod
+    def format_bytes(bytes):
+        if bytes is None:
+            return 'N/A'
+        if type(bytes) is str:
+            bytes = float(bytes)
+        if bytes == 0.0:
+            exponent = 0
+        else:
+            exponent = int(math.log(bytes, 1024.0))
+        suffix = 'bkMGTPEZY'[exponent]
+        converted = float(bytes) / float(1024 ** exponent)
+        return '%.2f%s' % (converted, suffix)
+
+    @staticmethod
+    def calc_percent(byte_counter, data_len):
+        if data_len is None:
+            return '---.-%'
+        return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
+
+    @staticmethod
+    def calc_eta(start, now, total, current):
+        if total is None:
+            return '--:--'
+        dif = now - start
+        if current == 0 or dif < 0.001: # One millisecond
+            return '--:--'
+        rate = float(current) / dif
+        eta = int((float(total) - float(current)) / rate)
+        (eta_mins, eta_secs) = divmod(eta, 60)
+        if eta_mins > 99:
+            return '--:--'
+        return '%02d:%02d' % (eta_mins, eta_secs)
+
+    @staticmethod
+    def calc_speed(start, now, bytes):
+        dif = now - start
+        if bytes == 0 or dif < 0.001: # One millisecond
+            return '%10s' % '---b/s'
+        return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
+
+    @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 add_info_extractor(self, ie):
+        """Add an InfoExtractor object to the end of the list."""
+        self._ies.append(ie)
+        ie.set_downloader(self)
+
+    def add_post_processor(self, pp):
+        """Add a PostProcessor object to the end of the chain."""
+        self._pps.append(pp)
+        pp.set_downloader(self)
+
+    def to_screen(self, message, skip_eol=False):
+        """Print message to stdout if not in quiet mode."""
+        assert type(message) == type(u'')
+        if not self.params.get('quiet', False):
+            terminator = [u'\n', u''][skip_eol]
+            output = message + terminator
+            if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
+                output = output.encode(preferredencoding(), 'ignore')
+            self._screen_file.write(output)
+            self._screen_file.flush()
+
+    def to_stderr(self, message):
+        """Print message to stderr."""
+        assert type(message) == type(u'')
+        output = message + u'\n'
+        if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
+            output = output.encode(preferredencoding())
+        sys.stderr.write(output)
+
+    def to_cons_title(self, message):
+        """Set console/terminal window title to message."""
+        if not self.params.get('consoletitle', False):
+            return
+        if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
+            # c_wchar_p() might not be necessary if `message` is
+            # already of type unicode()
+            ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
+        elif 'TERM' in os.environ:
+            sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
+
+    def fixed_template(self):
+        """Checks if the output template is fixed."""
+        return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None)
+
+    def trouble(self, message=None):
+        """Determine action to take when a download problem appears.
+
+        Depending on if the downloader has been configured to ignore
+        download errors or not, this method may throw an exception or
+        not when errors are found, after printing the message.
+        """
+        if message is not None:
+            self.to_stderr(message)
+        if self.params.get('verbose'):
+            self.to_stderr(u''.join(traceback.format_list(traceback.extract_stack())))
+        if not self.params.get('ignoreerrors', False):
+            raise DownloadError(message)
+        self._download_retcode = 1
+
+    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) as err:
+            self.trouble(u'ERROR: 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
+        try:
+            os.utime(filename, (time.time(), filetime))
+        except:
+            pass
+        return filetime
+
+    def report_writedescription(self, descfn):
+        """ Report that the description file is being written """
+        self.to_screen(u'[info] Writing video description to: ' + descfn)
+
+    def report_writesubtitles(self, srtfn):
+        """ Report that the subtitles file is being written """
+        self.to_screen(u'[info] Writing video subtitles to: ' + srtfn)
+
+    def report_writeinfojson(self, infofn):
+        """ Report that the metadata file has been written """
+        self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
+
+    def report_destination(self, filename):
+        """Report destination filename."""
+        self.to_screen(u'[download] Destination: ' + filename)
+
+    def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
+        """Report download progress."""
+        if self.params.get('noprogress', False):
+            return
+        self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
+                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+        self.to_cons_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) as err:
+            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):
+        """Report download finished."""
+        if self.params.get('noprogress', False):
+            self.to_screen(u'[download] Download completed')
+        else:
+            self.to_screen(u'')
+
+    def increment_downloads(self):
+        """Increment the ordinal that assigns a number to each file."""
+        self._num_downloads += 1
+
+    def prepare_filename(self, info_dict):
+        """Generate the output filename."""
+        try:
+            template_dict = dict(info_dict)
+
+            template_dict['epoch'] = int(time.time())
+            template_dict['autonumber'] = u'%05d' % self._num_downloads
+
+            sanitize = lambda k,v: sanitize_filename(
+                u'NA' if v is None else compat_str(v),
+                restricted=self.params.get('restrictfilenames'),
+                is_id=(k==u'id'))
+            template_dict = dict((k, sanitize(k, v)) for k,v in template_dict.items())
+
+            filename = self.params['outtmpl'] % template_dict
+            return filename
+        except (ValueError, KeyError) as err:
+            self.trouble(u'ERROR: invalid system charset or erroneous output template')
+            return None
+
+    def _match_entry(self, info_dict):
+        """ Returns None iff the file should be downloaded """
+
+        title = info_dict['title']
+        matchtitle = self.params.get('matchtitle', False)
+        if matchtitle:
+            matchtitle = matchtitle.decode('utf8')
+            if not re.search(matchtitle, title, re.IGNORECASE):
+                return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+        rejecttitle = self.params.get('rejecttitle', False)
+        if rejecttitle:
+            rejecttitle = rejecttitle.decode('utf8')
+            if re.search(rejecttitle, title, re.IGNORECASE):
+                return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+        return None
+
+    def process_info(self, info_dict):
+        """Process a single dictionary returned by an InfoExtractor."""
+
+        # Keep for backwards compatibility
+        info_dict['stitle'] = info_dict['title']
+
+        if not 'format' in info_dict:
+            info_dict['format'] = info_dict['ext']
+
+        reason = self._match_entry(info_dict)
+        if reason is not None:
+            self.to_screen(u'[download] ' + reason)
+            return
+
+        max_downloads = self.params.get('max_downloads')
+        if max_downloads is not None:
+            if self._num_downloads > int(max_downloads):
+                raise MaxDownloadsReached()
+
+        filename = self.prepare_filename(info_dict)
+
+        # Forced printings
+        if self.params.get('forcetitle', False):
+            compat_print(info_dict['title'])
+        if self.params.get('forceurl', False):
+            compat_print(info_dict['url'])
+        if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
+            compat_print(info_dict['thumbnail'])
+        if self.params.get('forcedescription', False) and 'description' in info_dict:
+            compat_print(info_dict['description'])
+        if self.params.get('forcefilename', False) and filename is not None:
+            compat_print(filename)
+        if self.params.get('forceformat', False):
+            compat_print(info_dict['format'])
+
+        # Do nothing else if in simulate mode
+        if self.params.get('simulate', False):
+            return
+
+        if filename is None:
+            return
+
+        try:
+            dn = os.path.dirname(encodeFilename(filename))
+            if dn != '' and not os.path.exists(dn): # dn is already encoded
+                os.makedirs(dn)
+        except (OSError, IOError) as err:
+            self.trouble(u'ERROR: unable to create directory ' + compat_str(err))
+            return
+
+        if self.params.get('writedescription', False):
+            try:
+                descfn = filename + u'.description'
+                self.report_writedescription(descfn)
+                descfile = open(encodeFilename(descfn), 'wb')
+                try:
+                    descfile.write(info_dict['description'].encode('utf-8'))
+                finally:
+                    descfile.close()
+            except (OSError, IOError):
+                self.trouble(u'ERROR: Cannot write description file ' + descfn)
+                return
+
+        if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
+            # subtitles download errors are already managed as troubles in relevant IE
+            # that way it will silently go on when used with unsupporting IE
+            try:
+                srtfn = filename.rsplit('.', 1)[0] + u'.srt'
+                self.report_writesubtitles(srtfn)
+                srtfile = open(encodeFilename(srtfn), 'wb')
+                try:
+                    srtfile.write(info_dict['subtitles'].encode('utf-8'))
+                finally:
+                    srtfile.close()
+            except (OSError, IOError):
+                self.trouble(u'ERROR: Cannot write subtitles file ' + descfn)
+                return
+
+        if self.params.get('writeinfojson', False):
+            infofn = filename + u'.info.json'
+            self.report_writeinfojson(infofn)
+            try:
+                json.dump
+            except (NameError,AttributeError):
+                self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
+                return
+            try:
+                infof = open(encodeFilename(infofn), 'wb')
+                try:
+                    json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
+                    json.dump(json_info_dict, infof)
+                finally:
+                    infof.close()
+            except (OSError, IOError):
+                self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
+                return
+
+        if not self.params.get('skip_download', False):
+            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
+                success = True
+            else:
+                try:
+                    success = self._do_download(filename, info_dict)
+                except (OSError, IOError) as err:
+                    raise UnavailableVideoError()
+                except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                    self.trouble(u'ERROR: unable to download video data: %s' % str(err))
+                    return
+                except (ContentTooShortError, ) as err:
+                    self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+                    return
+
+            if success:
+                try:
+                    self.post_process(filename, info_dict)
+                except (PostProcessingError) as err:
+                    self.trouble(u'ERROR: postprocessing: %s' % str(err))
+                    return
+
+    def download(self, url_list):
+        """Download a given list of URLs."""
+        if len(url_list) > 1 and self.fixed_template():
+            raise SameFileError(self.params['outtmpl'])
+
+        for url in url_list:
+            suitable_found = False
+            for ie in self._ies:
+                # Go to next InfoExtractor if not suitable
+                if not ie.suitable(url):
+                    continue
+
+                # Warn if the _WORKING attribute is False
+                if not ie.working():
+                    self.trouble(u'WARNING: the program functionality for this site has been marked as broken, '
+                                 u'and will probably not work. If you want to go on, use the -i option.')
+
+                # Suitable InfoExtractor found
+                suitable_found = True
+
+                # Extract information from URL and process it
+                videos = ie.extract(url)
+                for video in videos or []:
+                    video['extractor'] = ie.IE_NAME
+                    try:
+                        self.increment_downloads()
+                        self.process_info(video)
+                    except UnavailableVideoError:
+                        self.trouble(u'\nERROR: unable to download video')
+
+                # Suitable InfoExtractor had been found; go to next URL
+                break
+
+            if not suitable_found:
+                self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
+
+        return self._download_retcode
+
+    def post_process(self, filename, ie_info):
+        """Run the postprocessing chain on the given file."""
+        info = dict(ie_info)
+        info['filepath'] = filename
+        for pp in self._pps:
+            info = pp.run(info)
+            if info is None:
+                break
+
+    def _download_with_rtmpdump(self, filename, url, player_url):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        # Check for rtmpdump first
+        try:
+            subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+        except (OSError, IOError):
+            self.trouble(u'ERROR: 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', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
+        args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
+        if self.params.get('verbose', False):
+            try:
+                import pipes
+                shell_quote = lambda args: ' '.join(map(pipes.quote, args))
+            except ImportError:
+                shell_quote = repr
+            self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args))
+        retval = subprocess.call(args)
+        while retval == 2 or retval == 1:
+            prevsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
+            time.sleep(5.0) # This seems to be needed
+            retval = subprocess.call(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'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+                retval = 0
+                break
+        if retval == 0:
+            self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(encodeFilename(tmpfilename)))
+            self.try_rename(tmpfilename, filename)
+            return True
+        else:
+            self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
+            return False
+
+    def _do_download(self, filename, info_dict):
+        url = info_dict['url']
+        player_url = info_dict.get('player_url', None)
+
+        # 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)
+            return True
+
+        # Attempt to download using rtmpdump
+        if url.startswith('rtmp'):
+            return self._download_with_rtmpdump(filename, url, player_url)
+
+        tmpfilename = self.temp_name(filename)
+        stream = None
+
+        # Do not include the Accept-Encoding header
+        headers = {'Youtubedl-no-compression': 'True'}
+        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)
+                            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.trouble(u'ERROR: 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
+        data_len_str = self.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.trouble(u'ERROR: unable to open for writing: %s' % str(err))
+                    return False
+            try:
+                stream.write(data_block)
+            except (IOError, OSError) as err:
+                self.trouble(u'\nERROR: 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_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
+            if data_len is None:
+                self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
+            else:
+                percent_str = self.calc_percent(byte_counter, data_len)
+                eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+                self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+
+            # Apply rate limit
+            self.slow_down(start, byte_counter - resume_len)
+
+        if stream is None:
+            self.trouble(u'\nERROR: Did not get any data blocks')
+            return False
+        stream.close()
+        self.report_finish()
+        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))
+
+        return True

youtube_dl/PostProcessor.py

@@ -0,0 +1,200 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from __future__ import absolute_import
+
+import os
+import subprocess
+import sys
+import time
+
+from .utils import *
+
+
+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.
+
+        When this method returns None, the postprocessing chain is
+        stopped. However, this method may return an information
+        dictionary that will be passed to the next postprocessing
+        object in the chain. It can be the one it received after
+        changing some fields.
+
+        In addition, this method may raise a PostProcessingError
+        exception that will be taken into account by the downloader
+        it was called from.
+        """
+        return information # by default, do nothing
+
+class AudioConversionError(BaseException):
+    def __init__(self, message):
+        self.message = message
+
+class FFmpegExtractAudioPP(PostProcessor):
+    def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
+        PostProcessor.__init__(self, downloader)
+        if preferredcodec is None:
+            preferredcodec = 'best'
+        self._preferredcodec = preferredcodec
+        self._preferredquality = preferredquality
+        self._keepvideo = keepvideo
+        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 get_audio_codec(self, path):
+        if not self._exes['ffprobe'] and not self._exes['avprobe']: return None
+        try:
+            cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', '--', encodeFilename(path)]
+            handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), 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.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]
+        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path), '-vn']
+               + acodec_opts + more_opts +
+               ['--', encodeFilename(out_path)])
+        p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        stdout,stderr = p.communicate()
+        if p.returncode != 0:
+            msg = stderr.strip().split('\n')[-1]
+            raise AudioConversionError(msg)
+
+    def run(self, information):
+        path = information['filepath']
+
+        filecodec = self.get_audio_codec(path)
+        if filecodec is None:
+            self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
+            return None
+
+        more_opts = []
+        if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
+            if self._preferredcodec == 'm4a' and filecodec == 'aac':
+                # Lossless, but in another container
+                acodec = 'copy'
+                extension = self._preferredcodec
+                more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
+            elif filecodec in ['aac', 'mp3', 'vorbis']:
+                # 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', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
+            extension = self._preferredcodec
+            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']
+            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
+        self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
+        try:
+            self.run_ffmpeg(path, new_path, acodec, more_opts)
+        except:
+            etype,e,tb = sys.exc_info()
+            if isinstance(e, AudioConversionError):
+                self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message)
+            else:
+                self._downloader.to_stderr(u'ERROR: error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg'))
+            return None
+
+        # 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.to_stderr(u'WARNING: Cannot update utime of audio file')
+
+        if not self._keepvideo:
+            try:
+                os.remove(encodeFilename(path))
+            except (IOError, OSError):
+                self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
+                return None
+
+        information['filepath'] = new_path
+        return information

youtube_dl/__init__.py

@@ -0,0 +1,602 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from __future__ import with_statement
+from __future__ import absolute_import
+
+__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',
+    )
+
+__license__ = 'Public Domain'
+
+import getpass
+import optparse
+import os
+import re
+import shlex
+import socket
+import subprocess
+import sys
+import warnings
+
+from .utils import *
+from .version import __version__
+from .FileDownloader import *
+from .InfoExtractors import *
+from .PostProcessor import *
+
+def updateSelf(downloader, filename):
+    """Update the program file with the latest version from the repository"""
+
+    # TODO: at least, check https certificates
+
+    from zipimport import zipimporter
+
+    API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
+    BIN_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl"
+    EXE_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl.exe"
+
+    if hasattr(sys, "frozen"): # PY2EXE
+        if not os.access(filename, os.W_OK):
+            sys.exit('ERROR: no write permissions on %s' % filename)
+
+        downloader.to_screen(u'Updating to latest version...')
+
+        urla = compat_urllib_request.urlopen(API_URL)
+        download = filter(lambda x: x["name"] == "youtube-dl.exe", json.loads(urla.read()))
+        if not download:
+            downloader.to_screen(u'ERROR: can\'t find the current version. Please try again later.')
+            return
+        newversion = download[0]["description"].strip()
+        if newversion == __version__:
+            downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
+            return
+        urla.close()
+
+        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:
+            urlh = compat_urllib_request.urlopen(EXE_URL)
+            newcontent = urlh.read()
+            urlh.close()
+            with open(exe + '.new', 'wb') as outf:
+                outf.write(newcontent)
+        except (IOError, OSError) as err:
+            sys.exit('ERROR: unable to download latest 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')
+
+    elif isinstance(globals().get('__loader__'), zipimporter): # UNIX ZIP
+        if not os.access(filename, os.W_OK):
+            sys.exit('ERROR: no write permissions on %s' % filename)
+
+        downloader.to_screen(u'Updating to latest version...')
+
+        urla = compat_urllib_request.urlopen(API_URL)
+        download = [x for x in json.loads(urla.read().decode('utf8')) if x["name"] == "youtube-dl"]
+        if not download:
+            downloader.to_screen(u'ERROR: can\'t find the current version. Please try again later.')
+            return
+        newversion = download[0]["description"].strip()
+        if newversion == __version__:
+            downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
+            return
+        urla.close()
+
+        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')
+
+    else:
+        downloader.to_screen(u'It looks like you installed youtube-dl with pip or setup.py. Please use that to update.')
+        return
+
+    downloader.to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
+
+def parseOpts():
+    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 _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
+
+    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')
+    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')
+    general.add_option('-i', '--ignore-errors',
+            action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
+    general.add_option('-r', '--rate-limit',
+            dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
+    general.add_option('-R', '--retries',
+            dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
+    general.add_option('--buffer-size',
+            dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16k) (default is %default)', default="1024")
+    general.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)
+    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('--list-extractors',
+            action='store_true', dest='list_extractors',
+            help='List all supported extractors and the URLs they would handle', default=False)
+    general.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
+
+    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', help='Abort after downloading NUMBER files', default=None)
+
+    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)
+
+
+    video_format.add_option('-f', '--format',
+            action='store', dest='format', metavar='FORMAT', help='video format code')
+    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)')
+    video_format.add_option('--write-srt',
+            action='store_true', dest='writesubtitles',
+            help='write video closed captions to a .srt file (currently youtube only)', default=False)
+    video_format.add_option('--srt-lang',
+            action='store', dest='subtitleslang', metavar='LANG',
+            help='language of the closed captions to download (optional) use IETF language tags like \'en\'')
+
+
+    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-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('--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)
+
+
+    filesystem.add_option('-t', '--title',
+            action='store_true', dest='usetitle', help='use title in file name', default=False)
+    filesystem.add_option('--id',
+            action='store_true', dest='useid', help='use 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, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id 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('--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='resume partially downloaded files', 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)
+
+
+    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", 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('-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')
+
+
+    parser.add_option_group(general)
+    parser.add_option_group(selection)
+    parser.add_option_group(filesystem)
+    parser.add_option_group(verbosity)
+    parser.add_option_group(video_format)
+    parser.add_option_group(authentication)
+    parser.add_option_group(postproc)
+
+    xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
+    if xdg_config_home:
+        userConf = os.path.join(xdg_config_home, 'youtube-dl.conf')
+    else:
+        userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
+    argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:]
+    opts, args = parser.parse_args(argv)
+
+    return parser, opts, args
+
+def gen_extractors():
+    """ Return a list of an instance of every supported extractor.
+    The order does matter; the first extractor matched is the one handling the URL.
+    """
+    return [
+        YoutubePlaylistIE(),
+        YoutubeChannelIE(),
+        YoutubeUserIE(),
+        YoutubeSearchIE(),
+        YoutubeIE(),
+        MetacafeIE(),
+        DailymotionIE(),
+        GoogleIE(),
+        GoogleSearchIE(),
+        PhotobucketIE(),
+        YahooIE(),
+        YahooSearchIE(),
+        DepositFilesIE(),
+        FacebookIE(),
+        BlipTVUserIE(),
+        BlipTVIE(),
+        VimeoIE(),
+        MyVideoIE(),
+        ComedyCentralIE(),
+        EscapistIE(),
+        CollegeHumorIE(),
+        XVideosIE(),
+        SoundcloudIE(),
+        InfoQIE(),
+        MixcloudIE(),
+        StanfordOpenClassroomIE(),
+        MTVIE(),
+        YoukuIE(),
+        XNXXIE(),
+        GooglePlusIE(),
+        ArteTvIE(),
+        GenericIE()
+    ]
+
+def _real_main():
+    parser, opts, args = parseOpts()
+
+    # Open appropriate CookieJar
+    if opts.cookiefile is None:
+        jar = compat_cookiejar.CookieJar()
+    else:
+        try:
+            jar = compat_cookiejar.MozillaCookieJar(opts.cookiefile)
+            if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
+                jar.load()
+        except (IOError, OSError) as err:
+            sys.exit(u'ERROR: unable to open cookie file')
+    # Set user agent
+    if opts.user_agent is not None:
+        std_headers['User-Agent'] = opts.user_agent
+
+    # Dump user agent
+    if opts.dump_user_agent:
+        print(std_headers['User-Agent'])
+        sys.exit(0)
+
+    # Batch file verification
+    batchurls = []
+    if opts.batchfile is not None:
+        try:
+            if opts.batchfile == '-':
+                batchfd = sys.stdin
+            else:
+                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)]
+        except IOError:
+            sys.exit(u'ERROR: batch file could not be read')
+    all_urls = batchurls + args
+    all_urls = [url.strip() for url in all_urls]
+
+    # General configuration
+    cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
+    proxy_handler = compat_urllib_request.ProxyHandler()
+    opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+    compat_urllib_request.install_opener(opener)
+    socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+    extractors = gen_extractors()
+
+    if opts.list_extractors:
+        for ie in extractors:
+            print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
+            matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
+            all_urls = filter(lambda url: url not in matchedUrls, all_urls)
+            for mu in matchedUrls:
+                print(u'  ' + mu)
+        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(u'using .netrc conflicts with giving username/password')
+    if opts.password is not None and opts.username is None:
+        parser.error(u'account username missing')
+    if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
+        parser.error(u'using output template conflicts with using title, video ID or auto number')
+    if opts.usetitle and opts.useid:
+        parser.error(u'using title conflicts with using video ID')
+    if opts.username is not None and opts.password is None:
+        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(u'invalid rate limit specified')
+        opts.ratelimit = numeric_limit
+    if opts.retries is not None:
+        try:
+            opts.retries = int(opts.retries)
+        except (TypeError, ValueError) as err:
+            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(u'invalid buffer size specified')
+        opts.buffersize = numeric_buffersize
+    try:
+        opts.playliststart = int(opts.playliststart)
+        if opts.playliststart <= 0:
+            raise ValueError(u'Playlist start must be positive')
+    except (TypeError, ValueError) as err:
+        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) as err:
+        parser.error(u'invalid playlist end number specified')
+    if opts.extractaudio:
+        if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']:
+            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(u'invalid audio quality specified')
+
+    # File downloader
+    fd = FileDownloader({
+        'usenetrc': opts.usenetrc,
+        'username': opts.username,
+        'password': opts.password,
+        'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+        'forceurl': opts.geturl,
+        'forcetitle': opts.gettitle,
+        'forcethumbnail': opts.getthumbnail,
+        'forcedescription': opts.getdescription,
+        'forcefilename': opts.getfilename,
+        'forceformat': opts.getformat,
+        'simulate': opts.simulate,
+        'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+        'format': opts.format,
+        'format_limit': opts.format_limit,
+        'listformats': opts.listformats,
+        'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
+            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'%(id)s.%(ext)s'),
+        'restrictfilenames': opts.restrictfilenames,
+        'ignoreerrors': opts.ignoreerrors,
+        'ratelimit': opts.ratelimit,
+        'nooverwrites': opts.nooverwrites,
+        'retries': opts.retries,
+        'buffersize': opts.buffersize,
+        'noresizebuffer': opts.noresizebuffer,
+        'continuedl': opts.continue_dl,
+        'noprogress': opts.noprogress,
+        'playliststart': opts.playliststart,
+        'playlistend': opts.playlistend,
+        'logtostderr': opts.outtmpl == '-',
+        'consoletitle': opts.consoletitle,
+        'nopart': opts.nopart,
+        'updatetime': opts.updatetime,
+        'writedescription': opts.writedescription,
+        'writeinfojson': opts.writeinfojson,
+        'writesubtitles': opts.writesubtitles,
+        'subtitleslang': opts.subtitleslang,
+        'matchtitle': opts.matchtitle,
+        'rejecttitle': opts.rejecttitle,
+        'max_downloads': opts.max_downloads,
+        'prefer_free_formats': opts.prefer_free_formats,
+        'verbose': opts.verbose,
+        'test': opts.test,
+        })
+
+    if opts.verbose:
+        fd.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies))
+
+    for extractor in extractors:
+        fd.add_info_extractor(extractor)
+
+    # PostProcessors
+    if opts.extractaudio:
+        fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
+
+    # Update version
+    if opts.update_self:
+        updateSelf(fd, sys.argv[0])
+
+    # Maybe do nothing
+    if len(all_urls) < 1:
+        if not opts.update_self:
+            parser.error(u'you must provide at least one URL')
+        else:
+            sys.exit()
+
+    try:
+        retcode = fd.download(all_urls)
+    except MaxDownloadsReached:
+        fd.to_screen(u'--max-download limit reached, aborting.')
+        retcode = 101
+
+    # Dump cookie jar if requested
+    if opts.cookiefile is not None:
+        try:
+            jar.save()
+        except (IOError, OSError) as err:
+            sys.exit(u'ERROR: unable to save cookie jar')
+
+    sys.exit(retcode)
+
+def main():
+    try:
+        _real_main()
+    except DownloadError:
+        sys.exit(1)
+    except SameFileError:
+        sys.exit(u'ERROR: fixed output name but more than one file to download')
+    except KeyboardInterrupt:
+        sys.exit(u'\nERROR: Interrupted by user')

youtube_dl/__main__.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+
+# Execute with
+# $ python youtube_dl/__main__.py (2.6+)
+# $ python -m youtube_dl          (2.7+)
+
+import sys
+
+if __package__ is None and not hasattr(sys, "frozen"):
+    # direct call of __main__.py
+    import os.path
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import youtube_dl
+
+if __name__ == '__main__':
+    youtube_dl.main()

youtube_dl/utils.py

@@ -0,0 +1,511 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import gzip
+import io
+import locale
+import os
+import re
+import sys
+import zlib
+import email.utils
+import json
+
+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 http.cookiejar as compat_cookiejar
+except ImportError: # Python 2
+    import cookielib as compat_cookiejar
+
+try:
+    import html.entities as compat_html_entities
+except ImportError: # Python 2
+    import htmlentitydefs as compat_html_entities
+
+try:
+    import html.parser as compat_html_parser
+except ImportError: # Python 2
+    import HTMLParser as compat_html_parser
+
+try:
+    import http.client as compat_http_client
+except ImportError: # Python 2
+    import httplib as compat_http_client
+
+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 _unquote(string, encoding='utf-8', errors='replace'):
+        if string == '':
+            return string
+        res = string.split('%')
+        if len(res) == 1:
+            return string
+        if encoding is None:
+            encoding = 'utf-8'
+        if errors is None:
+            errors = 'replace'
+        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
+        pct_sequence = b''
+        string = res[0]
+        for item in res[1:]:
+            try:
+                if not item:
+                    raise ValueError
+                pct_sequence += item[:2].decode('hex')
+                rest = item[2:]
+                if not rest:
+                    # This segment was just a single percent-encoded character.
+                    # May be part of a sequence of code units, so delay decoding.
+                    # (Stored in pct_sequence).
+                    continue
+            except ValueError:
+                rest = '%' + item
+            # Encountered non-percent-encoded characters. Flush the current
+            # pct_sequence.
+            string += pct_sequence.decode(encoding, errors) + rest
+            pct_sequence = b''
+        if pct_sequence:
+            # Flush the final pct_sequence
+            string += pct_sequence.decode(encoding, errors)
+        return string
+
+    def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
+                encoding='utf-8', errors='replace'):
+        qs, _coerce_result = qs, unicode
+        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 = _unquote(name, encoding=encoding, errors=errors)
+                name = _coerce_result(name)
+                value = nv[1].replace('+', ' ')
+                value = _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:
+    compat_str = unicode # Python 2
+except NameError:
+    compat_str = str
+
+try:
+    compat_chr = unichr # Python 2
+except NameError:
+    compat_chr = chr
+
+std_headers = {
+    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
+    'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
+    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+    'Accept-Encoding': 'gzip, deflate',
+    'Accept-Language': 'en-us,en;q=0.5',
+}
+def preferredencoding():
+    """Get preferred encoding.
+
+    Returns the best encoding scheme for the system, based on
+    locale.getpreferredencoding() and some further tweaks.
+    """
+    try:
+        pref = locale.getpreferredencoding()
+        u'TEST'.encode(pref)
+    except:
+        pref = 'UTF-8'
+
+    return pref
+
+if sys.version_info < (3,0):
+    def compat_print(s):
+        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
+else:
+    def compat_print(s):
+        assert type(s) == type(u'')
+        print(s)
+
+def htmlentity_transform(matchobj):
+    """Transforms an HTML entity to a character.
+
+    This function receives a match object and is intended to be used with
+    the re.sub() function.
+    """
+    entity = matchobj.group(1)
+
+    # Known non-numeric HTML entity
+    if entity in compat_html_entities.name2codepoint:
+        return compat_chr(compat_html_entities.name2codepoint[entity])
+
+    mobj = re.match(u'(?u)#(x?\\d+)', entity)
+    if mobj is not None:
+        numstr = mobj.group(1)
+        if numstr.startswith(u'x'):
+            base = 16
+            numstr = u'0%s' % numstr
+        else:
+            base = 10
+        return compat_chr(int(numstr, base))
+
+    # Unknown entity in name, return its literal representation
+    return (u'&%s;' % entity)
+
+compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
+class IDParser(compat_html_parser.HTMLParser):
+    """Modified HTMLParser that isolates a tag with the specified id"""
+    def __init__(self, id):
+        self.id = id
+        self.result = None
+        self.started = False
+        self.depth = {}
+        self.html = None
+        self.watch_startpos = False
+        self.error_count = 0
+        compat_html_parser.HTMLParser.__init__(self)
+
+    def error(self, message):
+        if self.error_count > 10 or self.started:
+            raise compat_html_parser.HTMLParseError(message, self.getpos())
+        self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
+        self.error_count += 1
+        self.goahead(1)
+
+    def loads(self, html):
+        self.html = html
+        self.feed(html)
+        self.close()
+
+    def handle_starttag(self, tag, attrs):
+        attrs = dict(attrs)
+        if self.started:
+            self.find_startpos(None)
+        if 'id' in attrs and attrs['id'] == self.id:
+            self.result = [tag]
+            self.started = True
+            self.watch_startpos = True
+        if self.started:
+            if not tag in self.depth: self.depth[tag] = 0
+            self.depth[tag] += 1
+
+    def handle_endtag(self, tag):
+        if self.started:
+            if tag in self.depth: self.depth[tag] -= 1
+            if self.depth[self.result[0]] == 0:
+                self.started = False
+                self.result.append(self.getpos())
+
+    def find_startpos(self, x):
+        """Needed to put the start position of the result (self.result[1])
+        after the opening tag with the requested id"""
+        if self.watch_startpos:
+            self.watch_startpos = False
+            self.result.append(self.getpos())
+    handle_entityref = handle_charref = handle_data = handle_comment = \
+    handle_decl = handle_pi = unknown_decl = find_startpos
+
+    def get_result(self):
+        if self.result is None:
+            return None
+        if len(self.result) != 3:
+            return None
+        lines = self.html.split('\n')
+        lines = lines[self.result[1][0]-1:self.result[2][0]]
+        lines[0] = lines[0][self.result[1][1]:]
+        if len(lines) == 1:
+            lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]]
+        lines[-1] = lines[-1][:self.result[2][1]]
+        return '\n'.join(lines).strip()
+
+def get_element_by_id(id, html):
+    """Return the content of the tag with the specified id in the passed HTML document"""
+    parser = IDParser(id)
+    try:
+        parser.loads(html)
+    except compat_html_parser.HTMLParseError:
+        pass
+    return parser.get_result()
+
+
+def clean_html(html):
+    """Clean an HTML snippet into a readable string"""
+    # Newline vs <br />
+    html = html.replace('\n', ' ')
+    html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html)
+    # Strip html tags
+    html = re.sub('<.*?>', '', html)
+    # Replace html entities
+    html = unescapeHTML(html)
+    return html
+
+
+def sanitize_open(filename, open_mode):
+    """Try to open the given filename, and slightly tweak it if this fails.
+
+    Attempts to open the given filename. If this fails, it tries to change
+    the filename slightly, step by step, until it's either able to open it
+    or it fails and raises a final exception, like the standard open()
+    function.
+
+    It returns the tuple (stream, definitive_file_name).
+    """
+    try:
+        if filename == u'-':
+            if sys.platform == 'win32':
+                import msvcrt
+                msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
+            return (sys.stdout, filename)
+        stream = open(encodeFilename(filename), open_mode)
+        return (stream, filename)
+    except (IOError, OSError) as err:
+        # In case of error, try to remove win32 forbidden chars
+        filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename)
+
+        # An exception here should be caught in the caller
+        stream = open(encodeFilename(filename), open_mode)
+        return (stream, filename)
+
+
+def timeconvert(timestr):
+    """Convert RFC 2822 defined time string into system timestamp"""
+    timestamp = None
+    timetuple = email.utils.parsedate_tz(timestr)
+    if timetuple is not None:
+        timestamp = email.utils.mktime_tz(timetuple)
+    return timestamp
+
+def sanitize_filename(s, restricted=False, is_id=False):
+    """Sanitizes a string so it could be used as part of a filename.
+    If restricted is set, use a stricter subset of allowed characters.
+    Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
+    """
+    def replace_insane(char):
+        if char == '?' or ord(char) < 32 or ord(char) == 127:
+            return ''
+        elif char == '"':
+            return '' if restricted else '\''
+        elif char == ':':
+            return '_-' if restricted else ' -'
+        elif char in '\\/|*<>':
+            return '_'
+        if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
+            return '_'
+        if restricted and ord(char) > 127:
+            return '_'
+        return char
+
+    result = u''.join(map(replace_insane, s))
+    if not is_id:
+        while '__' in result:
+            result = result.replace('__', '_')
+        result = result.strip('_')
+        # Common case of "Foreign band name - English song title"
+        if restricted and result.startswith('-_'):
+            result = result[2:]
+        if not result:
+            result = '_'
+    return result
+
+def orderedSet(iterable):
+    """ Remove all duplicates from the input iterable """
+    res = []
+    for el in iterable:
+        if el not in res:
+            res.append(el)
+    return res
+
+def unescapeHTML(s):
+    """
+    @param s a string
+    """
+    assert type(s) == type(u'')
+
+    result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s)
+    return result
+
+def encodeFilename(s):
+    """
+    @param s The name of the file
+    """
+
+    assert type(s) == type(u'')
+
+    # Python 3 has a Unicode API
+    if sys.version_info >= (3, 0):
+        return s
+
+    if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
+        # Pass u'' directly to use Unicode APIs on Windows 2000 and up
+        # (Detecting Windows NT 4 is tricky because 'major >= 4' would
+        # match Windows 9x series as well. Besides, NT 4 is obsolete.)
+        return s
+    else:
+        return s.encode(sys.getfilesystemencoding(), 'ignore')
+
+class DownloadError(Exception):
+    """Download Error exception.
+
+    This exception may be thrown by FileDownloader objects if they are not
+    configured to continue on errors. They will contain the appropriate
+    error message.
+    """
+    pass
+
+
+class SameFileError(Exception):
+    """Same File exception.
+
+    This exception will be thrown by FileDownloader objects if they detect
+    multiple files would have to be downloaded to the same file on disk.
+    """
+    pass
+
+
+class PostProcessingError(Exception):
+    """Post Processing exception.
+
+    This exception may be raised by PostProcessor's .run() method to
+    indicate an error in the postprocessing task.
+    """
+    pass
+
+class MaxDownloadsReached(Exception):
+    """ --max-downloads limit has been reached. """
+    pass
+
+
+class UnavailableVideoError(Exception):
+    """Unavailable Format exception.
+
+    This exception will be thrown when a video is requested
+    in a format that is not available for that video.
+    """
+    pass
+
+
+class ContentTooShortError(Exception):
+    """Content Too Short exception.
+
+    This exception may be raised by FileDownloader objects when a file they
+    download is too small for what the server announced first, indicating
+    the connection was probably interrupted.
+    """
+    # Both in bytes
+    downloaded = None
+    expected = None
+
+    def __init__(self, downloaded, expected):
+        self.downloaded = downloaded
+        self.expected = expected
+
+
+class Trouble(Exception):
+    """Trouble helper exception
+
+    This is an exception to be handled with
+    FileDownloader.trouble
+    """
+
+class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
+    """Handler for HTTP requests and responses.
+
+    This class, when installed with an OpenerDirector, automatically adds
+    the standard headers to every HTTP request and handles gzipped and
+    deflated responses from web servers. If compression is to be avoided in
+    a particular request, the original request in the program code only has
+    to include the HTTP header "Youtubedl-No-Compression", which will be
+    removed before making the real request.
+
+    Part of this code was copied from:
+
+    http://techknack.net/python-urllib2-handlers/
+
+    Andrew Rowls, the author of that code, agreed to release it to the
+    public domain.
+    """
+
+    @staticmethod
+    def deflate(data):
+        try:
+            return zlib.decompress(data, -zlib.MAX_WBITS)
+        except zlib.error:
+            return zlib.decompress(data)
+
+    @staticmethod
+    def addinfourl_wrapper(stream, headers, url, code):
+        if hasattr(compat_urllib_request.addinfourl, 'getcode'):
+            return compat_urllib_request.addinfourl(stream, headers, url, code)
+        ret = compat_urllib_request.addinfourl(stream, headers, url)
+        ret.code = code
+        return ret
+
+    def http_request(self, req):
+        for h in std_headers:
+            if h in req.headers:
+                del req.headers[h]
+            req.add_header(h, std_headers[h])
+        if 'Youtubedl-no-compression' in req.headers:
+            if 'Accept-encoding' in req.headers:
+                del req.headers['Accept-encoding']
+            del req.headers['Youtubedl-no-compression']
+        return req
+
+    def http_response(self, req, resp):
+        old_resp = resp
+        # gzip
+        if resp.headers.get('Content-encoding', '') == 'gzip':
+            gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r')
+            resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+            resp.msg = old_resp.msg
+        # deflate
+        if resp.headers.get('Content-encoding', '') == 'deflate':
+            gz = io.BytesIO(self.deflate(resp.read()))
+            resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+            resp.msg = old_resp.msg
+        return resp
+
+    https_request = http_request
+    https_response = http_response

youtube_dl/version.py

@@ -0,0 +1,2 @@
+
+__version__ = '2012.12.11'