release 2014.10.13

See issue #3753

.gitignore

@@ -11,6 +11,7 @@ MANIFEST
 README.txt
 youtube-dl.1
 youtube-dl.bash-completion
+youtube-dl.fish
 youtube-dl
 youtube-dl.exe
 youtube-dl.tar.gz
@@ -26,5 +27,7 @@ updates_key.pem
 *.m4a
 *.m4v
 *.part
+*.swp
 test/testdata
 .tox
+youtube-dl.zsh

LATEST_VERSION

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

MANIFEST.in

@@ -2,5 +2,6 @@ include README.md
 include test/*.py
 include test/*.json
 include youtube-dl.bash-completion
+include youtube-dl.fish
 include youtube-dl.1
 recursive-include docs Makefile conf.py *.rst

Makefile

@@ -1,15 +1,16 @@
-all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
+all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish
 
 cleanall: clean
 	rm -f youtube-dl youtube-dl.exe
 
-PREFIX=/usr/local
-BINDIR=$(PREFIX)/bin
-MANDIR=$(PREFIX)/man
-PYTHON=/usr/bin/env python
+PREFIX ?= /usr/local
+BINDIR ?= $(PREFIX)/bin
+MANDIR ?= $(PREFIX)/man
+SHAREDIR ?= $(PREFIX)/share
+PYTHON ?= /usr/bin/env python
 
 # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
 ifeq ($(PREFIX),/usr)
@@ -22,13 +23,17 @@ else
 	endif
 endif
 
-install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
+install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	install -d $(DESTDIR)$(BINDIR)
 	install -m 755 youtube-dl $(DESTDIR)$(BINDIR)
 	install -d $(DESTDIR)$(MANDIR)/man1
 	install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1
 	install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
 	install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
+	install -d $(DESTDIR)$(SHAREDIR)/zsh/site-functions
+	install -m 644 youtube-dl.zsh $(DESTDIR)$(SHAREDIR)/zsh/site-functions/_youtube-dl
+	install -d $(DESTDIR)$(SYSCONFDIR)/fish/completions
+	install -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish
 
 test:
 	#nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
@@ -36,9 +41,9 @@ test:
 
 tar: youtube-dl.tar.gz
 
-.PHONY: all clean install test tar bash-completion pypi-files
+.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion
 
-pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1
+pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
 
 youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	zip --quiet youtube-dl youtube_dl/*.py youtube_dl/*/*.py
@@ -64,7 +69,17 @@ youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-co
 
 bash-completion: youtube-dl.bash-completion
 
-youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
+youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
+	python devscripts/zsh-completion.py
+
+zsh-completion: youtube-dl.zsh
+
+youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
+	python devscripts/fish-completion.py
+
+fish-completion: youtube-dl.fish
+
+youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \
 		--exclude '*.kate-swp' \
@@ -78,5 +93,6 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		-- \
 		bin devscripts test youtube_dl docs \
 		LICENSE README.md README.txt \
-		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion setup.py \
+		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
+		youtube-dl.zsh youtube-dl.fish setup.py \
 		youtube-dl

README.md

@@ -17,6 +17,14 @@ If you do not have curl, you can alternatively use a recent wget:
 
 Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29).
 
+OS X users can install **youtube-dl** with [Homebrew](http://brew.sh/).
+
+    brew install youtube-dl
+
+You can also use pip:
+
+    sudo pip install youtube-dl
+
 Alternatively, refer to the developer instructions below for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
 
 # DESCRIPTION
@@ -91,8 +99,6 @@ which means you can modify it, redistribute it or use it however you like.
                                      downloaded videos in it.
     --include-ads                    Download advertisements as well
                                      (experimental)
-    --youtube-include-dash-manifest  Try to download the DASH manifest on
-                                     YouTube videos (experimental)
 
 ## Download Options:
     -r, --rate-limit LIMIT           maximum download rate in bytes per second
@@ -150,7 +156,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      downloads if possible.
     --no-continue                    do not resume partially downloaded files
                                      (restart from beginning)
-    --no-part                        do not use .part files
+    --no-part                        do not use .part files - write directly
+                                     into output file
     --no-mtime                       do not use the Last-modified header to set
                                      the file modification time
     --write-description              write video description to a .description
@@ -208,7 +215,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      information about the video. (Currently
                                      supported only for YouTube)
     --user-agent UA                  specify a custom user agent
-    --referer REF                    specify a custom referer, use if the video
+    --referer URL                    specify a custom referer, use if the video
                                      access is restricted to one domain
     --add-header FIELD:VALUE         specify a custom HTTP header and its value,
                                      separated by a colon ':'. You can use this
@@ -219,17 +226,22 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Video Format Options:
     -f, --format FORMAT              video format code, specify the order of
-                                     preference using slashes: "-f 22/17/18".
-                                     "-f mp4" and "-f flv" are also supported.
-                                     You can also use the special names "best",
-                                     "bestvideo", "bestaudio", "worst",
-                                     "worstvideo" and "worstaudio". By default,
-                                     youtube-dl will pick the best quality.
+                                     preference using slashes: -f 22/17/18 .  -f
+                                     mp4 , -f m4a and  -f flv  are also
+                                     supported. You can also use the special
+                                     names "best", "bestvideo", "bestaudio",
+                                     "worst", "worstvideo" and "worstaudio". By
+                                     default, youtube-dl will pick the best
+                                     quality. Use commas to download multiple
+                                     audio formats, such as  -f
+                                     136/137/mp4/bestvideo,140/m4a/bestaudio
     --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
+    --youtube-skip-dash-manifest     Do not download the DASH manifest on
+                                     YouTube videos
 
 ## Subtitle Options:
     --write-sub                      write subtitle file
@@ -245,8 +257,9 @@ which means you can modify it, redistribute it or use it however you like.
                                      language tags like 'en,pt'
 
 ## Authentication Options:
-    -u, --username USERNAME          account username
+    -u, --username USERNAME          login with this account ID
     -p, --password PASSWORD          account password
+    -2, --twofactor TWOFACTOR        two-factor auth code
     -n, --netrc                      use .netrc authentication data
     --video-password PASSWORD        video password (vimeo, smotri)
 
@@ -255,7 +268,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      (requires ffmpeg or avconv and ffprobe or
                                      avprobe)
     --audio-format FORMAT            "best", "aac", "vorbis", "mp3", "m4a",
-                                     "opus", or "wav"; best by default
+                                     "opus", 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
@@ -279,6 +292,10 @@ which means you can modify it, redistribute it or use it however you like.
                                      postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
                                      postprocessors
+    --exec CMD                       Execute a command on the file after
+                                     downloading, similar to find's -exec
+                                     syntax. Example: --exec 'adb push {}
+                                     /sdcard/Music/ && rm {}'
 
 # CONFIGURATION
 
@@ -303,10 +320,12 @@ The current default template is `%(title)s-%(id)s.%(ext)s`.
 
 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
+```bash
+$ 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
+```
 
 # VIDEO SELECTION
 
@@ -317,17 +336,51 @@ Videos can be filtered by their upload date using the options `--date`, `--dateb
  
 Examples:
 
-    # Download only the videos uploaded in the last 6 months
-    $ youtube-dl --dateafter now-6months
+```bash
+# Download only the videos uploaded in the last 6 months
+$ youtube-dl --dateafter now-6months
 
-    # Download only the videos uploaded on January 1, 1970
-    $ youtube-dl --date 19700101
+# Download only the videos uploaded on January 1, 1970
+$ youtube-dl --date 19700101
 
-    $ # will only download the videos uploaded in the 200x decade
-    $ youtube-dl --dateafter 20000101 --datebefore 20091231
+$ # will only download the videos uploaded in the 200x decade
+$ youtube-dl --dateafter 20000101 --datebefore 20091231
+```
 
 # FAQ
 
+### How do I update youtube-dl?
+
+If you've followed [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html), you can simply run `youtube-dl -U` (or, on Linux, `sudo youtube-dl -U`).
+
+If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update.
+
+If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distributions serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
+
+As a last resort, you can also uninstall the version installed by your package manager and follow our manual installation instructions. For that, remove the distribution's package, with a line like
+
+    sudo apt-get remove -y youtube-dl
+
+Afterwards, simply follow [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html):
+
+```
+sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl
+sudo chmod a+x /usr/local/bin/youtube-dl
+hash -r
+```
+
+Again, from then on you'll be able to update with `sudo youtube-dl -U`.
+
+### I'm getting an error `Unable to extract OpenGraph title` on YouTube playlists
+
+YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos.
+
+If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to report bugs to the Ubuntu packaging guys - all they have to do is update the package to a somewhat recent version. See above for a way to update.
+
+### Do I always have to pass in `--max-quality FORMAT`, or `-citw`?
+
+By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, `--max-quality` *limits* the video quality (so if you want the best quality, do NOT pass it in), and the only option out of `-citw` that is regularly useful is `-i`.
+
 ### 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.
@@ -399,49 +452,46 @@ If you want to add support for a new site, you can follow this quick list (assum
 2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
 3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
 4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
+    ```python
+    # coding: utf-8
+    from __future__ import unicode_literals
 
-        # coding: utf-8
-        from __future__ import unicode_literals
+    from .common import InfoExtractor
 
-        import re
 
-        from .common import InfoExtractor
-        
-        
-        class YourExtractorIE(InfoExtractor):
-            _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
-            _TEST = {
-                'url': 'http://yourextractor.com/watch/42',
-                'md5': 'TODO: md5 sum of the first 10KiB of the video file',
-                'info_dict': {
-                    'id': '42',
-                    'ext': 'mp4',
-                    'title': 'Video title goes here',
-                    # TODO more properties, either as:
-                    # * A value
-                    # * MD5 checksum; start the string with md5:
-                    # * A regular expression; start the string with re:
-                    # * Any Python type (for example int or float)
-                }
+    class YourExtractorIE(InfoExtractor):
+        _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
+        _TEST = {
+            'url': 'http://yourextractor.com/watch/42',
+            'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
+            'info_dict': {
+                'id': '42',
+                'ext': 'mp4',
+                'title': 'Video title goes here',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                # TODO more properties, either as:
+                # * A value
+                # * MD5 checksum; start the string with md5:
+                # * A regular expression; start the string with re:
+                # * Any Python type (for example int or float)
             }
+        }
 
-            def _real_extract(self, url):
-                mobj = re.match(self._VALID_URL, url)
-                video_id = mobj.group('id')
-
-                # TODO more code goes here, for example ...
-                webpage = self._download_webpage(url, video_id)
-                title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
-
-                return {
-                    'id': video_id,
-                    'title': title,
-                    # TODO more properties (see youtube_dl/extractor/common.py)
-                }
+        def _real_extract(self, url):
+            video_id = self._match_id(url)
 
+            # TODO more code goes here, for example ...
+            webpage = self._download_webpage(url, video_id)
+            title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
 
+            return {
+                'id': video_id,
+                'title': title,
+                # TODO more properties (see youtube_dl/extractor/common.py)
+            }
+    ```
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
-6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done.
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
 8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
 9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this:

devscripts/fish-completion.in

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

devscripts/fish-completion.py

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

devscripts/release.sh

@@ -73,7 +73,6 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 (cd build/$version/ && sha1sum $RELEASE_FILES > SHA1SUMS)
 (cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
 (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
-git checkout HEAD -- youtube-dl youtube-dl.exe
 
 /bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
 for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done

devscripts/zsh-completion.in

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

devscripts/zsh-completion.py

@@ -0,0 +1,46 @@
+#!/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
+
+ZSH_COMPLETION_FILE = "youtube-dl.zsh"
+ZSH_COMPLETION_TEMPLATE = "devscripts/zsh-completion.in"
+
+
+def build_completion(opt_parser):
+    opts = [opt for group in opt_parser.option_groups
+            for opt in group.option_list]
+    opts_file = [opt for opt in opts if opt.metavar == "FILE"]
+    opts_dir = [opt for opt in opts if opt.metavar == "DIR"]
+
+    fileopts = []
+    for opt in opts_file:
+        if opt._short_opts:
+            fileopts.extend(opt._short_opts)
+        if opt._long_opts:
+            fileopts.extend(opt._long_opts)
+
+    diropts = []
+    for opt in opts_dir:
+        if opt._short_opts:
+            diropts.extend(opt._short_opts)
+        if opt._long_opts:
+            diropts.extend(opt._long_opts)
+
+    flags = [opt.get_opt_string() for opt in opts]
+
+    with open(ZSH_COMPLETION_TEMPLATE) as f:
+        template = f.read()
+
+    template = template.replace("{{fileopts}}", "|".join(fileopts))
+    template = template.replace("{{diropts}}", "|".join(diropts))
+    template = template.replace("{{flags}}", " ".join(flags))
+
+    with open(ZSH_COMPLETION_FILE, "w") as f:
+        f.write(template)
+
+parser = youtube_dl.parseOpts()[0]
+build_completion(parser)

setup.py

@@ -48,6 +48,7 @@ if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
 else:
     files_spec = [
         ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
+        ('etc/fish/completions', ['youtube-dl.fish']),
         ('share/doc/youtube_dl', ['README.txt']),
         ('share/man/man1', ['youtube-dl.1'])
     ]

test/helper.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import errno
 import io
 import hashlib
@@ -12,6 +14,7 @@ from youtube_dl import YoutubeDL
 from youtube_dl.utils import (
     compat_str,
     preferredencoding,
+    write_string,
 )
 
 
@@ -40,10 +43,10 @@ def report_warning(message):
     If stderr is a tty file the 'WARNING:' will be colored
     '''
     if sys.stderr.isatty() and os.name != 'nt':
-        _msg_header = u'\033[0;33mWARNING:\033[0m'
+        _msg_header = '\033[0;33mWARNING:\033[0m'
     else:
-        _msg_header = u'WARNING:'
-    output = u'%s %s\n' % (_msg_header, message)
+        _msg_header = 'WARNING:'
+    output = '%s %s\n' % (_msg_header, message)
     if 'b' in getattr(sys.stderr, 'mode', '') or sys.version_info[0] < 3:
         output = output.encode(preferredencoding())
     sys.stderr.write(output)
@@ -102,26 +105,31 @@ def expect_info_dict(self, expected_dict, got_dict):
             match_rex = re.compile(match_str)
 
             self.assertTrue(
-                isinstance(got, compat_str) and match_rex.match(got),
-                u'field %s (value: %r) should match %r' % (info_field, got, match_str))
+                isinstance(got, compat_str),
+                'Expected a %s object, but got %s for field %s' % (
+                    compat_str.__name__, type(got).__name__, info_field))
+            self.assertTrue(
+                match_rex.match(got),
+                'field %s (value: %r) should match %r' % (info_field, got, match_str))
         elif isinstance(expected, type):
             got = got_dict.get(info_field)
             self.assertTrue(isinstance(got, expected),
-                u'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got)))
+                'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got)))
         else:
             if isinstance(expected, compat_str) and expected.startswith('md5:'):
                 got = 'md5:' + md5(got_dict.get(info_field))
             else:
                 got = got_dict.get(info_field)
             self.assertEqual(expected, got,
-                u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
+                'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
     # Check for the presence of mandatory fields
-    for key in ('id', 'url', 'title', 'ext'):
-        self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
+    if got_dict.get('_type') != 'playlist':
+        for key in ('id', 'url', 'title', 'ext'):
+            self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
     # Check for mandatory fields that are automatically set by YoutubeDL
     for key in ['webpage_url', 'extractor', 'extractor_key']:
-        self.assertTrue(got_dict.get(key), u'Missing field: %s' % key)
+        self.assertTrue(got_dict.get(key), 'Missing field: %s' % key)
 
     # Are checkable fields missing from the test case definition?
     test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
@@ -129,7 +137,15 @@ def expect_info_dict(self, expected_dict, got_dict):
         if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
     missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
     if missing_keys:
-        sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n')
+        def _repr(v):
+            if isinstance(v, compat_str):
+                return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'")
+            else:
+                return repr(v)
+        info_dict_str = ''.join(
+            '    %s: %s,\n' % (_repr(k), _repr(v))
+            for k, v in test_info_dict.items())
+        write_string('\n"info_dict": {' + info_dict_str + '}\n', out=sys.stderr)
         self.assertFalse(
             missing_keys,
             'Missing keys in test definition: %s' % (

test/parameters.json

@@ -27,7 +27,6 @@
     "rejecttitle": null, 
     "retries": 10, 
     "simulate": false, 
-    "skip_download": false, 
     "subtitleslang": null, 
     "subtitlesformat": "srt",
     "test": true, 

test/test_YoutubeDL.py

@@ -221,7 +221,7 @@ class TestFormatSelection(unittest.TestCase):
             '138', '137', '248', '136', '247', '135', '246',
             '245', '244', '134', '243', '133', '242', '160',
             # Dash audio
-            '141', '172', '140', '139', '171',
+            '141', '172', '140', '171', '139',
         ]
 
         for f1id, f2id in zip(order, order[1:]):

test/test_all_urls.py

@@ -99,6 +99,7 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_facebook_matching(self):
         self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
+        self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
 
     def test_no_duplicates(self):
         ies = gen_extractors()
@@ -108,7 +109,9 @@ class TestAllURLsMatching(unittest.TestCase):
                 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
                     self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
                 else:
-                    self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
+                    self.assertFalse(
+                        ie.suitable(url),
+                        '%s should not match URL %r . That URL belongs to %s.' % (type(ie).__name__, url, tc['name']))
 
     def test_keywords(self):
         self.assertMatch(':ytsubs', ['youtube:subscriptions'])
@@ -140,32 +143,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
         self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
 
-    def test_ComedyCentralShows(self):
-        self.assertMatch(
-            'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
-            ['ComedyCentralShows'])
-        self.assertMatch(
-            'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
-            ['ComedyCentralShows'])
-
     def test_yahoo_https(self):
         # https://github.com/rg3/youtube-dl/issues/2701
         self.assertMatch(

test/test_cache.py

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

test/test_download.py

@@ -7,6 +7,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
+    assertGreaterEqual,
     get_params,
     gettestcases,
     expect_info_dict,
@@ -27,6 +28,7 @@ from youtube_dl.utils import (
     compat_HTTPError,
     DownloadError,
     ExtractorError,
+    format_bytes,
     UnavailableVideoError,
 )
 from youtube_dl.extractor import get_info_extractor
@@ -63,15 +65,21 @@ def generator(test_case):
     def test_template(self):
         ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
         other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
+        is_playlist = any(k.startswith('playlist') for k in test_case)
+        test_cases = test_case.get(
+            'playlist', [] if is_playlist else [test_case])
+
         def print_skipping(reason):
             print('Skipping %s: %s' % (test_case['name'], reason))
         if not ie.working():
             print_skipping('IE marked as not _WORKING')
             return
-        if 'playlist' not in test_case:
-            info_dict = test_case.get('info_dict', {})
-            if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
+
+        for tc in test_cases:
+            info_dict = tc.get('info_dict', {})
+            if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
                 raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
+
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
             return
@@ -81,6 +89,9 @@ def generator(test_case):
                 return
 
         params = get_params(test_case.get('params', {}))
+        if is_playlist and 'playlist' not in test_case:
+            params.setdefault('extract_flat', True)
+            params.setdefault('skip_download', True)
 
         ydl = YoutubeDL(params)
         ydl.add_default_info_extractors()
@@ -93,9 +104,11 @@ def generator(test_case):
         def get_tc_filename(tc):
             return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
 
-        test_cases = test_case.get('playlist', [test_case])
-        def try_rm_tcs_files():
-            for tc in test_cases:
+        res_dict = None
+        def try_rm_tcs_files(tcs=None):
+            if tcs is None:
+                tcs = test_cases
+            for tc in tcs:
                 tc_filename = get_tc_filename(tc)
                 try_rm(tc_filename)
                 try_rm(tc_filename + '.part')
@@ -105,7 +118,10 @@ def generator(test_case):
             try_num = 1
             while True:
                 try:
-                    ydl.download([test_case['url']])
+                    # We're not using .download here sine that is just a shim
+                    # for outside error handling, and returns the exit code
+                    # instead of the result dict.
+                    res_dict = ydl.extract_info(test_case['url'])
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
                     if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
@@ -121,22 +137,64 @@ def generator(test_case):
                 else:
                     break
 
+            if is_playlist:
+                self.assertEqual(res_dict['_type'], 'playlist')
+                self.assertTrue('entries' in res_dict)
+                expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
+
+            if 'playlist_mincount' in test_case:
+                assertGreaterEqual(
+                    self,
+                    len(res_dict['entries']),
+                    test_case['playlist_mincount'],
+                    'Expected at least %d in playlist %s, but got only %d' % (
+                        test_case['playlist_mincount'], test_case['url'],
+                        len(res_dict['entries'])))
+            if 'playlist_count' in test_case:
+                self.assertEqual(
+                    len(res_dict['entries']),
+                    test_case['playlist_count'],
+                    'Expected %d entries in playlist %s, but got %d.' % (
+                        test_case['playlist_count'],
+                        test_case['url'],
+                        len(res_dict['entries']),
+                    ))
+            if 'playlist_duration_sum' in test_case:
+                got_duration = sum(e['duration'] for e in res_dict['entries'])
+                self.assertEqual(
+                    test_case['playlist_duration_sum'], got_duration)
+
             for tc in test_cases:
                 tc_filename = get_tc_filename(tc)
                 if not test_case.get('params', {}).get('skip_download', False):
                     self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
                     self.assertTrue(tc_filename in finished_hook_called)
+                    expected_minsize = tc.get('file_minsize', 10000)
+                    if expected_minsize is not None:
+                        if params.get('test'):
+                            expected_minsize = max(expected_minsize, 10000)
+                        got_fsize = os.path.getsize(tc_filename)
+                        assertGreaterEqual(
+                            self, got_fsize, expected_minsize,
+                            'Expected %s to be at least %s, but it\'s only %s ' %
+                            (tc_filename, format_bytes(expected_minsize),
+                                format_bytes(got_fsize)))
+                    if 'md5' in tc:
+                        md5_for_file = _file_md5(tc_filename)
+                        self.assertEqual(md5_for_file, tc['md5'])
                 info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
                 self.assertTrue(os.path.exists(info_json_fn))
-                if 'md5' in tc:
-                    md5_for_file = _file_md5(tc_filename)
-                    self.assertEqual(md5_for_file, tc['md5'])
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
 
                 expect_info_dict(self, tc.get('info_dict', {}), info_dict)
         finally:
             try_rm_tcs_files()
+            if is_playlist and res_dict is not None and res_dict.get('entries'):
+                # Remove all other files that may have been extracted if the
+                # extractor returns full results even with extract_flat
+                res_tcs = [{'info_dict': e} for e in res_dict['entries']]
+                try_rm_tcs_files(res_tcs)
 
     return test_template
 

test/test_playlists.py

@@ -1,400 +0,0 @@
-#!/usr/bin/env python
-# encoding: utf-8
-
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from test.helper import (
-    assertRegexpMatches,
-    assertGreaterEqual,
-    expect_info_dict,
-    FakeYDL,
-)
-
-from youtube_dl.extractor import (
-    AcademicEarthCourseIE,
-    DailymotionPlaylistIE,
-    DailymotionUserIE,
-    VimeoChannelIE,
-    VimeoUserIE,
-    VimeoAlbumIE,
-    VimeoGroupsIE,
-    VineUserIE,
-    UstreamChannelIE,
-    SoundcloudSetIE,
-    SoundcloudUserIE,
-    SoundcloudPlaylistIE,
-    TeacherTubeUserIE,
-    LivestreamIE,
-    LivestreamOriginalIE,
-    NHLVideocenterIE,
-    BambuserChannelIE,
-    BandcampAlbumIE,
-    SmotriCommunityIE,
-    SmotriUserIE,
-    IviCompilationIE,
-    ImdbListIE,
-    KhanAcademyIE,
-    EveryonesMixtapeIE,
-    RutubeChannelIE,
-    RutubePersonIE,
-    GoogleSearchIE,
-    GenericIE,
-    TEDIE,
-    ToypicsUserIE,
-    XTubeUserIE,
-    InstagramUserIE,
-    CSpanIE,
-    AolIE,
-)
-
-
-class TestPlaylists(unittest.TestCase):
-    def assertIsPlaylist(self, info):
-        """Make sure the info has '_type' set to 'playlist'"""
-        self.assertEqual(info['_type'], 'playlist')
-
-    def test_dailymotion_playlist(self):
-        dl = FakeYDL()
-        ie = DailymotionPlaylistIE(dl)
-        result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'SPORT')
-        self.assertTrue(len(result['entries']) > 20)
-
-    def test_dailymotion_user(self):
-        dl = FakeYDL()
-        ie = DailymotionUserIE(dl)
-        result = ie.extract('https://www.dailymotion.com/user/nqtv')
-        self.assertIsPlaylist(result)
-        assertGreaterEqual(self, len(result['entries']), 100)
-        self.assertEqual(result['title'], 'Rémi Gaillard')
-
-    def test_vimeo_channel(self):
-        dl = FakeYDL()
-        ie = VimeoChannelIE(dl)
-        result = ie.extract('http://vimeo.com/channels/tributes')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Vimeo Tributes')
-        self.assertTrue(len(result['entries']) > 24)
-
-    def test_vimeo_user(self):
-        dl = FakeYDL()
-        ie = VimeoUserIE(dl)
-        result = ie.extract('http://vimeo.com/nkistudio/videos')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Nki')
-        self.assertTrue(len(result['entries']) > 65)
-
-    def test_vimeo_album(self):
-        dl = FakeYDL()
-        ie = VimeoAlbumIE(dl)
-        result = ie.extract('http://vimeo.com/album/2632481')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Staff Favorites: November 2013')
-        self.assertTrue(len(result['entries']) > 12)
-
-    def test_vimeo_groups(self):
-        dl = FakeYDL()
-        ie = VimeoGroupsIE(dl)
-        result = ie.extract('http://vimeo.com/groups/rolexawards')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Rolex Awards for Enterprise')
-        self.assertTrue(len(result['entries']) > 72)
-
-    def test_vine_user(self):
-        dl = FakeYDL()
-        ie = VineUserIE(dl)
-        result = ie.extract('https://vine.co/Visa')
-        self.assertIsPlaylist(result)
-        assertGreaterEqual(self, len(result['entries']), 47)
-
-    def test_ustream_channel(self):
-        dl = FakeYDL()
-        ie = UstreamChannelIE(dl)
-        result = ie.extract('http://www.ustream.tv/channel/channeljapan')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '10874166')
-        assertGreaterEqual(self, len(result['entries']), 54)
-
-    def test_soundcloud_set(self):
-        dl = FakeYDL()
-        ie = SoundcloudSetIE(dl)
-        result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'The Royal Concept EP')
-        assertGreaterEqual(self, len(result['entries']), 6)
-
-    def test_soundcloud_user(self):
-        dl = FakeYDL()
-        ie = SoundcloudUserIE(dl)
-        result = ie.extract('https://soundcloud.com/the-concept-band')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '9615865')
-        assertGreaterEqual(self, len(result['entries']), 12)
-
-    def test_soundcloud_likes(self):
-        dl = FakeYDL()
-        ie = SoundcloudUserIE(dl)
-        result = ie.extract('https://soundcloud.com/the-concept-band/likes')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '9615865')
-        assertGreaterEqual(self, len(result['entries']), 1)
-
-    def test_soundcloud_playlist(self):
-        dl = FakeYDL()
-        ie = SoundcloudPlaylistIE(dl)
-        result = ie.extract('http://api.soundcloud.com/playlists/4110309')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '4110309')
-        self.assertEqual(result['title'], 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]')
-        assertRegexpMatches(
-            self, result['description'], r'.*?TILT Brass - Bowery Poetry Club')
-        self.assertEqual(len(result['entries']), 6)
-
-    def test_livestream_event(self):
-        dl = FakeYDL()
-        ie = LivestreamIE(dl)
-        result = ie.extract('http://new.livestream.com/tedx/cityenglish')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'TEDCity2.0 (English)')
-        assertGreaterEqual(self, len(result['entries']), 4)
-
-    def test_livestreamoriginal_folder(self):
-        dl = FakeYDL()
-        ie = LivestreamOriginalIE(dl)
-        result = ie.extract('https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'a07bf706-d0e4-4e75-a747-b021d84f2fd3')
-        assertGreaterEqual(self, len(result['entries']), 28)
-
-    def test_nhl_videocenter(self):
-        dl = FakeYDL()
-        ie = NHLVideocenterIE(dl)
-        result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '999')
-        self.assertEqual(result['title'], 'Highlights')
-        self.assertEqual(len(result['entries']), 12)
-
-    def test_bambuser_channel(self):
-        dl = FakeYDL()
-        ie = BambuserChannelIE(dl)
-        result = ie.extract('http://bambuser.com/channel/pixelversity')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'pixelversity')
-        assertGreaterEqual(self, len(result['entries']), 60)
-
-    def test_bandcamp_album(self):
-        dl = FakeYDL()
-        ie = BandcampAlbumIE(dl)
-        result = ie.extract('http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Hierophany of the Open Grave')
-        assertGreaterEqual(self, len(result['entries']), 9)
-        
-    def test_smotri_community(self):
-        dl = FakeYDL()
-        ie = SmotriCommunityIE(dl)
-        result = ie.extract('http://smotri.com/community/video/kommuna')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'kommuna')
-        self.assertEqual(result['title'], 'КПРФ')
-        assertGreaterEqual(self, len(result['entries']), 4)
-        
-    def test_smotri_user(self):
-        dl = FakeYDL()
-        ie = SmotriUserIE(dl)
-        result = ie.extract('http://smotri.com/user/inspector')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'inspector')
-        self.assertEqual(result['title'], 'Inspector')
-        assertGreaterEqual(self, len(result['entries']), 9)
-
-    def test_AcademicEarthCourse(self):
-        dl = FakeYDL()
-        ie = AcademicEarthCourseIE(dl)
-        result = ie.extract('http://academicearth.org/playlists/laws-of-nature/')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'laws-of-nature')
-        self.assertEqual(result['title'], 'Laws of Nature')
-        self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
-        self.assertEqual(len(result['entries']), 4)
-        
-    def test_ivi_compilation(self):
-        dl = FakeYDL()
-        ie = IviCompilationIE(dl)
-        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'dvoe_iz_lartsa')
-        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008)')
-        assertGreaterEqual(self, len(result['entries']), 24)
-
-    def test_ivi_compilation_season(self):
-        dl = FakeYDL()
-        ie = IviCompilationIE(dl)
-        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa/season1')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'dvoe_iz_lartsa/season1')
-        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008) 1 сезон')
-        assertGreaterEqual(self, len(result['entries']), 12)
-        
-    def test_imdb_list(self):
-        dl = FakeYDL()
-        ie = ImdbListIE(dl)
-        result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'JFs9NWw6XI0')
-        self.assertEqual(result['title'], 'March 23, 2012 Releases')
-        self.assertEqual(len(result['entries']), 7)
-
-    def test_khanacademy_topic(self):
-        dl = FakeYDL()
-        ie = KhanAcademyIE(dl)
-        result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'cryptography')
-        self.assertEqual(result['title'], 'Journey into cryptography')
-        self.assertEqual(result['description'], 'How have humans protected their secret messages through history? What has changed today?')
-        assertGreaterEqual(self, len(result['entries']), 3)
-
-    def test_EveryonesMixtape(self):
-        dl = FakeYDL()
-        ie = EveryonesMixtapeIE(dl)
-        result = ie.extract('http://everyonesmixtape.com/#/mix/m7m0jJAbMQi')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'm7m0jJAbMQi')
-        self.assertEqual(result['title'], 'Driving')
-        self.assertEqual(len(result['entries']), 24)
-        
-    def test_rutube_channel(self):
-        dl = FakeYDL()
-        ie = RutubeChannelIE(dl)
-        result = ie.extract('http://rutube.ru/tags/video/1800/')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '1800')
-        assertGreaterEqual(self, len(result['entries']), 68)
-
-    def test_rutube_person(self):
-        dl = FakeYDL()
-        ie = RutubePersonIE(dl)
-        result = ie.extract('http://rutube.ru/video/person/313878/')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '313878')
-        assertGreaterEqual(self, len(result['entries']), 37)
-
-    def test_multiple_brightcove_videos(self):
-        # https://github.com/rg3/youtube-dl/issues/2283
-        dl = FakeYDL()
-        ie = GenericIE(dl)
-        result = ie.extract('http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'always-never-nuclear-command-and-control')
-        self.assertEqual(result['title'], 'Always/Never: A Little-Seen Movie About Nuclear Command and Control : The New Yorker')
-        self.assertEqual(len(result['entries']), 3)
-
-    def test_GoogleSearch(self):
-        dl = FakeYDL()
-        ie = GoogleSearchIE(dl)
-        result = ie.extract('gvsearch15:python language')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'python language')
-        self.assertEqual(result['title'], 'python language')
-        self.assertEqual(len(result['entries']), 15)
-
-    def test_generic_rss_feed(self):
-        dl = FakeYDL()
-        ie = GenericIE(dl)
-        result = ie.extract('http://phihag.de/2014/youtube-dl/rss.xml')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'http://phihag.de/2014/youtube-dl/rss.xml')
-        self.assertEqual(result['title'], 'Zero Punctuation')
-        self.assertTrue(len(result['entries']) > 10)
-
-    def test_ted_playlist(self):
-        dl = FakeYDL()
-        ie = TEDIE(dl)
-        result = ie.extract('http://www.ted.com/playlists/who_are_the_hackers')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '10')
-        self.assertEqual(result['title'], 'Who are the hackers?')
-        assertGreaterEqual(self, len(result['entries']), 6)
-
-    def test_toypics_user(self):
-        dl = FakeYDL()
-        ie = ToypicsUserIE(dl)
-        result = ie.extract('http://videos.toypics.net/Mikey')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'Mikey')
-        assertGreaterEqual(self, len(result['entries']), 17)
-
-    def test_xtube_user(self):
-        dl = FakeYDL()
-        ie = XTubeUserIE(dl)
-        result = ie.extract('http://www.xtube.com/community/profile.php?user=greenshowers')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'greenshowers')
-        assertGreaterEqual(self, len(result['entries']), 155)
-
-    def test_InstagramUser(self):
-        dl = FakeYDL()
-        ie = InstagramUserIE(dl)
-        result = ie.extract('http://instagram.com/porsche')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'porsche')
-        assertGreaterEqual(self, len(result['entries']), 2)
-        test_video = next(
-            e for e in result['entries']
-            if e['id'] == '614605558512799803_462752227')
-        dl.add_default_extra_info(test_video, ie, '(irrelevant URL)')
-        dl.process_video_result(test_video, download=False)
-        EXPECTED = {
-            'id': '614605558512799803_462752227',
-            'ext': 'mp4',
-            'title': '#Porsche Intelligent Performance.',
-            'thumbnail': 're:^https?://.*\.jpg',
-            'uploader': 'Porsche',
-            'uploader_id': 'porsche',
-            'timestamp': 1387486713,
-            'upload_date': '20131219',
-        }
-        expect_info_dict(self, EXPECTED, test_video)
-
-    def test_CSpan_playlist(self):
-        dl = FakeYDL()
-        ie = CSpanIE(dl)
-        result = ie.extract(
-            'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '342759')
-        self.assertEqual(
-            result['title'], 'General Motors Ignition Switch Recall')
-        whole_duration = sum(e['duration'] for e in result['entries'])
-        self.assertEqual(whole_duration, 14855)
-
-    def test_aol_playlist(self):
-        dl = FakeYDL()
-        ie = AolIE(dl)
-        result = ie.extract(
-            'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], '152147')
-        self.assertEqual(
-            result['title'], 'Brace Yourself - Today\'s Weirdest News')
-        assertGreaterEqual(self, len(result['entries']), 10)
-
-    def test_TeacherTubeUser(self):
-        dl = FakeYDL()
-        ie = TeacherTubeUserIE(dl)
-        result = ie.extract('http://www.teachertube.com/user/profile/rbhagwati2')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'rbhagwati2')
-        assertGreaterEqual(self, len(result['entries']), 179)
-
-if __name__ == '__main__':
-    unittest.main()

test/test_subtitles.py

@@ -15,6 +15,7 @@ from youtube_dl.extractor import (
     DailymotionIE,
     TEDIE,
     VimeoIE,
+    WallaIE,
 )
 
 
@@ -279,5 +280,32 @@ class TestVimeoSubtitles(BaseTestSubtitles):
             self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
 
+class TestWallaSubtitles(BaseTestSubtitles):
+    url = 'http://vod.walla.co.il/movie/2705958/the-yes-men'
+    IE = WallaIE
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_allsubtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['heb']))
+        self.assertEqual(md5(subtitles['heb']), 'e758c5d7cb982f6bef14f377ec7a3920')
+
+    def test_nosubtitles(self):
+        self.DL.expect_warning(u'video doesn\'t have subtitles')
+        self.url = 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles), 0)
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -1,6 +1,8 @@
 #!/usr/bin/env python
 # coding: utf-8
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
@@ -13,7 +15,6 @@ import io
 import json
 import xml.etree.ElementTree
 
-#from youtube_dl.utils import htmlentity_transform
 from youtube_dl.utils import (
     DateRange,
     encodeFilename,
@@ -21,7 +22,8 @@ from youtube_dl.utils import (
     fix_xml_ampersands,
     get_meta_content,
     orderedSet,
-    PagedList,
+    OnDemandPagedList,
+    InAdvancePagedList,
     parse_duration,
     read_batch_urls,
     sanitize_filename,
@@ -39,13 +41,12 @@ from youtube_dl.utils import (
     parse_iso8601,
     strip_jsonp,
     uppercase_escape,
+    limit_length,
+    escape_rfc3986,
+    escape_url,
+    js_to_json,
 )
 
-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):
@@ -67,9 +68,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('this - that', sanitize_filename('this: that'))
 
         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
-        aumlaut = _compat_str('\xe4')
+        aumlaut = 'ä'
         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
-        tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
+        tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
         self.assertEqual(sanitize_filename(tests), tests)
 
         forbidden = '"\0\\/'
@@ -91,9 +92,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 
-        tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
+        tests = '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
+        self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 
         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
         for fc in forbidden:
@@ -101,8 +102,8 @@ class TestUtil(unittest.TestCase):
                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 
         # Handle a common case more neatly
-        self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
-        self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
+        self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
+        self.assertEqual(sanitize_filename('\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) != '')
@@ -120,7 +121,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 
     def test_unescape_html(self):
-        self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
+        self.assertEqual(unescapeHTML('%20;'), '%20;')
+        self.assertEqual(
+            unescapeHTML('&eacute;'), 'é')
         
     def test_daterange(self):
         _20century = DateRange("19000101","20000101")
@@ -136,9 +139,10 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
+        self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
 
     def test_find_xpath_attr(self):
-        testxml = u'''<root>
+        testxml = '''<root>
             <node/>
             <node x="a"/>
             <node x="a" y="c" />
@@ -151,18 +155,18 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 
     def test_meta_parser(self):
-        testhtml = u'''
+        testhtml = '''
         <head>
             <meta name="description" content="foo &amp; bar">
             <meta content='Plato' name='author'/>
         </head>
         '''
         get_meta = lambda name: get_meta_content(name, testhtml)
-        self.assertEqual(get_meta('description'), u'foo & bar')
+        self.assertEqual(get_meta('description'), 'foo & bar')
         self.assertEqual(get_meta('author'), 'Plato')
 
     def test_xpath_with_ns(self):
-        testxml = u'''<root xmlns:media="http://example.com/">
+        testxml = '''<root xmlns:media="http://example.com/">
             <media:song>
                 <media:author>The Author</media:author>
                 <url>http://server.com/download.mp3</url>
@@ -171,8 +175,8 @@ class TestUtil(unittest.TestCase):
         doc = xml.etree.ElementTree.fromstring(testxml)
         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
         self.assertTrue(find('media:song') is not None)
-        self.assertEqual(find('media:song/media:author').text, u'The Author')
-        self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
+        self.assertEqual(find('media:song/media:author').text, 'The Author')
+        self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
     def test_smuggle_url(self):
         data = {u"ö": u"ö", u"abc": [3]}
@@ -187,22 +191,22 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(res_data, None)
 
     def test_shell_quote(self):
-        args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
-        self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
+        args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
+        self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 
     def test_str_to_int(self):
         self.assertEqual(str_to_int('123,456'), 123456)
         self.assertEqual(str_to_int('123.456'), 123456)
 
     def test_url_basename(self):
-        self.assertEqual(url_basename(u'http://foo.de/'), u'')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
+        self.assertEqual(url_basename('http://foo.de/'), '')
+        self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
         self.assertEqual(
-            url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
-            u'trailer.mp4')
+            url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
+            'trailer.mp4')
 
     def test_parse_duration(self):
         self.assertEqual(parse_duration(None), None)
@@ -213,12 +217,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('00:01:01'), 61)
         self.assertEqual(parse_duration('x:y'), None)
         self.assertEqual(parse_duration('3h11m53s'), 11513)
+        self.assertEqual(parse_duration('3h 11m 53s'), 11513)
+        self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
+        self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
         self.assertEqual(parse_duration('62m45s'), 3765)
         self.assertEqual(parse_duration('6m59s'), 419)
         self.assertEqual(parse_duration('49s'), 49)
         self.assertEqual(parse_duration('0h0m0s'), 0)
         self.assertEqual(parse_duration('0m0s'), 0)
         self.assertEqual(parse_duration('0s'), 0)
+        self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -241,10 +249,14 @@ class TestUtil(unittest.TestCase):
                 for i in range(firstid, upto):
                     yield i
 
-            pl = PagedList(get_page, pagesize)
+            pl = OnDemandPagedList(get_page, pagesize)
             got = pl.getslice(*sliceargs)
             self.assertEqual(got, expected)
 
+            iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
+            got = iapl.getslice(*sliceargs)
+            self.assertEqual(got, expected)
+
         testPL(5, 2, (), [0, 1, 2, 3, 4])
         testPL(5, 2, (1,), [1, 2, 3, 4])
         testPL(5, 2, (2,), [2, 3, 4])
@@ -255,16 +267,16 @@ class TestUtil(unittest.TestCase):
         testPL(5, 2, (20, 99), [])
 
     def test_struct_unpack(self):
-        self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
+        self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
 
     def test_read_batch_urls(self):
-        f = io.StringIO(u'''\xef\xbb\xbf foo
+        f = io.StringIO('''\xef\xbb\xbf foo
             bar\r
             baz
             # More after this line\r
             ; or after this
             bam''')
-        self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
+        self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 
     def test_urlencode_postdata(self):
         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
@@ -280,9 +292,68 @@ class TestUtil(unittest.TestCase):
         d = json.loads(stripped)
         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 
-    def test_uppercase_escpae(self):
-        self.assertEqual(uppercase_escape(u'aä'), u'aä')
-        self.assertEqual(uppercase_escape(u'\\U0001d550'), u'𝕐')
+    def test_uppercase_escape(self):
+        self.assertEqual(uppercase_escape('aä'), 'aä')
+        self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
+
+    def test_limit_length(self):
+        self.assertEqual(limit_length(None, 12), None)
+        self.assertEqual(limit_length('foo', 12), 'foo')
+        self.assertTrue(
+            limit_length('foo bar baz asd', 12).startswith('foo bar'))
+        self.assertTrue('...' in limit_length('foo bar baz asd', 12))
+
+    def test_escape_rfc3986(self):
+        reserved = "!*'();:@&=+$,/?#[]"
+        unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
+        self.assertEqual(escape_rfc3986(reserved), reserved)
+        self.assertEqual(escape_rfc3986(unreserved), unreserved)
+        self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
+        self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
+        self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
+        self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
+
+    def test_escape_url(self):
+        self.assertEqual(
+            escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
+            'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
+        )
+        self.assertEqual(
+            escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
+            'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
+        )
+        self.assertEqual(
+            escape_url('http://тест.рф/фрагмент'),
+            'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
+        )
+        self.assertEqual(
+            escape_url('http://тест.рф/абв?абв=абв#абв'),
+            'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
+        )
+        self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
+
+    def test_js_to_json_realworld(self):
+        inp = '''{
+            'clip':{'provider':'pseudo'}
+        }'''
+        self.assertEqual(js_to_json(inp), '''{
+            "clip":{"provider":"pseudo"}
+        }''')
+        json.loads(js_to_json(inp))
+
+        inp = '''{
+            'playlist':[{'controls':{'all':null}}]
+        }'''
+        self.assertEqual(js_to_json(inp), '''{
+            "playlist":[{"controls":{"all":null}}]
+        }''')
+
+    def test_js_to_json_edgecases(self):
+        on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
+        self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
+
+        on = js_to_json('{"abc": true}')
+        self.assertEqual(json.loads(on), {'abc': True})
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -10,7 +10,6 @@ from test.helper import FakeYDL
 
 
 from youtube_dl.extractor import (
-    YoutubeUserIE,
     YoutubePlaylistIE,
     YoutubeIE,
     YoutubeChannelIE,
@@ -25,15 +24,6 @@ class TestYoutubeLists(unittest.TestCase):
         """Make sure the info has '_type' set to 'playlist'"""
         self.assertEqual(info['_type'], 'playlist')
 
-    def test_youtube_playlist(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'ytdl test PL')
-        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
-        self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
-
     def test_youtube_playlist_noplaylist(self):
         dl = FakeYDL()
         dl.params['noplaylist'] = True
@@ -41,36 +31,7 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertEqual(result['_type'], 'url')
         self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
-
-    def test_issue_673(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('PLBB231211A4F62143')
-        self.assertTrue(len(result['entries']) > 25)
-
-    def test_youtube_playlist_long(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
-        self.assertIsPlaylist(result)
-        self.assertTrue(len(result['entries']) >= 799)
-
-    def test_youtube_playlist_with_deleted(self):
-        #651
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
-        self.assertFalse('pElCt5oNDuI' in ytie_results)
-        self.assertFalse('KdPEApIVdWM' in ytie_results)
-        
-    def test_youtube_playlist_empty(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')
-        self.assertIsPlaylist(result)
-        self.assertEqual(len(result['entries']), 0)
-
+    
     def test_youtube_course(self):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
@@ -81,34 +42,6 @@ class TestYoutubeLists(unittest.TestCase):
         self.assertEqual(len(entries), 25)
         self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
 
-    def test_youtube_channel(self):
-        dl = FakeYDL()
-        ie = YoutubeChannelIE(dl)
-        #test paginated channel
-        result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')
-        self.assertTrue(len(result['entries']) > 90)
-        #test autogenerated channel
-        result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
-        self.assertTrue(len(result['entries']) >= 18)
-
-    def test_youtube_user(self):
-        dl = FakeYDL()
-        ie = YoutubeUserIE(dl)
-        result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')
-        self.assertTrue(len(result['entries']) >= 320)
-
-    def test_youtube_safe_search(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')
-        self.assertEqual(len(result['entries']), 2)
-
-    def test_youtube_show(self):
-        dl = FakeYDL()
-        ie = YoutubeShowIE(dl)
-        result = ie.extract('http://www.youtube.com/show/airdisasters')
-        self.assertTrue(len(result) >= 3)
-
     def test_youtube_mix(self):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
@@ -127,21 +60,5 @@ class TestYoutubeLists(unittest.TestCase):
         entries = result['entries']
         self.assertEqual(len(entries), 100)
 
-    def test_youtube_toplist(self):
-        dl = FakeYDL()
-        ie = YoutubeTopListIE(dl)
-        result = ie.extract('yttoplist:music:Trending')
-        entries = result['entries']
-        self.assertTrue(len(entries) >= 5)
-
-    def test_youtube_search_url(self):
-        dl = FakeYDL()
-        ie = YoutubeSearchURLIE(dl)
-        result = ie.extract('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video')
-        entries = result['entries']
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'youtube-dl test video')
-        self.assertTrue(len(entries) >= 5)
-
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -47,18 +47,6 @@ _TESTS = [
         '2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
         'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
     ),
-    (
-        'http://s.ytimg.com/yts/swfbin/player-vfl5vIhK2/watch_as3.swf',
-        'swf',
-        86,
-        'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVWXY\\!"#$%&\'()*+,-./:;<=>?'
-    ),
-    (
-        'http://s.ytimg.com/yts/swfbin/player-vflmDyk47/watch_as3.swf',
-        'swf',
-        'F375F75BF2AFDAAF2666E43868D46816F83F13E81C46.3725A8218E446A0DECD33F79DC282994D6AA92C92C9',
-        '9C29AA6D499282CD97F33DCED0A644E8128A5273.64C18E31F38361864D86834E6662FAADFA2FB57F'
-    ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
         'js',

youtube-dl

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

youtube_dl/YoutubeDL.py

@@ -28,6 +28,7 @@ from .utils import (
     compat_str,
     compat_urllib_error,
     compat_urllib_request,
+    escape_url,
     ContentTooShortError,
     date_from_str,
     DateRange,
@@ -57,6 +58,7 @@ from .utils import (
     YoutubeDLHandler,
     prepend_extension,
 )
+from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
 from .downloader import get_suitable_downloader
 from .postprocessor import FFmpegMergerPP
@@ -133,7 +135,7 @@ class YoutubeDL(object):
     daterange:         A DateRange object, download only if the upload_date is in the range.
     skip_download:     Skip the actual download of the video file
     cachedir:          Location of the cache files in the filesystem.
-                       None to disable filesystem cache.
+                       False to disable filesystem cache.
     noplaylist:        Download single video instead of a playlist if in doubt.
     age_limit:         An integer representing the user's age in years.
                        Unsuitable videos for the given age are skipped.
@@ -162,6 +164,7 @@ class YoutubeDL(object):
     default_search:    Prepend this string if an input url is not valid.
                        'auto' for elaborate guessing
     encoding:          Use this encoding instead of the system-specified.
+    extract_flat:      Do not resolve URLs, return the immediate result.
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:
@@ -171,6 +174,7 @@ class YoutubeDL(object):
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
+    exec_cmd:          Arbitrary command to run after downloading
     """
 
     params = None
@@ -193,6 +197,7 @@ class YoutubeDL(object):
         self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
         self._err_file = sys.stderr
         self.params = params
+        self.cache = Cache(self)
 
         if params.get('bidi_workaround', False):
             try:
@@ -223,11 +228,11 @@ class YoutubeDL(object):
 
         if (sys.version_info >= (3,) and sys.platform != 'win32' and
                 sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
-                and not params['restrictfilenames']):
+                and not params.get('restrictfilenames', False)):
             # On Python 3, the Unicode filesystem API will throw errors (#1474)
             self.report_warning(
                 'Assuming --restrict-filenames since file system encoding '
-                'cannot encode all charactes. '
+                'cannot encode all characters. '
                 'Set the LC_ALL environment variable to fix this.')
             self.params['restrictfilenames'] = True
 
@@ -423,7 +428,7 @@ class YoutubeDL(object):
             autonumber_templ = '%0' + str(autonumber_size) + 'd'
             template_dict['autonumber'] = autonumber_templ % self._num_downloads
             if template_dict.get('playlist_index') is not None:
-                template_dict['playlist_index'] = '%05d' % template_dict['playlist_index']
+                template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index'])
             if template_dict.get('resolution') is None:
                 if template_dict.get('width') and template_dict.get('height'):
                     template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
@@ -479,7 +484,10 @@ class YoutubeDL(object):
                 return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
         age_limit = self.params.get('age_limit')
         if age_limit is not None:
-            if age_limit < info_dict.get('age_limit', 0):
+            actual_age_limit = info_dict.get('age_limit')
+            if actual_age_limit is None:
+                actual_age_limit = 0
+            if age_limit < actual_age_limit:
                 return 'Skipping "' + title + '" because it is age restricted'
         if self.in_download_archive(info_dict):
             return '%s has already been recorded in archive' % video_title
@@ -558,7 +566,12 @@ class YoutubeDL(object):
         Returns the resolved ie_result.
         """
 
-        result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
+        result_type = ie_result.get('_type', 'video')
+
+        if self.params.get('extract_flat', False):
+            if result_type in ('url', 'url_transparent'):
+                return ie_result
+
         if result_type == 'video':
             self.add_extra_info(ie_result, extra_info)
             return self.process_video_result(ie_result, download=download)
@@ -627,6 +640,7 @@ class YoutubeDL(object):
             for i, entry in enumerate(entries, 1):
                 self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries))
                 extra = {
+                    'n_entries': n_entries,
                     'playlist': playlist,
                     'playlist_index': i + playliststart,
                     'extractor': ie_result['extractor'],
@@ -694,7 +708,7 @@ class YoutubeDL(object):
             if video_formats:
                 return video_formats[0]
         else:
-            extensions = ['mp4', 'flv', 'webm', '3gp']
+            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a']
             if format_spec in extensions:
                 filter_f = lambda f: f['ext'] == format_spec
             else:
@@ -795,28 +809,29 @@ class YoutubeDL(object):
         if req_format in ('-1', 'all'):
             formats_to_download = formats
         else:
-            # We can accept formats requested in the format: 34/5/best, we pick
-            # the first that is available, starting from left
-            req_formats = req_format.split('/')
-            for rf in req_formats:
-                if re.match(r'.+?\+.+?', rf) is not None:
-                    # Two formats have been requested like '137+139'
-                    format_1, format_2 = rf.split('+')
-                    formats_info = (self.select_format(format_1, formats),
-                        self.select_format(format_2, formats))
-                    if all(formats_info):
-                        selected_format = {
-                            'requested_formats': formats_info,
-                            'format': rf,
-                            'ext': formats_info[0]['ext'],
-                        }
+            for rfstr in req_format.split(','):
+                # We can accept formats requested in the format: 34/5/best, we pick
+                # the first that is available, starting from left
+                req_formats = rfstr.split('/')
+                for rf in req_formats:
+                    if re.match(r'.+?\+.+?', rf) is not None:
+                        # Two formats have been requested like '137+139'
+                        format_1, format_2 = rf.split('+')
+                        formats_info = (self.select_format(format_1, formats),
+                            self.select_format(format_2, formats))
+                        if all(formats_info):
+                            selected_format = {
+                                'requested_formats': formats_info,
+                                'format': rf,
+                                'ext': formats_info[0]['ext'],
+                            }
+                        else:
+                            selected_format = None
                     else:
-                        selected_format = None
-                else:
-                    selected_format = self.select_format(rf, formats)
-                if selected_format is not None:
-                    formats_to_download = [selected_format]
-                    break
+                        selected_format = self.select_format(rf, formats)
+                    if selected_format is not None:
+                        formats_to_download.append(selected_format)
+                        break
         if not formats_to_download:
             raise ExtractorError('requested format not available',
                                  expected=True)
@@ -1228,6 +1243,26 @@ class YoutubeDL(object):
 
     def urlopen(self, req):
         """ Start an HTTP download """
+
+        # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not
+        # always respected by websites, some tend to give out URLs with non percent-encoded
+        # non-ASCII characters (see telemb.py, ard.py [#3412])
+        # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
+        # To work around aforementioned issue we will replace request's original URL with
+        # percent-encoded one
+        req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str)
+        url = req if req_is_string else req.get_full_url()
+        url_escaped = escape_url(url)
+
+        # Substitute URL if any change after escaping
+        if url != url_escaped:
+            if req_is_string:
+                req = url_escaped
+            else:
+                req = compat_urllib_request.Request(
+                    url_escaped, data=req.data, headers=req.headers,
+                    origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
+
         return self._opener.open(req, timeout=self._socket_timeout)
 
     def print_debug_header(self):

youtube_dl/__init__.py

@@ -66,29 +66,40 @@ __authors__  = (
     'Naglis Jonaitis',
     'Charles Chen',
     'Hassaan Ali',
+    'Dobrosław Żybort',
+    'David Fabijan',
+    'Sebastian Haas',
+    'Alexander Kirk',
+    'Erik Johnson',
+    'Keith Beckman',
+    'Ole Ernst',
+    'Aaron McDaniel (mcd1992)',
+    'Magnus Kolstad',
+    'Hari Padmanaban',
+    'Carlos Ramos',
+    '5moufl',
+    'lenaten',
 )
 
 __license__ = 'Public Domain'
 
 import codecs
 import io
-import optparse
 import os
 import random
-import shlex
-import shutil
 import sys
 
 
+from .options import (
+    parseOpts,
+)
 from .utils import (
     compat_getpass,
     compat_print,
     DateRange,
     DEFAULT_OUTTMPL,
     decodeOption,
-    get_term_width,
     DownloadError,
-    get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,
@@ -102,7 +113,6 @@ from .downloader import (
     FileDownloader,
 )
 from .extractor import gen_extractors
-from .version import __version__
 from .YoutubeDL import YoutubeDL
 from .postprocessor import (
     AtomicParsleyPP,
@@ -112,474 +122,10 @@ from .postprocessor import (
     FFmpegExtractAudioPP,
     FFmpegEmbedSubtitlePP,
     XAttrMetadataPP,
+    ExecAfterDownloadPP,
 )
 
 
-def parseOpts(overrideArguments=None):
-    def _readOptions(filename_bytes, default=[]):
-        try:
-            optionf = open(filename_bytes)
-        except IOError:
-            return default  # 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 _readUserConf():
-        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
-        if xdg_config_home:
-            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
-        else:
-            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
-        userConf = _readOptions(userConfFile, None)
-
-        if userConf is None:
-            appdata_dir = os.environ.get('appdata')
-            if appdata_dir:
-                userConf = _readOptions(
-                    os.path.join(appdata_dir, 'youtube-dl', 'config'),
-                    default=None)
-                if userConf is None:
-                    userConf = _readOptions(
-                        os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
-                        default=None)
-
-        if userConf is None:
-            userConf = _readOptions(
-                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
-                default=None)
-        if userConf is None:
-            userConf = _readOptions(
-                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
-                default=None)
-
-        if userConf is None:
-            userConf = []
-
-        return userConf
-
-    def _format_option_string(option):
-        ''' ('-o', '--option') -> -o, --format METAVAR'''
-
-        opts = []
-
-        if option._short_opts:
-            opts.append(option._short_opts[0])
-        if option._long_opts:
-            opts.append(option._long_opts[0])
-        if len(opts) > 1:
-            opts.insert(1, ', ')
-
-        if option.takes_value(): opts.append(' %s' % option.metavar)
-
-        return "".join(opts)
-
-    def _comma_separated_values_options_callback(option, opt_str, value, parser):
-        setattr(parser.values, option.dest, value.split(','))
-
-    def _hide_login_info(opts):
-        opts = list(opts)
-        for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
-            try:
-                i = opts.index(private_opt)
-                opts[i+1] = '<PRIVATE>'
-            except ValueError:
-                pass
-        return opts
-
-    max_width = 80
-    max_help_position = 80
-
-    # No need to wrap help messages if we're on a wide console
-    columns = get_term_width()
-    if columns: max_width = columns
-
-    fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
-    fmt.format_option_strings = _format_option_string
-
-    kw = {
-        'version'   : __version__,
-        'formatter' : fmt,
-        'usage' : '%prog [options] url [url...]',
-        'conflict_handler' : 'resolve',
-    }
-
-    parser = optparse.OptionParser(**kw)
-
-    # option groups
-    general        = optparse.OptionGroup(parser, 'General Options')
-    selection      = optparse.OptionGroup(parser, 'Video Selection')
-    authentication = optparse.OptionGroup(parser, 'Authentication Options')
-    video_format   = optparse.OptionGroup(parser, 'Video Format Options')
-    subtitles      = optparse.OptionGroup(parser, 'Subtitle Options')
-    downloader     = optparse.OptionGroup(parser, 'Download Options')
-    postproc       = optparse.OptionGroup(parser, 'Post-processing Options')
-    filesystem     = optparse.OptionGroup(parser, 'Filesystem Options')
-    workarounds    = optparse.OptionGroup(parser, 'Workarounds')
-    verbosity      = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
-
-    general.add_option('-h', '--help',
-            action='help', help='print this help text and exit')
-    general.add_option('-v', '--version',
-            action='version', help='print program version and exit')
-    general.add_option('-U', '--update',
-            action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
-    general.add_option('-i', '--ignore-errors',
-            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False)
-    general.add_option('--abort-on-error',
-            action='store_false', dest='ignoreerrors',
-            help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')
-    general.add_option('--dump-user-agent',
-            action='store_true', dest='dump_user_agent',
-            help='display the current browser identification', default=False)
-    general.add_option('--list-extractors',
-            action='store_true', dest='list_extractors',
-            help='List all supported extractors and the URLs they would handle', default=False)
-    general.add_option('--extractor-descriptions',
-            action='store_true', dest='list_extractor_descriptions',
-            help='Output descriptions of all supported extractors', default=False)
-    general.add_option(
-        '--proxy', dest='proxy', default=None, metavar='URL',
-        help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
-    general.add_option(
-        '--socket-timeout', dest='socket_timeout',
-        type=float, default=None, help=u'Time to wait before giving up, in seconds')
-    general.add_option(
-        '--default-search',
-        dest='default_search', metavar='PREFIX',
-        help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.')
-    general.add_option(
-        '--ignore-config',
-        action='store_true',
-        help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
-
-    selection.add_option(
-        '--playlist-start',
-        dest='playliststart', metavar='NUMBER', default=1, type=int,
-        help='playlist video to start at (default is %default)')
-    selection.add_option(
-        '--playlist-end',
-        dest='playlistend', metavar='NUMBER', default=None, type=int,
-        help='playlist video to end at (default is last)')
-    selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
-    selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
-    selection.add_option('--max-downloads', metavar='NUMBER',
-                         dest='max_downloads', type=int, default=None,
-                         help='Abort after downloading NUMBER files')
-    selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None)
-    selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None)
-    selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
-    selection.add_option(
-        '--datebefore', metavar='DATE', dest='datebefore', default=None,
-        help='download only videos uploaded on or before this date (i.e. inclusive)')
-    selection.add_option(
-        '--dateafter', metavar='DATE', dest='dateafter', default=None,
-        help='download only videos uploaded on or after this date (i.e. inclusive)')
-    selection.add_option(
-        '--min-views', metavar='COUNT', dest='min_views',
-        default=None, type=int,
-        help="Do not download any videos with less than COUNT views",)
-    selection.add_option(
-        '--max-views', metavar='COUNT', dest='max_views',
-        default=None, type=int,
-        help="Do not download any videos with more than COUNT views",)
-    selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False)
-    selection.add_option('--age-limit', metavar='YEARS', dest='age_limit',
-                         help='download only videos suitable for the given age',
-                         default=None, type=int)
-    selection.add_option('--download-archive', metavar='FILE',
-                         dest='download_archive',
-                         help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.')
-    selection.add_option(
-        '--include-ads', dest='include_ads',
-        action='store_true',
-        help='Download advertisements as well (experimental)')
-    selection.add_option(
-        '--youtube-include-dash-manifest', action='store_true',
-        dest='youtube_include_dash_manifest', default=False,
-        help='Try to download the DASH manifest on YouTube videos (experimental)')
-
-    authentication.add_option('-u', '--username',
-            dest='username', metavar='USERNAME', help='account username')
-    authentication.add_option('-p', '--password',
-            dest='password', metavar='PASSWORD', help='account password')
-    authentication.add_option('-n', '--netrc',
-            action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
-    authentication.add_option('--video-password',
-            dest='videopassword', metavar='PASSWORD', help='video password (vimeo, smotri)')
-
-
-    video_format.add_option('-f', '--format',
-            action='store', dest='format', metavar='FORMAT', default=None,
-            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality.')
-    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')
-
-    subtitles.add_option('--write-sub', '--write-srt',
-            action='store_true', dest='writesubtitles',
-            help='write subtitle file', default=False)
-    subtitles.add_option('--write-auto-sub', '--write-automatic-sub',
-            action='store_true', dest='writeautomaticsub',
-            help='write automatic subtitle file (youtube only)', default=False)
-    subtitles.add_option('--all-subs',
-            action='store_true', dest='allsubtitles',
-            help='downloads all the available subtitles of the video', default=False)
-    subtitles.add_option('--list-subs',
-            action='store_true', dest='listsubtitles',
-            help='lists all available subtitles for the video', default=False)
-    subtitles.add_option('--sub-format',
-            action='store', dest='subtitlesformat', metavar='FORMAT',
-            help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
-    subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
-            action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
-            default=[], callback=_comma_separated_values_options_callback,
-            help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
-
-    downloader.add_option('-r', '--rate-limit',
-            dest='ratelimit', metavar='LIMIT', help='maximum download rate in bytes per second (e.g. 50K or 4.2M)')
-    downloader.add_option('-R', '--retries',
-            dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
-    downloader.add_option('--buffer-size',
-            dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16K) (default is %default)', default="1024")
-    downloader.add_option('--no-resize-buffer',
-            action='store_true', dest='noresizebuffer',
-            help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
-    downloader.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
-
-    workarounds.add_option(
-        '--encoding', dest='encoding', metavar='ENCODING',
-        help='Force the specified encoding (experimental)')
-    workarounds.add_option(
-        '--no-check-certificate', action='store_true',
-        dest='no_check_certificate', default=False,
-        help='Suppress HTTPS certificate validation.')
-    workarounds.add_option(
-        '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure',
-        help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
-    workarounds.add_option(
-        '--user-agent', metavar='UA',
-        dest='user_agent', help='specify a custom user agent')
-    workarounds.add_option(
-        '--referer', metavar='REF',
-        dest='referer', default=None,
-        help='specify a custom referer, use if the video access is restricted to one domain',
-    )
-    workarounds.add_option(
-        '--add-header', metavar='FIELD:VALUE',
-        dest='headers', action='append',
-        help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times',
-    )
-    workarounds.add_option(
-        '--bidi-workaround', dest='bidi_workaround', action='store_true',
-        help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
-
-    verbosity.add_option('-q', '--quiet',
-            action='store_true', dest='quiet', help='activates quiet mode', default=False)
-    verbosity.add_option(
-        '--no-warnings',
-        dest='no_warnings', action='store_true', default=False,
-        help='Ignore warnings')
-    verbosity.add_option('-s', '--simulate',
-            action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
-    verbosity.add_option('--skip-download',
-            action='store_true', dest='skip_download', help='do not download the video', default=False)
-    verbosity.add_option('-g', '--get-url',
-            action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
-    verbosity.add_option('-e', '--get-title',
-            action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
-    verbosity.add_option('--get-id',
-            action='store_true', dest='getid', help='simulate, quiet but print id', default=False)
-    verbosity.add_option('--get-thumbnail',
-            action='store_true', dest='getthumbnail',
-            help='simulate, quiet but print thumbnail URL', default=False)
-    verbosity.add_option('--get-description',
-            action='store_true', dest='getdescription',
-            help='simulate, quiet but print video description', default=False)
-    verbosity.add_option('--get-duration',
-            action='store_true', dest='getduration',
-            help='simulate, quiet but print video length', default=False)
-    verbosity.add_option('--get-filename',
-            action='store_true', dest='getfilename',
-            help='simulate, quiet but print output filename', default=False)
-    verbosity.add_option('--get-format',
-            action='store_true', dest='getformat',
-            help='simulate, quiet but print output format', default=False)
-    verbosity.add_option('-j', '--dump-json',
-            action='store_true', dest='dumpjson',
-            help='simulate, quiet but print JSON information. See --output for a description of available keys.', default=False)
-    verbosity.add_option('--newline',
-            action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
-    verbosity.add_option('--no-progress',
-            action='store_true', dest='noprogress', help='do not print progress bar', default=False)
-    verbosity.add_option('--console-title',
-            action='store_true', dest='consoletitle',
-            help='display progress in console titlebar', default=False)
-    verbosity.add_option('-v', '--verbose',
-            action='store_true', dest='verbose', help='print various debugging information', default=False)
-    verbosity.add_option('--dump-intermediate-pages',
-            action='store_true', dest='dump_intermediate_pages', default=False,
-            help='print downloaded pages to debug problems (very verbose)')
-    verbosity.add_option('--write-pages',
-            action='store_true', dest='write_pages', default=False,
-            help='Write downloaded intermediary pages to files in the current directory to debug problems')
-    verbosity.add_option('--youtube-print-sig-code',
-            action='store_true', dest='youtube_print_sig_code', default=False,
-            help=optparse.SUPPRESS_HELP)
-    verbosity.add_option('--print-traffic',
-            dest='debug_printtraffic', action='store_true', default=False,
-            help='Display sent and read HTTP traffic')
-
-
-    filesystem.add_option('-a', '--batch-file',
-            dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
-    filesystem.add_option('--id',
-            action='store_true', dest='useid', help='use only video ID in file name', default=False)
-    filesystem.add_option('-A', '--auto-number',
-            action='store_true', dest='autonumber',
-            help='number downloaded files starting from 00000', default=False)
-    filesystem.add_option('-o', '--output',
-            dest='outtmpl', metavar='TEMPLATE',
-            help=('output filename template. Use %(title)s to get the title, '
-                  '%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, '
-                  '%(autonumber)s to get an automatically incremented number, '
-                  '%(ext)s for the filename extension, '
-                  '%(format)s for the format description (like "22 - 1280x720" or "HD"), '
-                  '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), '
-                  '%(upload_date)s for the upload date (YYYYMMDD), '
-                  '%(extractor)s for the provider (youtube, metacafe, etc), '
-                  '%(id)s for the video id, %(playlist)s for the playlist the video is in, '
-                  '%(playlist_index)s for the position in the playlist and %% for a literal percent. '
-                  '%(height)s and %(width)s for the width and height of the video format. '
-                  '%(resolution)s for a textual description of the resolution of the video format. '
-                  'Use - to output to stdout. Can also be used to download to a different directory, '
-                  'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
-    filesystem.add_option('--autonumber-size',
-            dest='autonumber_size', metavar='NUMBER',
-            help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
-    filesystem.add_option('--restrict-filenames',
-            action='store_true', dest='restrictfilenames',
-            help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
-    filesystem.add_option('-t', '--title',
-            action='store_true', dest='usetitle', help='[deprecated] use title in file name (default)', default=False)
-    filesystem.add_option('-l', '--literal',
-            action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
-    filesystem.add_option('-w', '--no-overwrites',
-            action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
-    filesystem.add_option('-c', '--continue',
-            action='store_true', dest='continue_dl', help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.', default=True)
-    filesystem.add_option('--no-continue',
-            action='store_false', dest='continue_dl',
-            help='do not resume partially downloaded files (restart from beginning)')
-    filesystem.add_option('--no-part',
-            action='store_true', dest='nopart', help='do not use .part files', default=False)
-    filesystem.add_option('--no-mtime',
-            action='store_false', dest='updatetime',
-            help='do not use the Last-modified header to set the file modification time', default=True)
-    filesystem.add_option('--write-description',
-            action='store_true', dest='writedescription',
-            help='write video description to a .description file', default=False)
-    filesystem.add_option('--write-info-json',
-            action='store_true', dest='writeinfojson',
-            help='write video metadata to a .info.json file', default=False)
-    filesystem.add_option('--write-annotations',
-            action='store_true', dest='writeannotations',
-            help='write video annotations to a .annotation file', default=False)
-    filesystem.add_option('--write-thumbnail',
-            action='store_true', dest='writethumbnail',
-            help='write thumbnail image to disk', default=False)
-    filesystem.add_option('--load-info',
-            dest='load_info_filename', metavar='FILE',
-            help='json file containing the video information (created with the "--write-json" option)')
-    filesystem.add_option('--cookies',
-            dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
-    filesystem.add_option(
-        '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
-        help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
-    filesystem.add_option(
-        '--no-cache-dir', action='store_const', const=None, dest='cachedir',
-        help='Disable filesystem caching')
-    filesystem.add_option(
-        '--rm-cache-dir', action='store_true', dest='rm_cachedir',
-        help='Delete all filesystem cache files')
-
-
-    postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
-            help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
-    postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
-            help='"best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; best by default')
-    postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5',
-            help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
-    postproc.add_option('--recode-video', metavar='FORMAT', dest='recodevideo', default=None,
-            help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)')
-    postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
-            help='keeps the video file on disk after the post-processing; the video is erased by default')
-    postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
-            help='do not overwrite post-processed files; the post-processed files are overwritten by default')
-    postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
-            help='embed subtitles in the video (only for mp4 videos)')
-    postproc.add_option('--embed-thumbnail', action='store_true', dest='embedthumbnail', default=False,
-            help='embed thumbnail in the audio as cover art')
-    postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False,
-            help='write metadata to the video file')
-    postproc.add_option('--xattrs', action='store_true', dest='xattrs', default=False,
-            help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)')
-    postproc.add_option('--prefer-avconv', action='store_false', dest='prefer_ffmpeg',
-        help='Prefer avconv over ffmpeg for running the postprocessors (default)')
-    postproc.add_option('--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg',
-        help='Prefer ffmpeg over avconv for running the postprocessors')
-
-
-    parser.add_option_group(general)
-    parser.add_option_group(selection)
-    parser.add_option_group(downloader)
-    parser.add_option_group(filesystem)
-    parser.add_option_group(verbosity)
-    parser.add_option_group(workarounds)
-    parser.add_option_group(video_format)
-    parser.add_option_group(subtitles)
-    parser.add_option_group(authentication)
-    parser.add_option_group(postproc)
-
-    if overrideArguments is not None:
-        opts, args = parser.parse_args(overrideArguments)
-        if opts.verbose:
-            write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
-    else:
-        commandLineConf = sys.argv[1:]
-        if '--ignore-config' in commandLineConf:
-            systemConf = []
-            userConf = []
-        else:
-            systemConf = _readOptions('/etc/youtube-dl.conf')
-            if '--ignore-config' in systemConf:
-                userConf = []
-            else:
-                userConf = _readUserConf()
-        argv = systemConf + userConf + commandLineConf
-
-        opts, args = parser.parse_args(argv)
-        if opts.verbose:
-            write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
-            write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
-            write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
-
-    return parser, opts, args
-
-
 def _real_main(argv=None):
     # Compatibility fixes for Windows
     if sys.platform == 'win32':
@@ -745,6 +291,7 @@ def _real_main(argv=None):
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
+        'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
         'quiet': (opts.quiet or any_printing),
         'no_warnings': opts.no_warnings,
@@ -821,6 +368,7 @@ def _real_main(argv=None):
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
+        'exec_cmd': opts.exec_cmd,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -844,26 +392,20 @@ def _real_main(argv=None):
                 ydl.add_post_processor(FFmpegAudioFixPP())
             ydl.add_post_processor(AtomicParsleyPP())
 
+
+        # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
+        # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
+        if opts.exec_cmd:
+            ydl.add_post_processor(ExecAfterDownloadPP(
+                verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd))
+
         # Update version
         if opts.update_self:
             update_self(ydl.to_screen, opts.verbose)
 
         # Remove cache dir
         if opts.rm_cachedir:
-            if opts.cachedir is None:
-                ydl.to_screen(u'No cache dir specified (Did you combine --no-cache-dir and --rm-cache-dir?)')
-            else:
-                if ('.cache' not in opts.cachedir) or ('youtube-dl' not in opts.cachedir):
-                    ydl.to_screen(u'Not removing directory %s - this does not look like a cache dir')
-                    retcode = 141
-                else:
-                    ydl.to_screen(
-                        u'Removing cache dir %s .' % opts.cachedir,
-                        skip_eol=True)
-                    if os.path.exists(opts.cachedir):
-                        ydl.to_screen(u'.', skip_eol=True)
-                        shutil.rmtree(opts.cachedir)
-                    ydl.to_screen(u'.')
+            ydl.cache.remove()
 
         # Maybe do nothing
         if (len(all_urls) < 1) and (opts.load_info_filename is None):

youtube_dl/cache.py

@@ -0,0 +1,94 @@
+from __future__ import unicode_literals
+
+import errno
+import io
+import json
+import os
+import re
+import shutil
+import traceback
+
+from .utils import (
+    write_json_file,
+)
+
+
+class Cache(object):
+    def __init__(self, ydl):
+        self._ydl = ydl
+
+    def _get_root_dir(self):
+        res = self._ydl.params.get('cachedir')
+        if res is None:
+            cache_root = os.environ.get('XDG_CACHE_HOME', '~/.cache')
+            res = os.path.join(cache_root, 'youtube-dl')
+        return os.path.expanduser(res)
+
+    def _get_cache_fn(self, section, key, dtype):
+        assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \
+            'invalid section %r' % section
+        assert re.match(r'^[a-zA-Z0-9_.-]+$', key), 'invalid key %r' % key
+        return os.path.join(
+            self._get_root_dir(), section, '%s.%s' % (key, dtype))
+
+    @property
+    def enabled(self):
+        return self._ydl.params.get('cachedir') is not False
+
+    def store(self, section, key, data, dtype='json'):
+        assert dtype in ('json',)
+
+        if not self.enabled:
+            return
+
+        fn = self._get_cache_fn(section, key, dtype)
+        try:
+            try:
+                os.makedirs(os.path.dirname(fn))
+            except OSError as ose:
+                if ose.errno != errno.EEXIST:
+                    raise
+            write_json_file(data, fn)
+        except Exception:
+            tb = traceback.format_exc()
+            self._ydl.report_warning(
+                'Writing cache to %r failed: %s' % (fn, tb))
+
+    def load(self, section, key, dtype='json', default=None):
+        assert dtype in ('json',)
+
+        if not self.enabled:
+            return default
+
+        cache_fn = self._get_cache_fn(section, key, dtype)
+        try:
+            try:
+                with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
+                    return json.load(cachef)
+            except ValueError:
+                try:
+                    file_size = os.path.getsize(cache_fn)
+                except (OSError, IOError) as oe:
+                    file_size = str(oe)
+                self._ydl.report_warning(
+                    'Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
+        except IOError:
+            pass  # No cache available
+
+        return default
+
+    def remove(self):
+        if not self.enabled:
+            self._ydl.to_screen('Cache is disabled (Did you combine --no-cache-dir and --rm-cache-dir?)')
+            return
+
+        cachedir = self._get_root_dir()
+        if not any((term in cachedir) for term in ('cache', 'tmp')):
+            raise Exception('Not removing directory %s - this does not look like a cache dir' % cachedir)
+
+        self._ydl.to_screen(
+            'Removing cache dir %s .' % cachedir, skip_eol=True)
+        if os.path.exists(cachedir):
+            self._ydl.to_screen('.', skip_eol=True)
+            shutil.rmtree(cachedir)
+        self._ydl.to_screen('.')

youtube_dl/downloader/__init__.py

@@ -2,6 +2,7 @@ from __future__ import unicode_literals
 
 from .common import FileDownloader
 from .hls import HlsFD
+from .hls import NativeHlsFD
 from .http import HttpFD
 from .mplayer import MplayerFD
 from .rtmp import RtmpFD
@@ -19,6 +20,8 @@ def get_suitable_downloader(info_dict):
 
     if url.startswith('rtmp'):
         return RtmpFD
+    if protocol == 'm3u8_native':
+        return NativeHlsFD
     if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
         return HlsFD
     if url.startswith('mms') or url.startswith('rtsp'):

youtube_dl/downloader/common.py

@@ -42,6 +42,7 @@ class FileDownloader(object):
     Subclasses of this one must re-define the real_download method.
     """
 
+    _TEST_FILE_SIZE = 10241
     params = None
 
     def __init__(self, ydl, params):
@@ -292,7 +293,7 @@ class FileDownloader(object):
 
     def real_download(self, filename, info_dict):
         """Real download process. Redefine in subclasses."""
-        raise NotImplementedError(u'This method must be implemented by sublcasses')
+        raise NotImplementedError(u'This method must be implemented by subclasses')
 
     def _hook_progress(self, status):
         for ph in self._progress_hooks:

youtube_dl/downloader/f4m.py

@@ -16,6 +16,7 @@ from ..utils import (
     format_bytes,
     encodeFilename,
     sanitize_open,
+    xpath_text,
 )
 
 
@@ -251,6 +252,8 @@ class F4mFD(FileDownloader):
             # We only download the first fragment
             fragments_list = fragments_list[:1]
         total_frags = len(fragments_list)
+        # For some akamai manifests we'll need to add a query to the fragment url
+        akamai_pv = xpath_text(doc, _add_ns('pv-2.0'))
 
         tmpfilename = self.temp_name(filename)
         (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
@@ -290,6 +293,8 @@ class F4mFD(FileDownloader):
         for (seg_i, frag_i) in fragments_list:
             name = 'Seg%d-Frag%d' % (seg_i, frag_i)
             url = base_url + name
+            if akamai_pv:
+                url += '?' + akamai_pv.strip(';')
             frag_filename = '%s-%s' % (tmpfilename, name)
             success = http_dl.download(frag_filename, {'url': url})
             if not success:

youtube_dl/downloader/hls.py

@@ -1,8 +1,14 @@
+from __future__ import unicode_literals
+
 import os
+import re
 import subprocess
 
 from .common import FileDownloader
 from ..utils import (
+    compat_urlparse,
+    compat_urllib_request,
+    check_executable,
     encodeFilename,
 )
 
@@ -19,13 +25,11 @@ class HlsFD(FileDownloader):
             encodeFilename(tmpfilename, for_subprocess=True)]
 
         for program in ['avconv', 'ffmpeg']:
-            try:
-                subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+            if check_executable(program, ['-version']):
                 break
-            except (OSError, IOError):
-                pass
         else:
             self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            return False
         cmd = [program] + args
 
         retval = subprocess.call(cmd)
@@ -42,5 +46,59 @@ class HlsFD(FileDownloader):
             return True
         else:
             self.to_stderr(u"\n")
-            self.report_error(u'ffmpeg exited with code %d' % retval)
+            self.report_error(u'%s exited with code %d' % (program, retval))
             return False
+
+
+class NativeHlsFD(FileDownloader):
+    """ A more limited implementation that does not require ffmpeg """
+
+    def real_download(self, filename, info_dict):
+        url = info_dict['url']
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        self.to_screen(
+            '[hlsnative] %s: Downloading m3u8 manifest' % info_dict['id'])
+        data = self.ydl.urlopen(url).read()
+        s = data.decode('utf-8', 'ignore')
+        segment_urls = []
+        for line in s.splitlines():
+            line = line.strip()
+            if line and not line.startswith('#'):
+                segment_url = (
+                    line
+                    if re.match(r'^https?://', line)
+                    else compat_urlparse.urljoin(url, line))
+                segment_urls.append(segment_url)
+
+        is_test = self.params.get('test', False)
+        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
+        byte_counter = 0
+        with open(tmpfilename, 'wb') as outf:
+            for i, segurl in enumerate(segment_urls):
+                self.to_screen(
+                    '[hlsnative] %s: Downloading segment %d / %d' %
+                    (info_dict['id'], i + 1, len(segment_urls)))
+                seg_req = compat_urllib_request.Request(segurl)
+                if remaining_bytes is not None:
+                    seg_req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
+
+                segment = self.ydl.urlopen(seg_req).read()
+                if remaining_bytes is not None:
+                    segment = segment[:remaining_bytes]
+                    remaining_bytes -= len(segment)
+                outf.write(segment)
+                byte_counter += len(segment)
+                if remaining_bytes is not None and remaining_bytes <= 0:
+                    break
+
+        self._hook_progress({
+            'downloaded_bytes': byte_counter,
+            'total_bytes': byte_counter,
+            'filename': filename,
+            'status': 'finished',
+        })
+        self.try_rename(tmpfilename, filename)
+        return True
+

youtube_dl/downloader/http.py

@@ -14,8 +14,6 @@ from ..utils import (
 
 
 class HttpFD(FileDownloader):
-    _TEST_FILE_SIZE = 10241
-
     def real_download(self, filename, info_dict):
         url = info_dict['url']
         tmpfilename = self.temp_name(filename)
@@ -27,8 +25,16 @@ class HttpFD(FileDownloader):
             headers['Youtubedl-user-agent'] = info_dict['user_agent']
         if 'http_referer' in info_dict:
             headers['Referer'] = info_dict['http_referer']
-        basic_request = compat_urllib_request.Request(url, None, headers)
-        request = compat_urllib_request.Request(url, None, headers)
+        add_headers = info_dict.get('http_headers')
+        if add_headers:
+            headers.update(add_headers)
+        data = info_dict.get('http_post_data')
+        http_method = info_dict.get('http_method')
+        basic_request = compat_urllib_request.Request(url, data, headers)
+        request = compat_urllib_request.Request(url, data, headers)
+        if http_method is not None:
+            basic_request.get_method = lambda: http_method
+            request.get_method = lambda: http_method
 
         is_test = self.params.get('test', False)
 
@@ -185,7 +191,8 @@ class HttpFD(FileDownloader):
             self.to_stderr(u"\n")
             self.report_error(u'Did not get any data blocks')
             return False
-        stream.close()
+        if tmpfilename != u'-':
+            stream.close()
         self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))

youtube_dl/downloader/rtmp.py

@@ -8,9 +8,10 @@ import time
 
 from .common import FileDownloader
 from ..utils import (
+    check_executable,
+    compat_str,
     encodeFilename,
     format_bytes,
-    compat_str,
 )
 
 
@@ -103,9 +104,7 @@ class RtmpFD(FileDownloader):
         test = self.params.get('test', False)
 
         # Check for rtmpdump first
-        try:
-            subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
-        except (OSError, IOError):
+        if not check_executable('rtmpdump', ['-h']):
             self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.')
             return False
 

youtube_dl/extractor/__init__.py

@@ -4,12 +4,13 @@ from .addanime import AddAnimeIE
 from .adultswim import AdultSwimIE
 from .aftonbladet import AftonbladetIE
 from .anitube import AnitubeIE
+from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
-from .ard import ARDIE
+from .ard import ARDIE, ARDMediathekIE
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
@@ -23,6 +24,8 @@ from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
+from .beeg import BeegIE
+from .behindkink import BehindKinkIE
 from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
@@ -44,6 +47,7 @@ from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
+from .cloudy import CloudyIE
 from .clubic import ClubicIE
 from .cmt import CMTIE
 from .cnet import CNETIE
@@ -65,10 +69,14 @@ from .dailymotion import (
     DailymotionUserIE,
 )
 from .daum import DaumIE
+from .dbtv import DBTVIE
+from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .drtuber import DrTuberIE
 from .drtv import DRTVIE
+from .dump import DumpIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE
@@ -76,13 +84,20 @@ from .dropbox import DropboxIE
 from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
+from .einthusan import EinthusanIE
 from .eitb import EitbIE
+from .ellentv import (
+    EllenTVIE,
+    EllenTVClipsIE,
+)
 from .elpais import ElPaisIE
-from .empflix import EmpflixIE
+from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
+from .eporner import EpornerIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
+from .expotv import ExpoTVIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
@@ -110,22 +125,32 @@ from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
-from .gameone import GameOneIE
+from .gameone import (
+    GameOneIE,
+    GameOnePlaylistIE,
+)
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gametrailers import GametrailersIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
+from .globo import GloboIE
 from .godtube import GodTubeIE
+from .golem import GolemIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
+from .grooveshark import GroovesharkIE
 from .hark import HarkIE
+from .heise import HeiseIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .hornbunny import HornBunnyIE
+from .hostingbulk import HostingBulkIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
+from .howstuffworks import HowStuffWorksIE
 from .huffpost import HuffPostIE
 from .hypem import HypemIE
 from .iconosquare import IconosquareIE
@@ -146,6 +171,7 @@ from .ivi import (
 from .izlesene import IzleseneIE
 from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
+from .jove import JoveIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
 from .jpopsukitv import JpopsukiIE
@@ -165,6 +191,7 @@ from .livestream import (
     LivestreamOriginalIE,
     LivestreamShortenerIE,
 )
+from .lrt import LRTIE
 from .lynda import (
     LyndaIE,
     LyndaCourseIE
@@ -176,15 +203,22 @@ from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
+from .mgoon import MgoonIE
+from .ministrygrid import MinistryGridIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
+from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
 from .mlb import MLBIE
 from .mpora import MporaIE
+from .moevideo import MoeVideoIE
 from .mofosex import MofosexIE
+from .mojvideo import MojvideoIE
+from .moniker import MonikerIE
 from .mooshare import MooshareIE
 from .morningstar import MorningstarIE
 from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
+from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
 from .movshare import MovShareIE
 from .mtv import (
@@ -192,7 +226,9 @@ from .mtv import (
     MTVServicesEmbeddedIE,
     MTVIggyIE,
 )
+from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
+from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE
 from .myspass import MySpassIE
@@ -208,15 +244,20 @@ from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nfb import NFBIE
+from .nfl import NFLIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
+from .nosvideo import NosVideoIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
-from .npo import NPOIE
+from .npo import (
+    NPOIE,
+    TegenlichtVproIE,
+)
 from .nrk import (
     NRKIE,
     NRKTVIE,
@@ -224,17 +265,27 @@ from .nrk import (
 from .ntv import NTVIE
 from .nytimes import NYTimesIE
 from .nuvid import NuvidIE
-from .oe1 import OE1IE
+from .oktoberfesttv import OktoberfestTVIE
 from .ooyala import OoyalaIE
-from .orf import ORFIE
+from .orf import (
+    ORFTVthekIE,
+    ORFOE1IE,
+    ORFFM4IE,
+)
 from .parliamentliveuk import ParliamentLiveUKIE
+from .patreon import PatreonIE
 from .pbs import PBSIE
 from .photobucket import PhotobucketIE
+from .planetaplay import PlanetaPlayIE
+from .played import PlayedIE
+from .playfm import PlayFMIE
 from .playvid import PlayvidIE
 from .podomatic import PodomaticIE
 from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
+from .pornoxo import PornoXOIE
+from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .radiofrance import RadioFranceIE
@@ -247,9 +298,10 @@ from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
+from .rtlnl import RtlXlIE
 from .rtlnow import RTLnowIE
 from .rts import RTSIE
-from .rtve import RTVEALaCartaIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE
 from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
@@ -260,10 +312,12 @@ from .rutube import (
 from .rutv import RUTVIE
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
+from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .servingsys import ServingSysIE
 from .shared import SharedIE
+from .sharesix import ShareSixIE
 from .sina import SinaIE
 from .slideshare import SlideshareIE
 from .slutload import SlutloadIE
@@ -289,17 +343,22 @@ from .southpark import (
 )
 from .space import SpaceIE
 from .spankwire import SpankwireIE
-from .spiegel import SpiegelIE
+from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
+from .sport5 import Sport5IE
+from .sportbox import SportBoxIE
+from .sportdeutschland import SportDeutschlandIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .sunporno import SunPornoIE
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
 from .tagesschau import TagesschauIE
+from .tapely import TapelyIE
 from .teachertube import (
     TeacherTubeIE,
     TeacherTubeUserIE,
@@ -308,13 +367,21 @@ from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .telemb import TeleMBIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
+from .theonion import TheOnionIE
 from .theplatform import ThePlatformIE
+from .thesixtyone import TheSixtyOneIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
+from .tnaflix import TNAFlixIE
+from .thvideo import (
+    THVideoIE,
+    THVideoPlaylistIE
+)
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
@@ -323,11 +390,12 @@ from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
+from .turbo import TurboIE
 from .tutv import TutvIE
 from .tvigle import TvigleIE
 from .tvp import TvpIE
 from .tvplay import TVPlayIE
-from.ubu import UbuIE
+from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
     UdemyCourseIE
@@ -340,23 +408,26 @@ from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vesti import VestiIE
 from .vevo import VevoIE
+from .vgtv import VGTVIE
 from .vh1 import VH1IE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
 from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
+from .videomega import VideoMegaIE
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vimeo import (
     VimeoIE,
-    VimeoChannelIE,
-    VimeoUserIE,
     VimeoAlbumIE,
+    VimeoChannelIE,
     VimeoGroupsIE,
+    VimeoLikesIE,
     VimeoReviewIE,
+    VimeoUserIE,
     VimeoWatchLaterIE,
 )
 from .vimple import VimpleIE
@@ -367,11 +438,14 @@ from .vine import (
 from .viki import VikiIE
 from .vk import VKIE
 from .vodlocker import VodlockerIE
+from .vporn import VpornIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
 from .vulture import VultureIE
+from .walla import WallaIE
 from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
+from .wayofthemaster import WayOfTheMasterIE
 from .wdr import (
     WDRIE,
     WDRMobileIE,
@@ -383,18 +457,20 @@ from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .wrzuta import WrzutaIE
 from .xbef import XBefIE
+from .xboxclips import XboxClipsIE
 from .xhamster import XHamsterIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .xtube import XTubeUserIE, XTubeIE
 from .yahoo import (
     YahooIE,
-    YahooNewsIE,
     YahooSearchIE,
 )
+from .ynet import YnetIE
 from .youjizz import YouJizzIE
 from .youku import YoukuIE
 from .youporn import YouPornIE
+from .yourupload import YourUploadIE
 from .youtube import (
     YoutubeIE,
     YoutubeChannelIE,

youtube_dl/extractor/abc.py

@@ -22,8 +22,7 @@ class ABCIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         urls_info_json = self._search_regex(

youtube_dl/extractor/academicearth.py

@@ -7,6 +7,15 @@ from .common import InfoExtractor
 class AcademicEarthCourseIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
     IE_NAME = 'AcademicEarth:Course'
+    _TEST = {
+        'url': 'http://academicearth.org/playlists/laws-of-nature/',
+        'info_dict': {
+            'id': 'laws-of-nature',
+            'title': 'Laws of Nature',
+            'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
+        },
+        'playlist_count': 4,
+    }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

youtube_dl/extractor/adultswim.py

@@ -75,7 +75,9 @@ class AdultSwimIE(InfoExtractor):
         video_path = mobj.group('path')
 
         webpage = self._download_webpage(url, video_path)
-        episode_id = self._html_search_regex(r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', webpage, 'episode_id')
+        episode_id = self._html_search_regex(
+            r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>',
+            webpage, 'episode_id')
         title = self._og_search_title(webpage)
 
         index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id
@@ -97,7 +99,9 @@ class AdultSwimIE(InfoExtractor):
             duration = segment_el.attrib.get('duration')
 
             segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id
-            idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information')
+            idoc = self._download_xml(
+                segment_url, segment_title,
+                'Downloading segment information', 'Unable to download segment information')
 
             formats = []
             file_els = idoc.findall('.//files/file')

youtube_dl/extractor/anysex.py

@@ -0,0 +1,61 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
+
+
+class AnySexIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://anysex.com/156592/',
+        'md5': '023e9fbb7f7987f5529a394c34ad3d3d',
+        'info_dict': {
+            'id': '156592',
+            'ext': 'mp4',
+            'title': 'Busty and sexy blondie in her bikini strips for you',
+            'description': 'md5:de9e418178e2931c10b62966474e1383',
+            'categories': ['Erotic'],
+            'duration': 270,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
+
+        title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
+
+        categories = re.findall(
+            r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
+
+        duration = parse_duration(self._search_regex(
+            r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._html_search_regex(
+            r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'duration': duration,
+            'view_count': view_count,
+            'age_limit': 18,
+        }

youtube_dl/extractor/aol.py

@@ -21,7 +21,7 @@ class AolIE(InfoExtractor):
         (?:$|\?)
     '''
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
         'md5': '18ef68f48740e86ae94b98da815eec42',
         'info_dict': {
@@ -30,7 +30,14 @@ class AolIE(InfoExtractor):
             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
         },
         'add_ie': ['FiveMin'],
-    }
+    }, {
+        'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
+        'info_dict': {
+            'id': '152147',
+            'title': 'Brace Yourself - Today\'s Weirdest News',
+        },
+        'playlist_mincount': 10,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/aparat.py

@@ -1,5 +1,7 @@
 #coding: utf-8
 
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -13,13 +15,14 @@ class AparatIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
 
     _TEST = {
-        u'url': u'http://www.aparat.com/v/wP8On',
-        u'file': u'wP8On.mp4',
-        u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1',
-        u'info_dict': {
-            u"title": u"تیم گلکسی 11 - زومیت",
+        'url': 'http://www.aparat.com/v/wP8On',
+        'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
+        'info_dict': {
+            'id': 'wP8On',
+            'ext': 'mp4',
+            'title': 'تیم گلکسی 11 - زومیت',
         },
-        #u'skip': u'Extremely unreliable',
+        # 'skip': 'Extremely unreliable',
     }
 
     def _real_extract(self, url):
@@ -29,8 +32,8 @@ class AparatIE(InfoExtractor):
         # Note: There is an easier-to-parse configuration at
         # http://www.aparat.com/video/video/config/videohash/%video_id
         # but the URL in there does not work
-        embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' +
-                     video_id + u'/vt/frame')
+        embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
+                     video_id + '/vt/frame')
         webpage = self._download_webpage(embed_url, video_id)
 
         video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)

youtube_dl/extractor/appletrailers.py

@@ -6,6 +6,7 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
+    int_or_none,
 )
 
 
@@ -110,8 +111,8 @@ class AppleTrailersIE(InfoExtractor):
                 formats.append({
                     'url': format_url,
                     'format': format['type'],
-                    'width': format['width'],
-                    'height': int(format['height']),
+                    'width': int_or_none(format['width']),
+                    'height': int_or_none(format['height']),
                 })
 
             self._sort_formats(formats)

youtube_dl/extractor/ard.py

@@ -8,12 +8,15 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     qualities,
-    compat_urllib_parse_urlparse,
-    compat_urllib_parse,
+    int_or_none,
+    parse_duration,
+    unified_strdate,
+    xpath_text,
 )
 
 
-class ARDIE(InfoExtractor):
+class ARDMediathekIE(InfoExtractor):
+    IE_NAME = 'ARD:mediathek'
     _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
@@ -46,11 +49,11 @@ class ARDIE(InfoExtractor):
         else:
             video_id = m.group('video_id')
 
-        urlp = compat_urllib_parse_urlparse(url)
-        url = urlp._replace(path=compat_urllib_parse.quote(urlp.path.encode('utf-8'))).geturl()
-
         webpage = self._download_webpage(url, video_id)
 
+        if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
+            raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
+
         title = self._html_search_regex(
             [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
              r'<meta name="dcterms.title" content="(.*?)"/>',
@@ -125,3 +128,61 @@ class ARDIE(InfoExtractor):
             'formats': formats,
             'thumbnail': thumbnail,
         }
+
+
+class ARDIE(InfoExtractor):
+    _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _TEST = {
+        'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
+        'md5': 'd216c3a86493f9322545e045ddc3eb35',
+        'info_dict': {
+            'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge',
+            'id': '100',
+            'ext': 'mp4',
+            'duration': 2600,
+            'title': 'Die Story im Ersten: Mission unter falscher Flagge',
+            'upload_date': '20140804',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+
+        player_url = mobj.group('mainurl') + '~playerXml.xml'
+        doc = self._download_xml(player_url, display_id)
+        video_node = doc.find('./video')
+        upload_date = unified_strdate(xpath_text(
+            video_node, './broadcastDate'))
+        thumbnail = xpath_text(video_node, './/teaserImage//variant/url')
+
+        formats = []
+        for a in video_node.findall('.//asset'):
+            f = {
+                'format_id': a.attrib['type'],
+                'width': int_or_none(a.find('./frameWidth').text),
+                'height': int_or_none(a.find('./frameHeight').text),
+                'vbr': int_or_none(a.find('./bitrateVideo').text),
+                'abr': int_or_none(a.find('./bitrateAudio').text),
+                'vcodec': a.find('./codecVideo').text,
+                'tbr': int_or_none(a.find('./totalBitrate').text),
+            }
+            if a.find('./serverPrefix').text:
+                f['url'] = a.find('./serverPrefix').text
+                f['playpath'] = a.find('./fileName').text
+            else:
+                f['url'] = a.find('./fileName').text
+            formats.append(f)
+        self._sort_formats(formats)
+
+        return {
+            'id': mobj.group('id'),
+            'formats': formats,
+            'display_id': display_id,
+            'title': video_node.find('./title').text,
+            'duration': parse_duration(video_node.find('./duration').text),
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+        }
+

youtube_dl/extractor/arte.py

@@ -78,18 +78,23 @@ class ArteTVPlus7IE(InfoExtractor):
 
     def _extract_from_webpage(self, webpage, video_id, lang):
         json_url = self._html_search_regex(
-            r'arte_vp_url="(.*?)"', webpage, 'json vp url')
+            [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
+            webpage, 'json vp url')
         return self._extract_from_json_url(json_url, video_id, lang)
 
     def _extract_from_json_url(self, json_url, video_id, lang):
         info = self._download_json(json_url, video_id)
         player_info = info['videoJsonPlayer']
 
+        upload_date_str = player_info.get('shootingDate')
+        if not upload_date_str:
+            upload_date_str = player_info.get('VDA', '').split(' ')[0]
+
         info_dict = {
             'id': player_info['VID'],
             'title': player_info['VTI'],
             'description': player_info.get('VDE'),
-            'upload_date': unified_strdate(player_info.get('VDA', '').split(' ')[0]),
+            'upload_date': unified_strdate(upload_date_str),
             'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
         }
 
@@ -109,15 +114,19 @@ class ArteTVPlus7IE(InfoExtractor):
             regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
             return any(re.match(r, f['versionCode']) for r in regexes)
         # Some formats may not be in the same language as the url
+        # TODO: Might want not to drop videos that does not match requested language
+        # but to process those formats with lower precedence
         formats = filter(_match_lang, all_formats)
-        formats = list(formats) # in python3 filter returns an iterator
+        formats = list(formats)  # in python3 filter returns an iterator
         if not formats:
             # Some videos are only available in the 'Originalversion'
             # they aren't tagged as being in French or German
-            if all(f['versionCode'] == 'VO' or f['versionCode'] == 'VA' for f in all_formats):
-                formats = all_formats
-            else:
-                raise ExtractorError(u'The formats list is empty')
+            # Sometimes there are neither videos of requested lang code
+            # nor original version videos available
+            # For such cases we just take all_formats as is
+            formats = all_formats
+            if not formats:
+                raise ExtractorError('The formats list is empty')
 
         if re.match(r'[A-Z]Q', formats[0]['quality']) is not None:
             def sort_key(f):
@@ -173,16 +182,26 @@ class ArteTVPlus7IE(InfoExtractor):
 # It also uses the arte_vp_url url from the webpage to extract the information
 class ArteTVCreativeIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:creative'
-    _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/magazine?/(?P<id>.+)'
+    _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/(?:magazine?/)?(?P<id>[^?#]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
         'info_dict': {
-            'id': '050489-002',
+            'id': '72176',
             'ext': 'mp4',
-            'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design',
+            'title': 'Folge 2 - Corporate Design',
+            'upload_date': '20131004',
         },
-    }
+    }, {
+        'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
+        'info_dict': {
+            'id': '160676',
+            'ext': 'mp4',
+            'title': 'Monty Python live (mostly)',
+            'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n',
+            'upload_date': '20140805',
+        }
+    }]
 
 
 class ArteTVFutureIE(ArteTVPlus7IE):

youtube_dl/extractor/bambuser.py

@@ -59,6 +59,13 @@ class BambuserChannelIE(InfoExtractor):
     _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
     # The maximum number we can get with each request
     _STEP = 50
+    _TEST = {
+        'url': 'http://bambuser.com/channel/pixelversity',
+        'info_dict': {
+            'title': 'pixelversity',
+        },
+        'playlist_mincount': 60,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -73,10 +80,10 @@ class BambuserChannelIE(InfoExtractor):
             req = compat_urllib_request.Request(req_url)
             # Without setting this header, we wouldn't get any result
             req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
-            info_json = self._download_webpage(req, user,
-                'Downloading page %d' % i)
-            results = json.loads(info_json)['result']
-            if len(results) == 0:
+            data = self._download_json(
+                req, user, 'Downloading page %d' % i)
+            results = data['result']
+            if not results:
                 break
             last_id = results[-1]['vid']
             urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)

youtube_dl/extractor/bandcamp.py

@@ -15,13 +15,23 @@ class BandcampIE(InfoExtractor):
     _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
     _TESTS = [{
         'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
-        'file': '1812978515.mp3',
         'md5': 'c557841d5e50261777a6585648adf439',
         'info_dict': {
-            "title": "youtube-dl  \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
-            "duration": 9.8485,
+            'id': '1812978515',
+            'ext': 'mp3',
+            'title': "youtube-dl  \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
+            'duration': 9.8485,
         },
         '_skip': 'There is a limit of 200 free downloads / month for the test song'
+    }, {
+        'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
+        'md5': '2b68e5851514c20efdff2afc5603b8b4',
+        'info_dict': {
+            'id': '2650410135',
+            'ext': 'mp3',
+            'title': 'Lanius (Battle)',
+            'uploader': 'Ben Prunty Music',
+        },
     }]
 
     def _real_extract(self, url):
@@ -59,9 +69,9 @@ class BandcampIE(InfoExtractor):
                 raise ExtractorError('No free songs found')
 
         download_link = m_download.group(1)
-        video_id = re.search(
-            r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
-            webpage, re.MULTILINE | re.DOTALL).group('id')
+        video_id = self._search_regex(
+            r'var TralbumData = {.*?id: (?P<id>\d+),?$',
+            webpage, 'video id', flags=re.MULTILINE | re.DOTALL)
 
         download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
         # We get the dictionary of the track from some javascript code
@@ -96,7 +106,7 @@ class BandcampAlbumIE(InfoExtractor):
     IE_NAME = 'Bandcamp:album'
     _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
         'playlist': [
             {
@@ -118,7 +128,13 @@ class BandcampAlbumIE(InfoExtractor):
             'playlistend': 2
         },
         'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
-    }
+    }, {
+        'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
+        'info_dict': {
+            'title': 'Hierophany of the Open Grave',
+        },
+        'playlist_mincount': 9,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/beeg.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class BeegIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://beeg.com/5416503',
+        'md5': '634526ae978711f6b748fe0dd6c11f57',
+        'info_dict': {
+            'id': '5416503',
+            'ext': 'mp4',
+            'title': 'Sultry Striptease',
+            'description': 'md5:6db3c6177972822aaba18652ff59c773',
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        quality_arr = self._search_regex(
+            r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
+
+        formats = [{
+            'url': fmt[1],
+            'format_id': fmt[0],
+            'height': int(fmt[0][:-1]),
+        } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
+
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
+        
+        description = self._html_search_regex(
+            r'<meta name="description" content="([^"]*)"',
+            webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'\'previewer.url\'\s*:\s*"([^"]*)"',
+            webpage, 'thumbnail', fatal=False)
+
+        categories_str = self._html_search_regex(
+            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
+        categories = (
+            None if categories_str is None
+            else categories_str.split(','))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'formats': formats,
+            'age_limit': 18,
+        }

youtube_dl/extractor/behindkink.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import url_basename
+
+
+class BehindKinkIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
+    _TEST = {
+        'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/',
+        'md5': '41ad01222b8442089a55528fec43ec01',
+        'info_dict': {
+            'id': '36370',
+            'ext': 'mp4',
+            'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!',
+            'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...',
+            'upload_date': '20140814',
+            'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        year = mobj.group('year')
+        month = mobj.group('month')
+        day = mobj.group('day')
+        upload_date = year + month + day
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._search_regex(
+            r"'file':\s*'([^']+)'",
+            webpage, 'URL base')
+
+        video_id = url_basename(video_url)
+        video_id = video_id.split('_')[0]
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': self._og_search_title(webpage),
+            'display_id': display_id,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+            'upload_date': upload_date,
+            'age_limit': 18,
+        }

youtube_dl/extractor/bliptv.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 
 class BlipTVIE(SubtitlesInfoExtractor):
-    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+]+)))'
+    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))'
 
     _TESTS = [
         {
@@ -49,6 +49,21 @@ class BlipTVIE(SubtitlesInfoExtractor):
                 'uploader_id': '792887',
                 'duration': 279,
             }
+        },
+        {
+            # https://bugzilla.redhat.com/show_bug.cgi?id=967465
+            'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI',
+            'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6',
+            'info_dict': {
+                'id': '6573122',
+                'ext': 'mov',
+                'upload_date': '20130520',
+                'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.',
+                'title': 'Red vs. Blue Season 11 Trailer',
+                'timestamp': 1369029609,
+                'uploader': 'redvsblue',
+                'uploader_id': '792887',
+            }
         }
     ]
 
@@ -150,7 +165,7 @@ class BlipTVIE(SubtitlesInfoExtractor):
 
 
 class BlipTVUserIE(InfoExtractor):
-    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
+    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$'
     _PAGE_SIZE = 12
     IE_NAME = 'blip.tv:user'
 

youtube_dl/extractor/br.py

@@ -26,17 +26,8 @@ class BRIE(InfoExtractor):
                 'title': 'Wenn das Traditions-Theater wackelt',
                 'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt',
                 'duration': 34,
-            }
-        },
-        {
-            'url': 'http://www.br.de/mediathek/video/sendungen/unter-unserem-himmel/unter-unserem-himmel-alpen-ueber-den-pass-100.html',
-            'md5': 'ab451b09d861dbed7d7cc9ab0be19ebe',
-            'info_dict': {
-                'id': '2c060e69-3a27-4e13-b0f0-668fac17d812',
-                'ext': 'mp4',
-                'title': 'Über den Pass',
-                'description': 'Die Eroberung der Alpen: Über den Pass',
-                'duration': 2588,
+                'uploader': 'BR',
+                'upload_date': '20140802',
             }
         },
         {
@@ -77,8 +68,7 @@ class BRIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('id')
+        display_id = self._match_id(url)
         page = self._download_webpage(url, display_id)
         xml_url = self._search_regex(
             r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL')

youtube_dl/extractor/breakcom.py

@@ -4,37 +4,61 @@ import re
 import json
 
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_age_limit,
+)
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
-    _TEST = {
+    _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
+    _TESTS = [{
         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
-        'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
+        'md5': '33aa4ff477ecd124d18d7b5d23b87ce5',
         'info_dict': {
             'id': '2468056',
             'ext': 'mp4',
             'title': 'When Girls Act Like D-Bags',
         }
-    }
+    }, {
+        'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1).split("-")[-1]
-        embed_url = 'http://www.break.com/embed/%s' % video_id
-        webpage = self._download_webpage(embed_url, video_id)
-        info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
-            webpage, 'info json', flags=re.DOTALL)
-        info = json.loads(info_json)
-        video_url = info['videoUri']
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            'http://www.break.com/embed/%s' % video_id, video_id)
+        info = json.loads(self._search_regex(
+            r'var embedVars = ({.*})\s*?</script>',
+            webpage, 'info json', flags=re.DOTALL))
+
         youtube_id = info.get('youtubeId')
         if youtube_id:
             return self.url_result(youtube_id, 'Youtube')
 
-        final_url = video_url + '?' + info['AuthToken']
+        formats = [{
+            'url': media['uri'] + '?' + info['AuthToken'],
+            'tbr': media['bitRate'],
+            'width': media['width'],
+            'height': media['height'],
+        } for media in info['media']]
+
+        if not formats:
+            formats.append({
+                'url': info['videoUri']
+            })
+
+        self._sort_formats(formats)
+
+        duration = int_or_none(info.get('videoLengthInSeconds'))
+        age_limit = parse_age_limit(info.get('audienceRating'))
+
         return {
             'id': video_id,
-            'url': final_url,
             'title': info['contentName'],
             'thumbnail': info['thumbUri'],
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
         }

youtube_dl/extractor/brightcove.py

@@ -154,12 +154,14 @@ class BrightcoveIE(InfoExtractor):
     def _extract_brightcove_urls(cls, webpage):
         """Return a list of all Brightcove URLs from the webpage """
 
-        url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
+        url_m = re.search(
+            r'<meta\s+property="og:video"\s+content="(https?://(?:secure|c)\.brightcove.com/[^"]+)"',
+            webpage)
         if url_m:
             url = unescapeHTML(url_m.group(1))
             # Some sites don't add it, we can't download with this url, for example:
             # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/
-            if 'playerKey' in url:
+            if 'playerKey' in url or 'videoId' in url:
                 return [url]
 
         matches = re.findall(
@@ -188,9 +190,13 @@ class BrightcoveIE(InfoExtractor):
             referer = smuggled_data.get('Referer', url)
             return self._get_video_info(
                 videoPlayer[0], query_str, query, referer=referer)
-        else:
+        elif 'playerKey' in query:
             player_key = query['playerKey']
             return self._get_playlist_info(player_key[0])
+        else:
+            raise ExtractorError(
+                'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?',
+                expected=True)
 
     def _get_video_info(self, video_id, query_str, query, referer=None):
         request_url = self._FEDERATED_URL_TEMPLATE % query_str
@@ -202,6 +208,13 @@ class BrightcoveIE(InfoExtractor):
             req.add_header('Referer', referer)
         webpage = self._download_webpage(req, video_id)
 
+        error_msg = self._html_search_regex(
+            r"<h1>We're sorry.</h1>\s*<p>(.*?)</p>", webpage,
+            'error message', default=None)
+        if error_msg is not None:
+            raise ExtractorError(
+                'brightcove said: %s' % error_msg, expected=True)
+
         self.report_extraction(video_id)
         info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json')
         info = json.loads(info)['data']

youtube_dl/extractor/cbs.py

@@ -25,7 +25,7 @@ class CBSIE(InfoExtractor):
     }, {
         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
         'info_dict': {
-            'id': 'P9gjWjelt6iP',
+            'id': 'WWF_5KqY3PK1',
             'ext': 'flv',
             'title': 'Live on Letterman - St. Vincent',
             'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',

youtube_dl/extractor/chilloutzone.py

@@ -42,7 +42,7 @@ class ChilloutzoneIE(InfoExtractor):
             'id': '85523671',
             'ext': 'mp4',
             'title': 'The Sunday Times - Icons',
-            'description': 'md5:a5f7ff82e2f7a9ed77473fe666954e84',
+            'description': 're:(?s)^Watch the making of - makingoficons.com.{300,}',
             'uploader': 'Us',
             'uploader_id': 'usfilms',
             'upload_date': '20140131'

youtube_dl/extractor/cliphunter.py

@@ -1,11 +1,13 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
-translation_table = {
+_translation_table = {
     'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
     'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
     'y': 'l', 'z': 'i',
@@ -13,6 +15,10 @@ translation_table = {
 }
 
 
+def _decode(s):
+    return ''.join(_translation_table.get(c, c) for c in s)
+
+
 class CliphunterIE(InfoExtractor):
     IE_NAME = 'cliphunter'
 
@@ -22,10 +28,13 @@ class CliphunterIE(InfoExtractor):
     '''
     _TEST = {
         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
-        'file': '1012420.flv',
-        'md5': '15e7740f30428abf70f4223478dc1225',
+        'md5': 'a2ba71eebf523859fe527a61018f723e',
         'info_dict': {
+            'id': '1012420',
+            'ext': 'mp4',
             'title': 'Fun Jynx Maze solo',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'age_limit': 18,
         }
     }
 
@@ -35,22 +44,52 @@ class CliphunterIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        video_title = self._search_regex(
+            r'mediaTitle = "([^"]+)"', webpage, 'title')
+
         pl_fiji = self._search_regex(
             r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
         pl_c_qual = self._search_regex(
             r'pl_c_qual = "(.)"', webpage, 'video quality')
-        video_title = self._search_regex(
-            r'mediaTitle = "([^"]+)"', webpage, 'title')
-
-        video_url = ''.join(translation_table.get(c, c) for c in pl_fiji)
-
+        video_url = _decode(pl_fiji)
         formats = [{
             'url': video_url,
-            'format_id': pl_c_qual,
+            'format_id': 'default-%s' % pl_c_qual,
         }]
 
+        qualities_json = self._search_regex(
+            r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
+        qualities_data = json.loads(qualities_json)
+
+        for i, t in enumerate(
+                re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
+            quality_id, crypted_url = t
+            video_url = _decode(crypted_url)
+            f = {
+                'format_id': quality_id,
+                'url': video_url,
+                'quality': i,
+            }
+            if quality_id in qualities_data:
+                qd = qualities_data[quality_id]
+                m = re.match(
+                    r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
+                        \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
+                if m:
+                    f['width'] = int(m.group('width'))
+                    f['height'] = int(m.group('height'))
+                    f['tbr'] = int(m.group('tbr'))
+            formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = self._search_regex(
+            r"var\s+mov_thumb\s*=\s*'([^']+)';",
+            webpage, 'thumbnail', fatal=False)
+
         return {
             'id': video_id,
             'title': video_title,
             'formats': formats,
+            'age_limit': self._rta_search(webpage),
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/cloudy.py

@@ -0,0 +1,108 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_parse_qs,
+    compat_urllib_parse,
+    remove_end,
+    HEADRequest,
+    compat_HTTPError,
+)
+
+
+class CloudyIE(InfoExtractor):
+    _IE_DESC = 'cloudy.ec and videoraj.ch'
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/
+        (?:v/|embed\.php\?id=)
+        (?P<id>[A-Za-z0-9]+)
+        '''
+    _EMBED_URL = 'http://www.%s/embed.php?id=%s'
+    _API_URL = 'http://www.%s/api/player.api.php?%s'
+    _MAX_TRIES = 2
+    _TESTS = [
+        {
+            'url': 'https://www.cloudy.ec/v/af511e2527aac',
+            'md5': '5cb253ace826a42f35b4740539bedf07',
+            'info_dict': {
+                'id': 'af511e2527aac',
+                'ext': 'flv',
+                'title': 'Funny Cats and Animals Compilation june 2013',
+            }
+        },
+        {
+            'url': 'http://www.videoraj.ch/v/47f399fd8bb60',
+            'md5': '7d0f8799d91efd4eda26587421c3c3b0',
+            'info_dict': {
+                'id': '47f399fd8bb60',
+                'ext': 'flv',
+                'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?',
+            }
+        }
+    ]
+
+    def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0):
+
+        if try_num > self._MAX_TRIES - 1:
+            raise ExtractorError('Unable to extract video URL', expected=True)
+
+        form = {
+            'file': video_id,
+            'key': file_key,
+        }
+
+        if error_url:
+            form.update({
+                'numOfErrors': try_num,
+                'errorCode': '404',
+                'errorUrl': error_url,
+            })
+
+        data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode(form))
+        player_data = self._download_webpage(
+            data_url, video_id, 'Downloading player data')
+        data = compat_parse_qs(player_data)
+
+        try_num += 1
+
+        if 'error' in data:
+            raise ExtractorError(
+                '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
+                expected=True)
+
+        title = data.get('title', [None])[0]
+        if title:
+            title = remove_end(title, '&asdasdas').strip()
+
+        video_url = data.get('url', [None])[0]
+
+        if video_url:
+            try:
+                self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL')
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
+                    self.report_warning('Invalid video URL, requesting another', video_id)
+                    return self._extract_video(video_host, video_id, file_key, video_url, try_num)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+        }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_host = mobj.group('host')
+        video_id = mobj.group('id')
+
+        url = self._EMBED_URL % (video_host, video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        file_key = self._search_regex(
+            r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
+
+        return self._extract_video(video_host, video_id, file_key)

youtube_dl/extractor/comedycentral.py

@@ -43,14 +43,14 @@ class ComedyCentralShowsIE(InfoExtractor):
                           (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
                          ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
                           (?P<clip>
-                              (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+))
+                              (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
                               |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
                               |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
                           )|
                           (?P<interview>
                               extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
                      (?:[?#].*|$)'''
-    _TEST = {
+    _TESTS = [{
         'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
         'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
         'info_dict': {
@@ -61,7 +61,34 @@ class ComedyCentralShowsIE(InfoExtractor):
             'uploader': 'thedailyshow',
             'title': 'thedailyshow kristen-stewart part 1',
         }
-    }
+    }, {
+        'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
+        'only_matching': True,
+    }, {
+        'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
+        'only_matching': True,
+    }, {
+        'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
+        'only_matching': True,
+    }, {
+        'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
+        'only_matching': True,
+    }, {
+        'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
+        'only_matching': True,
+    }]
 
     _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
 
@@ -185,6 +212,9 @@ class ComedyCentralShowsIE(InfoExtractor):
                     'ext': self._video_extensions.get(format, 'mp4'),
                     'height': h,
                     'width': w,
+
+                    'format_note': 'HTTP 400 at the moment (patches welcome!)',
+                    'preference': -100,
                 })
                 formats.append({
                     'format_id': 'rtmp-%s' % format,

youtube_dl/extractor/common.py

@@ -1,4 +1,7 @@
+from __future__ import unicode_literals
+
 import base64
+import datetime
 import hashlib
 import json
 import netrc
@@ -13,11 +16,13 @@ from ..utils import (
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
+    compat_urlparse,
     compat_str,
 
     clean_html,
     compiled_regex_type,
     ExtractorError,
+    float_or_none,
     int_or_none,
     RegexNotFoundError,
     sanitize_filename,
@@ -84,6 +89,12 @@ class InfoExtractor(object):
                                  format, irrespective of the file format.
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
+                    * http_referer  HTTP Referer header value to set.
+                    * http_method  HTTP method to use for the download.
+                    * http_headers  A dictionary of additional HTTP headers
+                                 to add to the request.
+                    * http_post_data  Additional data to send with a POST
+                                 request.
     url:            Final video URL.
     ext:            Video filename extension.
     format:         The video format, defaults to ext (used for --get-format)
@@ -108,7 +119,7 @@ class InfoExtractor(object):
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
-    location:       Physical location of the video.
+    location:       Physical location where the video was filmed.
     subtitles:      The subtitle file contents as a dictionary in the format
                     {language: subtitles}.
     duration:       Length of the video in seconds, as an integer.
@@ -122,9 +133,13 @@ class InfoExtractor(object):
                     by YoutubeDL if it's missing)
     categories:     A list of categories that the video falls in, for example
                     ["Sports", "Berlin"]
+    is_live:        True, False, or None (=unknown). Whether this video is a
+                    live stream that goes on instead of a fixed-length video.
 
     Unless mentioned otherwise, the fields should be Unicode strings.
 
+    Unless mentioned otherwise, None is equivalent to absence of information.
+
     Subclasses of this one should re-define the _real_initialize() and
     _real_extract() methods and define a _VALID_URL regexp.
     Probably, they should also be added to the list of extractors.
@@ -153,6 +168,14 @@ class InfoExtractor(object):
             cls._VALID_URL_RE = re.compile(cls._VALID_URL)
         return cls._VALID_URL_RE.match(url) is not None
 
+    @classmethod
+    def _match_id(cls, url):
+        if '_VALID_URL_RE' not in cls.__dict__:
+            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+        m = cls._VALID_URL_RE.match(url)
+        assert m
+        return m.group('id')
+
     @classmethod
     def working(cls):
         """Getter method for _WORKING."""
@@ -196,17 +219,17 @@ class InfoExtractor(object):
             self.report_download_webpage(video_id)
         elif note is not False:
             if video_id is None:
-                self.to_screen(u'%s' % (note,))
+                self.to_screen('%s' % (note,))
             else:
-                self.to_screen(u'%s: %s' % (video_id, note))
+                self.to_screen('%s: %s' % (video_id, note))
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if errnote is False:
                 return False
             if errnote is None:
-                errnote = u'Unable to download webpage'
-            errmsg = u'%s: %s' % (errnote, compat_str(err))
+                errnote = 'Unable to download webpage'
+            errmsg = '%s: %s' % (errnote, compat_str(err))
             if fatal:
                 raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
             else:
@@ -243,7 +266,7 @@ class InfoExtractor(object):
                 url = url_or_request.get_full_url()
             except AttributeError:
                 url = url_or_request
-            self.to_screen(u'Dumping request to ' + url)
+            self.to_screen('Dumping request to ' + url)
             dump = base64.b64encode(webpage_bytes).decode('ascii')
             self._downloader.to_screen(dump)
         if self._downloader.params.get('write_pages', False):
@@ -253,11 +276,11 @@ class InfoExtractor(object):
                 url = url_or_request
             basen = '%s_%s' % (video_id, url)
             if len(basen) > 240:
-                h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
+                h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
                 basen = basen[:240 - len(h)] + h
             raw_filename = basen + '.dump'
             filename = sanitize_filename(raw_filename, restricted=True)
-            self.to_screen(u'Saving request to ' + filename)
+            self.to_screen('Saving request to ' + filename)
             with open(filename, 'wb') as outf:
                 outf.write(webpage_bytes)
 
@@ -266,14 +289,14 @@ class InfoExtractor(object):
         except LookupError:
             content = webpage_bytes.decode('utf-8', 'replace')
 
-        if (u'<title>Access to this site is blocked</title>' in content and
-                u'Websense' in content[:512]):
-            msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
+        if ('<title>Access to this site is blocked</title>' in content and
+                'Websense' in content[:512]):
+            msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
             blocked_iframe = self._html_search_regex(
                 r'<iframe src="([^"]+)"', content,
-                u'Websense information URL', default=None)
+                'Websense information URL', default=None)
             if blocked_iframe:
-                msg += u' Visit %s for more details' % blocked_iframe
+                msg += ' Visit %s for more details' % blocked_iframe
             raise ExtractorError(msg, expected=True)
 
         return (content, urlh)
@@ -288,7 +311,7 @@ class InfoExtractor(object):
             return content
 
     def _download_xml(self, url_or_request, video_id,
-                      note=u'Downloading XML', errnote=u'Unable to download XML',
+                      note='Downloading XML', errnote='Unable to download XML',
                       transform_source=None, fatal=True):
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(
@@ -300,8 +323,8 @@ class InfoExtractor(object):
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
 
     def _download_json(self, url_or_request, video_id,
-                       note=u'Downloading JSON metadata',
-                       errnote=u'Unable to download JSON metadata',
+                       note='Downloading JSON metadata',
+                       errnote='Unable to download JSON metadata',
                        transform_source=None,
                        fatal=True):
         json_string = self._download_webpage(
@@ -313,32 +336,36 @@ class InfoExtractor(object):
         try:
             return json.loads(json_string)
         except ValueError as ve:
-            raise ExtractorError('Failed to download JSON', cause=ve)
+            errmsg = '%s: Failed to parse JSON ' % video_id
+            if fatal:
+                raise ExtractorError(errmsg, cause=ve)
+            else:
+                self.report_warning(errmsg + str(ve))
 
     def report_warning(self, msg, video_id=None):
-        idstr = u'' if video_id is None else u'%s: ' % video_id
+        idstr = '' if video_id is None else '%s: ' % video_id
         self._downloader.report_warning(
-            u'[%s] %s%s' % (self.IE_NAME, idstr, msg))
+            '[%s] %s%s' % (self.IE_NAME, idstr, msg))
 
     def to_screen(self, msg):
         """Print msg to screen, prefixing it with '[ie_name]'"""
-        self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
+        self._downloader.to_screen('[%s] %s' % (self.IE_NAME, msg))
 
     def report_extraction(self, id_or_name):
         """Report information extraction."""
-        self.to_screen(u'%s: Extracting information' % id_or_name)
+        self.to_screen('%s: Extracting information' % id_or_name)
 
     def report_download_webpage(self, video_id):
         """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
+        self.to_screen('%s: Downloading webpage' % video_id)
 
     def report_age_confirmation(self):
         """Report attempt to confirm age."""
-        self.to_screen(u'Confirming age')
+        self.to_screen('Confirming age')
 
     def report_login(self):
         """Report attempt to log in."""
-        self.to_screen(u'Logging in')
+        self.to_screen('Logging in')
 
     #Methods for following #608
     @staticmethod
@@ -378,7 +405,7 @@ class InfoExtractor(object):
                     break
 
         if os.name != 'nt' and sys.stderr.isatty():
-            _name = u'\033[0;34m%s\033[0m' % name
+            _name = '\033[0;34m%s\033[0m' % name
         else:
             _name = name
 
@@ -388,10 +415,10 @@ class InfoExtractor(object):
         elif default is not _NO_DEFAULT:
             return default
         elif fatal:
-            raise RegexNotFoundError(u'Unable to extract %s' % _name)
+            raise RegexNotFoundError('Unable to extract %s' % _name)
         else:
-            self._downloader.report_warning(u'unable to extract %s; '
-                u'please report this issue on http://yt-dl.org/bug' % _name)
+            self._downloader.report_warning('unable to extract %s; '
+                'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
     def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
@@ -430,10 +457,26 @@ class InfoExtractor(object):
                 else:
                     raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
             except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
+                self._downloader.report_warning('parsing .netrc: %s' % compat_str(err))
         
         return (username, password)
 
+    def _get_tfa_info(self):
+        """
+        Get the two-factor authentication info
+        TODO - asking the user will be required for sms/phone verify
+        currently just uses the command line option
+        If there's no info available, return None
+        """
+        if self._downloader is None:
+            return None
+        downloader_params = self._downloader.params
+
+        if downloader_params.get('twofactor', None) is not None:
+            return downloader_params['twofactor']
+
+        return None
+
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
@@ -454,7 +497,7 @@ class InfoExtractor(object):
         return unescapeHTML(escaped)
 
     def _og_search_thumbnail(self, html, **kargs):
-        return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)
+        return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs)
 
     def _og_search_description(self, html, **kargs):
         return self._og_search_property('description', html, fatal=False, **kargs)
@@ -463,8 +506,9 @@ class InfoExtractor(object):
         return self._og_search_property('title', html, **kargs)
 
     def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
-        regexes = self._og_regexes('video')
-        if secure: regexes = self._og_regexes('video:secure_url') + regexes
+        regexes = self._og_regexes('video') + self._og_regexes('video:url')
+        if secure:
+            regexes = self._og_regexes('video:secure_url') + regexes
         return self._html_search_regex(regexes, html, name, **kargs)
 
     def _og_search_url(self, html, **kargs):
@@ -512,7 +556,7 @@ class InfoExtractor(object):
 
     def _sort_formats(self, formats):
         if not formats:
-            raise ExtractorError(u'No video formats found')
+            raise ExtractorError('No video formats found')
 
         def _formats_key(f):
             # TODO remove the following workaround
@@ -532,9 +576,9 @@ class InfoExtractor(object):
 
             if f.get('vcodec') == 'none':  # audio only
                 if self._downloader.params.get('prefer_free_formats'):
-                    ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus']
+                    ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                 else:
-                    ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a']
+                    ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a']
                 ext_preference = 0
                 try:
                     audio_ext_preference = ORDER.index(f['ext'])
@@ -542,9 +586,9 @@ class InfoExtractor(object):
                     audio_ext_preference = -1
             else:
                 if self._downloader.params.get('prefer_free_formats'):
-                    ORDER = [u'flv', u'mp4', u'webm']
+                    ORDER = ['flv', 'mp4', 'webm']
                 else:
-                    ORDER = [u'webm', u'flv', u'mp4']
+                    ORDER = ['webm', 'flv', 'mp4']
                 try:
                     ext_preference = ORDER.index(f['ext'])
                 except ValueError:
@@ -586,7 +630,7 @@ class InfoExtractor(object):
 
     def _sleep(self, timeout, video_id, msg_template=None):
         if msg_template is None:
-            msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds'
+            msg_template = '%(video_id)s: Waiting for %(timeout)s seconds'
         msg = msg_template % {'video_id': video_id, 'timeout': timeout}
         self.to_screen(msg)
         time.sleep(timeout)
@@ -597,11 +641,15 @@ class InfoExtractor(object):
             'Unable to download f4m manifest')
 
         formats = []
-        for media_el in manifest.findall('{http://ns.adobe.com/f4m/1.0}media'):
+        media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
+        for i, media_el in enumerate(media_nodes):
+            tbr = int_or_none(media_el.attrib.get('bitrate'))
+            format_id = 'f4m-%d' % (i if tbr is None else tbr)
             formats.append({
+                'format_id': format_id,
                 'url': manifest_url,
                 'ext': 'flv',
-                'tbr': int_or_none(media_el.attrib.get('bitrate')),
+                'tbr': tbr,
                 'width': int_or_none(media_el.attrib.get('width')),
                 'height': int_or_none(media_el.attrib.get('height')),
             })
@@ -609,6 +657,98 @@ class InfoExtractor(object):
 
         return formats
 
+    def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
+                              entry_protocol='m3u8', preference=None):
+
+        formats = [{
+            'format_id': 'm3u8-meta',
+            'url': m3u8_url,
+            'ext': ext,
+            'protocol': 'm3u8',
+            'preference': -1,
+            'resolution': 'multiple',
+            'format_note': 'Quality selection URL',
+        }]
+
+        format_url = lambda u: (
+            u
+            if re.match(r'^https?://', u)
+            else compat_urlparse.urljoin(m3u8_url, u))
+
+        m3u8_doc = self._download_webpage(m3u8_url, video_id)
+        last_info = None
+        kv_rex = re.compile(
+            r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')
+        for line in m3u8_doc.splitlines():
+            if line.startswith('#EXT-X-STREAM-INF:'):
+                last_info = {}
+                for m in kv_rex.finditer(line):
+                    v = m.group('val')
+                    if v.startswith('"'):
+                        v = v[1:-1]
+                    last_info[m.group('key')] = v
+            elif line.startswith('#') or not line.strip():
+                continue
+            else:
+                if last_info is None:
+                    formats.append({'url': format_url(line)})
+                    continue
+                tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
+
+                f = {
+                    'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)),
+                    'url': format_url(line.strip()),
+                    'tbr': tbr,
+                    'ext': ext,
+                    'protocol': entry_protocol,
+                    'preference': preference,
+                }
+                codecs = last_info.get('CODECS')
+                if codecs:
+                    # TODO: looks like video codec is not always necessarily goes first
+                    va_codecs = codecs.split(',')
+                    if va_codecs[0]:
+                        f['vcodec'] = va_codecs[0].partition('.')[0]
+                    if len(va_codecs) > 1 and va_codecs[1]:
+                        f['acodec'] = va_codecs[1].partition('.')[0]
+                resolution = last_info.get('RESOLUTION')
+                if resolution:
+                    width_str, height_str = resolution.split('x')
+                    f['width'] = int(width_str)
+                    f['height'] = int(height_str)
+                formats.append(f)
+                last_info = {}
+        self._sort_formats(formats)
+        return formats
+
+    def _live_title(self, name):
+        """ Generate the title for a live video """
+        now = datetime.datetime.now()
+        now_str = now.strftime("%Y-%m-%d %H:%M")
+        return name + ' ' + now_str
+
+    def _int(self, v, name, fatal=False, **kwargs):
+        res = int_or_none(v, **kwargs)
+        if 'get_attr' in kwargs:
+            print(getattr(v, kwargs['get_attr']))
+        if res is None:
+            msg = 'Failed to extract %s: Could not parse value %r' % (name, v)
+            if fatal:
+                raise ExtractorError(msg)
+            else:
+                self._downloader.report_warning(msg)
+        return res
+
+    def _float(self, v, name, fatal=False, **kwargs):
+        res = float_or_none(v, **kwargs)
+        if res is None:
+            msg = 'Failed to extract %s: Could not parse value %r' % (name, v)
+            if fatal:
+                raise ExtractorError(msg)
+            else:
+                self._downloader.report_warning(msg)
+        return res
+
 
 class SearchInfoExtractor(InfoExtractor):
     """
@@ -628,7 +768,7 @@ class SearchInfoExtractor(InfoExtractor):
     def _real_extract(self, query):
         mobj = re.match(self._make_valid_url(), query)
         if mobj is None:
-            raise ExtractorError(u'Invalid search query "%s"' % query)
+            raise ExtractorError('Invalid search query "%s"' % query)
 
         prefix = mobj.group('prefix')
         query = mobj.group('query')
@@ -639,9 +779,9 @@ class SearchInfoExtractor(InfoExtractor):
         else:
             n = int(prefix)
             if n <= 0:
-                raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
+                raise ExtractorError('invalid download number %s for query "%s"' % (n, query))
             elif n > self._MAX_RESULTS:
-                self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
+                self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
                 n = self._MAX_RESULTS
             return self._get_n_results(query, n)
 

youtube_dl/extractor/crunchyroll.py

@@ -5,10 +5,11 @@ import re
 import json
 import base64
 import zlib
+import xml.etree.ElementTree
 
 from hashlib import sha1
 from math import pow, sqrt, floor
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
     ExtractorError,
     compat_urllib_parse,
@@ -17,6 +18,7 @@ from ..utils import (
     intlist_to_bytes,
     unified_strdate,
     clean_html,
+    urlencode_postdata,
 )
 from ..aes import (
     aes_cbc_decrypt,
@@ -24,7 +26,7 @@ from ..aes import (
 )
 
 
-class CrunchyrollIE(InfoExtractor):
+class CrunchyrollIE(SubtitlesInfoExtractor):
     _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _TEST = {
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
@@ -51,6 +53,26 @@ class CrunchyrollIE(InfoExtractor):
         '1080': ('80', '108'),
     }
 
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+        self.report_login()
+        login_url = 'https://www.crunchyroll.com/?a=formhandler'
+        data = urlencode_postdata({
+            'formname': 'RpcApiUser_Login',
+            'name': username,
+            'password': password,
+        })
+        login_request = compat_urllib_request.Request(login_url, data)
+        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        self._download_webpage(login_request, None, False, 'Wrong login info')
+
+
+    def _real_initialize(self):
+        self._login()
+
+
     def _decrypt_subtitles(self, data, iv, id):
         data = bytes_to_intlist(data)
         iv = bytes_to_intlist(iv)
@@ -97,6 +119,75 @@ class CrunchyrollIE(InfoExtractor):
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
         return output
 
+    def _convert_subtitles_to_ass(self, subtitles):
+        output = ''
+
+        def ass_bool(strvalue):
+            assvalue = '0'
+            if strvalue == '1':
+                assvalue = '-1'
+            return assvalue
+
+        sub_root = xml.etree.ElementTree.fromstring(subtitles)
+        if not sub_root:
+            return output
+
+        output = '[Script Info]\n'
+        output += 'Title: %s\n' % sub_root.attrib["title"]
+        output += 'ScriptType: v4.00+\n'
+        output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"]
+        output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"]
+        output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"]
+        output += """ScaledBorderAndShadow: yes
+
+[V4+ Styles]
+Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
+"""
+        for style in sub_root.findall('./styles/style'):
+            output += 'Style: ' + style.attrib["name"]
+            output += ',' + style.attrib["font_name"]
+            output += ',' + style.attrib["font_size"]
+            output += ',' + style.attrib["primary_colour"]
+            output += ',' + style.attrib["secondary_colour"]
+            output += ',' + style.attrib["outline_colour"]
+            output += ',' + style.attrib["back_colour"]
+            output += ',' + ass_bool(style.attrib["bold"])
+            output += ',' + ass_bool(style.attrib["italic"])
+            output += ',' + ass_bool(style.attrib["underline"])
+            output += ',' + ass_bool(style.attrib["strikeout"])
+            output += ',' + style.attrib["scale_x"]
+            output += ',' + style.attrib["scale_y"]
+            output += ',' + style.attrib["spacing"]
+            output += ',' + style.attrib["angle"]
+            output += ',' + style.attrib["border_style"]
+            output += ',' + style.attrib["outline"]
+            output += ',' + style.attrib["shadow"]
+            output += ',' + style.attrib["alignment"]
+            output += ',' + style.attrib["margin_l"]
+            output += ',' + style.attrib["margin_r"]
+            output += ',' + style.attrib["margin_v"]
+            output += ',' + style.attrib["encoding"]
+            output += '\n'
+
+        output += """
+[Events]
+Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
+"""
+        for event in sub_root.findall('./events/event'):
+            output += 'Dialogue: 0'
+            output += ',' + event.attrib["start"]
+            output += ',' + event.attrib["end"]
+            output += ',' + event.attrib["style"]
+            output += ',' + event.attrib["name"]
+            output += ',' + event.attrib["margin_l"]
+            output += ',' + event.attrib["margin_r"]
+            output += ',' + event.attrib["margin_v"]
+            output += ',' + event.attrib["effect"]
+            output += ',' + event.attrib["text"]
+            output += '\n'
+
+        return output
+
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
@@ -158,6 +249,7 @@ class CrunchyrollIE(InfoExtractor):
             })
 
         subtitles = {}
+        sub_format = self._downloader.params.get('subtitlesformat', 'srt')
         for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
             sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
                                               video_id, note='Downloading subtitles for '+sub_name)
@@ -174,7 +266,14 @@ class CrunchyrollIE(InfoExtractor):
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
-            subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+            if sub_format == 'ass':
+                subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle)
+            else:
+                subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
 
         return {
             'id':          video_id,

youtube_dl/extractor/cspan.py

@@ -34,6 +34,13 @@ class CSpanIE(InfoExtractor):
             'title': 'International Health Care Models',
             'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
         }
+    }, {
+        'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
+        'info_dict': {
+            'id': '342759',
+            'title': 'General Motors Ignition Switch Recall',
+        },
+        'playlist_duration_sum': 14855,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/dailymotion.py

@@ -1,3 +1,6 @@
+#coding: utf-8
+from __future__ import unicode_literals
+
 import re
 import json
 import itertools
@@ -28,60 +31,58 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
     """Information Extractor for Dailymotion"""
 
     _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
-    IE_NAME = u'dailymotion'
+    IE_NAME = 'dailymotion'
 
     _FORMATS = [
-        (u'stream_h264_ld_url', u'ld'),
-        (u'stream_h264_url', u'standard'),
-        (u'stream_h264_hq_url', u'hq'),
-        (u'stream_h264_hd_url', u'hd'),
-        (u'stream_h264_hd1080_url', u'hd180'),
+        ('stream_h264_ld_url', 'ld'),
+        ('stream_h264_url', 'standard'),
+        ('stream_h264_hq_url', 'hq'),
+        ('stream_h264_hd_url', 'hd'),
+        ('stream_h264_hd1080_url', 'hd180'),
     ]
 
     _TESTS = [
         {
-            u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
-            u'file': u'x33vw9.mp4',
-            u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
-            u'info_dict': {
-                u"uploader": u"Amphora Alex and Van .", 
-                u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
+            'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
+            'md5': '392c4b85a60a90dc4792da41ce3144eb',
+            'info_dict': {
+                'id': 'x33vw9',
+                'ext': 'mp4',
+                'uploader': 'Amphora Alex and Van .',
+                'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"',
             }
         },
         # Vevo video
         {
-            u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
-            u'file': u'USUV71301934.mp4',
-            u'info_dict': {
-                u'title': u'Roar (Official)',
-                u'uploader': u'Katy Perry',
-                u'upload_date': u'20130905',
+            'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
+            'info_dict': {
+                'title': 'Roar (Official)',
+                'id': 'USUV71301934',
+                'ext': 'mp4',
+                'uploader': 'Katy Perry',
+                'upload_date': '20130905',
             },
-            u'params': {
-                u'skip_download': True,
+            'params': {
+                'skip_download': True,
             },
-            u'skip': u'VEVO is only available in some countries',
+            'skip': 'VEVO is only available in some countries',
         },
         # age-restricted video
         {
-            u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
-            u'file': u'xyh2zz.mp4',
-            u'md5': u'0d667a7b9cebecc3c89ee93099c4159d',
-            u'info_dict': {
-                u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
-                u'uploader': 'HotWaves1012',
-                u'age_limit': 18,
+            'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
+            'md5': '0d667a7b9cebecc3c89ee93099c4159d',
+            'info_dict': {
+                'id': 'xyh2zz',
+                'ext': 'mp4',
+                'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
+                'uploader': 'HotWaves1012',
+                'age_limit': 18,
             }
-
         }
     ]
 
     def _real_extract(self, url):
-        # Extract id and simplified title from URL
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         url = 'http://www.dailymotion.com/video/%s' % video_id
 
         # Retrieve video webpage to extract further information
@@ -97,8 +98,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             webpage)
         if m_vevo is not None:
             vevo_id = m_vevo.group('id')
-            self.to_screen(u'Vevo video detected: %s' % vevo_id)
-            return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
+            self.to_screen('Vevo video detected: %s' % vevo_id)
+            return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 
         age_limit = self._rta_search(webpage)
 
@@ -109,7 +110,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
         embed_page = self._download_webpage(embed_url, video_id,
-                                            u'Downloading embed page')
+                                            'Downloading embed page')
         info = self._search_regex(r'var info = ({.*?}),$', embed_page,
             'video info', flags=re.MULTILINE)
         info = json.loads(info)
@@ -134,7 +135,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
                     'height': height,
                 })
         if not formats:
-            raise ExtractorError(u'Unable to extract video URL')
+            raise ExtractorError('Unable to extract video URL')
 
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, webpage)
@@ -142,18 +143,23 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             self._list_available_subtitles(video_id, webpage)
             return
 
-        view_count = self._search_regex(
-            r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False)
-        if view_count is not None:
-            view_count = str_to_int(view_count)
+        view_count = str_to_int(self._search_regex(
+            r'video_views_count[^>]+>\s+([\d\.,]+)',
+            webpage, 'view count', fatal=False))
+
+        title = self._og_search_title(webpage, default=None)
+        if title is None:
+            title = self._html_search_regex(
+                r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
+                'title')
 
         return {
-            'id':       video_id,
+            'id': video_id,
             'formats': formats,
             'uploader': info['owner.screenname'],
-            'upload_date':  video_upload_date,
-            'title':    self._og_search_title(webpage),
-            'subtitles':    video_subtitles,
+            'upload_date': video_upload_date,
+            'title': title,
+            'subtitles': video_subtitles,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'view_count': view_count,
@@ -165,28 +171,35 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
                 video_id, note=False)
         except ExtractorError as err:
-            self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+            self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
             return {}
         info = json.loads(sub_list)
         if (info['total'] > 0):
             sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
             return sub_lang_list
-        self._downloader.report_warning(u'video doesn\'t have subtitles')
+        self._downloader.report_warning('video doesn\'t have subtitles')
         return {}
 
 
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
-    IE_NAME = u'dailymotion:playlist'
+    IE_NAME = 'dailymotion:playlist'
     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
     _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
+    _TESTS = [{
+        'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
+        'info_dict': {
+            'title': 'SPORT',
+        },
+        'playlist_mincount': 20,
+    }]
 
     def _extract_entries(self, id):
         video_ids = []
         for pagenum in itertools.count(1):
             request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
             webpage = self._download_webpage(request,
-                                             id, u'Downloading page %s' % pagenum)
+                                             id, 'Downloading page %s' % pagenum)
 
             video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
 
@@ -209,9 +222,17 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 
 class DailymotionUserIE(DailymotionPlaylistIE):
-    IE_NAME = u'dailymotion:user'
+    IE_NAME = 'dailymotion:user'
     _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
+    _TESTS = [{
+        'url': 'https://www.dailymotion.com/user/nqtv',
+        'info_dict': {
+            'id': 'nqtv',
+            'title': 'Rémi Gaillard',
+        },
+        'playlist_mincount': 100,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -219,7 +240,7 @@ class DailymotionUserIE(DailymotionPlaylistIE):
         webpage = self._download_webpage(url, user)
         full_user = unescapeHTML(self._html_search_regex(
             r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
-            webpage, u'user', flags=re.DOTALL))
+            webpage, 'user'))
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/daum.py

@@ -11,10 +11,10 @@ from ..utils import (
 
 
 class DaumIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)'
     IE_NAME = 'daum.net'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
         'info_dict': {
             'id': '52554690',
@@ -24,11 +24,17 @@ class DaumIE(InfoExtractor):
             'upload_date': '20130831',
             'duration': 3868,
         },
-    }
+    }, {
+        'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
+        'only_matching': True,
+    }, {
+        'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)
         full_id = self._search_regex(
@@ -42,7 +48,6 @@ class DaumIE(InfoExtractor):
             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
             video_id, 'Downloading video formats info')
 
-        self.to_screen(u'%s: Getting video urls' % video_id)
         formats = []
         for format_el in urls.findall('result/output_list/output_list'):
             profile = format_el.attrib['profile']
@@ -52,7 +57,7 @@ class DaumIE(InfoExtractor):
             })
             url_doc = self._download_xml(
                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
-                video_id, note=False)
+                video_id, note='Downloading video data for %s format' % profile)
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,

youtube_dl/extractor/dbtv.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    clean_html,
+)
+
+
+class DBTVIE(InfoExtractor):
+    _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)'
+    _TEST = {
+        'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
+        'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
+        'info_dict': {
+            'id': '33100',
+            'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
+            'ext': 'mp4',
+            'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
+            'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'timestamp': 1404039863.438,
+            'upload_date': '20140629',
+            'duration': 69.544,
+            'view_count': int,
+            'categories': list,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        data = self._download_json(
+            'http://api.dbtv.no/discovery/%s' % video_id, display_id)
+
+        video = data['playlist'][0]
+
+        formats = [{
+            'url': f['URL'],
+            'vcodec': f.get('container'),
+            'width': int_or_none(f.get('width')),
+            'height': int_or_none(f.get('height')),
+            'vbr': float_or_none(f.get('rate'), 1000),
+            'filesize': int_or_none(f.get('size')),
+        } for f in video['renditions'] if 'URL' in f]
+
+        if not formats:
+            for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]:
+                if url_key in video:
+                    formats.append({
+                        'url': video[url_key],
+                        'format_id': format_id,
+                    })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video['id'],
+            'display_id': display_id,
+            'title': video['title'],
+            'description': clean_html(video['desc']),
+            'thumbnail': video.get('splash') or video.get('thumb'),
+            'timestamp': float_or_none(video.get('publishedAt'), 1000),
+            'duration': float_or_none(video.get('length'), 1000),
+            'view_count': int_or_none(video.get('views')),
+            'categories': video.get('tags'),
+            'formats': formats,
+        }

youtube_dl/extractor/deezer.py

@@ -0,0 +1,89 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    orderedSet,
+)
+
+
+class DeezerPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?deezer\.com/playlist/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.deezer.com/playlist/176747451',
+        'info_dict': {
+            'id': '176747451',
+            'title': 'Best!',
+            'uploader': 'Anonymous',
+            'thumbnail': 're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$',
+        },
+        'playlist_count': 30,
+        'skip': 'Only available in .de',
+    }
+
+    def _real_extract(self, url):
+        if 'test' not in self._downloader.params:
+            self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
+
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, playlist_id)
+        geoblocking_msg = self._html_search_regex(
+            r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
+            default=None)
+        if geoblocking_msg is not None:
+            raise ExtractorError(
+                'Deezer said: %s' % geoblocking_msg, expected=True)
+
+        data_json = self._search_regex(
+            r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n', webpage, 'data JSON')
+        data = json.loads(data_json)
+
+        playlist_title = data.get('DATA', {}).get('TITLE')
+        playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
+        playlist_thumbnail = self._search_regex(
+            r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
+            'playlist thumbnail')
+
+        preview_pattern = self._search_regex(
+            r"var SOUND_PREVIEW_GATEWAY\s*=\s*'([^']+)';", webpage,
+            'preview URL pattern', fatal=False)
+        entries = []
+        for s in data['SONGS']['data']:
+            puid = s['MD5_ORIGIN']
+            preview_video_url = preview_pattern.\
+                replace('{0}', puid[0]).\
+                replace('{1}', puid).\
+                replace('{2}', s['MEDIA_VERSION'])
+            formats = [{
+                'format_id': 'preview',
+                'url': preview_video_url,
+                'preference': -100,  # Only the first 30 seconds
+                'ext': 'mp3',
+            }]
+            self._sort_formats(formats)
+            artists = ', '.join(
+                orderedSet(a['ART_NAME'] for a in s['ARTISTS']))
+            entries.append({
+                'id': s['SNG_ID'],
+                'duration': int_or_none(s.get('DURATION')),
+                'title': '%s - %s' % (artists, s['SNG_TITLE']),
+                'uploader': s['ART_NAME'],
+                'uploader_id': s['ART_ID'],
+                'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
+                'formats': formats,
+            })
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': playlist_title,
+            'uploader': playlist_uploader,
+            'thumbnail': playlist_thumbnail,
+            'entries': entries,
+        }

youtube_dl/extractor/dfb.py

@@ -30,7 +30,7 @@ class DFBIE(InfoExtractor):
             video_id)
         video_info = player_info.find('video')
 
-        f4m_info = self._download_xml(video_info.find('url').text, video_id)
+        f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id)
         token_el = f4m_info.find('token')
         manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
 

youtube_dl/extractor/divxstage.py

@@ -7,7 +7,7 @@ class DivxStageIE(NovaMovIE):
     IE_NAME = 'divxstage'
     IE_DESC = 'DivxStage'
 
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag)'}
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag|to)'}
 
     _HOST = 'www.divxstage.eu'
 
@@ -24,4 +24,4 @@ class DivxStageIE(NovaMovIE):
             'title': 'youtubedl test video',
             'description': 'This is a test video for youtubedl.',
         }
-    }
+    }

youtube_dl/extractor/dropbox.py

@@ -5,27 +5,32 @@ import os.path
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse_unquote
+from ..utils import compat_urllib_parse_unquote, url_basename
 
 
 class DropboxIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)'
-    _TEST = {
-        'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4',
-        'md5': '8a3d905427a6951ccb9eb292f154530b',
+    _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*'
+    _TESTS = [{
+        'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
         'info_dict': {
             'id': 'nelirfsxnmcfbfh',
             'ext': 'mp4',
             'title': 'youtube-dl test video \'ä"BaW_jenozKc'
         }
-    }
+    },
+    {
+        'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v',
+        'only_matching': True,
+    },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        fn = compat_urllib_parse_unquote(mobj.group('title'))
+        fn = compat_urllib_parse_unquote(url_basename(url))
         title = os.path.splitext(fn)[0]
-        video_url = url + '?dl=1'
+        video_url = re.sub(r'[?&]dl=0', '', url)
+        video_url += ('?' if '?' not in video_url else '&') + 'dl=1'
 
         return {
             'id': video_id,

youtube_dl/extractor/drtuber.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import str_to_int
+
+
+class DrTuberIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
+    _TEST = {
+        'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
+        'md5': '93e680cf2536ad0dfb7e74d94a89facd',
+        'info_dict': {
+            'id': '1740434',
+            'display_id': 'hot-perky-blonde-naked-golf',
+            'ext': 'mp4',
+            'title': 'Hot Perky Blonde Naked Golf',
+            'like_count': int,
+            'dislike_count': int,
+            'comment_count': int,
+            'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._html_search_regex(
+            r'<source src="([^"]+)"', webpage, 'video URL')
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
+
+        thumbnail = self._html_search_regex(
+            r'poster="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        like_count = str_to_int(self._html_search_regex(
+            r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
+            webpage, 'like count', fatal=False))
+        dislike_count = str_to_int(self._html_search_regex(
+            r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
+            webpage, 'like count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<span class="comments_count">([\d,\.]+)</span>',
+            webpage, 'comment count', fatal=False))
+
+        cats_str = self._search_regex(
+            r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
+        categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
+            'categories': categories,
+            'age_limit': self._rta_search(webpage),
+        }

youtube_dl/extractor/drtv.py

@@ -8,7 +8,7 @@ from ..utils import parse_iso8601
 
 
 class DRTVIE(SubtitlesInfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/[^/]+/(?P<id>[\da-z-]+)'
+    _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)'
 
     _TEST = {
         'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',

youtube_dl/extractor/dump.py

@@ -0,0 +1,39 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class DumpIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/'
+
+    _TEST = {
+        'url': 'http://www.dump.com/oneus/',
+        'md5': 'ad71704d1e67dfd9e81e3e8b42d69d99',
+        'info_dict': {
+            'id': 'oneus',
+            'ext': 'flv',
+            'title': "He's one of us.",
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._search_regex(
+            r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL')
+
+        thumb = self._og_search_thumbnail(webpage)
+        title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'thumbnail': thumb,
+        }

youtube_dl/extractor/ebaumsworld.py

@@ -1,19 +1,21 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class EbaumsWorldIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ebaumsworld\.com/video/watch/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.ebaumsworld.com/video/watch/83367677/',
-        u'file': u'83367677.mp4',
-        u'info_dict': {
-            u'title': u'A Giant Python Opens The Door',
-            u'description': u'This is how nightmares start...',
-            u'uploader': u'jihadpizza',
+        'url': 'http://www.ebaumsworld.com/video/watch/83367677/',
+        'info_dict': {
+            'id': '83367677',
+            'ext': 'mp4',
+            'title': 'A Giant Python Opens The Door',
+            'description': 'This is how nightmares start...',
+            'uploader': 'jihadpizza',
         },
     }
 
@@ -28,7 +30,6 @@ class EbaumsWorldIE(InfoExtractor):
             'id': video_id,
             'title': config.find('title').text,
             'url': video_url,
-            'ext': determine_ext(video_url),
             'description': config.find('description').text,
             'thumbnail': config.find('image').text,
             'uploader': config.find('username').text,

youtube_dl/extractor/eighttracks.py

@@ -1,10 +1,13 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
 import json
 import random
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
+    compat_str,
 )
 
 
@@ -12,86 +15,98 @@ class EightTracksIE(InfoExtractor):
     IE_NAME = '8tracks'
     _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
     _TEST = {
-        u"name": u"EightTracks",
-        u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
-        u"playlist": [
+        "name": "EightTracks",
+        "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
+        "info_dict": {
+            'id': '1336550',
+            'display_id': 'youtube-dl-test-tracks-a',
+            "description": "test chars:  \"'/\\ä↭",
+            "title": "youtube-dl test tracks \"'/\\ä↭<>",
+        },
+        "playlist": [
             {
-                u"file": u"11885610.m4a",
-                u"md5": u"96ce57f24389fc8734ce47f4c1abcc55",
-                u"info_dict": {
-                    u"title": u"youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "96ce57f24389fc8734ce47f4c1abcc55",
+                "info_dict": {
+                    "id": "11885610",
+                    "ext": "m4a",
+                    "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885608.m4a",
-                u"md5": u"4ab26f05c1f7291ea460a3920be8021f",
-                u"info_dict": {
-                    u"title": u"youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "4ab26f05c1f7291ea460a3920be8021f",
+                "info_dict": {
+                    "id": "11885608",
+                    "ext": "m4a",
+                    "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885679.m4a",
-                u"md5": u"d30b5b5f74217410f4689605c35d1fd7",
-                u"info_dict": {
-                    u"title": u"youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "d30b5b5f74217410f4689605c35d1fd7",
+                "info_dict": {
+                    "id": "11885679",
+                    "ext": "m4a",
+                    "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885680.m4a",
-                u"md5": u"4eb0a669317cd725f6bbd336a29f923a",
-                u"info_dict": {
-                    u"title": u"youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "4eb0a669317cd725f6bbd336a29f923a",
+                "info_dict": {
+                    "id": "11885680",
+                    "ext": "m4a",
+                    "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885682.m4a",
-                u"md5": u"1893e872e263a2705558d1d319ad19e8",
-                u"info_dict": {
-                    u"title": u"PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "1893e872e263a2705558d1d319ad19e8",
+                "info_dict": {
+                    "id": "11885682",
+                    "ext": "m4a",
+                    "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885683.m4a",
-                u"md5": u"b673c46f47a216ab1741ae8836af5899",
-                u"info_dict": {
-                    u"title": u"PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "b673c46f47a216ab1741ae8836af5899",
+                "info_dict": {
+                    "id": "11885683",
+                    "ext": "m4a",
+                    "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885684.m4a",
-                u"md5": u"1d74534e95df54986da7f5abf7d842b7",
-                u"info_dict": {
-                    u"title": u"phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "1d74534e95df54986da7f5abf7d842b7",
+                "info_dict": {
+                    "id": "11885684",
+                    "ext": "m4a",
+                    "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             },
             {
-                u"file": u"11885685.m4a",
-                u"md5": u"f081f47af8f6ae782ed131d38b9cd1c0",
-                u"info_dict": {
-                    u"title": u"phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
-                    u"uploader_id": u"ytdl"
+                "md5": "f081f47af8f6ae782ed131d38b9cd1c0",
+                "info_dict": {
+                    "id": "11885685",
+                    "ext": "m4a",
+                    "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
+                    "uploader_id": "ytdl"
                 }
             }
         ]
     }
 
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         playlist_id = mobj.group('id')
 
         webpage = self._download_webpage(url, playlist_id)
 
-        json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL)
+        json_like = self._search_regex(
+            r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information')
         data = json.loads(json_like)
 
         session = str(random.randint(0, 1000000000))
@@ -99,21 +114,30 @@ class EightTracksIE(InfoExtractor):
         track_count = data['tracks_count']
         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
         next_url = first_url
-        res = []
+        entries = []
         for i in range(track_count):
-            api_json = self._download_webpage(next_url, playlist_id,
-                note=u'Downloading song information %s/%s' % (str(i+1), track_count),
-                errnote=u'Failed to download song information')
+            api_json = self._download_webpage(
+                next_url, playlist_id,
+                note='Downloading song information %d/%d' % (i + 1, track_count),
+                errnote='Failed to download song information')
             api_data = json.loads(api_json)
-            track_data = api_data[u'set']['track']
+            track_data = api_data['set']['track']
             info = {
-                'id': track_data['id'],
+                'id': compat_str(track_data['id']),
                 'url': track_data['track_file_stream_url'],
                 'title': track_data['performer'] + u' - ' + track_data['name'],
                 'raw_title': track_data['name'],
                 'uploader_id': data['user']['login'],
                 'ext': 'm4a',
             }
-            res.append(info)
-            next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
-        return res
+            entries.append(info)
+            next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
+                session, mix_id, track_data['id'])
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            'id': compat_str(mix_id),
+            'display_id': playlist_id,
+            'title': data.get('name'),
+            'description': data.get('description'),
+        }

youtube_dl/extractor/einthusan.py

@@ -0,0 +1,61 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class EinthusanIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)'
+    _TESTS = [
+        {
+            'url': 'http://www.einthusan.com/movies/watch.php?id=2447',
+            'md5': 'af244f4458cd667205e513d75da5b8b1',
+            'info_dict': {
+                'id': '2447',
+                'ext': 'mp4',
+                'title': 'Ek Villain',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'description': 'md5:9d29fc91a7abadd4591fb862fa560d93',
+            }
+        },
+        {
+            'url': 'http://www.einthusan.com/movies/watch.php?id=1671',
+            'md5': 'ef63c7a803e22315880ed182c10d1c5c',
+            'info_dict': {
+                'id': '1671',
+                'ext': 'mp4',
+                'title': 'Soodhu Kavvuum',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'description': 'md5:05d8a0c0281a4240d86d76e14f2f4d51',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        video_title = self._html_search_regex(
+            r'<h1><a class="movie-title".*?>(.*?)</a></h1>', webpage, 'title')
+
+        video_url = self._html_search_regex(
+            r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''',
+            webpage, 'video url')
+
+        description = self._html_search_meta('description', webpage)
+        thumbnail = self._html_search_regex(
+            r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
+            webpage, "thumbnail url", fatal=False)
+        if thumbnail is not None:
+            thumbnail = thumbnail.replace('..', 'http://www.einthusan.com')
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'description': description,
+        }

youtube_dl/extractor/eitb.py

@@ -1,4 +1,6 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -7,20 +9,20 @@ from ..utils import ExtractorError
 
 
 class EitbIE(InfoExtractor):
-    IE_NAME = u'eitb.tv'
+    IE_NAME = 'eitb.tv'
     _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
 
     _TEST = {
-        u'add_ie': ['Brightcove'],
-        u'url': u'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
-        u'md5': u'edf4436247185adee3ea18ce64c47998',
-        u'info_dict': {
-            u'id': u'2743577154001',
-            u'ext': u'mp4',
-            u'title': u'60 minutos (Lasa y Zabala, 30 años)',
+        'add_ie': ['Brightcove'],
+        'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
+        'md5': 'edf4436247185adee3ea18ce64c47998',
+        'info_dict': {
+            'id': '2743577154001',
+            'ext': 'mp4',
+            'title': '60 minutos (Lasa y Zabala, 30 años)',
             # All videos from eitb has this description in the brightcove info
-            u'description': u'.',
-            u'uploader': u'Euskal Telebista',
+            'description': '.',
+            'uploader': 'Euskal Telebista',
         },
     }
 
@@ -30,7 +32,7 @@ class EitbIE(InfoExtractor):
         webpage = self._download_webpage(url, chapter_id)
         bc_url = BrightcoveIE._extract_brightcove_url(webpage)
         if bc_url is None:
-            raise ExtractorError(u'Could not extract the Brightcove url')
+            raise ExtractorError('Could not extract the Brightcove url')
         # The BrightcoveExperience object doesn't contain the video id, we set
         # it manually
         bc_url += '&%40videoPlayer={0}'.format(chapter_id)

youtube_dl/extractor/ellentv.py

@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_iso8601,
+)
+
+
+class EllenTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)'
+    _TEST = {
+        'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
+        'md5': 'e4af06f3bf0d5f471921a18db5764642',
+        'info_dict': {
+            'id': '0-7jqrsr18',
+            'ext': 'mp4',
+            'title': 'What\'s Wrong with These Photos? A Whole Lot',
+            'timestamp': 1406876400,
+            'upload_date': '20140801',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        timestamp = parse_iso8601(self._search_regex(
+            r'<span class="publish-date"><time datetime="([^"]+)">',
+            webpage, 'timestamp'))
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'url': self._html_search_meta('VideoURL', webpage, 'url'),
+            'timestamp': timestamp,
+        }
+
+
+class EllenTVClipsIE(InfoExtractor):
+    IE_NAME = 'EllenTV:clips'
+    _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
+    _TEST = {
+        'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
+        'info_dict': {
+            'id': 'meryl-streep-vanessa-hudgens',
+            'title': 'Meryl Streep, Vanessa Hudgens',
+        },
+        'playlist_mincount': 9,
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, playlist_id)
+        playlist = self._extract_playlist(webpage)
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': self._og_search_title(webpage),
+            'entries': self._extract_entries(playlist)
+        }
+
+    def _extract_playlist(self, webpage):
+        json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
+        try:
+            return json.loads("[{" + json_string + "}]")
+        except ValueError as ve:
+            raise ExtractorError('Failed to download JSON', cause=ve)
+
+    def _extract_entries(self, playlist):
+        return [self.url_result(item['url'], 'EllenTV') for item in playlist]

youtube_dl/extractor/empflix.py

@@ -1,54 +1,25 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
+from .tnaflix import TNAFlixIE
 
 
-class EmpflixIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
+class EMPFlixIE(TNAFlixIE):
+    _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html'
+
+    _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
+    _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
+    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
+
     _TEST = {
         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
         'md5': 'b1bc15b6412d33902d6e5952035fcabc',
         'info_dict': {
             'id': '33051',
+            'display_id': 'Amateur-Finger-Fuck',
             'ext': 'mp4',
             'title': 'Amateur Finger Fuck',
             'description': 'Amateur solo finger fucking.',
+            'thumbnail': 're:https?://.*\.jpg$',
             'age_limit': 18,
         }
     }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        webpage = self._download_webpage(url, video_id)
-        age_limit = self._rta_search(webpage)
-
-        video_title = self._html_search_regex(
-            r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
-        video_description = self._html_search_regex(
-            r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
-
-        cfg_url = self._html_search_regex(
-            r'flashvars\.config = escape\("([^"]+)"',
-            webpage, 'flashvars.config')
-
-        cfg_xml = self._download_xml(
-            cfg_url, video_id, note='Downloading metadata')
-
-        formats = [
-            {
-                'url': item.find('videoLink').text,
-                'format_id': item.find('res').text,
-            } for item in cfg_xml.findall('./quality/item')
-        ]
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'description': video_description,
-            'formats': formats,
-            'age_limit': age_limit,
-        }

youtube_dl/extractor/eporner.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    str_to_int,
+)
+
+
+class EpornerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)'
+    _TEST = {
+        'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
+        'md5': '39d486f046212d8e1b911c52ab4691f8',
+        'info_dict': {
+            'id': '95008',
+            'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
+            'ext': 'mp4',
+            'title': 'Infamous Tiffany Teen Strip Tease Video',
+            'duration': 194,
+            'view_count': int,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+        title = self._html_search_regex(
+            r'<title>(.*?) - EPORNER', webpage, 'title')
+
+        redirect_code = self._html_search_regex(
+            r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
+            webpage, 'redirect_code')
+        redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
+        player_code = self._download_webpage(
+            redirect_url, display_id, note='Downloading player config')
+
+        sources = self._search_regex(
+            r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
+
+        formats = []
+        for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
+            fmt = {
+                'url': video_url,
+                'format_id': format_id,
+            }
+            m = re.search(r'^(\d+)', format_id)
+            if m:
+                fmt['height'] = int(m.group(1))
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        duration = parse_duration(self._search_regex(
+            r'class="mbtim">([0-9:]+)</div>', webpage, 'duration',
+            fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
+            webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': self._rta_search(webpage),
+        }

youtube_dl/extractor/escapist.py

@@ -36,7 +36,7 @@ class EscapistIE(InfoExtractor):
             r'<meta name="description" content="([^"]*)"',
             webpage, 'description', fatal=False)
 
-        playerUrl = self._og_search_video_url(webpage, name=u'player URL')
+        playerUrl = self._og_search_video_url(webpage, name='player URL')
 
         title = self._html_search_regex(
             r'<meta name="title" content="([^"]*)"',

youtube_dl/extractor/everyonesmixtape.py

@@ -12,10 +12,11 @@ from ..utils import (
 class EveryonesMixtapeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?everyonesmixtape\.com/#/mix/(?P<id>[0-9a-zA-Z]+)(?:/(?P<songnr>[0-9]))?$'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5',
-        'file': '5bfseWNmlds.mp4',
         "info_dict": {
+            'id': '5bfseWNmlds',
+            'ext': 'mp4',
             "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)",
             "uploader": "FKR.TV",
             "uploader_id": "frenchkissrecords",
@@ -25,7 +26,14 @@ class EveryonesMixtapeIE(InfoExtractor):
         'params': {
             'skip_download': True,  # This is simply YouTube
         }
-    }
+    }, {
+        'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi',
+        'info_dict': {
+            'id': 'm7m0jJAbMQi',
+            'title': 'Driving',
+        },
+        'playlist_count': 24
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/expotv.py

@@ -0,0 +1,73 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+)
+
+
+class ExpoTVIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
+    _TEST = {
+        'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561',
+        'md5': '2985e6d7a392b2f7a05e0ca350fe41d0',
+        'info_dict': {
+            'id': '17561',
+            'ext': 'mp4',
+            'upload_date': '20060212',
+            'title': 'My Favorite Online Scrapbook Store',
+            'view_count': int,
+            'description': 'You\'ll find most everything you need at this virtual store front.',
+            'uploader': 'Anna T.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        player_key = self._search_regex(
+            r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
+        config_url = 'http://client.expotv.com/video/config/%s/%s' % (
+            video_id, player_key)
+        config = self._download_json(
+            config_url, video_id,
+            note='Downloading video configuration')
+
+        formats = [{
+            'url': fcfg['file'],
+            'height': int_or_none(fcfg.get('height')),
+            'format_note': fcfg.get('label'),
+            'ext': self._search_regex(
+                r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'],
+                'file extension', default=None),
+        } for fcfg in config['sources']]
+        self._sort_formats(formats)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = config.get('image')
+        view_count = int_or_none(self._search_regex(
+            r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts'))
+        uploader = self._search_regex(
+            r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader',
+            fatal=False)
+        upload_date = unified_strdate(self._search_regex(
+            r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
+            fatal=False))
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'description': description,
+            'view_count': view_count,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/extremetube.py

@@ -7,6 +7,7 @@ from ..utils import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
+    str_to_int,
 )
 
 
@@ -20,6 +21,7 @@ class ExtremeTubeIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
+            'view_count': int,
             'age_limit': 18,
         }
     }, {
@@ -39,8 +41,12 @@ class ExtremeTubeIE(InfoExtractor):
         video_title = self._html_search_regex(
             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(
-            r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
-            fatal=False)
+            r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
+            webpage, 'uploader', fatal=False)
+        view_count = str_to_int(self._html_search_regex(
+            r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
+            webpage, 'view count', fatal=False))
+
         video_url = compat_urllib_parse.unquote(self._html_search_regex(
             r'video_url=(.+?)&amp;', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path
@@ -51,6 +57,7 @@ class ExtremeTubeIE(InfoExtractor):
             'id': video_id,
             'title': video_title,
             'uploader': uploader,
+            'view_count': view_count,
             'url': video_url,
             'format': format,
             'format_id': format,

youtube_dl/extractor/facebook.py

@@ -12,32 +12,43 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     urlencode_postdata,
-
     ExtractorError,
+    limit_length,
 )
 
 
 class FacebookIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         https?://(?:\w+\.)?facebook\.com/
-        (?:[^#?]*\#!/)?
-        (?:video/video\.php|photo\.php|video/embed)\?(?:.*?)
+        (?:[^#]*?\#!/)?
+        (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
         (?:v|video_id)=(?P<id>[0-9]+)
         (?:.*)'''
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
     IE_NAME = 'facebook'
-    _TEST = {
-        'url': 'https://www.facebook.com/photo.php?v=120708114770723',
-        'md5': '48975a41ccc4b7a581abd68651c1a5a8',
+    _TESTS = [{
+        'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
+        'md5': '6a40d33c0eccbb1af76cf0485a052659',
         'info_dict': {
-            'id': '120708114770723',
+            'id': '637842556329505',
             'ext': 'mp4',
-            'duration': 279,
-            'title': 'PEOPLE ARE AWESOME 2013',
+            'duration': 38,
+            'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
         }
-    }
+    }, {
+        'note': 'Video without discernible title',
+        'url': 'https://www.facebook.com/video.php?v=274175099429670',
+        'info_dict': {
+            'id': '274175099429670',
+            'ext': 'mp4',
+            'title': 'Facebook video #274175099429670',
+        }
+    }, {
+        'url': 'https://www.facebook.com/video.php?v=10204634152394104',
+        'only_matching': True,
+    }]
 
     def _login(self):
         (useremail, password) = self._get_login_info()
@@ -76,7 +87,8 @@ class FacebookIE(InfoExtractor):
 
             check_form = {
                 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'),
-                'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'),
+                'h': self._search_regex(
+                    r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
                 'name_action_selected': 'dont_save',
             }
             check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
@@ -121,7 +133,15 @@ class FacebookIE(InfoExtractor):
             raise ExtractorError('Cannot find video URL')
 
         video_title = self._html_search_regex(
-            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title')
+            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',
+            fatal=False)
+        if not video_title:
+            video_title = self._html_search_regex(
+                r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
+                webpage, 'alternative title', default=None)
+            video_title = limit_length(video_title, 80)
+        if not video_title:
+            video_title = 'Facebook video #%s' % video_id
 
         return {
             'id': video_id,

youtube_dl/extractor/firedrive.py

@@ -42,7 +42,6 @@ class FiredriveIE(InfoExtractor):
         fields = dict(re.findall(r'''(?x)<input\s+
             type="hidden"\s+
             name="([^"]+)"\s+
-            (?:id="[^"]+"\s+)?
             value="([^"]*)"
             ''', webpage))
 
@@ -66,7 +65,7 @@ class FiredriveIE(InfoExtractor):
         ext = self._search_regex(r'type:\s?\'([^\']+)\',',
                                  webpage, 'extension', fatal=False)
         video_url = self._search_regex(
-            r'file:\s?\'(http[^\']+)\',', webpage, 'file url')
+            r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url')
 
         formats = [{
             'format_id': 'sd',

youtube_dl/extractor/flickr.py

@@ -10,13 +10,13 @@ from ..utils import (
 
 
 class FlickrIE(InfoExtractor):
-    """Information Extractor for Flickr videos"""
-    _VALID_URL = r'(?:https?://)?(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
+    _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
     _TEST = {
         'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
-        'file': '5645318632.mp4',
         'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b',
         'info_dict': {
+            'id': '5645318632',
+            'ext': 'mp4',
             "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", 
             "uploader_id": "forestwander-nature-pictures", 
             "title": "Dark Hollow Waterfalls"
@@ -49,12 +49,12 @@ class FlickrIE(InfoExtractor):
             raise ExtractorError('Unable to extract video url')
         video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
 
-        return [{
-            'id':          video_id,
-            'url':         video_url,
-            'ext':         'mp4',
-            'title':       self._og_search_title(webpage),
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
-            'thumbnail':   self._og_search_thumbnail(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
             'uploader_id': video_uploader_id,
-        }]
+        }

youtube_dl/extractor/franceinter.py

@@ -4,16 +4,21 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class FranceInterIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
+    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
-        'file': '793962.mp3',
         'md5': '4764932e466e6f6c79c317d2e74f6884',
         "info_dict": {
-            "title": "L’Histoire dans les jeux vidéo",
+            'id': '793962',
+            'ext': 'mp3',
+            'title': 'L’Histoire dans les jeux vidéo',
+            'description': 'md5:7e93ddb4451e7530022792240a3049c7',
+            'timestamp': 1387369800,
+            'upload_date': '20131218',
         },
     }
 
@@ -22,17 +27,26 @@ class FranceInterIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(
-            r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title')
+
         path = self._search_regex(
-            r'&urlAOD=(.*?)&startTime', webpage, 'video url')
+            r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
         video_url = 'http://www.franceinter.fr/' + path
 
+        title = self._html_search_regex(
+            r'<span class="title">(.+?)</span>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<span class="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
+        timestamp = int_or_none(self._search_regex(
+            r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
+
         return {
             'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
             'formats': [{
                 'url': video_url,
                 'vcodec': 'none',
             }],
-            'title': title,
         }

youtube_dl/extractor/francetv.py

@@ -8,45 +8,68 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
+    ExtractorError,
+    clean_html,
+    parse_duration,
+    compat_urllib_parse_urlparse,
+    int_or_none,
 )
 
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
-    def _extract_video(self, video_id):
-        info = self._download_xml(
-            'http://www.francetvinfo.fr/appftv/webservices/video/'
-            'getInfosOeuvre.php?id-diffusion='
-            + video_id, video_id, 'Downloading XML config')
+    def _extract_video(self, video_id, catalogue):
+        info = self._download_json(
+            'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
+            % (video_id, catalogue),
+            video_id, 'Downloading video JSON')
 
-        manifest_url = info.find('videos/video/url').text
-        manifest_url = manifest_url.replace('/z/', '/i/')
-        
-        if manifest_url.startswith('rtmp'):
-            formats = [{'url': manifest_url, 'ext': 'flv'}]
-        else:
-            formats = []
-            available_formats = self._search_regex(r'/[^,]*,(.*?),k\.mp4', manifest_url, 'available formats')
-            for index, format_descr in enumerate(available_formats.split(',')):
-                format_info = {
-                    'url': manifest_url.replace('manifest.f4m', 'index_%d_av.m3u8' % index),
-                    'ext': 'mp4',
-                }
-                m_resolution = re.search(r'(?P<width>\d+)x(?P<height>\d+)', format_descr)
-                if m_resolution is not None:
-                    format_info.update({
-                        'width': int(m_resolution.group('width')),
-                        'height': int(m_resolution.group('height')),
-                    })
-                formats.append(format_info)
+        if info.get('status') == 'NOK':
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
 
-        thumbnail_path = info.find('image').text
+        formats = []
+        for video in info['videos']:
+            if video['statut'] != 'ONLINE':
+                continue
+            video_url = video['url']
+            if not video_url:
+                continue
+            format_id = video['format']
+            if video_url.endswith('.f4m'):
+                video_url_parsed = compat_urllib_parse_urlparse(video_url)
+                f4m_url = self._download_webpage(
+                    'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
+                    video_id, 'Downloading f4m manifest token', fatal=False)
+                if f4m_url:
+                    f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
+                    for f4m_format in f4m_formats:
+                        f4m_format['preference'] = 1
+                    formats.extend(f4m_formats)
+            elif video_url.endswith('.m3u8'):
+                formats.extend(self._extract_m3u8_formats(video_url, video_id))
+            elif video_url.startswith('rtmp'):
+                formats.append({
+                    'url': video_url,
+                    'format_id': 'rtmp-%s' % format_id,
+                    'ext': 'flv',
+                    'preference': 1,
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                    'preference': 2,
+                })
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': info.find('titre').text,
+            'title': info['titre'],
+            'description': clean_html(info['synopsis']),
+            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
+            'duration': parse_duration(info['duree']),
+            'timestamp': int_or_none(info['diffusion']['timestamp']),
             'formats': formats,
-            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
-            'description': info.find('synopsis').text,
         }
 
 
@@ -61,7 +84,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
         webpage = self._download_webpage(url, title)
         video_id = self._search_regex(
             r'data-diffusion="(\d+)"', webpage, 'ID')
-        return self._extract_video(video_id)
+        return self._extract_video(video_id, 'Pluzz')
 
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
@@ -70,13 +93,13 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
+        'md5': '9cecf35f99c4079c199e9817882a9a1c',
         'info_dict': {
             'id': '84981923',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Soir 3',
-        },
-        'params': {
-            'skip_download': True,
+            'upload_date': '20130826',
+            'timestamp': 1377548400,
         },
     }, {
         'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
@@ -88,15 +111,17 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
         },
         'params': {
             'skip_download': 'HLS (reqires ffmpeg)'
-        }
+        },
+        'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
-        video_id = self._search_regex(r'id-video=((?:[^0-9]*?_)?[0-9]+)[@"]', webpage, 'video id')
-        return self._extract_video(video_id)
+        video_id, catalogue = self._search_regex(
+            r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
+        return self._extract_video(video_id, catalogue)
 
 
 class FranceTVIE(FranceTVBaseInfoExtractor):
@@ -112,91 +137,77 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
         # france2
         {
             'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
-            'file': '75540104.mp4',
+            'md5': 'c03fc87cb85429ffd55df32b9fc05523',
             'info_dict': {
-                'title': '13h15, le samedi...',
-                'description': 'md5:2e5b58ba7a2d3692b35c792be081a03d',
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
+                'id': '109169362',
+                'ext': 'flv',
+                'title': '13h15, le dimanche...',
+                'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
+                'upload_date': '20140914',
+                'timestamp': 1410693600,
             },
         },
         # france3
         {
             'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
+            'md5': '679bb8f8921f8623bd658fa2f8364da0',
             'info_dict': {
                 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Le scandale du prix des médicaments',
                 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
+                'upload_date': '20131113',
+                'timestamp': 1384380000,
             },
         },
         # france4
         {
             'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+            'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
             'info_dict': {
                 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Hero Corp Making of - Extrait 1',
                 'description': 'md5:c87d54871b1790679aec1197e73d650a',
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
+                'upload_date': '20131106',
+                'timestamp': 1383766500,
             },
         },
         # france5
         {
             'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+            'md5': '78f0f4064f9074438e660785bbf2c5d9',
             'info_dict': {
-                'id': '92837968',
-                'ext': 'mp4',
+                'id': '108961659',
+                'ext': 'flv',
                 'title': 'C à dire ?!',
-                'description': 'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
+                'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
+                'upload_date': '20140915',
+                'timestamp': 1410795000,
             },
         },
         # franceo
         {
             'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+            'md5': '52f0bfe202848b15915a2f39aaa8981b',
             'info_dict': {
-                'id': '92327925',
-                'ext': 'mp4',
-                'title': 'Infô-Afrique',
+                'id': '108634970',
+                'ext': 'flv',
+                'title': 'Infô Afrique',
                 'description': 'md5:ebf346da789428841bee0fd2a935ea55',
+                'upload_date': '20140915',
+                'timestamp': 1410822000,
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-            'skip': 'The id changes frequently',
         },
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj.group('key'):
-            webpage = self._download_webpage(url, mobj.group('key'))
-            id_res = [
-                (r'''(?x)<div\s+class="video-player">\s*
-                    <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
-                    class="francetv-video-player">'''),
-                (r'<a id="player_direct" href="http://info\.francetelevisions'
-                 '\.fr/\?id-video=([^"/&]+)'),
-                (r'<a class="video" id="ftv_player_(.+?)"'),
-            ]
-            video_id = self._html_search_regex(id_res, webpage, 'video ID')
-        else:
-            video_id = mobj.group('id')
-        return self._extract_video(video_id)
+        webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id'))
+        video_id, catalogue = self._html_search_regex(
+            r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"',
+            webpage, 'video ID').split('@')
+        return self._extract_video(video_id, catalogue)
 
 
 class GenerationQuoiIE(InfoExtractor):
@@ -232,16 +243,15 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 
     _TEST = {
-        'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',
+        'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553',
+        'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6',
         'info_dict': {
-            'id': 'EV_6785',
-            'ext': 'mp4',
-            'title': 'Einstein on the beach au Théâtre du Châtelet',
-            'description': 'md5:9ce2888b1efefc617b5e58b3f6200eeb',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+            'id': 'EV_22853',
+            'ext': 'flv',
+            'title': 'Dans les jardins de William Christie - Le Camus',
+            'description': 'md5:4710c82315c40f0c865ca8b9a68b5299',
+            'upload_date': '20140829',
+            'timestamp': 1409317200,
         },
     }
 
@@ -249,5 +259,7 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, 'video id')
-        return self._extract_video(video_id)
+        video_id, catalogue = self._search_regex(
+            r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
+
+        return self._extract_video(video_id, catalogue)

youtube_dl/extractor/funnyordie.py

@@ -21,7 +21,7 @@ class FunnyOrDieIE(InfoExtractor):
         },
     }, {
         'url': 'http://www.funnyordie.com/embed/e402820827',
-        'md5': 'ff4d83318f89776ed0250634cfaa8d36',
+        'md5': '29f4c5e5a61ca39dfd7e8348a75d0aad',
         'info_dict': {
             'id': 'e402820827',
             'ext': 'mp4',

youtube_dl/extractor/gameone.py

@@ -88,3 +88,28 @@ class GameOneIE(InfoExtractor):
             'age_limit': age_limit,
             'timestamp': timestamp,
         }
+
+
+class GameOnePlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$'
+    IE_NAME = 'gameone:playlist'
+    _TEST = {
+        'url': 'http://www.gameone.de/tv',
+        'info_dict': {
+            'title': 'GameOne',
+        },
+        'playlist_mincount': 294,
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage('http://www.gameone.de/tv', 'TV')
+        max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage)))
+        entries = [
+            self.url_result('http://www.gameone.de/tv/%d' % video_id, 'GameOne')
+            for video_id in range(max_id, 0, -1)]
+
+        return {
+            '_type': 'playlist',
+            'title': 'GameOne',
+            'entries': entries,
+        }

youtube_dl/extractor/generic.py

@@ -8,18 +8,20 @@ import re
 from .common import InfoExtractor
 from .youtube import YoutubeIE
 from ..utils import (
-    compat_urllib_error,
     compat_urllib_parse,
-    compat_urllib_request,
     compat_urlparse,
     compat_xml_parse_error,
 
+    determine_ext,
     ExtractorError,
+    float_or_none,
     HEADRequest,
+    orderedSet,
     parse_xml,
     smuggle_url,
     unescapeHTML,
     unified_strdate,
+    unsmuggle_url,
     url_basename,
 )
 from .brightcove import BrightcoveIE
@@ -153,7 +155,6 @@ class GenericIE(InfoExtractor):
         # funnyordie embed
         {
             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
-            'md5': '7cf780be104d40fea7bae52eed4a470e',
             'info_dict': {
                 'id': '18e820ec3f',
                 'ext': 'mp4',
@@ -178,13 +179,13 @@ class GenericIE(InfoExtractor):
         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
-            'md5': 'deeeabcc1085eb2ba205474e7235a3d5',
+            'md5': '65fdff94098e4a607385a60c5177c638',
             'info_dict': {
-                'id': '981',
+                'id': '1969',
                 'ext': 'mp4',
-                'title': 'My web playroom',
-                'uploader': 'Ze Frank',
-                'description': 'md5:ddb2a40ecd6b6a147e400e535874947b',
+                'title': 'Hidden miracles of the natural world',
+                'uploader': 'Louie Schwartzberg',
+                'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
             }
         },
         # Embeded Ustream video
@@ -224,21 +225,6 @@ class GenericIE(InfoExtractor):
                 'skip_download': 'Requires rtmpdump'
             }
         },
-        # smotri embed
-        {
-            'url': 'http://rbctv.rbc.ru/archive/news/562949990879132.shtml',
-            'md5': 'ec40048448e9284c9a1de77bb188108b',
-            'info_dict': {
-                'id': 'v27008541fad',
-                'ext': 'mp4',
-                'title': 'Крым и Севастополь вошли в состав России',
-                'description': 'md5:fae01b61f68984c7bd2fa741e11c3175',
-                'duration': 900,
-                'upload_date': '20140318',
-                'uploader': 'rbctv_2012_4',
-                'uploader_id': 'rbctv_2012_4',
-            },
-        },
         # Condé Nast embed
         {
             'url': 'http://www.wired.com/2014/04/honda-asimo/',
@@ -289,70 +275,116 @@ class GenericIE(InfoExtractor):
                 'description': 'Mario\'s life in the fast lane has never looked so good.',
             },
         },
+        # YouTube embed via <data-embed-url="">
+        {
+            'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
+            'info_dict': {
+                'id': '4vAffPZIT44',
+                'ext': 'mp4',
+                'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
+                'uploader': 'Gameloft',
+                'uploader_id': 'gameloft',
+                'upload_date': '20140828',
+                'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
+            },
+            'params': {
+                'skip_download': True,
+            }
+        },
+        # Camtasia studio
+        {
+            'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
+            'playlist': [{
+                'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
+                'info_dict': {
+                    'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
+                    'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
+                    'ext': 'flv',
+                    'duration': 2235.90,
+                }
+            }, {
+                'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
+                'info_dict': {
+                    'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
+                    'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
+                    'ext': 'flv',
+                    'duration': 2235.93,
+                }
+            }],
+            'info_dict': {
+                'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
+            }
+        },
+        # Flowplayer
+        {
+            'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
+            'md5': '9d65602bf31c6e20014319c7d07fba27',
+            'info_dict': {
+                'id': '5123ea6d5e5a7',
+                'ext': 'mp4',
+                'age_limit': 18,
+                'uploader': 'www.handjobhub.com',
+                'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
+            }
+        },
+        # RSS feed
+        {
+            'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+            'info_dict': {
+                'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+                'title': 'Zero Punctuation',
+                'description': 're:'
+            },
+            'playlist_mincount': 11,
+        },
+        # Multiple brightcove videos
+        # https://github.com/rg3/youtube-dl/issues/2283
+        {
+            'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
+            'info_dict': {
+                'id': 'always-never',
+                'title': 'Always / Never - The New Yorker',
+            },
+            'playlist_count': 3,
+            'params': {
+                'extract_flat': False,
+                'skip_download': True,
+            }
+        },
+        # MLB embed
+        {
+            'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
+            'md5': '96f09a37e44da40dd083e12d9a683327',
+            'info_dict': {
+                'id': '33322633',
+                'ext': 'mp4',
+                'title': 'Ump changes call to ball',
+                'description': 'md5:71c11215384298a172a6dcb4c2e20685',
+                'duration': 48,
+                'timestamp': 1401537900,
+                'upload_date': '20140531',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        # Wistia embed
+        {
+            'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
+            'md5': '8788b683c777a5cf25621eaf286d0c23',
+            'info_dict': {
+                'id': '1cfaf6b7ea',
+                'ext': 'mov',
+                'title': 'md5:51364a8d3d009997ba99656004b5e20d',
+                'duration': 643.0,
+                'filesize': 182808282,
+                'uploader': 'education-portal.com',
+            },
+        },
     ]
 
-    def report_download_webpage(self, video_id):
-        """Report webpage download."""
-        if not self._downloader.params.get('test', False):
-            self._downloader.report_warning('Falling back on generic information extractor.')
-        super(GenericIE, self).report_download_webpage(video_id)
-
     def report_following_redirect(self, new_url):
         """Report information extraction."""
         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
 
-    def _send_head(self, url):
-        """Check if it is a redirect, like url shorteners, in case return the new url."""
-
-        class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
-            """
-            Subclass the HTTPRedirectHandler to make it use our
-            HEADRequest also on the redirected URL
-            """
-            def redirect_request(self, req, fp, code, msg, headers, newurl):
-                if code in (301, 302, 303, 307):
-                    newurl = newurl.replace(' ', '%20')
-                    newheaders = dict((k,v) for k,v in req.headers.items()
-                                      if k.lower() not in ("content-length", "content-type"))
-                    try:
-                        # This function was deprecated in python 3.3 and removed in 3.4
-                        origin_req_host = req.get_origin_req_host()
-                    except AttributeError:
-                        origin_req_host = req.origin_req_host
-                    return HEADRequest(newurl,
-                                       headers=newheaders,
-                                       origin_req_host=origin_req_host,
-                                       unverifiable=True)
-                else:
-                    raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
-        class HTTPMethodFallback(compat_urllib_request.BaseHandler):
-            """
-            Fallback to GET if HEAD is not allowed (405 HTTP error)
-            """
-            def http_error_405(self, req, fp, code, msg, headers):
-                fp.read()
-                fp.close()
-
-                newheaders = dict((k,v) for k,v in req.headers.items()
-                                  if k.lower() not in ("content-length", "content-type"))
-                return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
-                                                 headers=newheaders,
-                                                 origin_req_host=req.get_origin_req_host(),
-                                                 unverifiable=True))
-
-        # Build our opener
-        opener = compat_urllib_request.OpenerDirector()
-        for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
-                        HTTPMethodFallback, HEADRedirectHandler,
-                        compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
-            opener.add_handler(handler())
-
-        response = opener.open(HEADRequest(url))
-        if response is None:
-            raise ExtractorError('Invalid URL protocol')
-        return response
-
     def _extract_rss(self, url, video_id, doc):
         playlist_title = doc.find('./channel/title').text
         playlist_desc_el = doc.find('./channel/description')
@@ -372,6 +404,43 @@ class GenericIE(InfoExtractor):
             'entries': entries,
         }
 
+    def _extract_camtasia(self, url, video_id, webpage):
+        """ Returns None if no camtasia video can be found. """
+
+        camtasia_cfg = self._search_regex(
+            r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
+            webpage, 'camtasia configuration file', default=None)
+        if camtasia_cfg is None:
+            return None
+
+        title = self._html_search_meta('DC.title', webpage, fatal=True)
+
+        camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
+        camtasia_cfg = self._download_xml(
+            camtasia_url, video_id,
+            note='Downloading camtasia configuration',
+            errnote='Failed to download camtasia configuration')
+        fileset_node = camtasia_cfg.find('./playlist/array/fileset')
+
+        entries = []
+        for n in fileset_node.getchildren():
+            url_n = n.find('./uri')
+            if url_n is None:
+                continue
+
+            entries.append({
+                'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
+                'title': '%s - %s' % (title, n.tag),
+                'url': compat_urlparse.urljoin(url, url_n.text),
+                'duration': float_or_none(n.find('./duration').text),
+            })
+
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            'title': title,
+        }
+
     def _real_extract(self, url):
         if url.startswith('//'):
             return {
@@ -408,17 +477,32 @@ class GenericIE(InfoExtractor):
             else:
                 assert ':' in default_search
                 return self.url_result(default_search + url)
-        video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
+
+        url, smuggled_data = unsmuggle_url(url)
+        force_videoid = None
+        is_intentional = smuggled_data and smuggled_data.get('to_generic')
+        if smuggled_data and 'force_videoid' in smuggled_data:
+            force_videoid = smuggled_data['force_videoid']
+            video_id = force_videoid
+        else:
+            video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
 
         self.to_screen('%s: Requesting header' % video_id)
 
-        try:
-            response = self._send_head(url)
+        head_req = HEADRequest(url)
+        response = self._request_webpage(
+            head_req, video_id,
+            note=False, errnote='Could not send HEAD request to %s' % url,
+            fatal=False)
 
+        if response is not False:
             # Check for redirect
             new_url = response.geturl()
             if url != new_url:
                 self.report_following_redirect(new_url)
+                if force_videoid:
+                    new_url = smuggle_url(
+                        new_url, {'force_videoid': force_videoid})
                 return self.url_result(new_url)
 
             # Check for direct link to a video
@@ -439,9 +523,8 @@ class GenericIE(InfoExtractor):
                     'upload_date': upload_date,
                 }
 
-        except compat_urllib_error.HTTPError:
-            # This may be a stupid server that doesn't like HEAD, our UA, or so
-            pass
+        if not self._downloader.params.get('test', False) and not is_intentional:
+            self._downloader.report_warning('Falling back on generic information extractor.')
 
         try:
             webpage = self._download_webpage(url, video_id)
@@ -460,6 +543,11 @@ class GenericIE(InfoExtractor):
         except compat_xml_parse_error:
             pass
 
+        # Is it a Camtasia project?
+        camtasia_res = self._extract_camtasia(url, video_id, webpage)
+        if camtasia_res is not None:
+            return camtasia_res
+
         # Sometimes embedded video player is hidden behind percent encoding
         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
         # Unescaping the whole page allows to handle those cases in a generic way
@@ -475,10 +563,28 @@ class GenericIE(InfoExtractor):
             r'(?s)<title>(.*?)</title>', webpage, 'video title',
             default='video')
 
+        # Try to detect age limit automatically
+        age_limit = self._rta_search(webpage)
+        # And then there are the jokers who advertise that they use RTA,
+        # but actually don't.
+        AGE_LIMIT_MARKERS = [
+            r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
+        ]
+        if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
+            age_limit = 18
+
         # video uploader is domain name
         video_uploader = self._search_regex(
             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
 
+        # Helper method
+        def _playlist_from_matches(matches, getter, ie=None):
+            urlrs = orderedSet(
+                self.url_result(self._proto_relative_url(getter(m)), ie)
+                for m in matches)
+            return self.playlist_result(
+                urlrs, playlist_id=video_id, playlist_title=video_title)
+
         # Look for BrightCove:
         bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
         if bc_urls:
@@ -514,27 +620,34 @@ class GenericIE(InfoExtractor):
         matches = re.findall(r'''(?x)
             (?:
                 <iframe[^>]+?src=|
+                data-video-url=|
                 <embed[^>]+?src=|
                 embedSWF\(?:\s*
             )
             (["\'])
-                (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
-                (?:embed|v)/.+?)
+                (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
+                (?:embed|v|p)/.+?)
             \1''', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
-                     for tuppl in matches]
-            return self.playlist_result(
-                urlrs, playlist_id=video_id, playlist_title=video_title)
+            return _playlist_from_matches(
+                matches, lambda m: unescapeHTML(m[1]))
 
         # Look for embedded Dailymotion player
         matches = re.findall(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(tuppl[1]))
-                     for tuppl in matches]
-            return self.playlist_result(
-                urlrs, playlist_id=video_id, playlist_title=video_title)
+            return _playlist_from_matches(
+                matches, lambda m: unescapeHTML(m[1]))
+
+        # Look for embedded Dailymotion playlist player (#3822)
+        m = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
+        if m:
+            playlists = re.findall(
+                r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
+            if playlists:
+                return _playlist_from_matches(
+                    playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
 
         # Look for embedded Wistia player
         match = re.search(
@@ -548,12 +661,22 @@ class GenericIE(InfoExtractor):
                 'title': video_title,
                 'id': video_id,
             }
+        match = re.search(r'(?:id=["\']wistia_|data-wistiaid=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
+        if match:
+            return {
+                '_type': 'url_transparent',
+                'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
+                'ie_key': 'Wistia',
+                'uploader': video_uploader,
+                'title': video_title,
+                'id': match.group('id')
+            }
 
         # Look for embedded blip.tv player
         mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
         if mobj:
             return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV')
-        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage)
+        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
         if mobj:
             return self.url_result(mobj.group(1), 'BlipTV')
 
@@ -648,10 +771,8 @@ class GenericIE(InfoExtractor):
         # Look for funnyordie embed
         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
-                     for eurl in matches]
-            return self.playlist_result(
-                urlrs, playlist_id=video_id, playlist_title=video_title)
+            return _playlist_from_matches(
+                matches, getter=unescapeHTML, ie='FunnyOrDie')
 
         # Look for embedded RUTV player
         rutv_url = RUTVIE._extract_url(webpage)
@@ -706,40 +827,78 @@ class GenericIE(InfoExtractor):
             url = unescapeHTML(mobj.group('url'))
             return self.url_result(url, ie='MTVServicesEmbedded')
 
+        # Look for embedded yahoo player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Yahoo')
+
+        # Look for embedded sbs.com.au player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'SBS')
+
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'MLB')
+
+        def check_video(vurl):
+            vpath = compat_urlparse.urlparse(vurl).path
+            vext = determine_ext(vpath)
+            return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
+
+        def filter_video(urls):
+            return list(filter(check_video, urls))
+
         # Start with something easy: JW Player in SWFObject
-        found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+        found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
         if not found:
             # Look for gorilla-vid style embedding
-            found = re.findall(r'''(?sx)
+            found = filter_video(re.findall(r'''(?sx)
                 (?:
                     jw_plugins|
                     JWPlayerOptions|
                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
                 )
-                .*?file\s*:\s*["\'](.*?)["\']''', webpage)
+                .*?file\s*:\s*["\'](.*?)["\']''', webpage))
         if not found:
             # Broaden the search a little bit
-            found = re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+            found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
         if not found:
             # Broaden the findall a little bit: JWPlayer JS loader
-            found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+            found = filter_video(re.findall(
+                r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
+        if not found:
+            # Flow player
+            found = filter_video(re.findall(r'''(?xs)
+                flowplayer\("[^"]+",\s*
+                    \{[^}]+?\}\s*,
+                    \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
+                        ["']?url["']?\s*:\s*["']([^"']+)["']
+            ''', webpage))
         if not found:
             # Try to find twitter cards info
-            found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
+            found = filter_video(re.findall(
+                r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
         if not found:
             # We look for Open Graph info:
             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
-                found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
+                found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
         if not found:
             # HTML5 video
-            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage)
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage)
         if not found:
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
-                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"',
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
                 webpage)
             if found:
                 new_url = found.group(1)
@@ -769,6 +928,7 @@ class GenericIE(InfoExtractor):
                 'url': video_url,
                 'uploader': video_uploader,
                 'title': video_title,
+                'age_limit': age_limit,
             })
 
         if len(entries) == 1:

youtube_dl/extractor/globo.py

@@ -0,0 +1,398 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+import math
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    compat_str,
+    compat_chr,
+    compat_ord,
+)
+
+
+class GloboIE(InfoExtractor):
+    _VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)'
+
+    _API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist'
+    _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=2.9.9.50&resource_id=%s'
+
+    _VIDEOID_REGEXES = [
+        r'\bdata-video-id="(\d+)"',
+        r'\bdata-player-videosids="(\d+)"',
+        r'<div[^>]+\bid="(\d+)"',
+    ]
+
+    _RESIGN_EXPIRATION = 86400
+
+    _TESTS = [
+        {
+            'url': 'http://globotv.globo.com/sportv/futebol-nacional/v/os-gols-de-atletico-mg-3-x-2-santos-pela-24a-rodada-do-brasileirao/3654973/',
+            'md5': '03ebf41cb7ade43581608b7d9b71fab0',
+            'info_dict': {
+                'id': '3654973',
+                'ext': 'mp4',
+                'title': 'Os gols de Atlético-MG 3 x 2 Santos pela 24ª rodada do Brasileirão',
+                'duration': 251.585,
+                'uploader': 'SporTV',
+                'uploader_id': 698,
+                'like_count': int,
+            }
+        },
+        {
+            'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/',
+            'md5': 'b3ccc801f75cd04a914d51dadb83a78d',
+            'info_dict': {
+                'id': '3607726',
+                'ext': 'mp4',
+                'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa',
+                'duration': 103.204,
+                'uploader': 'Globo.com',
+                'uploader_id': 265,
+                'like_count': int,
+            }
+        },
+        {
+            'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
+            'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
+            'info_dict': {
+                'id': '3652183',
+                'ext': 'mp4',
+                'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
+                'duration': 110.711,
+                'uploader': 'Rede Globo',
+                'uploader_id': 196,
+                'like_count': int,
+            }
+        },
+    ]
+
+    class MD5():
+        HEX_FORMAT_LOWERCASE = 0
+        HEX_FORMAT_UPPERCASE = 1
+        BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = ''
+        BASE64_PAD_CHARACTER_RFC_COMPLIANCE = '='
+        PADDING = '=0xFF01DD'
+        hexcase = 0
+        b64pad = ''
+
+        def __init__(self):
+            pass
+
+        class JSArray(list):
+            def __getitem__(self, y):
+                try:
+                    return list.__getitem__(self, y)
+                except IndexError:
+                    return 0
+
+            def __setitem__(self, i, y):
+                try:
+                    return list.__setitem__(self, i, y)
+                except IndexError:
+                    self.extend([0] * (i - len(self) + 1))
+                    self[-1] = y
+
+        @classmethod
+        def hex_md5(cls, param1):
+            return cls.rstr2hex(cls.rstr_md5(cls.str2rstr_utf8(param1)))
+
+        @classmethod
+        def b64_md5(cls, param1, param2=None):
+            return cls.rstr2b64(cls.rstr_md5(cls.str2rstr_utf8(param1, param2)))
+
+        @classmethod
+        def any_md5(cls, param1, param2):
+            return cls.rstr2any(cls.rstr_md5(cls.str2rstr_utf8(param1)), param2)
+
+        @classmethod
+        def rstr_md5(cls, param1):
+            return cls.binl2rstr(cls.binl_md5(cls.rstr2binl(param1), len(param1) * 8))
+
+        @classmethod
+        def rstr2hex(cls, param1):
+            _loc_2 = '0123456789ABCDEF' if cls.hexcase else '0123456789abcdef'
+            _loc_3 = ''
+            for _loc_5 in range(0, len(param1)):
+                _loc_4 = compat_ord(param1[_loc_5])
+                _loc_3 += _loc_2[_loc_4 >> 4 & 15] + _loc_2[_loc_4 & 15]
+            return _loc_3
+
+        @classmethod
+        def rstr2b64(cls, param1):
+            _loc_2 = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_'
+            _loc_3 = ''
+            _loc_4 = len(param1)
+            for _loc_5 in range(0, _loc_4, 3):
+                _loc_6_1 = compat_ord(param1[_loc_5]) << 16
+                _loc_6_2 = compat_ord(param1[_loc_5 + 1]) << 8 if _loc_5 + 1 < _loc_4 else 0
+                _loc_6_3 = compat_ord(param1[_loc_5 + 2]) if _loc_5 + 2 < _loc_4 else 0
+                _loc_6 = _loc_6_1 | _loc_6_2 | _loc_6_3
+                for _loc_7 in range(0, 4):
+                    if _loc_5 * 8 + _loc_7 * 6 > len(param1) * 8:
+                        _loc_3 += cls.b64pad
+                    else:
+                        _loc_3 += _loc_2[_loc_6 >> 6 * (3 - _loc_7) & 63]
+            return _loc_3
+
+        @staticmethod
+        def rstr2any(param1, param2):
+            _loc_3 = len(param2)
+            _loc_4 = []
+            _loc_9 = [0] * ((len(param1) >> 2) + 1)
+            for _loc_5 in range(0, len(_loc_9)):
+                _loc_9[_loc_5] = compat_ord(param1[_loc_5 * 2]) << 8 | compat_ord(param1[_loc_5 * 2 + 1])
+
+            while len(_loc_9) > 0:
+                _loc_8 = []
+                _loc_7 = 0
+                for _loc_5 in range(0, len(_loc_9)):
+                    _loc_7 = (_loc_7 << 16) + _loc_9[_loc_5]
+                    _loc_6 = math.floor(_loc_7 / _loc_3)
+                    _loc_7 -= _loc_6 * _loc_3
+                    if len(_loc_8) > 0 or _loc_6 > 0:
+                        _loc_8[len(_loc_8)] = _loc_6
+
+                _loc_4[len(_loc_4)] = _loc_7
+                _loc_9 = _loc_8
+
+            _loc_10 = ''
+            _loc_5 = len(_loc_4) - 1
+            while _loc_5 >= 0:
+                _loc_10 += param2[_loc_4[_loc_5]]
+                _loc_5 -= 1
+
+            return _loc_10
+
+        @classmethod
+        def str2rstr_utf8(cls, param1, param2=None):
+            _loc_3 = ''
+            _loc_4 = -1
+            if not param2:
+                param2 = cls.PADDING
+            param1 = param1 + param2[1:9]
+            while True:
+                _loc_4 += 1
+                if _loc_4 >= len(param1):
+                    break
+                _loc_5 = compat_ord(param1[_loc_4])
+                _loc_6 = compat_ord(param1[_loc_4 + 1]) if _loc_4 + 1 < len(param1) else 0
+                if 55296 <= _loc_5 <= 56319 and 56320 <= _loc_6 <= 57343:
+                    _loc_5 = 65536 + ((_loc_5 & 1023) << 10) + (_loc_6 & 1023)
+                    _loc_4 += 1
+                if _loc_5 <= 127:
+                    _loc_3 += compat_chr(_loc_5)
+                    continue
+                if _loc_5 <= 2047:
+                    _loc_3 += compat_chr(192 | _loc_5 >> 6 & 31) + compat_chr(128 | _loc_5 & 63)
+                    continue
+                if _loc_5 <= 65535:
+                    _loc_3 += compat_chr(224 | _loc_5 >> 12 & 15) + compat_chr(128 | _loc_5 >> 6 & 63) + compat_chr(
+                        128 | _loc_5 & 63)
+                    continue
+                if _loc_5 <= 2097151:
+                    _loc_3 += compat_chr(240 | _loc_5 >> 18 & 7) + compat_chr(128 | _loc_5 >> 12 & 63) + compat_chr(
+                        128 | _loc_5 >> 6 & 63) + compat_chr(128 | _loc_5 & 63)
+            return _loc_3
+
+        @staticmethod
+        def rstr2binl(param1):
+            _loc_2 = [0] * ((len(param1) >> 2) + 1)
+            for _loc_3 in range(0, len(_loc_2)):
+                _loc_2[_loc_3] = 0
+            for _loc_3 in range(0, len(param1) * 8, 8):
+                _loc_2[_loc_3 >> 5] |= (compat_ord(param1[_loc_3 // 8]) & 255) << _loc_3 % 32
+            return _loc_2
+
+        @staticmethod
+        def binl2rstr(param1):
+            _loc_2 = ''
+            for _loc_3 in range(0, len(param1) * 32, 8):
+                _loc_2 += compat_chr(param1[_loc_3 >> 5] >> _loc_3 % 32 & 255)
+            return _loc_2
+
+        @classmethod
+        def binl_md5(cls, param1, param2):
+            param1 = cls.JSArray(param1)
+            param1[param2 >> 5] |= 128 << param2 % 32
+            param1[(param2 + 64 >> 9 << 4) + 14] = param2
+            _loc_3 = 1732584193
+            _loc_4 = -271733879
+            _loc_5 = -1732584194
+            _loc_6 = 271733878
+            for _loc_7 in range(0, len(param1), 16):
+                _loc_8 = _loc_3
+                _loc_9 = _loc_4
+                _loc_10 = _loc_5
+                _loc_11 = _loc_6
+                _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 0], 7, -680876936)
+                _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 1], 12, -389564586)
+                _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 2], 17, 606105819)
+                _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 3], 22, -1044525330)
+                _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 4], 7, -176418897)
+                _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 5], 12, 1200080426)
+                _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 6], 17, -1473231341)
+                _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 7], 22, -45705983)
+                _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 8], 7, 1770035416)
+                _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 9], 12, -1958414417)
+                _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 10], 17, -42063)
+                _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 11], 22, -1990404162)
+                _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 12], 7, 1804603682)
+                _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 13], 12, -40341101)
+                _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 14], 17, -1502002290)
+                _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 15], 22, 1236535329)
+                _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 1], 5, -165796510)
+                _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 6], 9, -1069501632)
+                _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 11], 14, 643717713)
+                _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 0], 20, -373897302)
+                _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 5], 5, -701558691)
+                _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 10], 9, 38016083)
+                _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 15], 14, -660478335)
+                _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 4], 20, -405537848)
+                _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 9], 5, 568446438)
+                _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 14], 9, -1019803690)
+                _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 3], 14, -187363961)
+                _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 8], 20, 1163531501)
+                _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 13], 5, -1444681467)
+                _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 2], 9, -51403784)
+                _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 7], 14, 1735328473)
+                _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 12], 20, -1926607734)
+                _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 5], 4, -378558)
+                _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 8], 11, -2022574463)
+                _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 11], 16, 1839030562)
+                _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 14], 23, -35309556)
+                _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 1], 4, -1530992060)
+                _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 4], 11, 1272893353)
+                _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 7], 16, -155497632)
+                _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 10], 23, -1094730640)
+                _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 13], 4, 681279174)
+                _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 0], 11, -358537222)
+                _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 3], 16, -722521979)
+                _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 6], 23, 76029189)
+                _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 9], 4, -640364487)
+                _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 12], 11, -421815835)
+                _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 15], 16, 530742520)
+                _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 2], 23, -995338651)
+                _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 0], 6, -198630844)
+                _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 7], 10, 1126891415)
+                _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 14], 15, -1416354905)
+                _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 5], 21, -57434055)
+                _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 12], 6, 1700485571)
+                _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 3], 10, -1894986606)
+                _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 10], 15, -1051523)
+                _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 1], 21, -2054922799)
+                _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 8], 6, 1873313359)
+                _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 15], 10, -30611744)
+                _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 6], 15, -1560198380)
+                _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 13], 21, 1309151649)
+                _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 4], 6, -145523070)
+                _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 11], 10, -1120210379)
+                _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 2], 15, 718787259)
+                _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 9], 21, -343485551)
+                _loc_3 = cls.safe_add(_loc_3, _loc_8)
+                _loc_4 = cls.safe_add(_loc_4, _loc_9)
+                _loc_5 = cls.safe_add(_loc_5, _loc_10)
+                _loc_6 = cls.safe_add(_loc_6, _loc_11)
+            return [_loc_3, _loc_4, _loc_5, _loc_6]
+
+        @classmethod
+        def md5_cmn(cls, param1, param2, param3, param4, param5, param6):
+            return cls.safe_add(
+                cls.bit_rol(cls.safe_add(cls.safe_add(param2, param1), cls.safe_add(param4, param6)), param5), param3)
+
+        @classmethod
+        def md5_ff(cls, param1, param2, param3, param4, param5, param6, param7):
+            return cls.md5_cmn(param2 & param3 | ~param2 & param4, param1, param2, param5, param6, param7)
+
+        @classmethod
+        def md5_gg(cls, param1, param2, param3, param4, param5, param6, param7):
+            return cls.md5_cmn(param2 & param4 | param3 & ~param4, param1, param2, param5, param6, param7)
+
+        @classmethod
+        def md5_hh(cls, param1, param2, param3, param4, param5, param6, param7):
+            return cls.md5_cmn(param2 ^ param3 ^ param4, param1, param2, param5, param6, param7)
+
+        @classmethod
+        def md5_ii(cls, param1, param2, param3, param4, param5, param6, param7):
+            return cls.md5_cmn(param3 ^ (param2 | ~param4), param1, param2, param5, param6, param7)
+
+        @classmethod
+        def safe_add(cls, param1, param2):
+            _loc_3 = (param1 & 65535) + (param2 & 65535)
+            _loc_4 = (param1 >> 16) + (param2 >> 16) + (_loc_3 >> 16)
+            return cls.lshift(_loc_4, 16) | _loc_3 & 65535
+
+        @classmethod
+        def bit_rol(cls, param1, param2):
+            return cls.lshift(param1, param2) | (param1 & 0xFFFFFFFF) >> (32 - param2)
+
+        @staticmethod
+        def lshift(value, count):
+            r = (0xFFFFFFFF & value) << count
+            return -(~(r - 1) & 0xFFFFFFFF) if r > 0x7FFFFFFF else r
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
+
+        video = self._download_json(
+            self._API_URL_TEMPLATE % video_id, video_id)['videos'][0]
+
+        title = video['title']
+        duration = float_or_none(video['duration'], 1000)
+        like_count = video['likes']
+        uploader = video['channel']
+        uploader_id = video['channel_id']
+
+        formats = []
+
+        for resource in video['resources']:
+            resource_id = resource.get('_id')
+            if not resource_id:
+                continue
+
+            security = self._download_json(
+                self._SECURITY_URL_TEMPLATE % (video_id, resource_id),
+                video_id, 'Downloading security hash for %s' % resource_id)
+
+            security_hash = security.get('hash')
+            if not security_hash:
+                message = security.get('message')
+                if message:
+                    raise ExtractorError(
+                        '%s returned error: %s' % (self.IE_NAME, message), expected=True)
+                continue
+
+            hash_code = security_hash[:2]
+            received_time = int(security_hash[2:12])
+            received_random = security_hash[12:22]
+            received_md5 = security_hash[22:]
+
+            sign_time = received_time + self._RESIGN_EXPIRATION
+            padding = '%010d' % random.randint(1, 10000000000)
+
+            signed_md5 = self.MD5.b64_md5(received_md5 + compat_str(sign_time) + padding)
+            signed_hash = hash_code + compat_str(received_time) + received_random + compat_str(sign_time) + padding + signed_md5
+
+            formats.append({
+                'url': '%s?h=%s&k=%s' % (resource['url'], signed_hash, 'flash'),
+                'format_id': resource_id,
+                'height': resource['height']
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'duration': duration,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'like_count': like_count,
+            'formats': formats
+        }

youtube_dl/extractor/godtube.py

@@ -36,16 +36,16 @@ class GodTubeIE(InfoExtractor):
             'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(),
             video_id, 'Downloading player config XML')
 
-        video_url = config.find('.//file').text
-        uploader = config.find('.//author').text
-        timestamp = parse_iso8601(config.find('.//date').text)
-        duration = parse_duration(config.find('.//duration').text)
-        thumbnail = config.find('.//image').text
+        video_url = config.find('file').text
+        uploader = config.find('author').text
+        timestamp = parse_iso8601(config.find('date').text)
+        duration = parse_duration(config.find('duration').text)
+        thumbnail = config.find('image').text
 
         media = self._download_xml(
             'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML')
 
-        title = media.find('.//title').text
+        title = media.find('title').text
 
         return {
             'id': video_id,

youtube_dl/extractor/golem.py

@@ -0,0 +1,69 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    determine_ext,
+)
+
+
+class GolemIE(InfoExtractor):
+    _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
+    _TEST = {
+        'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
+        'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
+        'info_dict': {
+            'id': '14095',
+            'format_id': 'high',
+            'ext': 'mp4',
+            'title': 'iPhone 6 und 6 Plus - Test',
+            'duration': 300.44,
+            'filesize': 65309548,
+        }
+    }
+
+    _PREFIX = 'http://video.golem.de'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        config = self._download_xml(
+            'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id)
+
+        info = {
+            'id': video_id,
+            'title': config.findtext('./title', 'golem'),
+            'duration': self._float(config.findtext('./playtime'), 'duration'),
+        }
+
+        formats = []
+        for e in config:
+            url = e.findtext('./url')
+            if not url:
+                continue
+
+            formats.append({
+                'format_id': e.tag,
+                'url': compat_urlparse.urljoin(self._PREFIX, url),
+                'height': self._int(e.get('height'), 'height'),
+                'width': self._int(e.get('width'), 'width'),
+                'filesize': self._int(e.findtext('filesize'), 'filesize'),
+                'ext': determine_ext(e.findtext('./filename')),
+            })
+        self._sort_formats(formats)
+        info['formats'] = formats
+
+        thumbnails = []
+        for e in config.findall('.//teaser'):
+            url = e.findtext('./url')
+            if not url:
+                continue
+            thumbnails.append({
+                'url': compat_urlparse.urljoin(self._PREFIX, url),
+                'width': self._int(e.get('width'), 'thumbnail width'),
+                'height': self._int(e.get('height'), 'thumbnail height'),
+            })
+        info['thumbnails'] = thumbnails
+
+        return info

youtube_dl/extractor/googleplus.py

@@ -1,13 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import datetime
 import re
+import codecs
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+from ..utils import unified_strdate
 
 
 class GooglePlusIE(InfoExtractor):
@@ -19,74 +17,57 @@ class GooglePlusIE(InfoExtractor):
         'info_dict': {
             'id': 'ZButuJc6CtH',
             'ext': 'flv',
+            'title': '嘆きの天使 降臨',
             'upload_date': '20120613',
             'uploader': '井上ヨシマサ',
-            'title': '嘆きの天使 降臨',
         }
     }
 
     def _real_extract(self, url):
-        # Extract id from URL
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         # Step 1, Retrieve post webpage to extract further information
         webpage = self._download_webpage(url, video_id, 'Downloading entry webpage')
 
-        self.report_extraction(video_id)
-
-        # Extract update date
-        upload_date = self._html_search_regex(
+        title = self._og_search_description(webpage).splitlines()[0]
+        upload_date = unified_strdate(self._html_search_regex(
             r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*>
                     ([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''',
-            webpage, 'upload date', fatal=False, flags=re.VERBOSE)
-        if upload_date:
-            # Convert timestring to a format suitable for filename
-            upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
-            upload_date = upload_date.strftime('%Y%m%d')
-
-        # Extract uploader
-        uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>',
-            webpage, 'uploader', fatal=False)
-
-        # Extract title
-        # Get the first line for title
-        video_title = self._og_search_description(webpage).splitlines()[0]
+            webpage, 'upload date', fatal=False, flags=re.VERBOSE))
+        uploader = self._html_search_regex(
+            r'rel="author".*?>(.*?)</a>', webpage, 'uploader', fatal=False)
 
         # Step 2, Simulate clicking the image box to launch video
         DOMAIN = 'https://plus.google.com/'
-        video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
+        video_page = self._search_regex(
+            r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
             webpage, 'video page URL')
         if not video_page.startswith(DOMAIN):
             video_page = DOMAIN + video_page
 
         webpage = self._download_webpage(video_page, video_id, 'Downloading video page')
 
+        def unicode_escape(s):
+            decoder = codecs.getdecoder('unicode_escape')
+            return re.sub(
+                r'\\u[0-9a-fA-F]{4,}',
+                lambda m: decoder(m.group(0))[0],
+                s)
+
         # Extract video links all sizes
-        pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
-        mobj = re.findall(pattern, webpage)
-        if len(mobj) == 0:
-            raise ExtractorError('Unable to extract video links')
-
-        # Sort in resolution
-        links = sorted(mobj)
-
-        # Choose the lowest of the sort, i.e. highest resolution
-        video_url = links[-1]
-        # Only get the url. The resolution part in the tuple has no use anymore
-        video_url = video_url[-1]
-        # Treat escaped \u0026 style hex
-        try:
-            video_url = video_url.decode("unicode_escape")
-        except AttributeError: # Python 3
-            video_url = bytes(video_url, 'ascii').decode('unicode-escape')
+        formats = [{
+            'url': unicode_escape(video_url),
+            'ext': 'flv',
+            'width': int(width),
+            'height': int(height),
+        } for width, height, video_url in re.findall(
+            r'\d+,(\d+),(\d+),"(https?://redirector\.googlevideo\.com.*?)"', webpage)]
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'url': video_url,
+            'title': title,
             'uploader': uploader,
             'upload_date': upload_date,
-            'title': video_title,
-            'ext': 'flv',
+            'formats': formats,
         }

youtube_dl/extractor/googlesearch.py

@@ -14,6 +14,14 @@ class GoogleSearchIE(SearchInfoExtractor):
     _MAX_RESULTS = 1000
     IE_NAME = 'video.google:search'
     _SEARCH_KEY = 'gvsearch'
+    _TEST = {
+        'url': 'gvsearch15:python language',
+        'info_dict': {
+            'id': 'python language',
+            'title': 'python language',
+        },
+        'playlist_count': 15,
+    }
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""

youtube_dl/extractor/gorillavid.py

@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     determine_ext,
     compat_urllib_parse,
     compat_urllib_request,
@@ -12,20 +13,22 @@ from ..utils import (
 
 
 class GorillaVidIE(InfoExtractor):
-    IE_DESC = 'GorillaVid.in and daclips.in'
+    IE_DESC = 'GorillaVid.in, daclips.in and movpod.in'
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?
-            (?:daclips\.in|gorillavid\.in))/
+            (?:daclips\.in|gorillavid\.in|movpod\.in))/
         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
     '''
 
+    _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
+
     _TESTS = [{
         'url': 'http://gorillavid.in/06y9juieqpmi',
         'md5': '5ae4a3580620380619678ee4875893ba',
         'info_dict': {
             'id': '06y9juieqpmi',
             'ext': 'flv',
-            'title': 'Rebecca Black My Moment Official Music Video Reaction',
+            'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
@@ -46,6 +49,9 @@ class GorillaVidIE(InfoExtractor):
             'title': 'Micro Pig piglets ready on 16th July 2009',
             'thumbnail': 're:http://.*\.jpg',
         },
+    }, {
+        'url': 'http://movpod.in/0wguyyxi1yca',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -54,6 +60,9 @@ class GorillaVidIE(InfoExtractor):
 
         webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
 
+        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
         fields = dict(re.findall(r'''(?x)<input\s+
             type="hidden"\s+
             name="([^"]+)"\s+
@@ -69,14 +78,14 @@ class GorillaVidIE(InfoExtractor):
 
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
-        title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
-        thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
-        url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')
+        title = self._search_regex(r'style="z-index: [0-9]+;">([^<]+)</span>', webpage, 'title')
+        video_url = self._search_regex(r'file\s*:\s*\'(http[^\']+)\',', webpage, 'file url')
+        thumbnail = self._search_regex(r'image\s*:\s*\'(http[^\']+)\',', webpage, 'thumbnail', fatal=False)
 
         formats = [{
             'format_id': 'sd',
-            'url': url,
-            'ext': determine_ext(url),
+            'url': video_url,
+            'ext': determine_ext(video_url),
             'quality': 1,
         }]
 

youtube_dl/extractor/grooveshark.py

@@ -0,0 +1,190 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import time
+import math
+import os.path
+import re
+
+
+from .common import InfoExtractor
+from ..utils import ExtractorError, compat_urllib_request, compat_html_parser
+
+from ..utils import (
+    compat_urllib_parse,
+    compat_urlparse,
+)
+
+
+class GroovesharkHtmlParser(compat_html_parser.HTMLParser):
+    def __init__(self):
+        self._current_object = None
+        self.objects = []
+        compat_html_parser.HTMLParser.__init__(self)
+
+    def handle_starttag(self, tag, attrs):
+        attrs = dict((k, v) for k, v in attrs)
+        if tag == 'object':
+            self._current_object = {'attrs': attrs, 'params': []}
+        elif tag == 'param':
+            self._current_object['params'].append(attrs)
+
+    def handle_endtag(self, tag):
+        if tag == 'object':
+            self.objects.append(self._current_object)
+            self._current_object = None
+
+    @classmethod
+    def extract_object_tags(cls, html):
+        p = cls()
+        p.feed(html)
+        p.close()
+        return p.objects
+
+
+class GroovesharkIE(InfoExtractor):
+    _VALID_URL = r'https?://(www\.)?grooveshark\.com/#!/s/([^/]+)/([^/]+)'
+    _TEST = {
+        'url': 'http://grooveshark.com/#!/s/Jolene+Tenth+Key+Remix+Ft+Will+Sessions/6SS1DW?src=5',
+        'md5': '7ecf8aefa59d6b2098517e1baa530023',
+        'info_dict': {
+            'id': '6SS1DW',
+            'title': 'Jolene (Tenth Key Remix ft. Will Sessions)',
+            'ext': 'mp3',
+            'duration': 227,
+        }
+    }
+
+    do_playerpage_request = True
+    do_bootstrap_request = True
+
+    def _parse_target(self, target):
+        uri = compat_urlparse.urlparse(target)
+        hash = uri.fragment[1:].split('?')[0]
+        token = os.path.basename(hash.rstrip('/'))
+        return (uri, hash, token)
+
+    def _build_bootstrap_url(self, target):
+        (uri, hash, token) = self._parse_target(target)
+        query = 'getCommunicationToken=1&hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts)
+        return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
+
+    def _build_meta_url(self, target):
+        (uri, hash, token) = self._parse_target(target)
+        query = 'hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts)
+        return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
+
+    def _build_stream_url(self, meta):
+        return compat_urlparse.urlunparse(('http', meta['streamKey']['ip'], '/stream.php', None, None, None))
+
+    def _build_swf_referer(self, target, obj):
+        (uri, _, _) = self._parse_target(target)
+        return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None))
+
+    def _transform_bootstrap(self, js):
+        return re.split('(?m)^\s*try\s*{', js)[0] \
+                 .split(' = ', 1)[1].strip().rstrip(';')
+
+    def _transform_meta(self, js):
+        return js.split('\n')[0].split('=')[1].rstrip(';')
+
+    def _get_meta(self, target):
+        (meta_url, token) = self._build_meta_url(target)
+        self.to_screen('Metadata URL: %s' % meta_url)
+
+        headers = {'Referer': compat_urlparse.urldefrag(target)[0]}
+        req = compat_urllib_request.Request(meta_url, headers=headers)
+        res = self._download_json(req, token,
+                                  transform_source=self._transform_meta)
+
+        if 'getStreamKeyWithSong' not in res:
+            raise ExtractorError(
+                'Metadata not found. URL may be malformed, or Grooveshark API may have changed.')
+
+        if res['getStreamKeyWithSong'] is None:
+            raise ExtractorError(
+                'Metadata download failed, probably due to Grooveshark anti-abuse throttling. Wait at least an hour before retrying from this IP.',
+                expected=True)
+
+        return res['getStreamKeyWithSong']
+
+    def _get_bootstrap(self, target):
+        (bootstrap_url, token) = self._build_bootstrap_url(target)
+
+        headers = {'Referer': compat_urlparse.urldefrag(target)[0]}
+        req = compat_urllib_request.Request(bootstrap_url, headers=headers)
+        res = self._download_json(req, token, fatal=False,
+                                  note='Downloading player bootstrap data',
+                                  errnote='Unable to download player bootstrap data',
+                                  transform_source=self._transform_bootstrap)
+        return res
+
+    def _get_playerpage(self, target):
+        (_, _, token) = self._parse_target(target)
+
+        webpage = self._download_webpage(
+            target, token,
+            note='Downloading player page',
+            errnote='Unable to download player page',
+            fatal=False)
+
+        if webpage is not None:
+            # Search (for example German) error message
+            error_msg = self._html_search_regex(
+                r'<div id="content">\s*<h2>(.*?)</h2>', webpage,
+                'error message', default=None)
+            if error_msg is not None:
+                error_msg = error_msg.replace('\n', ' ')
+                raise ExtractorError('Grooveshark said: %s' % error_msg)
+
+        if webpage is not None:
+            o = GroovesharkHtmlParser.extract_object_tags(webpage)
+            return (webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed'])
+
+        return (webpage, None)
+
+    def _real_initialize(self):
+        self.ts = int(time.time() * 1000)  # timestamp in millis
+
+    def _real_extract(self, url):
+        (target_uri, _, token) = self._parse_target(url)
+
+        # 1. Fill cookiejar by making a request to the player page
+        swf_referer = None
+        if self.do_playerpage_request:
+            (_, player_objs) = self._get_playerpage(url)
+            if player_objs is not None:
+                swf_referer = self._build_swf_referer(url, player_objs[0])
+                self.to_screen('SWF Referer: %s' % swf_referer)
+
+        # 2. Ask preload.php for swf bootstrap data to better mimic webapp
+        if self.do_bootstrap_request:
+            bootstrap = self._get_bootstrap(url)
+            self.to_screen('CommunicationToken: %s' % bootstrap['getCommunicationToken'])
+
+        # 3. Ask preload.php for track metadata.
+        meta = self._get_meta(url)
+
+        # 4. Construct stream request for track.
+        stream_url = self._build_stream_url(meta)
+        duration = int(math.ceil(float(meta['streamKey']['uSecs']) / 1000000))
+        post_dict = {'streamKey': meta['streamKey']['streamKey']}
+        post_data = compat_urllib_parse.urlencode(post_dict).encode('utf-8')
+        headers = {
+            'Content-Length': len(post_data),
+            'Content-Type': 'application/x-www-form-urlencoded'
+        }
+        if swf_referer is not None:
+            headers['Referer'] = swf_referer
+
+        return {
+            'id': token,
+            'title': meta['song']['Name'],
+            'http_method': 'POST',
+            'url': stream_url,
+            'ext': 'mp3',
+            'format': 'mp3 audio',
+            'duration': duration,
+            'http_post_data': post_data,
+            'http_headers': headers,
+        }

youtube_dl/extractor/heise.py

@@ -0,0 +1,81 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    get_meta_content,
+    parse_iso8601,
+)
+
+
+class HeiseIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?heise\.de/video/artikel/
+        .+?(?P<id>[0-9]+)\.html(?:$|[?#])
+    '''
+    _TEST = {
+        'url': (
+            'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
+        ),
+        'md5': 'ffed432483e922e88545ad9f2f15d30e',
+        'info_dict': {
+            'id': '2404147',
+            'ext': 'mp4',
+            'title': (
+                "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone"
+            ),
+            'format_id': 'mp4_720',
+            'timestamp': 1411812600,
+            'upload_date': '20140927',
+            'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        json_url = self._search_regex(
+            r'json_url:\s*"([^"]+)"', webpage, 'json URL')
+        config = self._download_json(json_url, video_id)
+
+        info = {
+            'id': video_id,
+            'thumbnail': config.get('poster'),
+            'timestamp': parse_iso8601(get_meta_content('date', webpage)),
+            'description': self._og_search_description(webpage),
+        }
+
+        title = get_meta_content('fulltitle', webpage)
+        if title:
+            info['title'] = title
+        elif config.get('title'):
+            info['title'] = config['title']
+        else:
+            info['title'] = self._og_search_title(webpage)
+
+        formats = []
+        for t, rs in config['formats'].items():
+            if not rs or not hasattr(rs, 'items'):
+                self._downloader.report_warning(
+                    'formats: {0}: no resolutions'.format(t))
+                continue
+
+            for height_str, obj in rs.items():
+                format_id = '{0}_{1}'.format(t, height_str)
+
+                if not obj or not obj.get('url'):
+                    self._downloader.report_warning(
+                        'formats: {0}: no url'.format(format_id))
+                    continue
+
+                formats.append({
+                    'url': obj['url'],
+                    'format_id': format_id,
+                    'height': self._int(height_str, 'height'),
+                })
+
+        self._sort_formats(formats)
+        info['formats'] = formats
+
+        return info

youtube_dl/extractor/hornbunny.py

@@ -0,0 +1,56 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+)
+
+
+class HornBunnyIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
+    _TEST = {
+        'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
+        'md5': '95e40865aedd08eff60272b704852ad7',
+        'info_dict': {
+            'id': '5227',
+            'ext': 'flv',
+            'title': 'panty slut jerk off instruction',
+            'duration': 550,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(
+            url, video_id, note='Downloading initial webpage')
+        title = self._html_search_regex(
+            r'class="title">(.*?)</h2>', webpage, 'title')
+        redirect_url = self._html_search_regex(
+            r'pg&settings=(.*?)\|0"\);', webpage, 'title')
+        webpage2 = self._download_webpage(redirect_url, video_id)
+        video_url = self._html_search_regex(
+            r'flvMask:(.*?);', webpage2, 'video_url')
+        
+        duration = parse_duration(self._search_regex(
+            r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
+            webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'<strong>Views:</strong>\s*(\d+)</div>',
+            webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'ext': 'flv',
+            'duration': duration,
+            'view_count': view_count,
+            'age_limit': 18,
+        }

youtube_dl/extractor/hostingbulk.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    int_or_none,
+    urlencode_postdata,
+)
+
+
+class HostingBulkIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?hostingbulk\.com/
+        (?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html'''
+    _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
+    _TEST = {
+        'url': 'http://hostingbulk.com/n0ulw1hv20fm.html',
+        'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f',
+        'info_dict': {
+            'id': 'n0ulw1hv20fm',
+            'ext': 'mp4',
+            'title': 'md5:5afeba33f48ec87219c269e054afd622',
+            'filesize': 6816081,
+            'thumbnail': 're:^http://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
+
+        # Custom request with cookie to set language to English, so our file
+        # deleted regex would work.
+        request = compat_urllib_request.Request(
+            url, headers={'Cookie': 'lang=english'})
+        webpage = self._download_webpage(request, video_id)
+
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
+        title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title')
+        filesize = int_or_none(
+            self._search_regex(
+                r'<small>\((\d+)\sbytes?\)</small>',
+                webpage,
+                'filesize',
+                fatal=False
+            )
+        )
+        thumbnail = self._search_regex(
+            r'<img src="([^"]+)".+?class="pic"',
+            webpage, 'thumbnail', fatal=False)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            value="([^"]*)"
+            ''', webpage))
+
+        request = compat_urllib_request.Request(url, urlencode_postdata(fields))
+        request.add_header('Content-type', 'application/x-www-form-urlencoded')
+        response = self._request_webpage(request, video_id,
+                                         'Submiting download request')
+        video_url = response.geturl()
+
+        formats = [{
+            'format_id': 'sd',
+            'filesize': filesize,
+            'url': video_url,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/howstuffworks.py

@@ -0,0 +1,134 @@
+from __future__ import unicode_literals
+
+import re
+import json
+import random
+import string
+
+from .common import InfoExtractor
+from ..utils import find_xpath_attr
+
+
+class HowStuffWorksIE(InfoExtractor):
+    _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm'
+    _TESTS = [
+        {
+            'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm',
+            'info_dict': {
+                'id': '450221',
+                'display_id': 'cool-jobs-iditarod-musher',
+                'ext': 'flv',
+                'title': 'Cool Jobs - Iditarod Musher',
+                'description': 'md5:82bb58438a88027b8186a1fccb365f90',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                # md5 is not consistent
+                'skip_download': True
+            }
+        },
+        {
+            'url': 'http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm',
+            'info_dict': {
+                'id': '453464',
+                'display_id': 'survival-zone-food-and-water-in-the-savanna',
+                'ext': 'mp4',
+                'title': 'Survival Zone: Food and Water In the Savanna',
+                'description': 'md5:7e1c89f6411434970c15fa094170c371',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                # md5 is not consistent
+                'skip_download': True
+            }
+        },
+        {
+            'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm',
+            'info_dict': {
+                'id': '440011',
+                'display_id': 'sword-swallowing-1-by-dan-meyer',
+                'ext': 'flv',
+                'title': 'Sword Swallowing #1 by Dan Meyer',
+                'description': 'md5:b2409e88172913e2e7d3d1159b0ef735',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                # md5 is not consistent
+                'skip_download': True
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        webpage = self._download_webpage(url, display_id)
+
+        content_id = self._search_regex(r'var siteSectionId="(\d+)";', webpage, 'content id')
+
+        mp4 = self._search_regex(
+            r'''(?xs)var\s+clip\s*=\s*{\s*
+                .+?\s*
+                content_id\s*:\s*%s\s*,\s*
+                .+?\s*
+                mp4\s*:\s*\[(.*?),?\]\s*
+                };\s*
+                videoData\.push\(clip\);''' % content_id,
+            webpage, 'mp4', fatal=False, default=None)
+
+        smil = self._download_xml(
+            'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % content_id,
+            content_id, 'Downloading video SMIL')
+
+        http_base = find_xpath_attr(
+            smil,
+            './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'),
+            'name',
+            'httpBase').get('content')
+
+        def random_string(str_len=0):
+            return ''.join([random.choice(string.ascii_uppercase) for _ in range(str_len)])
+
+        URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=%s&g=%s' % (random_string(5), random_string(12))
+
+        formats = []
+
+        if mp4:
+            for video in json.loads('[%s]' % mp4):
+                bitrate = video['bitrate']
+                fmt = {
+                    'url': video['src'].replace('http://pmd.video.howstuffworks.com', http_base) + URL_SUFFIX,
+                    'format_id': bitrate,
+                }
+                m = re.search(r'(?P<vbr>\d+)[Kk]', bitrate)
+                if m:
+                    fmt['vbr'] = int(m.group('vbr'))
+                formats.append(fmt)
+        else:
+            for video in smil.findall(
+                    './/{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')):
+                vbr = int(video.attrib['system-bitrate']) / 1000
+                formats.append({
+                    'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX),
+                    'format_id': '%dk' % vbr,
+                    'vbr': vbr,
+                })
+
+        self._sort_formats(formats)
+
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' : HowStuffWorks'
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
+
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        return {
+            'id': content_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/huffpost.py

@@ -33,8 +33,7 @@ class HuffPostIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         api_url = 'http://embed.live.huffingtonpost.com/api/segments/%s.json' % video_id
         data = self._download_json(api_url, video_id)['data']