release 2015.02.17.2

So that we don't have to implement all the methods used by the cookiejar.

.travis.yml

@@ -4,6 +4,9 @@ python:
   - "2.7"
   - "3.3"
   - "3.4"
+before_install:
+  - sudo apt-get update -qq
+  - sudo apt-get install -yqq rtmpdump
 script: nosetests test --verbose
 notifications:
   email:

AUTHORS

@@ -101,3 +101,13 @@ Thijs Vermeir
 Joel Leclerc
 Christopher Krooss
 Ondřej Caletka
+Dinesh S
+Johan K. Jensen
+Yen Chi Hsuan
+Enam Mijbah Noor
+David Luhmer
+Shaya Goldberg
+Paul Hartmann
+Frans de Jonge
+Robin de Rooij
+Ryan Schmidt

CONTRIBUTING.md

@@ -1,4 +1,6 @@
-Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
+**Please include the full output of youtube-dl when run with `-v`**.
+
+The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
 Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
 
@@ -44,7 +46,7 @@ In particular, every site support request issue should only pertain to services
 
 ###  Is anyone going to need the feature?
 
-Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
+Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
 
 ###  Is your question about youtube-dl?
 
@@ -122,7 +124,7 @@ If you want to add support for a new site, you can follow this quick list (assum
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/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).
+8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/__init__.py

Makefile

@@ -1,10 +1,7 @@
 all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json CONTRIBUTING.md.tmp
-
-cleanall: clean
-	rm -f youtube-dl youtube-dl.exe
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
 
 PREFIX ?= /usr/local
 BINDIR ?= $(PREFIX)/bin
@@ -63,7 +60,7 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	chmod a+x youtube-dl
 
 README.md: youtube_dl/*.py youtube_dl/*/*.py
-	COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
+	COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
 
 CONTRIBUTING.md: README.md
 	python devscripts/make_contributing.py README.md CONTRIBUTING.md

README.md

@@ -60,10 +60,6 @@ which means you can modify it, redistribute it or use it however you like.
                                      they would handle
     --extractor-descriptions         Output descriptions of all supported
                                      extractors
-    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
-                                     an empty string (--proxy "") for direct
-                                     connection
-    --socket-timeout None            Time to wait before giving up, in seconds
     --default-search PREFIX          Use this prefix for unqualified URLs. For
                                      example "gvsearch2:" downloads two videos
                                      from google videos for  youtube-dl "large
@@ -81,10 +77,31 @@ which means you can modify it, redistribute it or use it however you like.
                                      on Windows)
     --flat-playlist                  Do not extract the videos of a playlist,
                                      only list them.
+    --no-color                       Do not emit color codes in output.
+
+## Network Options:
+    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
+                                     an empty string (--proxy "") for direct
+                                     connection
+    --socket-timeout SECONDS         Time to wait before giving up, in seconds
+    --source-address IP              Client-side IP address to bind to
+                                     (experimental)
+    -4, --force-ipv4                 Make all connections via IPv4
+                                     (experimental)
+    -6, --force-ipv6                 Make all connections via IPv6
+                                     (experimental)
 
 ## Video Selection:
     --playlist-start NUMBER          playlist video to start at (default is 1)
     --playlist-end NUMBER            playlist video to end at (default is last)
+    --playlist-items ITEM_SPEC       playlist video items to download. Specify
+                                     indices of the videos in the playlist
+                                     seperated by commas like: "--playlist-items
+                                     1,2,5,8" if you want to download videos
+                                     indexed 1, 2, 5, 8 in the playlist. You can
+                                     specify range: "--playlist-items
+                                     1-3,7,10-13", it will download the videos
+                                     at index 1, 2, 3, 7, 10, 11, 12 and 13.
     --match-title REGEX              download only matching titles (regex or
                                      caseless sub-string)
     --reject-title REGEX             skip download for matching titles (regex or
@@ -103,6 +120,23 @@ which means you can modify it, redistribute it or use it however you like.
                                      COUNT views
     --max-views COUNT                Do not download any videos with more than
                                      COUNT views
+    --match-filter FILTER            (Experimental) Generic video filter.
+                                     Specify any key (see help for -o for a list
+                                     of available keys) to match if the key is
+                                     present, !key to check if the key is not
+                                     present,key > NUMBER (like "comment_count >
+                                     12", also works with >=, <, <=, !=, =) to
+                                     compare against a number, and & to require
+                                     multiple matches. Values which are not
+                                     known are excluded unless you put a
+                                     question mark (?) after the operator.For
+                                     example, to only match videos that have
+                                     been liked more than 100 times and disliked
+                                     less than 50 times (or the dislike
+                                     functionality is not available at the given
+                                     service), but who also have a description,
+                                     use  --match-filter "like_count > 100 &
+                                     dislike_count <? 50 & description" .
     --no-playlist                    If the URL refers to a video and a
                                      playlist, download only the video.
     --age-limit YEARS                download only videos suitable for the given
@@ -116,7 +150,8 @@ which means you can modify it, redistribute it or use it however you like.
 ## Download Options:
     -r, --rate-limit LIMIT           maximum download rate in bytes per second
                                      (e.g. 50K or 4.2M)
-    -R, --retries RETRIES            number of retries (default is 10)
+    -R, --retries RETRIES            number of retries (default is 10), or
+                                     "infinite".
     --buffer-size SIZE               size of download buffer (e.g. 1024 or 16K)
                                      (default is 1024)
     --no-resize-buffer               do not automatically adjust the buffer
@@ -124,6 +159,13 @@ which means you can modify it, redistribute it or use it however you like.
                                      automatically resized from an initial value
                                      of SIZE.
     --playlist-reverse               Download playlist videos in reverse order
+    --xattr-set-filesize             (experimental) set file xattribute
+                                     ytdl.filesize with expected filesize
+    --hls-prefer-native              (experimental) Use the native HLS
+                                     downloader instead of ffmpeg.
+    --external-downloader COMMAND    (experimental) Use the specified external
+                                     downloader. Currently supports
+                                     aria2c,curl,wget
 
 ## Filesystem Options:
     -a, --batch-file FILE            file containing URLs to download ('-' for
@@ -183,7 +225,6 @@ which means you can modify it, redistribute it or use it however you like.
     --write-info-json                write video metadata to a .info.json file
     --write-annotations              write video annotations to a .annotation
                                      file
-    --write-thumbnail                write thumbnail image to disk
     --load-info FILE                 json file containing the video information
                                      (created with the "--write-json" option)
     --cookies FILE                   file to read cookies from and dump cookie
@@ -198,6 +239,12 @@ which means you can modify it, redistribute it or use it however you like.
     --no-cache-dir                   Disable filesystem caching
     --rm-cache-dir                   Delete all filesystem cache files
 
+## Thumbnail images:
+    --write-thumbnail                write thumbnail image to disk
+    --write-all-thumbnails           write all thumbnail image formats to disk
+    --list-thumbnails                Simulate and list all available thumbnail
+                                     formats
+
 ## Verbosity / Simulation Options:
     -q, --quiet                      activates quiet mode
     --no-warnings                    Ignore warnings
@@ -219,6 +266,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      for each command-line argument. If the URL
                                      refers to a playlist, dump the whole
                                      playlist information in a single line.
+    --print-json                     Be quiet and print the video information as
+                                     JSON (video is still being downloaded).
     --newline                        output progress bar as new lines
     --no-progress                    do not print progress bar
     --console-title                  display progress in console titlebar
@@ -229,6 +278,10 @@ which means you can modify it, redistribute it or use it however you like.
                                      files in the current directory to debug
                                      problems
     --print-traffic                  Display sent and read HTTP traffic
+    -C, --call-home                  Contact the youtube-dl server for
+                                     debugging.
+    --no-call-home                   Do NOT contact the youtube-dl server for
+                                     debugging.
 
 ## Workarounds:
     --encoding ENCODING              Force the specified encoding (experimental)
@@ -245,17 +298,34 @@ which means you can modify it, redistribute it or use it however you like.
     --bidi-workaround                Work around terminals that lack
                                      bidirectional text support. Requires bidiv
                                      or fribidi executable in PATH
+    --sleep-interval SECONDS         Number of seconds to sleep before each
+                                     download.
 
 ## Video Format Options:
     -f, --format FORMAT              video format code, specify the order of
-                                     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
+                                     preference using slashes, as in -f 22/17/18
+                                     .  Instead of format codes, you can select
+                                     by extension for the extensions aac, m4a,
+                                     mp3, mp4, ogg, wav, webm. You can also use
+                                     the special names "best", "bestvideo",
+                                     "bestaudio", "worst".  You can filter the
+                                     video results by putting a condition in
+                                     brackets, as in -f "best[height=720]" (or
+                                     -f "[filesize>10M]").  This works for
+                                     filesize, height, width, tbr, abr, vbr,
+                                     asr, and fps and the comparisons <, <=, >,
+                                     >=, =, != and for ext, acodec, vcodec,
+                                     container, and protocol and the comparisons
+                                     =, != . Formats for which the value is not
+                                     known are excluded unless you put a
+                                     question mark (?) after the operator. You
+                                     can combine format filters, so  -f "[height
+                                     <=? 720][tbr>500]" selects up to 720p
+                                     videos (or videos where the height is not
+                                     known) with a bitrate of at least 500
+                                     KBit/s. 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.
                                      You can merge the video and audio of two
                                      formats into a single file using -f <video-
@@ -269,6 +339,10 @@ which means you can modify it, redistribute it or use it however you like.
     -F, --list-formats               list all available formats
     --youtube-skip-dash-manifest     Do not download the DASH manifest on
                                      YouTube videos
+    --merge-output-format FORMAT     If a merge is required (e.g.
+                                     bestvideo+bestaudio), output to given
+                                     container format. One of mkv, mp4, ogg,
+                                     webm, flv.Ignored if no merge is required
 
 ## Subtitle Options:
     --write-sub                      write subtitle file
@@ -285,7 +359,8 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Authentication Options:
     -u, --username USERNAME          login with this account ID
-    -p, --password PASSWORD          account password
+    -p, --password PASSWORD          account password. If this option is left
+                                     out, youtube-dl will ask interactively.
     -2, --twofactor TWOFACTOR        two-factor auth code
     -n, --netrc                      use .netrc authentication data
     --video-password PASSWORD        video password (vimeo, smotri)
@@ -315,10 +390,18 @@ which means you can modify it, redistribute it or use it however you like.
     --add-metadata                   write metadata to the video file
     --xattrs                         write metadata to the video file's xattrs
                                      (using dublin core and xdg standards)
+    --fixup POLICY                   Automatically correct known faults of the
+                                     file. One of never (do nothing), warn (only
+                                     emit a warning), detect_or_warn(the
+                                     default; fix file if we can, warn
+                                     otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the
                                      postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
                                      postprocessors
+    --ffmpeg-location PATH           Location of the ffmpeg/avconv binary;
+                                     either the path to the binary or its
+                                     containing directory.
     --exec CMD                       Execute a command on the file after
                                      downloading, similar to find's -exec
                                      syntax. Example: --exec 'adb push {}
@@ -326,7 +409,7 @@ which means you can modify it, redistribute it or use it however you like.
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -420,9 +503,15 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much.
 
 Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
 
-### The links provided by youtube-dl -g are not working anymore
+### I extracted a video URL with -g, but it does not play on another machine / in my webbrowser.
 
-The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
+It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies.  Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
+
+It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
+
+Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using -g, your own downloader must support these as well.
+
+If you want to play the video on a machine that is not running youtube-dl, you can relay the video content from the machine that runs youtube-dl. You can use `-o -` to let youtube-dl stream a video to stdout, or simply allow the player to download the files written by youtube-dl in turn.
 
 ### ERROR: no fmt_url_map or conn information found in video info
 
@@ -449,9 +538,36 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
 
 To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
 
+### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?
+
+If you put youtube-dl and ffmpeg in the same directory that you're running the command from, it will work, but that's rather cumbersome.
+
+To make a different directory work - either for ffmpeg, or for youtube-dl, or for both - simply create the directory (say, `C:\bin`, or `C:\Users\<User name>\bin`), put all the executables directly in there, and then [set your PATH environment variable](https://www.java.com/en/download/help/path.xml) to include that directory.
+
+From then on, after restarting your shell, you will be able to access both youtube-dl and ffmpeg (and youtube-dl will be able to find ffmpeg) by simply typing `youtube-dl` or `ffmpeg`, no matter what directory you're in.
+
+### How do I put downloads into a specific folder?
+
+Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration).
+
+### How do I download a video starting with a `-` ?
+
+Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
+
+    youtube-dl -- -wNyEUrxzFU
+    youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
+
+### Can you add support for this anime video site, or site which shows current movies for free?
+
+As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
+
+A note on the service that they don't host the infringing content, but just link to those who do, is evidence that the service should **not** be included into youtube-dl. The same goes for any DMCA note when the whole front page of the service is filled with videos they are not allowed to distribute. A "fair use" note is equally unconvincing if the service shows copyright-protected videos in full without authorization.
+
+Support requests for services that **do** purchase the rights to distribute their content are perfectly fine though. If in doubt, you can simply include a source that mentions the legitimate purchase of content.
+
 ### How can I detect whether a given URL is supported by youtube-dl?
 
-For one, have a look at the [list of supported sites](docs/supportedsites). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
+For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
 
 It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor.
 
@@ -529,7 +645,7 @@ If you want to add support for a new site, you can follow this quick list (assum
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/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).
+8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/__init__.py
@@ -597,7 +713,9 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
 
 Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode.
 
-Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
+**Please include the full output of youtube-dl when run with `-v`**.
+
+The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
 Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
 
@@ -643,7 +761,7 @@ In particular, every site support request issue should only pertain to services
 
 ###  Is anyone going to need the feature?
 
-Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
+Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
 
 ###  Is your question about youtube-dl?
 

devscripts/gh-pages/update-sites.py

@@ -16,7 +16,7 @@ def main():
         template = tmplf.read()
 
     ie_htmls = []
-    for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
+    for ie in youtube_dl.list_extractors(age_limit=None):
         ie_html = '<b>{}</b>'.format(ie.IE_NAME)
         ie_desc = getattr(ie, 'IE_DESC', None)
         if ie_desc is False:

devscripts/make_supportedsites.py

@@ -23,12 +23,12 @@ def main():
 
     def gen_ies_md(ies):
         for ie in ies:
-            ie_md = '**{}**'.format(ie.IE_NAME)
+            ie_md = '**{0}**'.format(ie.IE_NAME)
             ie_desc = getattr(ie, 'IE_DESC', None)
             if ie_desc is False:
                 continue
             if ie_desc is not None:
-                ie_md += ': {}'.format(ie.IE_DESC)
+                ie_md += ': {0}'.format(ie.IE_DESC)
             if not ie.working():
                 ie_md += ' (Currently broken)'
             yield ie_md

devscripts/release.sh

@@ -35,7 +35,7 @@ if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $us
 if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
 
 /bin/echo -e "\n### First of all, testing..."
-make cleanall
+make clean
 if $skip_tests ; then
     echo 'SKIPPING TESTS'
 else
@@ -45,9 +45,9 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 
-/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..."
-make README.md
-git add README.md youtube_dl/version.py
+/bin/echo -e "\n### Committing documentation and youtube_dl/version.py..."
+make README.md CONTRIBUTING.md supportedsites
+git add README.md CONTRIBUTING.md docs/supportedsites.md youtube_dl/version.py
 git commit -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."

docs/supportedsites.md

@@ -1,4 +1,5 @@
 # Supported sites
+ - **1tv**: Первый канал
  - **1up.com**
  - **220.ro**
  - **24video**
@@ -9,16 +10,21 @@
  - **8tracks**
  - **9gag**
  - **abc.net.au**
+ - **Abc7News**
  - **AcademicEarth:Course**
  - **AddAnime**
  - **AdobeTV**
  - **AdultSwim**
+ - **Aftenposten**
  - **Aftonbladet**
  - **AlJazeera**
  - **Allocine**
+ - **AlphaPorno**
  - **anitube.se**
  - **AnySex**
  - **Aparat**
+ - **AppleDailyAnimationNews**
+ - **AppleDailyRealtimeNews**
  - **AppleTrailers**
  - **archive.org**: archive.org videos
  - **ARD**
@@ -30,8 +36,10 @@
  - **arte.tv:ddc**
  - **arte.tv:embed**
  - **arte.tv:future**
+ - **AtresPlayer**
+ - **ATTTechChannel**
  - **audiomack**
- - **AUEngine**
+ - **audiomack:album**
  - **Azubu**
  - **bambuser**
  - **bambuser:channel**
@@ -53,6 +61,8 @@
  - **Brightcove**
  - **BuzzFeed**
  - **BYUtv**
+ - **Camdemy**
+ - **CamdemyFolder**
  - **Canal13cl**
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
@@ -71,8 +81,10 @@
  - **cmt.com**
  - **CNET**
  - **CNN**
+ - **CNNArticle**
  - **CNNBlogs**
  - **CollegeHumor**
+ - **CollegeRama**
  - **ComCarCoff**
  - **ComedyCentral**
  - **ComedyCentralShows**: The Daily Show / The Colbert Report
@@ -82,23 +94,27 @@
  - **Crunchyroll**
  - **crunchyroll:playlist**
  - **CSpan**: C-SPAN
+ - **CtsNews**
  - **culturebox.francetvinfo.fr**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
  - **daum.net**
  - **DBTV**
+ - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
  - **Discovery**
  - **divxstage**: DivxStage
  - **Dotsub**
+ - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
  - **DRTV**
  - **Dump**
  - **dvtv**: http://video.aktualne.cz/
  - **EbaumsWorld**
+ - **EchoMsk**
  - **eHow**
  - **Einthusan**
  - **eitb.tv**
@@ -108,6 +124,7 @@
  - **EMPFlix**
  - **Engadget**
  - **Eporner**
+ - **EroProfile**
  - **Escapist**
  - **EveryonesMixtape**
  - **exfm**: ex.fm
@@ -120,7 +137,6 @@
  - **fernsehkritik.tv:postecke**
  - **Firedrive**
  - **Firstpost**
- - **firsttv**: Видеоархив - Первый канал
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **Foxgay**
@@ -143,6 +159,7 @@
  - **GDCVault**
  - **generic**: Generic downloader that works on some sites
  - **GiantBomb**
+ - **Giga**
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
  - **GodTube**
@@ -153,9 +170,15 @@
  - **Grooveshark**
  - **Groupon**
  - **Hark**
+ - **HearThisAt**
  - **Heise**
+ - **HellPorno**
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
+ - **HistoricFilms**
+ - **History**
+ - **hitbox**
+ - **hitbox:live**
  - **HornBunny**
  - **HostingBulk**
  - **HotNewHipHop**
@@ -182,6 +205,7 @@
  - **jpopsuki.tv**
  - **Jukebox**
  - **Kankan**
+ - **Karaoketv**
  - **keek**
  - **KeezMovies**
  - **KhanAcademy**
@@ -195,6 +219,7 @@
  - **LiveLeak**
  - **livestream**
  - **livestream:original**
+ - **LnkGo**
  - **lrt.lt**
  - **lynda**: lynda.com videos
  - **lynda:course**: lynda.com online courses
@@ -203,6 +228,7 @@
  - **mailru**: Видео@Mail.Ru
  - **Malemotion**
  - **MDR**
+ - **media.ccc.de**
  - **metacafe**
  - **Metacritic**
  - **Mgoon**
@@ -235,6 +261,7 @@
  - **MySpass**
  - **myvideo**
  - **MyVidster**
+ - **n-tv.de**
  - **Naver**
  - **NBA**
  - **NBC**
@@ -242,11 +269,16 @@
  - **ndr**: NDR.de - Mediathek
  - **NDTV**
  - **NerdCubedFeed**
+ - **Nerdist**
+ - **Netzkino**
  - **Newgrounds**
  - **Newstube**
+ - **NextMedia**
+ - **NextMediaActionNews**
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
+ - **nhl.com:news**: NHL news
  - **nhl.com:videocenter**: NHL videocenter category
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
@@ -257,18 +289,22 @@
  - **Nowness**
  - **nowvideo**: NowVideo
  - **npo.nl**
+ - **npo.nl:live**
+ - **npo.nl:radio**
+ - **npo.nl:radio:fragment**
  - **NRK**
  - **NRKTV**
- - **NTV**
+ - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
  - **ocw.mit.edu**
  - **OktoberfestTV**
  - **on.aol.com**
  - **Ooyala**
+ - **OpenFilm**
+ - **orf:fm4**: radio FM4
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
- - **ORFFM4**: radio FM4
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **PBS**
@@ -290,6 +326,7 @@
  - **Pyvideo**
  - **QuickVid**
  - **radio.de**
+ - **radiobremen**
  - **radiofrance**
  - **Rai**
  - **RBMARadio**
@@ -300,8 +337,10 @@
  - **RottenTomatoes**
  - **Roxwel**
  - **RTBF**
+ - **Rte**
+ - **rtl.nl**: rtl.nl and rtlxl.nl
+ - **RTL2**
  - **RTLnow**
- - **rtlxl.nl**
  - **RTP**
  - **RTS**: RTS.ch
  - **rtve.es:alacarta**: RTVE a la carta
@@ -309,6 +348,7 @@
  - **RUHD**
  - **rutube**: Rutube videos
  - **rutube:channel**: Rutube channels
+ - **rutube:embed**: Rutube embedded videos
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
  - **RUTV**: RUTV.RU
@@ -351,12 +391,14 @@
  - **Sport5**
  - **SportBox**
  - **SportDeutschland**
- - **SRMediathek**: Süddeutscher Rundfunk
+ - **SRMediathek**: Saarländischer Rundfunk
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **streamcloud.eu**
  - **StreamCZ**
+ - **StreetVoice**
  - **SunPorno**
+ - **SVTPlay**
  - **SWRMediathek**
  - **Syfy**
  - **SztvHu**
@@ -375,7 +417,9 @@
  - **TeleBruxelles**
  - **telecinco.es**
  - **TeleMB**
+ - **TeleTask**
  - **TenPlay**
+ - **TestTube**
  - **TF1**
  - **TheOnion**
  - **ThePlatform**
@@ -403,8 +447,16 @@
  - **tv.dfb.de**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvp.pl**
+ - **tvp.pl:Series**
  - **TVPlay**: TV3Play and related services
- - **Twitch**
+ - **Tweakers**
+ - **twitch:bookmarks**
+ - **twitch:chapter**
+ - **twitch:past_broadcasts**
+ - **twitch:profile**
+ - **twitch:stream**
+ - **twitch:video**
+ - **twitch:vod**
  - **Ubu**
  - **udemy**
  - **udemy:course**
@@ -433,6 +485,8 @@
  - **videoweed**: VideoWeed
  - **Vidme**
  - **Vidzi**
+ - **vier**
+ - **vier:videos**
  - **viki**
  - **vimeo**
  - **vimeo:album**
@@ -460,11 +514,13 @@
  - **WDR**
  - **wdr:mobile**
  - **WDRMaus**: Sendung mit der Maus
+ - **WebOfStories**
  - **Weibo**
  - **Wimp**
  - **Wistia**
  - **WorldStarHipHop**
  - **wrzuta.pl**
+ - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
  - **XHamster**
@@ -472,8 +528,11 @@
  - **XNXX**
  - **XTube**
  - **XTubeUser**: XTube user profile
+ - **Xuite**
  - **XVideos**
+ - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
+ - **Yam**
  - **YesJapan**
  - **Ynet**
  - **YouJizz**
@@ -491,7 +550,6 @@
  - **youtube:search_url**: YouTube.com search URLs
  - **youtube:show**: YouTube.com (multi-season) shows
  - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- - **youtube:toplist**: YouTube.com top lists, "yttoplist:{channel}:{list title}" (Example: "yttoplist:music:Top Tracks")
  - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
  - **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
  - **ZDF**

setup.cfg

@@ -2,5 +2,5 @@
 universal = True
 
 [flake8]
-exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build
-ignore = E501
+exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build,.git
+ignore = E402,E501,E731

test/helper.py

@@ -82,18 +82,8 @@ class FakeYDL(YoutubeDL):
 
 def gettestcases(include_onlymatching=False):
     for ie in youtube_dl.extractor.gen_extractors():
-        t = getattr(ie, '_TEST', None)
-        if t:
-            assert not hasattr(ie, '_TESTS'), \
-                '%s has _TEST and _TESTS' % type(ie).__name__
-            tests = [t]
-        else:
-            tests = getattr(ie, '_TESTS', [])
-        for t in tests:
-            if not include_onlymatching and t.get('only_matching', False):
-                continue
-            t['name'] = type(ie).__name__[:-len('IE')]
-            yield t
+        for tc in ie.get_testcases(include_onlymatching):
+            yield tc
 
 
 md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
@@ -113,6 +103,16 @@ def expect_info_dict(self, got_dict, expected_dict):
             self.assertTrue(
                 match_rex.match(got),
                 'field %s (value: %r) should match %r' % (info_field, got, match_str))
+        elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
+            got = got_dict.get(info_field)
+            start_str = expected[len('startswith:'):]
+            self.assertTrue(
+                isinstance(got, compat_str),
+                'Expected a %s object, but got %s for field %s' % (
+                    compat_str.__name__, type(got).__name__, info_field))
+            self.assertTrue(
+                got.startswith(start_str),
+                'field %s (value: %r) should start with %r' % (info_field, got, start_str))
         elif isinstance(expected, type):
             got = got_dict.get(info_field)
             self.assertTrue(isinstance(got, expected),
@@ -120,6 +120,20 @@ def expect_info_dict(self, got_dict, expected_dict):
         else:
             if isinstance(expected, compat_str) and expected.startswith('md5:'):
                 got = 'md5:' + md5(got_dict.get(info_field))
+            elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
+                got = got_dict.get(info_field)
+                self.assertTrue(
+                    isinstance(got, list),
+                    'Expected field %s to be a list, but it is of type %s' % (
+                        info_field, type(got).__name__))
+                expected_num = int(expected.partition(':')[2])
+                assertGreaterEqual(
+                    self, len(got), expected_num,
+                    'Expected %d items in field %s, but only got %d' % (
+                        expected_num, info_field, len(got)
+                    )
+                )
+                continue
             else:
                 got = got_dict.get(info_field)
             self.assertEqual(expected, got,
@@ -136,7 +150,7 @@ def expect_info_dict(self, got_dict, expected_dict):
     # Are checkable fields missing from the test case definition?
     test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
                           for key, value in got_dict.items()
-                          if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
+                          if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
     missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
     if missing_keys:
         def _repr(v):
@@ -144,9 +158,15 @@ def expect_info_dict(self, got_dict, expected_dict):
                 return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
             else:
                 return repr(v)
-        info_dict_str = ''.join(
+        info_dict_str = ''
+        if len(missing_keys) != len(expected_dict):
+            info_dict_str += ''.join(
                 '    %s: %s,\n' % (_repr(k), _repr(v))
-            for k, v in test_info_dict.items())
+                for k, v in test_info_dict.items() if k not in missing_keys)
+            info_dict_str += '\n'
+        info_dict_str += ''.join(
+            '    %s: %s,\n' % (_repr(k), _repr(test_info_dict[k]))
+            for k in missing_keys)
         write_string(
             '\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr)
         self.assertFalse(

test/parameters.json

@@ -39,5 +39,6 @@
     "writesubtitles": false,
     "allsubtitles": false,
     "listssubtitles": false,
-    "socket_timeout": 20
+    "socket_timeout": 20,
+    "fixup": "never"
 }

test/test_InfoExtractor.py

@@ -40,5 +40,23 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
         self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
 
+    def test_html_search_meta(self):
+        ie = self.ie
+        html = '''
+            <meta name="a" content="1" />
+            <meta name='b' content='2'>
+            <meta name="c" content='3'>
+            <meta name=d content='4'>
+            <meta property="e" content='5' >
+            <meta content="6" name="f">
+        '''
+
+        self.assertEqual(ie._html_search_meta('a', html), '1')
+        self.assertEqual(ie._html_search_meta('b', html), '2')
+        self.assertEqual(ie._html_search_meta('c', html), '3')
+        self.assertEqual(ie._html_search_meta('d', html), '4')
+        self.assertEqual(ie._html_search_meta('e', html), '5')
+        self.assertEqual(ie._html_search_meta('f', html), '6')
+
 if __name__ == '__main__':
     unittest.main()

test/test_YoutubeDL.py

@@ -8,9 +8,12 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
+import copy
+
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
+from youtube_dl.postprocessor.common import PostProcessor
 
 
 class YDL(FakeYDL):
@@ -192,6 +195,37 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-high')
 
+    def test_format_selection_audio_exts(self):
+        formats = [
+            {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
+        ]
+
+        info_dict = _make_result(formats)
+        ydl = YDL({'format': 'best'})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'aac-64')
+
+        ydl = YDL({'format': 'mp3'})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'mp3-64')
+
+        ydl = YDL({'prefer_free_formats': True})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'ogg-64')
+
     def test_format_selection_video(self):
         formats = [
             {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
@@ -248,6 +282,61 @@ class TestFormatSelection(unittest.TestCase):
             downloaded = ydl.downloaded_info_dicts[0]
             self.assertEqual(downloaded['format_id'], f1id)
 
+    def test_format_filtering(self):
+        formats = [
+            {'format_id': 'A', 'filesize': 500, 'width': 1000},
+            {'format_id': 'B', 'filesize': 1000, 'width': 500},
+            {'format_id': 'C', 'filesize': 1000, 'width': 400},
+            {'format_id': 'D', 'filesize': 2000, 'width': 600},
+            {'format_id': 'E', 'filesize': 3000},
+            {'format_id': 'F'},
+            {'format_id': 'G', 'filesize': 1000000},
+        ]
+        for f in formats:
+            f['url'] = 'http://_/'
+            f['ext'] = 'unknown'
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'best[filesize<3000]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'D')
+
+        ydl = YDL({'format': 'best[filesize<=3000]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'E')
+
+        ydl = YDL({'format': 'best[filesize <= ? 3000]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'F')
+
+        ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'B')
+
+        ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'C')
+
+        ydl = YDL({'format': '[filesize>?1]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'G')
+
+        ydl = YDL({'format': '[filesize<1M]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'E')
+
+        ydl = YDL({'format': '[filesize<1MiB]'})
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'G')
+
     def test_add_extra_info(self):
         test_dict = {
             'extractor': 'Foo',
@@ -282,5 +371,35 @@ class TestFormatSelection(unittest.TestCase):
             'vbr': 10,
         }), '^\s*10k$')
 
+    def test_postprocessors(self):
+        filename = 'post-processor-testfile.mp4'
+        audiofile = filename + '.mp3'
+
+        class SimplePP(PostProcessor):
+            def run(self, info):
+                with open(audiofile, 'wt') as f:
+                    f.write('EXAMPLE')
+                info['filepath']
+                return False, info
+
+        def run_pp(params):
+            with open(filename, 'wt') as f:
+                f.write('EXAMPLE')
+            ydl = YoutubeDL(params)
+            ydl.add_post_processor(SimplePP())
+            ydl.post_process(filename, {'filepath': filename})
+
+        run_pp({'keepvideo': True})
+        self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
+        self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
+        os.unlink(filename)
+        os.unlink(audiofile)
+
+        run_pp({'keepvideo': False})
+        self.assertFalse(os.path.exists(filename), '%s exists' % filename)
+        self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
+        os.unlink(audiofile)
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_age_restriction.py

@@ -45,11 +45,6 @@ class TestAgeRestriction(unittest.TestCase):
             'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
             '505835.mp4', 2, old_age=25)
 
-    def test_pornotube(self):
-        self._assert_restricted(
-            'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
-            '1689755.flv', 13)
-
 
 if __name__ == '__main__':
     unittest.main()

test/test_all_urls.py

@@ -14,7 +14,6 @@ from test.helper import gettestcases
 from youtube_dl.extractor import (
     FacebookIE,
     gen_extractors,
-    TwitchIE,
     YoutubeIE,
 )
 
@@ -72,18 +71,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
         self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
 
-    def test_twitch_channelid_matching(self):
-        self.assertTrue(TwitchIE.suitable('twitch.tv/vanillatv'))
-        self.assertTrue(TwitchIE.suitable('www.twitch.tv/vanillatv'))
-        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv'))
-        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/'))
-
-    def test_twitch_videoid_matching(self):
-        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
-
-    def test_twitch_chapterid_matching(self):
-        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
-
     def test_youtube_extract(self):
         assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
         assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
@@ -115,8 +102,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':ythistory', ['youtube:history'])
         self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
         self.assertMatch(':tds', ['ComedyCentralShows'])
-        self.assertMatch(':colbertreport', ['ComedyCentralShows'])
-        self.assertMatch(':cr', ['ComedyCentralShows'])
 
     def test_vimeo_matching(self):
         self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])

test/test_download.py

@@ -89,7 +89,7 @@ def generator(test_case):
 
         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')):
+            if not (info_dict.get('id') and info_dict.get('ext')):
                 raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
 
         if 'skip' in test_case:
@@ -116,7 +116,7 @@ def generator(test_case):
         expect_warnings(ydl, test_case.get('expected_warnings', []))
 
         def get_tc_filename(tc):
-            return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
+            return ydl.prepare_filename(tc.get('info_dict', {}))
 
         res_dict = None
 

test/test_http.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl import YoutubeDL
+from youtube_dl.compat import compat_http_server
+import ssl
+import threading
+
+TEST_DIR = os.path.dirname(os.path.abspath(__file__))
+
+
+class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+    def log_message(self, format, *args):
+        pass
+
+    def do_GET(self):
+        if self.path == '/video.html':
+            self.send_response(200)
+            self.send_header('Content-Type', 'text/html; charset=utf-8')
+            self.end_headers()
+            self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
+        elif self.path == '/vid.mp4':
+            self.send_response(200)
+            self.send_header('Content-Type', 'video/mp4')
+            self.end_headers()
+            self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
+        else:
+            assert False
+
+
+class FakeLogger(object):
+    def debug(self, msg):
+        pass
+
+    def warning(self, msg):
+        pass
+
+    def error(self, msg):
+        pass
+
+
+class TestHTTP(unittest.TestCase):
+    def setUp(self):
+        certfn = os.path.join(TEST_DIR, 'testcert.pem')
+        self.httpd = compat_http_server.HTTPServer(
+            ('localhost', 0), HTTPTestRequestHandler)
+        self.httpd.socket = ssl.wrap_socket(
+            self.httpd.socket, certfile=certfn, server_side=True)
+        self.port = self.httpd.socket.getsockname()[1]
+        self.server_thread = threading.Thread(target=self.httpd.serve_forever)
+        self.server_thread.daemon = True
+        self.server_thread.start()
+
+    def test_nocheckcertificate(self):
+        if sys.version_info >= (2, 7, 9):  # No certificate checking anyways
+            ydl = YoutubeDL({'logger': FakeLogger()})
+            self.assertRaises(
+                Exception,
+                ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
+
+        ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
+        r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
+        self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_jsinterp.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.jsinterp import JSInterpreter
+
+
+class TestJSInterpreter(unittest.TestCase):
+    def test_basic(self):
+        jsi = JSInterpreter('function x(){;}')
+        self.assertEqual(jsi.call_function('x'), None)
+
+        jsi = JSInterpreter('function x3(){return 42;}')
+        self.assertEqual(jsi.call_function('x3'), 42)
+
+    def test_calc(self):
+        jsi = JSInterpreter('function x4(a){return 2*a+1;}')
+        self.assertEqual(jsi.call_function('x4', 3), 7)
+
+    def test_empty_return(self):
+        jsi = JSInterpreter('function f(){return; y()}')
+        self.assertEqual(jsi.call_function('f'), None)
+
+    def test_morespace(self):
+        jsi = JSInterpreter('function x (a) { return 2 * a + 1 ; }')
+        self.assertEqual(jsi.call_function('x', 3), 7)
+
+        jsi = JSInterpreter('function f () { x =  2  ; return x; }')
+        self.assertEqual(jsi.call_function('f'), 2)
+
+    def test_strange_chars(self):
+        jsi = JSInterpreter('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }')
+        self.assertEqual(jsi.call_function('$_xY1', 20), 21)
+
+    def test_operators(self):
+        jsi = JSInterpreter('function f(){return 1 << 5;}')
+        self.assertEqual(jsi.call_function('f'), 32)
+
+        jsi = JSInterpreter('function f(){return 19 & 21;}')
+        self.assertEqual(jsi.call_function('f'), 17)
+
+        jsi = JSInterpreter('function f(){return 11 >> 2;}')
+        self.assertEqual(jsi.call_function('f'), 2)
+
+    def test_array_access(self):
+        jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
+        self.assertEqual(jsi.call_function('f'), [5, 2, 7])
+
+    def test_parens(self):
+        jsi = JSInterpreter('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}')
+        self.assertEqual(jsi.call_function('f'), 7)
+
+        jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
+        self.assertEqual(jsi.call_function('f'), 9)
+
+    def test_assignments(self):
+        jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
+        self.assertEqual(jsi.call_function('f'), 31)
+
+        jsi = JSInterpreter('function f(){var x = 20; x += 30 + 1; return x;}')
+        self.assertEqual(jsi.call_function('f'), 51)
+
+        jsi = JSInterpreter('function f(){var x = 20; x -= 30 + 1; return x;}')
+        self.assertEqual(jsi.call_function('f'), -11)
+
+    def test_comments(self):
+        jsi = JSInterpreter('''
+        function x() {
+            var x = /* 1 + */ 2;
+            var y = /* 30
+            * 40 */ 50;
+            return x + y;
+        }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 52)
+
+    def test_precedence(self):
+        jsi = JSInterpreter('''
+        function x() {
+            var a = [10, 20, 30, 40, 50];
+            var b = 6;
+            a[0]=a[b%a.length];
+            return a;
+        }''')
+        self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_subtitles.py

@@ -138,7 +138,7 @@ class TestDailymotionSubtitles(BaseTestSubtitles):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(len(subtitles.keys()), 5)
+        self.assertTrue(len(subtitles.keys()) >= 6)
 
     def test_list_subtitles(self):
         self.DL.expect_warning('Automatic Captions not supported by this server')
@@ -247,7 +247,7 @@ class TestVimeoSubtitles(BaseTestSubtitles):
     def test_subtitles(self):
         self.DL.params['writesubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '26399116d23ae3cf2c087cea94bc43b4')
+        self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
 
     def test_subtitles_lang(self):
         self.DL.params['writesubtitles'] = True
@@ -334,7 +334,7 @@ class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(set(subtitles.keys()), set(['cs']))
-        self.assertEqual(md5(subtitles['cs']), '9bf52d9549533c32c427e264bf0847d4')
+        self.assertTrue(len(subtitles['cs']) > 20000)
 
     def test_nosubtitles(self):
         self.DL.expect_warning('video doesn\'t have subtitles')

test/test_utils.py

@@ -16,6 +16,7 @@ import json
 import xml.etree.ElementTree
 
 from youtube_dl.utils import (
+    age_restricted,
     args_to_str,
     clean_html,
     DateRange,
@@ -27,6 +28,7 @@ from youtube_dl.utils import (
     fix_xml_ampersands,
     InAdvancePagedList,
     intlist_to_bytes,
+    is_html,
     js_to_json,
     limit_length,
     OnDemandPagedList,
@@ -50,6 +52,8 @@ from youtube_dl.utils import (
     urlencode_postdata,
     version_tuple,
     xpath_with_ns,
+    render_table,
+    match_str,
 )
 
 
@@ -78,6 +82,10 @@ class TestUtil(unittest.TestCase):
         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
         self.assertEqual(sanitize_filename(tests), tests)
 
+        self.assertEqual(
+            sanitize_filename('New World record at 0:12:34'),
+            'New World record at 0_12_34')
+
         forbidden = '"\0\\/'
         for fc in forbidden:
             for fbc in forbidden:
@@ -143,11 +151,15 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
+        self.assertEqual(unified_strdate('1968 12 10'), '19681210')
         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
         self.assertEqual(
             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
             '20141126')
+        self.assertEqual(
+            unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
+            '20150202')
 
     def test_find_xpath_attr(self):
         testxml = '''<root>
@@ -207,6 +219,8 @@ class TestUtil(unittest.TestCase):
 
     def test_parse_duration(self):
         self.assertEqual(parse_duration(None), None)
+        self.assertEqual(parse_duration(False), None)
+        self.assertEqual(parse_duration('invalid'), None)
         self.assertEqual(parse_duration('1'), 1)
         self.assertEqual(parse_duration('1337:12'), 80232)
         self.assertEqual(parse_duration('9:12:43'), 33163)
@@ -228,6 +242,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('5 s'), 5)
         self.assertEqual(parse_duration('3 min'), 180)
         self.assertEqual(parse_duration('2.5 hours'), 9000)
+        self.assertEqual(parse_duration('02:03:04'), 7384)
+        self.assertEqual(parse_duration('01:02:03:04'), 93784)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -361,6 +377,16 @@ class TestUtil(unittest.TestCase):
         on = js_to_json('{"abc": true}')
         self.assertEqual(json.loads(on), {'abc': True})
 
+        # Ignore JavaScript code as well
+        on = js_to_json('''{
+            "x": 1,
+            y: "a",
+            z: some.code
+        }''')
+        d = json.loads(on)
+        self.assertEqual(d['x'], 1)
+        self.assertEqual(d['y'], 'a')
+
     def test_clean_html(self):
         self.assertEqual(clean_html('a:\nb'), 'a: b')
         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
@@ -402,5 +428,69 @@ Trying to open render node...
 Success at /dev/dri/renderD128.
 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
 
+    def test_age_restricted(self):
+        self.assertFalse(age_restricted(None, 10))  # unrestricted content
+        self.assertFalse(age_restricted(1, None))  # unrestricted policy
+        self.assertFalse(age_restricted(8, 10))
+        self.assertTrue(age_restricted(18, 14))
+        self.assertFalse(age_restricted(18, 18))
+
+    def test_is_html(self):
+        self.assertFalse(is_html(b'\x49\x44\x43<html'))
+        self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
+        self.assertTrue(is_html(  # UTF-8 with BOM
+            b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
+        self.assertTrue(is_html(  # UTF-16-LE
+            b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
+        ))
+        self.assertTrue(is_html(  # UTF-16-BE
+            b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
+        ))
+        self.assertTrue(is_html(  # UTF-32-BE
+            b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
+        self.assertTrue(is_html(  # UTF-32-LE
+            b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
+
+    def test_render_table(self):
+        self.assertEqual(
+            render_table(
+                ['a', 'bcd'],
+                [[123, 4], [9999, 51]]),
+            'a    bcd\n'
+            '123  4\n'
+            '9999 51')
+
+    def test_match_str(self):
+        self.assertRaises(ValueError, match_str, 'xy>foobar', {})
+        self.assertFalse(match_str('xy', {'x': 1200}))
+        self.assertTrue(match_str('!xy', {'x': 1200}))
+        self.assertTrue(match_str('x', {'x': 1200}))
+        self.assertFalse(match_str('!x', {'x': 1200}))
+        self.assertTrue(match_str('x', {'x': 0}))
+        self.assertFalse(match_str('x>0', {'x': 0}))
+        self.assertFalse(match_str('x>0', {}))
+        self.assertTrue(match_str('x>?0', {}))
+        self.assertTrue(match_str('x>1K', {'x': 1200}))
+        self.assertFalse(match_str('x>2K', {'x': 1200}))
+        self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
+        self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
+        self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
+        self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
+        self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
+        self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
+        self.assertFalse(match_str(
+            'like_count > 100 & dislike_count <? 50 & description',
+            {'like_count': 90, 'description': 'foo'}))
+        self.assertTrue(match_str(
+            'like_count > 100 & dislike_count <? 50 & description',
+            {'like_count': 190, 'description': 'foo'}))
+        self.assertFalse(match_str(
+            'like_count > 100 & dislike_count <? 50 & description',
+            {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
+        self.assertFalse(match_str(
+            'like_count > 100 & dislike_count <? 50 & description',
+            {'like_count': 190, 'dislike_count': 10}))
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -8,11 +8,11 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-
 import io
 import re
 import string
 
+from test.helper import FakeYDL
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.compat import compat_str, compat_urlretrieve
 
@@ -88,7 +88,8 @@ def make_tfunc(url, stype, sig_input, expected_sig):
         if not os.path.exists(fn):
             compat_urlretrieve(url, fn)
 
-        ie = YoutubeIE()
+        ydl = FakeYDL()
+        ie = YoutubeIE(ydl)
         if stype == 'js':
             with io.open(fn, encoding='utf-8') as testf:
                 jscode = testf.read()

test/testcert.pem

@@ -0,0 +1,52 @@
+-----BEGIN PRIVATE KEY-----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+-----END PRIVATE KEY-----
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----

youtube_dl/YoutubeDL.py

@@ -10,6 +10,7 @@ import io
 import itertools
 import json
 import locale
+import operator
 import os
 import platform
 import re
@@ -24,6 +25,7 @@ if os.name == 'nt':
     import ctypes
 
 from .compat import (
+    compat_basestring,
     compat_cookiejar,
     compat_expanduser,
     compat_http_client,
@@ -49,26 +51,33 @@ from .utils import (
     make_HTTPS_handler,
     MaxDownloadsReached,
     PagedList,
+    parse_filesize,
     PostProcessingError,
     platform_name,
     preferredencoding,
+    render_table,
     SameFileError,
     sanitize_filename,
+    std_headers,
     subtitles_filename,
     takewhile_inclusive,
     UnavailableVideoError,
     url_basename,
+    version_tuple,
     write_json_file,
     write_string,
     YoutubeDLHandler,
     prepend_extension,
     args_to_str,
+    age_restricted,
 )
 from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
 from .downloader import get_suitable_downloader
 from .downloader.rtmp import rtmpdump_version
 from .postprocessor import (
+    FFmpegFixupM4aPP,
+    FFmpegFixupStretchedPP,
     FFmpegMergerPP,
     FFmpegPostProcessor,
     get_postprocessor,
@@ -129,6 +138,7 @@ class YoutubeDL(object):
     nooverwrites:      Prevent overwriting files.
     playliststart:     Playlist item to start at.
     playlistend:       Playlist item to end at.
+    playlist_items:    Specific indices of playlist to download.
     playlistreverse:   Download playlist items in reverse order.
     matchtitle:        Download only matching titles.
     rejecttitle:       Reject downloads for matching titles.
@@ -138,6 +148,7 @@ class YoutubeDL(object):
     writeinfojson:     Write the video description to a .info.json file
     writeannotations:  Write the video annotations to a .annotations.xml file
     writethumbnail:    Write the thumbnail image to a file
+    write_all_thumbnails:  Write all thumbnail formats to files
     writesubtitles:    Write the video subtitles to a file
     writeautomaticsub: Write the automatic subtitles to a file
     allsubtitles:      Downloads all the subtitles of the video
@@ -188,11 +199,12 @@ class YoutubeDL(object):
                        postprocessor.
     progress_hooks:    A list of functions that get called on download
                        progress, with a dictionary with the entries
-                       * filename: The final filename
-                       * status: One of "downloading" and "finished"
-
-                       The dict may also have some of the following entries:
+                       * status: One of "downloading" and "finished".
+                                 Check this first and ignore unknown values.
 
+                       If status is one of "downloading" or "finished", the
+                       following properties may also be present:
+                       * filename: The final filename (always present)
                        * downloaded_bytes: Bytes on disk
                        * total_bytes: Size of the whole file, None if unknown
                        * tmpfilename: The filename we're currently writing to
@@ -202,12 +214,36 @@ class YoutubeDL(object):
 
                        Progress hooks are guaranteed to be called at least once
                        (with status "finished") if the download is successful.
+    merge_output_format: Extension to use when merging formats.
+    fixup:             Automatically correct known faults of the file.
+                       One of:
+                       - "never": do nothing
+                       - "warn": only emit a warning
+                       - "detect_or_warn": check whether we can do anything
+                                           about it, warn otherwise (default)
+    source_address:    (Experimental) Client-side IP address to bind to.
+    call_home:         Boolean, true iff we are allowed to contact the
+                       youtube-dl servers for debugging.
+    sleep_interval:    Number of seconds to sleep before each download.
+    listformats:       Print an overview of available video formats and exit.
+    list_thumbnails:   Print a table of all thumbnails and exit.
+    match_filter:      A function that gets called with the info_dict of
+                       every video.
+                       If it returns a message, the video is ignored.
+                       If it returns None, the video is downloaded.
+                       match_filter_func in utils.py is one example for this.
+    no_color:          Do not emit color codes in output.
 
+    The following options determine which downloader is picked:
+    external_downloader: Executable of the external downloader to call.
+                       None or unset for standard (built-in) downloader.
+    hls_prefer_native: Use the native HLS downloader instead of ffmpeg/avconv.
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:
     nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
-    noresizebuffer, retries, continuedl, noprogress, consoletitle
+    noresizebuffer, retries, continuedl, noprogress, consoletitle,
+    xattr_set_filesize.
 
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
@@ -458,7 +494,7 @@ class YoutubeDL(object):
         else:
             if self.params.get('no_warnings'):
                 return
-            if self._err_file.isatty() and os.name != 'nt':
+            if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':
                 _msg_header = '\033[0;33mWARNING:\033[0m'
             else:
                 _msg_header = 'WARNING:'
@@ -470,7 +506,7 @@ class YoutubeDL(object):
         Do the same as trouble, but prefixes the message with 'ERROR:', colored
         in red if stderr is a tty file.
         '''
-        if self._err_file.isatty() and os.name != 'nt':
+        if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':
             _msg_header = '\033[0;31mERROR:\033[0m'
         else:
             _msg_header = 'ERROR:'
@@ -517,12 +553,17 @@ class YoutubeDL(object):
             outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
             tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
+            # Temporary fix for #4787
+            # 'Treat' all problem characters by passing filename through preferredencoding
+            # to workaround encoding issues with subprocess on python2 @ Windows
+            if sys.version_info < (3, 0) and sys.platform == 'win32':
+                filename = encodeFilename(filename, True).decode(preferredencoding())
             return filename
         except ValueError as err:
             self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
 
-    def _match_entry(self, info_dict):
+    def _match_entry(self, info_dict, incomplete):
         """ Returns None iff the file should be downloaded """
 
         video_title = info_dict.get('title', info_dict.get('id', 'video'))
@@ -550,15 +591,18 @@ class YoutubeDL(object):
             max_views = self.params.get('max_views')
             if max_views is not None and view_count > max_views:
                 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:
-            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 age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
+            return 'Skipping "%s" because it is age restricted' % video_title
         if self.in_download_archive(info_dict):
             return '%s has already been recorded in archive' % video_title
+
+        if not incomplete:
+            match_filter = self.params.get('match_filter')
+            if match_filter is not None:
+                ret = match_filter(info_dict)
+                if ret is not None:
+                    return ret
+
         return None
 
     @staticmethod
@@ -685,15 +729,38 @@ class YoutubeDL(object):
             if playlistend == -1:
                 playlistend = None
 
+            playlistitems_str = self.params.get('playlist_items', None)
+            playlistitems = None
+            if playlistitems_str is not None:
+                def iter_playlistitems(format):
+                    for string_segment in format.split(','):
+                        if '-' in string_segment:
+                            start, end = string_segment.split('-')
+                            for item in range(int(start), int(end) + 1):
+                                yield int(item)
+                        else:
+                            yield int(string_segment)
+                playlistitems = iter_playlistitems(playlistitems_str)
+
             ie_entries = ie_result['entries']
             if isinstance(ie_entries, list):
                 n_all_entries = len(ie_entries)
+                if playlistitems:
+                    entries = [ie_entries[i - 1] for i in playlistitems]
+                else:
                     entries = ie_entries[playliststart:playlistend]
                 n_entries = len(entries)
                 self.to_screen(
                     "[%s] playlist %s: Collected %d video ids (downloading %d of them)" %
                     (ie_result['extractor'], playlist, n_all_entries, n_entries))
             elif isinstance(ie_entries, PagedList):
+                if playlistitems:
+                    entries = []
+                    for item in playlistitems:
+                        entries.extend(ie_entries.getslice(
+                            item - 1, item
+                        ))
+                else:
                     entries = ie_entries.getslice(
                         playliststart, playlistend)
                 n_entries = len(entries)
@@ -701,6 +768,10 @@ class YoutubeDL(object):
                     "[%s] playlist %s: Downloading %d videos" %
                     (ie_result['extractor'], playlist, n_entries))
             else:  # iterable
+                if playlistitems:
+                    entry_list = list(ie_entries)
+                    entries = [entry_list[i - 1] for i in playlistitems]
+                else:
                     entries = list(itertools.islice(
                         ie_entries, playliststart, playlistend))
                 n_entries = len(entries)
@@ -725,7 +796,7 @@ class YoutubeDL(object):
                     'extractor_key': ie_result['extractor_key'],
                 }
 
-                reason = self._match_entry(entry)
+                reason = self._match_entry(entry, incomplete=True)
                 if reason is not None:
                     self.to_screen('[download] ' + reason)
                     continue
@@ -760,7 +831,76 @@ class YoutubeDL(object):
         else:
             raise Exception('Invalid result type: %s' % result_type)
 
+    def _apply_format_filter(self, format_spec, available_formats):
+        " Returns a tuple of the remaining format_spec and filtered formats "
+
+        OPERATORS = {
+            '<': operator.lt,
+            '<=': operator.le,
+            '>': operator.gt,
+            '>=': operator.ge,
+            '=': operator.eq,
+            '!=': operator.ne,
+        }
+        operator_rex = re.compile(r'''(?x)\s*\[
+            (?P<key>width|height|tbr|abr|vbr|asr|filesize|fps)
+            \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
+            (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
+            \]$
+            ''' % '|'.join(map(re.escape, OPERATORS.keys())))
+        m = operator_rex.search(format_spec)
+        if m:
+            try:
+                comparison_value = int(m.group('value'))
+            except ValueError:
+                comparison_value = parse_filesize(m.group('value'))
+                if comparison_value is None:
+                    comparison_value = parse_filesize(m.group('value') + 'B')
+                if comparison_value is None:
+                    raise ValueError(
+                        'Invalid value %r in format specification %r' % (
+                            m.group('value'), format_spec))
+            op = OPERATORS[m.group('op')]
+
+        if not m:
+            STR_OPERATORS = {
+                '=': operator.eq,
+                '!=': operator.ne,
+            }
+            str_operator_rex = re.compile(r'''(?x)\s*\[
+                \s*(?P<key>ext|acodec|vcodec|container|protocol)
+                \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
+                \s*(?P<value>[a-zA-Z0-9_-]+)
+                \s*\]$
+                ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
+            m = str_operator_rex.search(format_spec)
+            if m:
+                comparison_value = m.group('value')
+                op = STR_OPERATORS[m.group('op')]
+
+        if not m:
+            raise ValueError('Invalid format specification %r' % format_spec)
+
+        def _filter(f):
+            actual_value = f.get(m.group('key'))
+            if actual_value is None:
+                return m.group('none_inclusive')
+            return op(actual_value, comparison_value)
+        new_formats = [f for f in available_formats if _filter(f)]
+
+        new_format_spec = format_spec[:-len(m.group(0))]
+        if not new_format_spec:
+            new_format_spec = 'best'
+
+        return (new_format_spec, new_formats)
+
     def select_format(self, format_spec, available_formats):
+        while format_spec.endswith(']'):
+            format_spec, available_formats = self._apply_format_filter(
+                format_spec, available_formats)
+        if not available_formats:
+            return None
+
         if format_spec == 'best' or format_spec is None:
             return available_formats[-1]
         elif format_spec == 'worst':
@@ -790,7 +930,7 @@ class YoutubeDL(object):
             if video_formats:
                 return video_formats[0]
         else:
-            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a']
+            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
             if format_spec in extensions:
                 filter_f = lambda f: f['ext'] == format_spec
             else:
@@ -800,6 +940,24 @@ class YoutubeDL(object):
                 return matches[-1]
         return None
 
+    def _calc_headers(self, info_dict):
+        res = std_headers.copy()
+
+        add_headers = info_dict.get('http_headers')
+        if add_headers:
+            res.update(add_headers)
+
+        cookies = self._calc_cookies(info_dict)
+        if cookies:
+            res['Cookie'] = cookies
+
+        return res
+
+    def _calc_cookies(self, info_dict):
+        pr = compat_urllib_request.Request(info_dict['url'])
+        self.cookiejar.add_cookie_header(pr)
+        return pr.get_header('Cookie')
+
     def process_video_result(self, info_dict, download=True):
         assert info_dict.get('_type', 'video') == 'video'
 
@@ -814,12 +972,19 @@ class YoutubeDL(object):
             info_dict['playlist_index'] = None
 
         thumbnails = info_dict.get('thumbnails')
+        if thumbnails is None:
+            thumbnail = info_dict.get('thumbnail')
+            if thumbnail:
+                info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}]
         if thumbnails:
             thumbnails.sort(key=lambda t: (
-                t.get('width'), t.get('height'), t.get('url')))
-            for t in thumbnails:
+                t.get('preference'), t.get('width'), t.get('height'),
+                t.get('id'), t.get('url')))
+            for i, t in enumerate(thumbnails):
                 if 'width' in t and 'height' in t:
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
+                if t.get('id') is None:
+                    t['id'] = '%d' % i
 
         if thumbnails and 'thumbnail' not in info_dict:
             info_dict['thumbnail'] = thumbnails[-1]['url']
@@ -868,6 +1033,11 @@ class YoutubeDL(object):
             # Automatically determine file extension if missing
             if 'ext' not in format:
                 format['ext'] = determine_ext(format['url']).lower()
+            # Add HTTP headers, so that external programs can use them from the
+            # json output
+            full_format_info = info_dict.copy()
+            full_format_info.update(format)
+            format['http_headers'] = self._calc_headers(full_format_info)
 
         format_limit = self.params.get('format_limit', None)
         if format_limit:
@@ -883,9 +1053,12 @@ class YoutubeDL(object):
             # element in the 'formats' field in info_dict is info_dict itself,
             # wich can't be exported to json
             info_dict['formats'] = formats
-        if self.params.get('listformats', None):
+        if self.params.get('listformats'):
             self.list_formats(info_dict)
             return
+        if self.params.get('list_thumbnails'):
+            self.list_thumbnails(info_dict)
+            return
 
         req_format = self.params.get('format')
         if req_format is None:
@@ -913,10 +1086,26 @@ class YoutubeDL(object):
                                                   'contain the video, try using '
                                                   '"-f %s+%s"' % (format_2, format_1))
                                 return
+                            output_ext = (
+                                formats_info[0]['ext']
+                                if self.params.get('merge_output_format') is None
+                                else self.params['merge_output_format'])
                             selected_format = {
                                 'requested_formats': formats_info,
-                                'format': rf,
-                                'ext': formats_info[0]['ext'],
+                                'format': '%s+%s' % (formats_info[0].get('format'),
+                                                     formats_info[1].get('format')),
+                                'format_id': '%s+%s' % (formats_info[0].get('format_id'),
+                                                        formats_info[1].get('format_id')),
+                                'width': formats_info[0].get('width'),
+                                'height': formats_info[0].get('height'),
+                                'resolution': formats_info[0].get('resolution'),
+                                'fps': formats_info[0].get('fps'),
+                                'vcodec': formats_info[0].get('vcodec'),
+                                'vbr': formats_info[0].get('vbr'),
+                                'stretched_ratio': formats_info[0].get('stretched_ratio'),
+                                'acodec': formats_info[1].get('acodec'),
+                                'abr': formats_info[1].get('abr'),
+                                'ext': output_ext,
                             }
                         else:
                             selected_format = None
@@ -960,14 +1149,14 @@ class YoutubeDL(object):
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 
-        reason = self._match_entry(info_dict)
+        reason = self._match_entry(info_dict, incomplete=False)
         if reason is not None:
             self.to_screen('[download] ' + reason)
             return
 
         self._num_downloads += 1
 
-        filename = self.prepare_filename(info_dict)
+        info_dict['_filename'] = filename = self.prepare_filename(info_dict)
 
         # Forced printings
         if self.params.get('forcetitle', False):
@@ -992,10 +1181,7 @@ class YoutubeDL(object):
         if self.params.get('forceformat', False):
             self.to_stdout(info_dict['format'])
         if self.params.get('forcejson', False):
-            info_dict['_filename'] = filename
             self.to_stdout(json.dumps(info_dict))
-        if self.params.get('dump_single_json', False):
-            info_dict['_filename'] = filename
 
         # Do nothing else if in simulate mode
         if self.params.get('simulate', False):
@@ -1078,43 +1264,23 @@ class YoutubeDL(object):
                     self.report_error('Cannot write metadata to JSON file ' + infofn)
                     return
 
-        if self.params.get('writethumbnail', False):
-            if info_dict.get('thumbnail') is not None:
-                thumb_format = determine_ext(info_dict['thumbnail'], 'jpg')
-                thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format
-                if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
-                    self.to_screen('[%s] %s: Thumbnail is already present' %
-                                   (info_dict['extractor'], info_dict['id']))
-                else:
-                    self.to_screen('[%s] %s: Downloading thumbnail ...' %
-                                   (info_dict['extractor'], info_dict['id']))
-                    try:
-                        uf = self.urlopen(info_dict['thumbnail'])
-                        with open(thumb_filename, 'wb') as thumbf:
-                            shutil.copyfileobj(uf, thumbf)
-                        self.to_screen('[%s] %s: Writing thumbnail to: %s' %
-                                       (info_dict['extractor'], info_dict['id'], thumb_filename))
-                    except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                        self.report_warning('Unable to download thumbnail "%s": %s' %
-                                            (info_dict['thumbnail'], compat_str(err)))
+        self._write_thumbnails(info_dict, filename)
 
         if not self.params.get('skip_download', False):
-            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
-                success = True
-            else:
             try:
                 def dl(name, info):
-                        fd = get_suitable_downloader(info)(self, self.params)
+                    fd = get_suitable_downloader(info, self.params)(self, self.params)
                     for ph in self._progress_hooks:
                         fd.add_progress_hook(ph)
                     if self.params.get('verbose'):
                         self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
                     return fd.download(name, info)
+
                 if info_dict.get('requested_formats') is not None:
                     downloaded = []
                     success = True
                     merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
-                        if not merger._executable:
+                    if not merger.available:
                         postprocessors = []
                         self.report_warning('You have requested multiple '
                                             'formats but ffmpeg or avconv are not installed.'
@@ -1144,6 +1310,44 @@ class YoutubeDL(object):
                 return
 
             if success:
+                # Fixup content
+                fixup_policy = self.params.get('fixup')
+                if fixup_policy is None:
+                    fixup_policy = 'detect_or_warn'
+
+                stretched_ratio = info_dict.get('stretched_ratio')
+                if stretched_ratio is not None and stretched_ratio != 1:
+                    if fixup_policy == 'warn':
+                        self.report_warning('%s: Non-uniform pixel ratio (%s)' % (
+                            info_dict['id'], stretched_ratio))
+                    elif fixup_policy == 'detect_or_warn':
+                        stretched_pp = FFmpegFixupStretchedPP(self)
+                        if stretched_pp.available:
+                            info_dict.setdefault('__postprocessors', [])
+                            info_dict['__postprocessors'].append(stretched_pp)
+                        else:
+                            self.report_warning(
+                                '%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % (
+                                    info_dict['id'], stretched_ratio))
+                    else:
+                        assert fixup_policy in ('ignore', 'never')
+
+                if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash':
+                    if fixup_policy == 'warn':
+                        self.report_warning('%s: writing DASH m4a. Only some players support this container.' % (
+                            info_dict['id']))
+                    elif fixup_policy == 'detect_or_warn':
+                        fixup_pp = FFmpegFixupM4aPP(self)
+                        if fixup_pp.available:
+                            info_dict.setdefault('__postprocessors', [])
+                            info_dict['__postprocessors'].append(fixup_pp)
+                        else:
+                            self.report_warning(
+                                '%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % (
+                                    info_dict['id']))
+                    else:
+                        assert fixup_policy in ('ignore', 'never')
+
                 try:
                     self.post_process(filename, info_dict)
                 except (PostProcessingError) as err:
@@ -1192,14 +1396,15 @@ class YoutubeDL(object):
         """Run all the postprocessors on the given file."""
         info = dict(ie_info)
         info['filepath'] = filename
-        keep_video = None
         pps_chain = []
         if ie_info.get('__postprocessors') is not None:
             pps_chain.extend(ie_info['__postprocessors'])
         pps_chain.extend(self._pps)
         for pp in pps_chain:
+            keep_video = None
+            old_filename = info['filepath']
             try:
-                keep_video_wish, new_info = pp.run(info)
+                keep_video_wish, info = pp.run(info)
                 if keep_video_wish is not None:
                     if keep_video_wish:
                         keep_video = keep_video_wish
@@ -1210,8 +1415,8 @@ class YoutubeDL(object):
                 self.report_error(e.msg)
             if keep_video is False and not self.params.get('keepvideo', False):
                 try:
-                self.to_screen('Deleting original file %s (pass -k to keep)' % filename)
-                os.remove(encodeFilename(filename))
+                    self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
+                    os.remove(encodeFilename(old_filename))
                 except (IOError, OSError):
                     self.report_warning('Unable to remove downloaded video file')
 
@@ -1337,15 +1542,32 @@ class YoutubeDL(object):
             line(f, idlen) for f in formats
             if f.get('preference') is None or f['preference'] >= -1000]
         if len(formats) > 1:
-            formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)'
             formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'
 
         header_line = line({
             'format_id': 'format code', 'ext': 'extension',
             'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen)
-        self.to_screen('[info] Available formats for %s:\n%s\n%s' %
+        self.to_screen(
+            '[info] Available formats for %s:\n%s\n%s' %
             (info_dict['id'], header_line, '\n'.join(formats_s)))
 
+    def list_thumbnails(self, info_dict):
+        thumbnails = info_dict.get('thumbnails')
+        if not thumbnails:
+            tn_url = info_dict.get('thumbnail')
+            if tn_url:
+                thumbnails = [{'id': '0', 'url': tn_url}]
+            else:
+                self.to_screen(
+                    '[info] No thumbnails present for %s' % info_dict['id'])
+                return
+
+        self.to_screen(
+            '[info] Thumbnails for %s:' % info_dict['id'])
+        self.to_screen(render_table(
+            ['ID', 'width', 'height', 'URL'],
+            [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails]))
+
     def urlopen(self, req):
         """ Start an HTTP download """
 
@@ -1355,7 +1577,7 @@ class YoutubeDL(object):
         # 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)
+        req_is_string = isinstance(req, compat_basestring)
         url = req if req_is_string else req.get_full_url()
         url_escaped = escape_url(url)
 
@@ -1407,7 +1629,7 @@ class YoutubeDL(object):
         self._write_string('[debug] Python version %s - %s\n' % (
             platform.python_version(), platform_name()))
 
-        exe_versions = FFmpegPostProcessor.get_versions()
+        exe_versions = FFmpegPostProcessor.get_versions(self)
         exe_versions['rtmpdump'] = rtmpdump_version()
         exe_str = ', '.join(
             '%s %s' % (exe, v)
@@ -1424,6 +1646,17 @@ class YoutubeDL(object):
                 proxy_map.update(handler.proxies)
         self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n')
 
+        if self.params.get('call_home', False):
+            ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode('utf-8')
+            self._write_string('[debug] Public IP address: %s\n' % ipaddr)
+            latest_version = self.urlopen(
+                'https://yt-dl.org/latest/version').read().decode('utf-8')
+            if version_tuple(latest_version) > version_tuple(__version__):
+                self.report_warning(
+                    'You are using an outdated version (newest version: %s)! '
+                    'See https://yt-dl.org/update if you need help updating.' %
+                    latest_version)
+
     def _setup_opener(self):
         timeout_val = self.params.get('socket_timeout')
         self._socket_timeout = 600 if timeout_val is None else float(timeout_val)
@@ -1454,9 +1687,8 @@ class YoutubeDL(object):
         proxy_handler = compat_urllib_request.ProxyHandler(proxies)
 
         debuglevel = 1 if self.params.get('debug_printtraffic') else 0
-        https_handler = make_HTTPS_handler(
-            self.params.get('nocheckcertificate', False), debuglevel=debuglevel)
-        ydlh = YoutubeDLHandler(debuglevel=debuglevel)
+        https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
+        ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
         opener = compat_urllib_request.build_opener(
             https_handler, proxy_handler, cookie_processor, ydlh)
         # Delete the default user-agent header, which would otherwise apply in
@@ -1480,3 +1712,39 @@ class YoutubeDL(object):
         if encoding is None:
             encoding = preferredencoding()
         return encoding
+
+    def _write_thumbnails(self, info_dict, filename):
+        if self.params.get('writethumbnail', False):
+            thumbnails = info_dict.get('thumbnails')
+            if thumbnails:
+                thumbnails = [thumbnails[-1]]
+        elif self.params.get('write_all_thumbnails', False):
+            thumbnails = info_dict.get('thumbnails')
+        else:
+            return
+
+        if not thumbnails:
+            # No thumbnails present, so return immediately
+            return
+
+        for t in thumbnails:
+            thumb_ext = determine_ext(t['url'], 'jpg')
+            suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
+            thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
+            thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
+
+            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
+                self.to_screen('[%s] %s: Thumbnail %sis already present' %
+                               (info_dict['extractor'], info_dict['id'], thumb_display_id))
+            else:
+                self.to_screen('[%s] %s: Downloading thumbnail %s...' %
+                               (info_dict['extractor'], info_dict['id'], thumb_display_id))
+                try:
+                    uf = self.urlopen(t['url'])
+                    with open(thumb_filename, 'wb') as thumbf:
+                        shutil.copyfileobj(uf, thumbf)
+                    self.to_screen('[%s] %s: Writing thumbnail %sto: %s' %
+                                   (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
+                except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                    self.report_warning('Unable to download thumbnail "%s": %s' %
+                                        (t['url'], compat_str(err)))

youtube_dl/__init__.py

@@ -23,9 +23,10 @@ from .compat import (
 )
 from .utils import (
     DateRange,
-    DEFAULT_OUTTMPL,
     decodeOption,
+    DEFAULT_OUTTMPL,
     DownloadError,
+    match_filter_func,
     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,
@@ -38,7 +39,7 @@ from .update import update_self
 from .downloader import (
     FileDownloader,
 )
-from .extractor import gen_extractors
+from .extractor import gen_extractors, list_extractors
 from .YoutubeDL import YoutubeDL
 
 
@@ -95,17 +96,15 @@ def _real_main(argv=None):
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
-    extractors = gen_extractors()
-
     if opts.list_extractors:
-        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+        for ie in list_extractors(opts.age_limit):
             compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
             for mu in matchedUrls:
                 compat_print('  ' + mu)
         sys.exit(0)
     if opts.list_extractor_descriptions:
-        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+        for ie in list_extractors(opts.age_limit):
             if not ie._WORKING:
                 continue
             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
@@ -145,8 +144,11 @@ def _real_main(argv=None):
             parser.error('invalid max_filesize specified')
         opts.max_filesize = numeric_limit
     if opts.retries is not None:
+        if opts.retries in ('inf', 'infinite'):
+            opts_retries = float('inf')
+        else:
             try:
-            opts.retries = int(opts.retries)
+                opts_retries = int(opts.retries)
             except (TypeError, ValueError):
                 parser.error('invalid retry count specified')
     if opts.buffersize is not None:
@@ -168,6 +170,7 @@ def _real_main(argv=None):
     if opts.recodevideo is not None:
         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
             parser.error('invalid video recode format specified')
+
     if opts.date is not None:
         date = DateRange.day(opts.date)
     else:
@@ -199,7 +202,8 @@ def _real_main(argv=None):
                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
                      ' template'.format(outtmpl))
 
-    any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
+    any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
+    any_printing = opts.print_json
     download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 
     # PostProcessors
@@ -238,6 +242,15 @@ def _real_main(argv=None):
             'verboseOutput': opts.verbose,
             'exec_cmd': opts.exec_cmd,
         })
+    if opts.xattr_set_filesize:
+        try:
+            import xattr
+            xattr  # Confuse flake8
+        except ImportError:
+            parser.error('setting filesize xattr requested but python-xattr is not available')
+    match_filter = (
+        None if opts.match_filter is None
+        else match_filter_func(opts.match_filter))
 
     ydl_opts = {
         'usenetrc': opts.usenetrc,
@@ -245,7 +258,7 @@ def _real_main(argv=None):
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
-        'quiet': (opts.quiet or any_printing),
+        'quiet': (opts.quiet or any_getting or any_printing),
         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
@@ -255,9 +268,9 @@ def _real_main(argv=None):
         'forceduration': opts.getduration,
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,
-        'forcejson': opts.dumpjson,
+        'forcejson': opts.dumpjson or opts.print_json,
         'dump_single_json': opts.dump_single_json,
-        'simulate': opts.simulate or any_printing,
+        'simulate': opts.simulate or any_getting,
         'skip_download': opts.skip_download,
         'format': opts.format,
         'format_limit': opts.format_limit,
@@ -268,7 +281,7 @@ def _real_main(argv=None):
         'ignoreerrors': opts.ignoreerrors,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
-        'retries': opts.retries,
+        'retries': opts_retries,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,
@@ -286,6 +299,7 @@ def _real_main(argv=None):
         'writeannotations': opts.writeannotations,
         'writeinfojson': opts.writeinfojson,
         'writethumbnail': opts.writethumbnail,
+        'write_all_thumbnails': opts.write_all_thumbnails,
         'writesubtitles': opts.writesubtitles,
         'writeautomaticsub': opts.writeautomaticsub,
         'allsubtitles': opts.allsubtitles,
@@ -324,7 +338,20 @@ def _real_main(argv=None):
         'encoding': opts.encoding,
         'exec_cmd': opts.exec_cmd,
         'extract_flat': opts.extract_flat,
+        'merge_output_format': opts.merge_output_format,
         'postprocessors': postprocessors,
+        'fixup': opts.fixup,
+        'source_address': opts.source_address,
+        'call_home': opts.call_home,
+        'sleep_interval': opts.sleep_interval,
+        'external_downloader': opts.external_downloader,
+        'list_thumbnails': opts.list_thumbnails,
+        'playlist_items': opts.playlist_items,
+        'xattr_set_filesize': opts.xattr_set_filesize,
+        'match_filter': match_filter,
+        'no_color': opts.no_color,
+        'ffmpeg_location': opts.ffmpeg_location,
+        'hls_prefer_native': opts.hls_prefer_native,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -342,7 +369,9 @@ def _real_main(argv=None):
                 sys.exit()
 
             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
-            parser.error('you must provide at least one URL')
+            parser.error(
+                'You must provide at least one URL.\n'
+                'Type youtube-dl --help to see a list of all options.')
 
         try:
             if opts.load_info_filename is not None:
@@ -365,3 +394,5 @@ def main(argv=None):
         sys.exit('ERROR: fixed output name but more than one file to download')
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')
+
+__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']

youtube_dl/aes.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']
-
 import base64
 from math import ceil
 
@@ -329,3 +327,5 @@ def inc(data):
             data[i] = data[i] + 1
             break
     return data
+
+__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']

youtube_dl/compat.py

@@ -4,6 +4,7 @@ import getpass
 import optparse
 import os
 import re
+import socket
 import subprocess
 import sys
 
@@ -70,6 +71,11 @@ try:
 except ImportError:
     compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
 
+try:
+    import http.server as compat_http_server
+except ImportError:
+    import BaseHTTPServer as compat_http_server
+
 try:
     from urllib.parse import unquote as compat_urllib_parse_unquote
 except ImportError:
@@ -108,6 +114,26 @@ except ImportError:
             string += pct_sequence.decode(encoding, errors)
         return string
 
+try:
+    compat_str = unicode  # Python 2
+except NameError:
+    compat_str = str
+
+try:
+    compat_basestring = basestring  # Python 2
+except NameError:
+    compat_basestring = str
+
+try:
+    compat_chr = unichr  # Python 2
+except NameError:
+    compat_chr = chr
+
+try:
+    from xml.etree.ElementTree import ParseError as compat_xml_parse_error
+except ImportError:  # Python 2.6
+    from xml.parsers.expat import ExpatError as compat_xml_parse_error
+
 
 try:
     from urllib.parse import parse_qs as compat_parse_qs
@@ -117,7 +143,7 @@ except ImportError:  # Python 2
 
     def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
                    encoding='utf-8', errors='replace'):
-        qs, _coerce_result = qs, unicode
+        qs, _coerce_result = qs, compat_str
         pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
         r = []
         for name_value in pairs:
@@ -156,21 +182,6 @@ except ImportError:  # Python 2
                 parsed_result[name] = [value]
         return parsed_result
 
-try:
-    compat_str = unicode  # Python 2
-except NameError:
-    compat_str = str
-
-try:
-    compat_chr = unichr  # Python 2
-except NameError:
-    compat_chr = chr
-
-try:
-    from xml.etree.ElementTree import ParseError as compat_xml_parse_error
-except ImportError:  # Python 2.6
-    from xml.parsers.expat import ExpatError as compat_xml_parse_error
-
 try:
     from shlex import quote as shlex_quote
 except ImportError:  # Python < 3.3
@@ -307,6 +318,32 @@ else:
     compat_kwargs = lambda kwargs: kwargs
 
 
+if sys.version_info < (2, 7):
+    def compat_socket_create_connection(address, timeout, source_address=None):
+        host, port = address
+        err = None
+        for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
+            af, socktype, proto, canonname, sa = res
+            sock = None
+            try:
+                sock = socket.socket(af, socktype, proto)
+                sock.settimeout(timeout)
+                if source_address:
+                    sock.bind(source_address)
+                sock.connect(sa)
+                return sock
+            except socket.error as _:
+                err = _
+                if sock is not None:
+                    sock.close()
+        if err is not None:
+            raise err
+        else:
+            raise socket.error("getaddrinfo returns an empty list")
+else:
+    compat_socket_create_connection = socket.create_connection
+
+
 # Fix https://github.com/rg3/youtube-dl/issues/4223
 # See http://bugs.python.org/issue9161 for what is broken
 def workaround_optparse_bug9161():
@@ -330,6 +367,7 @@ def workaround_optparse_bug9161():
 
 __all__ = [
     'compat_HTTPError',
+    'compat_basestring',
     'compat_chr',
     'compat_cookiejar',
     'compat_expanduser',
@@ -338,10 +376,12 @@ __all__ = [
     'compat_html_entities',
     'compat_html_parser',
     'compat_http_client',
+    'compat_http_server',
     'compat_kwargs',
     'compat_ord',
     'compat_parse_qs',
     'compat_print',
+    'compat_socket_create_connection',
     'compat_str',
     'compat_subprocess_get_DEVNULL',
     'compat_urllib_error',

youtube_dl/downloader/__init__.py

@@ -1,35 +1,44 @@
 from __future__ import unicode_literals
 
 from .common import FileDownloader
+from .external import get_external_downloader
+from .f4m import F4mFD
 from .hls import HlsFD
 from .hls import NativeHlsFD
 from .http import HttpFD
 from .mplayer import MplayerFD
 from .rtmp import RtmpFD
-from .f4m import F4mFD
 
 from ..utils import (
-    determine_ext,
+    determine_protocol,
 )
 
+PROTOCOL_MAP = {
+    'rtmp': RtmpFD,
+    'm3u8_native': NativeHlsFD,
+    'm3u8': HlsFD,
+    'mms': MplayerFD,
+    'rtsp': MplayerFD,
+    'f4m': F4mFD,
+}
 
-def get_suitable_downloader(info_dict):
+
+def get_suitable_downloader(info_dict, params={}):
     """Get the downloader class that can handle the info dict."""
-    url = info_dict['url']
-    protocol = info_dict.get('protocol')
+    protocol = determine_protocol(info_dict)
+    info_dict['protocol'] = protocol
 
-    if url.startswith('rtmp'):
-        return RtmpFD
-    if protocol == 'm3u8_native':
+    external_downloader = params.get('external_downloader')
+    if external_downloader is not None:
+        ed = get_external_downloader(external_downloader)
+        if ed.supports(info_dict):
+            return ed
+
+    if protocol == 'm3u8' and params.get('hls_prefer_native'):
         return NativeHlsFD
-    if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
-        return HlsFD
-    if url.startswith('mms') or url.startswith('rtsp'):
-        return MplayerFD
-    if determine_ext(url) == 'f4m':
-        return F4mFD
-    else:
-        return HttpFD
+
+    return PROTOCOL_MAP.get(protocol, HttpFD)
+
 
 __all__ = [
     'get_suitable_downloader',

youtube_dl/downloader/common.py

@@ -40,6 +40,8 @@ class FileDownloader(object):
     test:               Download only first bytes to test the downloader.
     min_filesize:       Skip files smaller than this size
     max_filesize:       Skip files larger than this size
+    xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
+                        (experimenatal)
 
     Subclasses of this one must re-define the real_download method.
     """
@@ -284,8 +286,20 @@ class FileDownloader(object):
         """Download to a filename using the info from info_dict
         Return True on success and False otherwise
         """
+
+        nooverwrites_and_exists = (
+            self.params.get('nooverwrites', False)
+            and os.path.exists(encodeFilename(filename))
+        )
+
+        continuedl_and_exists = (
+            self.params.get('continuedl', False)
+            and os.path.isfile(encodeFilename(filename))
+            and not self.params.get('nopart', False)
+        )
+
         # Check file already present
-        if filename != '-' and self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
+        if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
             self.report_file_already_downloaded(filename)
             self._hook_progress({
                 'filename': filename,
@@ -294,6 +308,11 @@ class FileDownloader(object):
             })
             return True
 
+        sleep_interval = self.params.get('sleep_interval')
+        if sleep_interval:
+            self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
+            time.sleep(sleep_interval)
+
         return self.real_download(filename, info_dict)
 
     def real_download(self, filename, info_dict):
@@ -308,3 +327,24 @@ class FileDownloader(object):
         # See YoutubeDl.py (search for progress_hooks) for a description of
         # this interface
         self._progress_hooks.append(ph)
+
+    def _debug_cmd(self, args, subprocess_encoding, exe=None):
+        if not self.params.get('verbose', False):
+            return
+
+        if exe is None:
+            exe = os.path.basename(args[0])
+
+        if subprocess_encoding:
+            str_args = [
+                a.decode(subprocess_encoding) if isinstance(a, bytes) else a
+                for a in args]
+        else:
+            str_args = args
+        try:
+            import pipes
+            shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
+        except ImportError:
+            shell_quote = repr
+        self.to_screen('[debug] %s command line: %s' % (
+            exe, shell_quote(str_args)))

youtube_dl/downloader/external.py

@@ -0,0 +1,126 @@
+from __future__ import unicode_literals
+
+import os.path
+import subprocess
+import sys
+
+from .common import FileDownloader
+from ..utils import (
+    encodeFilename,
+)
+
+
+class ExternalFD(FileDownloader):
+    def real_download(self, filename, info_dict):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        retval = self._call_downloader(tmpfilename, info_dict)
+        if retval == 0:
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr('\n')
+            self.report_error('%s exited with code %d' % (
+                self.get_basename(), retval))
+            return False
+
+    @classmethod
+    def get_basename(cls):
+        return cls.__name__[:-2].lower()
+
+    @property
+    def exe(self):
+        return self.params.get('external_downloader')
+
+    @classmethod
+    def supports(cls, info_dict):
+        return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
+
+    def _source_address(self, command_option):
+        source_address = self.params.get('source_address')
+        if source_address is None:
+            return []
+        return [command_option, source_address]
+
+    def _call_downloader(self, tmpfilename, info_dict):
+        """ Either overwrite this or implement _make_cmd """
+        cmd = self._make_cmd(tmpfilename, info_dict)
+
+        if sys.platform == 'win32' and sys.version_info < (3, 0):
+            # Windows subprocess module does not actually support Unicode
+            # on Python 2.x
+            # See http://stackoverflow.com/a/9951851/35070
+            subprocess_encoding = sys.getfilesystemencoding()
+            cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
+        else:
+            subprocess_encoding = None
+        self._debug_cmd(cmd, subprocess_encoding)
+
+        p = subprocess.Popen(
+            cmd, stderr=subprocess.PIPE)
+        _, stderr = p.communicate()
+        if p.returncode != 0:
+            self.to_stderr(stderr)
+        return p.returncode
+
+
+class CurlFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = [self.exe, '--location', '-o', tmpfilename]
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['--header', '%s: %s' % (key, val)]
+        cmd += self._source_address('--interface')
+        cmd += ['--', info_dict['url']]
+        return cmd
+
+
+class WgetFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['--header', '%s: %s' % (key, val)]
+        cmd += self._source_address('--bind-address')
+        cmd += ['--', info_dict['url']]
+        return cmd
+
+
+class Aria2cFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = [
+            self.exe, '-c',
+            '--min-split-size', '1M', '--max-connection-per-server', '4']
+        dn = os.path.dirname(tmpfilename)
+        if dn:
+            cmd += ['--dir', dn]
+        cmd += ['--out', os.path.basename(tmpfilename)]
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['--header', '%s: %s' % (key, val)]
+        cmd += self._source_address('--interface')
+        cmd += ['--', info_dict['url']]
+        return cmd
+
+_BY_NAME = dict(
+    (klass.get_basename(), klass)
+    for name, klass in globals().items()
+    if name.endswith('FD') and name != 'ExternalFD'
+)
+
+
+def list_external_downloaders():
+    return sorted(_BY_NAME.keys())
+
+
+def get_external_downloader(external_downloader):
+    """ Given the name of the executable, see whether we support the given
+        downloader . """
+    bn = os.path.basename(external_downloader)
+    return _BY_NAME[bn]

youtube_dl/downloader/f4m.py

@@ -177,34 +177,43 @@ def build_fragments_list(boot_info):
     """ Return a list of (segment, fragment) for each fragment in the video """
     res = []
     segment_run_table = boot_info['segments'][0]
-    # I've only found videos with one segment
-    segment_run_entry = segment_run_table['segment_run'][0]
-    n_frags = segment_run_entry[1]
     fragment_run_entry_table = boot_info['fragments'][0]['fragments']
     first_frag_number = fragment_run_entry_table[0]['first']
-    for (i, frag_number) in zip(range(1, n_frags + 1), itertools.count(first_frag_number)):
-        res.append((1, frag_number))
+    fragments_counter = itertools.count(first_frag_number)
+    for segment, fragments_count in segment_run_table['segment_run']:
+        for _ in range(fragments_count):
+            res.append((segment, next(fragments_counter)))
     return res
 
 
-def write_flv_header(stream, metadata):
-    """Writes the FLV header and the metadata to stream"""
+def write_unsigned_int(stream, val):
+    stream.write(struct_pack('!I', val))
+
+
+def write_unsigned_int_24(stream, val):
+    stream.write(struct_pack('!I', val)[1:])
+
+
+def write_flv_header(stream):
+    """Writes the FLV header to stream"""
     # FLV header
     stream.write(b'FLV\x01')
     stream.write(b'\x05')
     stream.write(b'\x00\x00\x00\x09')
-    # FLV File body
     stream.write(b'\x00\x00\x00\x00')
-    # FLVTAG
-    # Script data
-    stream.write(b'\x12')
-    # Size of the metadata with 3 bytes
-    stream.write(struct_pack('!L', len(metadata))[1:])
+
+
+def write_metadata_tag(stream, metadata):
+    """Writes optional metadata tag to stream"""
+    SCRIPT_TAG = b'\x12'
+    FLV_TAG_HEADER_LEN = 11
+
+    if metadata:
+        stream.write(SCRIPT_TAG)
+        write_unsigned_int_24(stream, len(metadata))
         stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
         stream.write(metadata)
-    # Magic numbers extracted from the output files produced by AdobeHDS.php
-    # (https://github.com/K-S-V/Scripts)
-    stream.write(b'\x00\x00\x01\x73')
+        write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata))
 
 
 def _add_ns(prop):
@@ -221,6 +230,23 @@ class F4mFD(FileDownloader):
     A downloader for f4m manifests or AdobeHDS.
     """
 
+    def _get_unencrypted_media(self, doc):
+        media = doc.findall(_add_ns('media'))
+        if not media:
+            self.report_error('No media found')
+        for e in (doc.findall(_add_ns('drmAdditionalHeader')) +
+                  doc.findall(_add_ns('drmAdditionalHeaderSet'))):
+            # If id attribute is missing it's valid for all media nodes
+            # without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
+            if 'id' not in e.attrib:
+                self.report_error('Missing ID in f4m DRM')
+        media = list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
+                                      'drmAdditionalHeaderSetId' not in e.attrib,
+                            media))
+        if not media:
+            self.report_error('Unsupported DRM')
+        return media
+
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         requested_bitrate = info_dict.get('tbr')
@@ -239,7 +265,8 @@ class F4mFD(FileDownloader):
         )
 
         doc = etree.fromstring(manifest)
-        formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
+        formats = [(int(f.attrib.get('bitrate', -1)), f)
+                   for f in self._get_unencrypted_media(doc)]
         if requested_bitrate is None:
             # get the best format
             formats = sorted(formats, key=lambda f: f[0])
@@ -256,7 +283,11 @@ class F4mFD(FileDownloader):
             bootstrap = self.ydl.urlopen(bootstrap_url).read()
         else:
             bootstrap = base64.b64decode(bootstrap_node.text)
-        metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
+        metadata_node = media.find(_add_ns('metadata'))
+        if metadata_node is not None:
+            metadata = base64.b64decode(metadata_node.text)
+        else:
+            metadata = None
         boot_info = read_bootstrap_info(bootstrap)
 
         fragments_list = build_fragments_list(boot_info)
@@ -269,7 +300,8 @@ class F4mFD(FileDownloader):
 
         tmpfilename = self.temp_name(filename)
         (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
-        write_flv_header(dest_stream, metadata)
+        write_flv_header(dest_stream)
+        write_metadata_tag(dest_stream, metadata)
 
         # This dict stores the download progress, it's updated by the progress
         # hook

youtube_dl/downloader/hls.py

@@ -11,6 +11,7 @@ from ..compat import (
     compat_urllib_request,
 )
 from ..utils import (
+    encodeArgument,
     encodeFilename,
 )
 
@@ -21,23 +22,21 @@ class HlsFD(FileDownloader):
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
 
-        args = [
-            '-y', '-i', url, '-f', 'mp4', '-c', 'copy',
-            '-bsf:a', 'aac_adtstoasc',
-            encodeFilename(tmpfilename, for_subprocess=True)]
-
         ffpp = FFmpegPostProcessor(downloader=self)
-        program = ffpp._executable
-        if program is None:
+        if not ffpp.available:
             self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
             return False
         ffpp.check_version()
-        cmd = [program] + args
 
-        retval = subprocess.call(cmd)
+        args = [
+            encodeArgument(opt)
+            for opt in (ffpp.executable, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')]
+        args.append(encodeFilename(tmpfilename, True))
+
+        retval = subprocess.call(args)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize))
+            self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
             self.try_rename(tmpfilename, filename)
             self._hook_progress({
                 'downloaded_bytes': fsize,
@@ -48,7 +47,7 @@ class HlsFD(FileDownloader):
             return True
         else:
             self.to_stderr('\n')
-            self.report_error('%s exited with code %d' % (program, retval))
+            self.report_error('%s exited with code %d' % (ffpp.basename, retval))
             return False
 
 

youtube_dl/downloader/http.py

@@ -3,6 +3,9 @@ from __future__ import unicode_literals
 import os
 import time
 
+from socket import error as SocketError
+import errno
+
 from .common import FileDownloader
 from ..compat import (
     compat_urllib_request,
@@ -24,10 +27,6 @@ class HttpFD(FileDownloader):
 
         # Do not include the Accept-Encoding header
         headers = {'Youtubedl-no-compression': 'True'}
-        if 'user_agent' in info_dict:
-            headers['Youtubedl-user-agent'] = info_dict['user_agent']
-        if 'http_referer' in info_dict:
-            headers['Referer'] = info_dict['http_referer']
         add_headers = info_dict.get('http_headers')
         if add_headers:
             headers.update(add_headers)
@@ -103,6 +102,11 @@ class HttpFD(FileDownloader):
                             resume_len = 0
                             open_mode = 'wb'
                             break
+            except SocketError as e:
+                if e.errno != errno.ECONNRESET:
+                    # Connection reset is no problem, just retry
+                    raise
+
             # Retry
             count += 1
             if count <= retries:
@@ -161,6 +165,14 @@ class HttpFD(FileDownloader):
                 except (OSError, IOError) as err:
                     self.report_error('unable to open for writing: %s' % str(err))
                     return False
+
+                if self.params.get('xattr_set_filesize', False) and data_len is not None:
+                    try:
+                        import xattr
+                        xattr.setxattr(tmpfilename, 'user.ytdl.filesize', str(data_len))
+                    except(OSError, IOError, ImportError) as err:
+                        self.report_error('unable to set filesize xattr: %s' % str(err))
+
             try:
                 stream.write(data_block)
             except (IOError, OSError) as err:

youtube_dl/downloader/rtmp.py

@@ -104,6 +104,9 @@ class RtmpFD(FileDownloader):
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
         protocol = info_dict.get('rtmp_protocol', None)
+        real_time = info_dict.get('rtmp_real_time', False)
+        no_resume = info_dict.get('no_resume', False)
+        continue_dl = info_dict.get('continuedl', False)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
@@ -141,7 +144,14 @@ class RtmpFD(FileDownloader):
             basic_args += ['--conn', conn]
         if protocol is not None:
             basic_args += ['--protocol', protocol]
-        args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
+        if real_time:
+            basic_args += ['--realtime']
+
+        args = basic_args
+        if not no_resume and continue_dl and not live:
+            args += ['--resume']
+        if not live and continue_dl:
+            args += ['--skip', '1']
 
         if sys.platform == 'win32' and sys.version_info < (3, 0):
             # Windows subprocess module does not actually support Unicode
@@ -152,19 +162,7 @@ class RtmpFD(FileDownloader):
         else:
             subprocess_encoding = None
 
-        if self.params.get('verbose', False):
-            if subprocess_encoding:
-                str_args = [
-                    a.decode(subprocess_encoding) if isinstance(a, bytes) else a
-                    for a in args]
-            else:
-                str_args = args
-            try:
-                import pipes
-                shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
-            except ImportError:
-                shell_quote = repr
-            self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
+        self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
 
         RD_SUCCESS = 0
         RD_FAILED = 1

youtube_dl/extractor/__init__.py

@@ -1,10 +1,12 @@
 from __future__ import unicode_literals
 
 from .abc import ABCIE
+from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
 from .adobetv import AdobeTVIE
 from .adultswim import AdultSwimIE
+from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
@@ -26,8 +28,8 @@ from .arte import (
     ArteTVEmbedIE,
 )
 from .atresplayer import AtresPlayerIE
-from .audiomack import AudiomackIE
-from .auengine import AUEngineIE
+from .atttechchannel import ATTTechChannelIE
+from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
@@ -47,11 +49,16 @@ from .brightcove import BrightcoveIE
 from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE
 from .c56 import C56IE
+from .camdemy import (
+    CamdemyIE,
+    CamdemyFolderIE
+)
 from .canal13cl import Canal13clIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .cbs import CBSIE
 from .cbsnews import CBSNewsIE
+from .ccc import CCCIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .chilloutzone import ChilloutzoneIE
@@ -69,9 +76,10 @@ from .cnn import (
     CNNArticleIE,
 )
 from .collegehumor import CollegeHumorIE
+from .collegerama import CollegeRamaIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .comcarcoff import ComCarCoffIE
-from .commonmistakes import CommonMistakesIE
+from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .criterion import CriterionIE
@@ -80,6 +88,7 @@ from .crunchyroll import (
     CrunchyrollShowPlaylistIE
 )
 from .cspan import CSpanIE
+from .ctsnews import CtsNewsIE
 from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
@@ -87,10 +96,12 @@ from .dailymotion import (
 )
 from .daum import DaumIE
 from .dbtv import DBTVIE
+from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
 from .drtv import DRTVIE
 from .dvtv import DVTVIE
@@ -172,10 +183,13 @@ from .goshgay import GoshgayIE
 from .grooveshark import GroovesharkIE
 from .groupon import GrouponIE
 from .hark import HarkIE
+from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
 from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .historicfilms import HistoricFilmsIE
+from .history import HistoryIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
 from .hostingbulk import HostingBulkIE
@@ -206,6 +220,7 @@ from .jove import JoveIE
 from .jukebox import JukeboxIE
 from .jpopsukitv import JpopsukiIE
 from .kankan import KankanIE
+from .karaoketv import KaraoketvIE
 from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
@@ -222,6 +237,7 @@ from .livestream import (
     LivestreamOriginalIE,
     LivestreamShortenerIE,
 )
+from .lnkgo import LnkGoIE
 from .lrt import LRTIE
 from .lynda import (
     LyndaIE,
@@ -274,12 +290,24 @@ from .nbc import (
 )
 from .ndr import NDRIE
 from .ndtv import NDTVIE
+from .netzkino import NetzkinoIE
 from .nerdcubed import NerdCubedFeedIE
+from .nerdist import NerdistIE
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
+from .nextmedia import (
+    NextMediaIE,
+    NextMediaActionNewsIE,
+    AppleDailyRealtimeNewsIE,
+    AppleDailyAnimationNewsIE
+)
 from .nfb import NFBIE
 from .nfl import NFLIE
-from .nhl import NHLIE, NHLVideocenterIE
+from .nhl import (
+    NHLIE,
+    NHLNewsIE,
+    NHLVideocenterIE,
+)
 from .niconico import NiconicoIE, NiconicoPlaylistIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
@@ -290,13 +318,17 @@ from .nowness import NownessIE
 from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,
+    NPOLiveIE,
+    NPORadioIE,
+    NPORadioFragmentIE,
     TegenlichtVproIE,
 )
 from .nrk import (
     NRKIE,
     NRKTVIE,
 )
-from .ntv import NTVIE
+from .ntvde import NTVDeIE
+from .ntvru import NTVRuIE
 from .nytimes import NYTimesIE
 from .nuvid import NuvidIE
 from .oktoberfesttv import OktoberfestTVIE
@@ -338,8 +370,10 @@ from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
-from .rtlnl import RtlXlIE
+from .rte import RteIE
+from .rtlnl import RtlNlIE
 from .rtlnow import RTLnowIE
+from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE
@@ -400,7 +434,9 @@ from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .streetvoice import StreetVoiceIE
 from .sunporno import SunPornoIE
+from .svtplay import SVTPlayIE
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
@@ -421,6 +457,7 @@ from .telemb import TeleMBIE
 from .teletask import TeleTaskIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
+from .testtube import TestTubeIE
 from .tf1 import TF1IE
 from .theonion import TheOnionIE
 from .theplatform import ThePlatformIE
@@ -446,10 +483,19 @@ from .tunein import TuneInIE
 from .turbo import TurboIE
 from .tutv import TutvIE
 from .tvigle import TvigleIE
-from .tvp import TvpIE
+from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
+from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
-from .twitch import TwitchIE
+from .twitch import (
+    TwitchVideoIE,
+    TwitchChapterIE,
+    TwitchVodIE,
+    TwitchProfileIE,
+    TwitchPastBroadcastsIE,
+    TwitchBookmarksIE,
+    TwitchStreamIE,
+)
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
@@ -519,6 +565,7 @@ from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .wrzuta import WrzutaIE
+from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
 from .xhamster import XHamsterIE
@@ -526,11 +573,13 @@ from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .xtube import XTubeUserIE, XTubeIE
+from .xuite import XuiteIE
 from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
     YahooIE,
     YahooSearchIE,
 )
+from .yam import YamIE
 from .yesjapan import YesJapanIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE
@@ -575,6 +624,17 @@ def gen_extractors():
     return [klass() for klass in _ALL_CLASSES]
 
 
+def list_extractors(age_limit):
+    """
+    Return a list of extractors that are suitable for the given age,
+    sorted by extractor ID.
+    """
+
+    return sorted(
+        filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()),
+        key=lambda ie: ie.IE_NAME.lower())
+
+
 def get_info_extractor(ie_name):
     """Returns the info extractor class with the given ie_name"""
     return globals()[ie_name + 'IE']

youtube_dl/extractor/abc7news.py

@@ -0,0 +1,68 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+
+
+class Abc7NewsIE(InfoExtractor):
+    _VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
+            'info_dict': {
+                'id': '472581',
+                'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
+                'ext': 'mp4',
+                'title': 'East Bay museum celebrates history of synthesized music',
+                'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'timestamp': 1421123075,
+                'upload_date': '20150113',
+                'uploader': 'Jonathan Bloom',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://abc7news.com/472581',
+            'only_matching': True,
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        webpage = self._download_webpage(url, display_id)
+
+        m3u8 = self._html_search_meta(
+            'contentURL', webpage, 'm3u8 url', fatal=True)
+
+        formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
+        self._sort_formats(formats)
+
+        title = self._og_search_title(webpage).strip()
+        description = self._og_search_description(webpage).strip()
+        thumbnail = self._og_search_thumbnail(webpage)
+        timestamp = parse_iso8601(self._search_regex(
+            r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
+            webpage, 'upload date', fatal=False))
+        uploader = self._search_regex(
+            r'rel="author">([^<]+)</a>',
+            webpage, 'uploader', default=None)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'formats': formats,
+        }

youtube_dl/extractor/aftenposten.py

@@ -0,0 +1,103 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    xpath_with_ns,
+    xpath_text,
+    find_xpath_attr,
+)
+
+
+class AftenpostenIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/([^/]+/)*(?P<id>[^/]+)-\d+\.html'
+
+    _TEST = {
+        'url': 'http://www.aftenposten.no/webtv/serier-og-programmer/sweatshopenglish/TRAILER-SWEATSHOP---I-cant-take-any-more-7800835.html?paging=&section=webtv_serierogprogrammer_sweatshop_sweatshopenglish',
+        'md5': 'fd828cd29774a729bf4d4425fe192972',
+        'info_dict': {
+            'id': '21039',
+            'ext': 'mov',
+            'title': 'TRAILER: "Sweatshop" - I can´t take any more',
+            'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
+            'timestamp': 1416927969,
+            'upload_date': '20141125',
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._html_search_regex(
+            r'data-xs-id="(\d+)"', webpage, 'video id')
+
+        data = self._download_xml(
+            'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id)
+
+        NS_MAP = {
+            'atom': 'http://www.w3.org/2005/Atom',
+            'xt': 'http://xstream.dk/',
+            'media': 'http://search.yahoo.com/mrss/',
+        }
+
+        entry = data.find(xpath_with_ns('./atom:entry', NS_MAP))
+
+        title = xpath_text(
+            entry, xpath_with_ns('./atom:title', NS_MAP), 'title')
+        description = xpath_text(
+            entry, xpath_with_ns('./atom:summary', NS_MAP), 'description')
+        timestamp = parse_iso8601(xpath_text(
+            entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date'))
+
+        formats = []
+        media_group = entry.find(xpath_with_ns('./media:group', NS_MAP))
+        for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)):
+            media_url = media_content.get('url')
+            if not media_url:
+                continue
+            tbr = int_or_none(media_content.get('bitrate'))
+            mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url)
+            if mobj:
+                formats.append({
+                    'url': mobj.group('url'),
+                    'play_path': 'mp4:%s' % mobj.group('playpath'),
+                    'app': mobj.group('app'),
+                    'ext': 'flv',
+                    'tbr': tbr,
+                    'format_id': 'rtmp-%d' % tbr,
+                })
+            else:
+                formats.append({
+                    'url': media_url,
+                    'tbr': tbr,
+                })
+        self._sort_formats(formats)
+
+        link = find_xpath_attr(
+            entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original')
+        if link is not None:
+            formats.append({
+                'url': link.get('href'),
+                'format_id': link.get('rel'),
+            })
+
+        thumbnails = [{
+            'url': splash.get('url'),
+            'width': int_or_none(splash.get('width')),
+            'height': int_or_none(splash.get('height')),
+        } for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/aftonbladet.py

@@ -1,8 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -21,9 +19,7 @@ class AftonbladetIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.search(self._VALID_URL, url)
-
-        video_id = mobj.group('video_id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         # find internal video meta data

youtube_dl/extractor/aparat.py

@@ -20,6 +20,7 @@ class AparatIE(InfoExtractor):
             'id': 'wP8On',
             'ext': 'mp4',
             'title': 'تیم گلکسی 11 - زومیت',
+            'age_limit': 0,
         },
         # 'skip': 'Extremely unreliable',
     }
@@ -34,7 +35,8 @@ class AparatIE(InfoExtractor):
                      video_id + '/vt/frame')
         webpage = self._download_webpage(embed_url, video_id)
 
-        video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
+        video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
+            r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
         for i, video_url in enumerate(video_urls):
             req = HEADRequest(video_url)
             res = self._request_webpage(
@@ -46,7 +48,7 @@ class AparatIE(InfoExtractor):
 
         title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
         thumbnail = self._search_regex(
-            r'\s+image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
+            r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
 
         return {
             'id': video_id,
@@ -54,4 +56,5 @@ class AparatIE(InfoExtractor):
             'url': video_url,
             'ext': 'mp4',
             'thumbnail': thumbnail,
+            'age_limit': self._family_friendly_search(webpage),
         }

youtube_dl/extractor/appletrailers.py

@@ -122,14 +122,15 @@ class AppleTrailersIE(InfoExtractor):
             playlist.append({
                 '_type': 'video',
                 'id': video_id,
-                'title': title,
                 'formats': formats,
                 'title': title,
                 'duration': duration,
                 'thumbnail': thumbnail,
                 'upload_date': upload_date,
                 'uploader_id': uploader_id,
-                'user_agent': 'QuickTime compatible (youtube-dl)',
+                'http_headers': {
+                    'User-Agent': 'QuickTime compatible (youtube-dl)',
+                },
             })
 
         return {

youtube_dl/extractor/ard.py

@@ -23,13 +23,7 @@ class ARDMediathekIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
-        'file': '22429276.mp4',
-        'md5': '469751912f1de0816a9fc9df8336476c',
-        'info_dict': {
-            'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?',
-            'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014',
-        },
-        'skip': 'Blocked outside of Germany',
+        'only_matching': True,
     }, {
         'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
         'info_dict': {

youtube_dl/extractor/atresplayer.py

@@ -3,10 +3,13 @@ from __future__ import unicode_literals
 import time
 import hmac
 
-from .common import InfoExtractor
-from ..utils import (
+from .subtitles import SubtitlesInfoExtractor
+from ..compat import (
     compat_str,
+    compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     int_or_none,
     float_or_none,
     xpath_text,
@@ -14,7 +17,7 @@ from ..utils import (
 )
 
 
-class AtresPlayerIE(InfoExtractor):
+class AtresPlayerIE(SubtitlesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
     _TESTS = [
         {
@@ -44,6 +47,33 @@ class AtresPlayerIE(InfoExtractor):
     _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
     _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
 
+    _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'j_username': username,
+            'j_password': password,
+        }
+
+        request = compat_urllib_request.Request(
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        response = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        error = self._html_search_regex(
+            r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
+        if error:
+            raise ExtractorError(
+                'Unable to login: %s' % error, expected=True)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -65,7 +95,7 @@ class AtresPlayerIE(InfoExtractor):
         for fmt in ['windows', 'android_tablet']:
             request = compat_urllib_request.Request(
                 self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
-            request.add_header('Youtubedl-user-agent', self._USER_AGENT)
+            request.add_header('User-Agent', self._USER_AGENT)
 
             fmt_json = self._download_json(
                 request, video_id, 'Downloading %s video JSON' % fmt)
@@ -75,13 +105,22 @@ class AtresPlayerIE(InfoExtractor):
                 raise ExtractorError(
                     '%s returned error: %s' % (self.IE_NAME, result), expected=True)
 
-            for _, video_url in fmt_json['resultObject'].items():
+            for format_id, video_url in fmt_json['resultObject'].items():
+                if format_id == 'token' or not video_url.startswith('http'):
+                    continue
                 if video_url.endswith('/Manifest'):
-                    formats.extend(self._extract_f4m_formats(video_url[:-9] + '/manifest.f4m', video_id))
+                    if 'geodeswowsmpra3player' in video_url:
+                        f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
+                        f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
+                        # this videos are protected by DRM, the f4m downloader doesn't support them
+                        continue
+                    else:
+                        f4m_url = video_url[:-9] + '/manifest.f4m'
+                    formats.extend(self._extract_f4m_formats(f4m_url, video_id))
                 else:
                     formats.append({
                         'url': video_url,
-                        'format_id': 'android',
+                        'format_id': 'android-%s' % format_id,
                         'preference': 1,
                     })
         self._sort_formats(formats)
@@ -104,6 +143,15 @@ class AtresPlayerIE(InfoExtractor):
         description = xpath_text(art, './description', 'description')
         thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
 
+        subtitles = {}
+        subtitle = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
+        if subtitle:
+            subtitles['es'] = subtitle
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
         return {
             'id': video_id,
             'title': title,
@@ -111,4 +159,5 @@ class AtresPlayerIE(InfoExtractor):
             'thumbnail': thumbnail,
             'duration': duration,
             'formats': formats,
+            'subtitles': self.extract_subtitles(video_id, subtitles),
         }

youtube_dl/extractor/atttechchannel.py

@@ -0,0 +1,55 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class ATTTechChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)'
+    _TEST = {
+        'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
+        'info_dict': {
+            'id': '11316',
+            'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
+            'ext': 'flv',
+            'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
+            'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20140127',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._search_regex(
+            r"url\s*:\s*'(rtmp://[^']+)'",
+            webpage, 'video URL')
+
+        video_id = self._search_regex(
+            r'mediaid\s*=\s*(\d+)',
+            webpage, 'video id', fatal=False)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        upload_date = unified_strdate(self._search_regex(
+            r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})',
+            webpage, 'upload date', fatal=False), False)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'ext': 'flv',
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/audiomack.py

@@ -1,11 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
+import time
+
 from .common import InfoExtractor
 from .soundcloud import SoundcloudIE
-from ..utils import ExtractorError
-
-import time
+from ..utils import (
+    ExtractorError,
+    url_basename,
+)
 
 
 class AudiomackIE(InfoExtractor):
@@ -17,12 +21,13 @@ class AudiomackIE(InfoExtractor):
             'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
             'info_dict':
             {
-                'id': 'roosh-williams/extraordinary',
+                'id': '310086',
                 'ext': 'mp3',
-                'title': 'Roosh Williams - Extraordinary'
+                'uploader': 'Roosh Williams',
+                'title': 'Extraordinary'
             }
         },
-        # hosted on soundcloud via audiomack
+        # audiomack wrapper around soundcloud song
         {
             'add_ie': ['Soundcloud'],
             'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
@@ -38,32 +43,102 @@ class AudiomackIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        # URLs end with [uploader name]/[uploader title]
+        # this title is whatever the user types in, and is rarely
+        # the proper song title.  Real metadata is in the api response
+        album_url_tag = self._match_id(url)
 
+        # Request the extended version of the api for extra fields like artist and title
         api_response = self._download_json(
-            "http://www.audiomack.com/api/music/url/song/%s?_=%d" % (
-                video_id, time.time()),
-            video_id)
+            'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % (
+                album_url_tag, time.time()),
+            album_url_tag)
 
-        if "url" not in api_response:
-            raise ExtractorError("Unable to deduce api url of song")
-        realurl = api_response["url"]
+        # API is inconsistent with errors
+        if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
+            raise ExtractorError('Invalid url %s', url)
 
         # Audiomack wraps a lot of soundcloud tracks in their branded wrapper
-        # - if so, pass the work off to the soundcloud extractor
-        if SoundcloudIE.suitable(realurl):
-            return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'}
-
-        webpage = self._download_webpage(url, video_id)
-        artist = self._html_search_regex(
-            r'<span class="artist">(.*?)</span>', webpage, "artist")
-        songtitle = self._html_search_regex(
-            r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>',
-            webpage, "title")
-        title = artist + " - " + songtitle
+        # if so, pass the work off to the soundcloud extractor
+        if SoundcloudIE.suitable(api_response['url']):
+            return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'}
 
         return {
-            'id': video_id,
-            'title': title,
-            'url': realurl,
+            'id': api_response.get('id', album_url_tag),
+            'uploader': api_response.get('artist'),
+            'title': api_response.get('title'),
+            'url': api_response['url'],
         }
+
+
+class AudiomackAlbumIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)'
+    IE_NAME = 'audiomack:album'
+    _TESTS = [
+        # Standard album playlist
+        {
+            'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
+            'playlist_count': 15,
+            'info_dict':
+            {
+                'id': '812251',
+                'title': 'Tha Tour: Part 2 (Official Mixtape)'
+            }
+        },
+        # Album playlist ripped from fakeshoredrive with no metadata
+        {
+            'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
+            'info_dict': {
+                'title': 'PPP (Pistol P Project)',
+                'id': '837572',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'title': 'PPP (Pistol P Project) - 9. Heaven or Hell (CHIMACA) ft Zuse (prod by DJ FU)',
+                    'id': '837577',
+                    'ext': 'mp3',
+                    'uploader': 'Lil Herb a.k.a. G Herbo',
+                }
+            }],
+            'params': {
+                'playliststart': 9,
+                'playlistend': 9,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        # URLs end with [uploader name]/[uploader title]
+        # this title is whatever the user types in, and is rarely
+        # the proper song title.  Real metadata is in the api response
+        album_url_tag = self._match_id(url)
+        result = {'_type': 'playlist', 'entries': []}
+        # There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
+        # Therefore we don't know how many songs the album has and must infi-loop until failure
+        for track_no in itertools.count():
+            # Get song's metadata
+            api_response = self._download_json(
+                'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
+                % (album_url_tag, track_no, time.time()), album_url_tag,
+                note='Querying song information (%d)' % (track_no + 1))
+
+            # Total failure, only occurs when url is totally wrong
+            # Won't happen in middle of valid playlist (next case)
+            if 'url' not in api_response or 'error' in api_response:
+                raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
+            # URL is good but song id doesn't exist - usually means end of playlist
+            elif not api_response['url']:
+                break
+            else:
+                # Pull out the album metadata and add to result (if it exists)
+                for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
+                    if apikey in api_response and resultkey not in result:
+                        result[resultkey] = api_response[apikey]
+                song_id = url_basename(api_response['url']).rpartition('.')[0]
+                result['entries'].append({
+                    'id': api_response.get('id', song_id),
+                    'uploader': api_response.get('artist'),
+                    'title': api_response.get('title', song_id),
+                    'url': api_response['url'],
+                })
+        return result

youtube_dl/extractor/auengine.py

@@ -1,50 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_urllib_parse
-from ..utils import (
-    determine_ext,
-    ExtractorError,
-    remove_end,
-)
-
-
-class AUEngineIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
-
-    _TEST = {
-        'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
-        'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
-        'info_dict': {
-            'id': 'lfvlytY6',
-            'ext': 'mp4',
-            'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(
-            r'<title>\s*(?P<title>.+?)\s*</title>', webpage, 'title')
-        video_urls = re.findall(r'http://\w+.auengine.com/vod/.*[^\W]', webpage)
-        video_url = compat_urllib_parse.unquote(video_urls[0])
-        thumbnails = re.findall(r'http://\w+.auengine.com/thumb/.*[^\W]', webpage)
-        thumbnail = compat_urllib_parse.unquote(thumbnails[0])
-
-        if not video_url:
-            raise ExtractorError('Could not find video URL')
-
-        ext = '.' + determine_ext(video_url)
-        title = remove_end(title, ext)
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': title,
-            'thumbnail': thumbnail,
-            'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
-        }

youtube_dl/extractor/bambuser.py

@@ -50,7 +50,7 @@ class BambuserIE(InfoExtractor):
             'duration': int(info['length']),
             'view_count': int(info['views_total']),
             'uploader': info['username'],
-            'uploader_id': info['uid'],
+            'uploader_id': info['owner']['uid'],
         }
 
 

youtube_dl/extractor/bandcamp.py

@@ -72,26 +72,29 @@ class BandcampIE(InfoExtractor):
 
         download_link = m_download.group(1)
         video_id = self._search_regex(
-            r'var TralbumData = {.*?id: (?P<id>\d+),?$',
-            webpage, 'video id', flags=re.MULTILINE | re.DOTALL)
+            r'(?ms)var TralbumData = {.*?id: (?P<id>\d+),?$',
+            webpage, 'video id')
 
         download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
         # We get the dictionary of the track from some javascript code
-        info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
-        info = json.loads(info)[0]
+        all_info = self._parse_json(self._search_regex(
+            r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
+        info = all_info[0]
         # We pick mp3-320 for now, until format selection can be easily implemented.
         mp3_info = info['downloads']['mp3-320']
         # If we try to use this url it says the link has expired
         initial_url = mp3_info['url']
-        re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
-        m_url = re.match(re_url, initial_url)
+        m_url = re.match(
+            r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
+            initial_url)
         # We build the url we will use to get the final track url
         # This url is build in Bandcamp in the script download_bunde_*.js
         request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
         final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
         # If we could correctly generate the .rand field the url would be
         # in the "download_url" key
-        final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
+        final_url = self._search_regex(
+            r'"retry_url":"(.*?)"', final_url_webpage, 'final video URL')
 
         return {
             'id': video_id,
@@ -161,7 +164,8 @@ class BandcampAlbumIE(InfoExtractor):
         entries = [
             self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
             for t_path in tracks_paths]
-        title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
+        title = self._search_regex(
+            r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
         return {
             '_type': 'playlist',
             'id': playlist_id,

youtube_dl/extractor/bbccouk.py

@@ -10,7 +10,7 @@ from ..compat import compat_HTTPError
 class BBCCoUkIE(SubtitlesInfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
 
     _TESTS = [
         {
@@ -118,6 +118,9 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
         }, {
             'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
             'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
+            'only_matching': True,
         }
     ]
 
@@ -270,7 +273,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
                     formats, subtitles = self._download_media_selector(programme_id)
                 return programme_id, title, description, duration, formats, subtitles
         except ExtractorError as ee:
-            if not isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+            if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
                 raise
 
         # fallback to legacy playlist

youtube_dl/extractor/beeg.py

@@ -9,7 +9,7 @@ class BeegIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
     _TEST = {
         'url': 'http://beeg.com/5416503',
-        'md5': '634526ae978711f6b748fe0dd6c11f57',
+        'md5': '1bff67111adb785c51d1b42959ec10e5',
         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',

youtube_dl/extractor/bet.py

@@ -16,7 +16,7 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
             'info_dict': {
-                'id': '406429c6-1b8a-463e-83fc-814adb81a9db',
+                'id': '740ab250-bb94-4a8a-8787-fe0de7c74471',
                 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
                 'ext': 'flv',
                 'title': 'BET News Presents: A Conversation With President Obama',
@@ -35,7 +35,7 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
             'info_dict': {
-                'id': '4160e53b-ad41-43b1-980f-8d85f63121f4',
+                'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d',
                 'display_id': 'justice-for-ferguson-a-community-reacts',
                 'ext': 'flv',
                 'title': 'Justice for Ferguson: A Community Reacts',
@@ -55,7 +55,6 @@ class BetIE(InfoExtractor):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-
         webpage = self._download_webpage(url, display_id)
 
         media_url = compat_urllib_parse.unquote(self._search_regex(

youtube_dl/extractor/bilibili.py

@@ -4,9 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_parse_qs
 from ..utils import (
-    ExtractorError,
     int_or_none,
     unified_strdate,
 )
@@ -54,19 +52,14 @@ class BiliBiliIE(InfoExtractor):
         thumbnail = self._html_search_meta(
             'thumbnailUrl', video_code, 'thumbnail', fatal=False)
 
-        player_params = compat_parse_qs(self._html_search_regex(
-            r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
-            webpage, 'player params'))
-
-        if 'cid' in player_params:
-            cid = player_params['cid'][0]
+        cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
 
         lq_doc = self._download_xml(
-                'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid,
+            'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
             video_id,
             note='Downloading LQ video info'
         )
-            lq_durl = lq_doc.find('.//durl')
+        lq_durl = lq_doc.find('./durl')
         formats = [{
             'format_id': 'lq',
             'quality': 1,
@@ -76,13 +69,13 @@ class BiliBiliIE(InfoExtractor):
         }]
 
         hq_doc = self._download_xml(
-                'http://interface.bilibili.cn/playurl?cid=%s' % cid,
+            'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
             video_id,
             note='Downloading HQ video info',
             fatal=False,
         )
         if hq_doc is not False:
-                hq_durl = hq_doc.find('.//durl')
+            hq_durl = hq_doc.find('./durl')
             formats.append({
                 'format_id': 'hq',
                 'quality': 2,
@@ -91,8 +84,6 @@ class BiliBiliIE(InfoExtractor):
                 'filesize': int_or_none(
                     hq_durl.find('./size'), get_attr='text'),
             })
-        else:
-            raise ExtractorError('Unsupported player parameters: %r' % (player_params,))
 
         self._sort_formats(formats)
         return {

youtube_dl/extractor/bliptv.py

@@ -199,7 +199,7 @@ class BlipTVIE(SubtitlesInfoExtractor):
         # For some weird reason, blip.tv serves a video instead of subtitles
         # when we request with a common UA
         req = compat_urllib_request.Request(url)
-        req.add_header('Youtubedl-user-agent', 'youtube-dl')
+        req.add_header('User-Agent', 'youtube-dl')
         return self._download_webpage(req, None, note=False)
 
 

youtube_dl/extractor/brightcove.py

@@ -108,7 +108,7 @@ class BrightcoveIE(InfoExtractor):
         """
 
         # Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553
-        object_str = re.sub(r'(<param name="[^"]+" value="[^"]+")>',
+        object_str = re.sub(r'(<param(?:\s+[a-zA-Z0-9_]+="[^"]*")*)>',
                             lambda m: m.group(1) + '/>', object_str)
         # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
         object_str = object_str.replace('<--', '<!--')

youtube_dl/extractor/buzzfeed.py

@@ -33,7 +33,7 @@ class BuzzFeedIE(InfoExtractor):
             'skip_download': True,  # Got enough YouTube download tests
         },
         'info_dict': {
-            'description': 'Munchkin the Teddy Bear is back !',
+            'description': 're:Munchkin the Teddy Bear is back ?!',
             'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
         },
         'playlist': [{
@@ -42,9 +42,9 @@ class BuzzFeedIE(InfoExtractor):
                 'ext': 'mp4',
                 'upload_date': '20141124',
                 'uploader_id': 'CindysMunchkin',
-                'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu',
+                'description': 're:© 2014 Munchkin the Shih Tzu',
                 'uploader': 'Munchkin the Shih Tzu',
-                'title': 'Munchkin the Teddy Bear gets her exercise',
+                'title': 're:Munchkin the Teddy Bear gets her exercise',
             },
         }]
     }]

youtube_dl/extractor/camdemy.py

@@ -0,0 +1,153 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import datetime
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urlparse,
+)
+from ..utils import (
+    parse_iso8601,
+    str_to_int,
+)
+
+
+class CamdemyIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
+    _TESTS = [{
+        # single file
+        'url': 'http://www.camdemy.com/media/5181/',
+        'md5': '5a5562b6a98b37873119102e052e311b',
+        'info_dict': {
+            'id': '5181',
+            'ext': 'mp4',
+            'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': '',
+            'creator': 'ss11spring',
+            'upload_date': '20130114',
+            'timestamp': 1358154556,
+            'view_count': int,
+        }
+    }, {
+        # With non-empty description
+        'url': 'http://www.camdemy.com/media/13885',
+        'md5': '4576a3bb2581f86c61044822adbd1249',
+        'info_dict': {
+            'id': '13885',
+            'ext': 'mp4',
+            'title': 'EverCam + Camdemy QuickStart',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'md5:050b62f71ed62928f8a35f1a41e186c9',
+            'creator': 'evercam',
+            'upload_date': '20140620',
+            'timestamp': 1403271569,
+        }
+    }, {
+        # External source
+        'url': 'http://www.camdemy.com/media/14842',
+        'md5': '50e1c3c3aa233d3d7b7daa2fa10b1cf7',
+        'info_dict': {
+            'id': '2vsYQzNIsJo',
+            'ext': 'mp4',
+            'upload_date': '20130211',
+            'uploader': 'Hun Kim',
+            'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
+            'uploader_id': 'hunkimtutorials',
+            'title': 'Excel 2013 Tutorial - How to add Password Protection',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        page = self._download_webpage(url, video_id)
+
+        src_from = self._html_search_regex(
+            r"<div class='srcFrom'>Source: <a title='([^']+)'", page,
+            'external source', default=None)
+        if src_from:
+            return self.url_result(src_from)
+
+        oembed_obj = self._download_json(
+            'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
+
+        thumb_url = oembed_obj['thumbnail_url']
+        video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
+        file_list_doc = self._download_xml(
+            compat_urlparse.urljoin(video_folder, 'fileList.xml'),
+            video_id, 'Filelist XML')
+        file_name = file_list_doc.find('./video/item/fileName').text
+        video_url = compat_urlparse.urljoin(video_folder, file_name)
+
+        timestamp = parse_iso8601(self._html_search_regex(
+            r"<div class='title'>Posted\s*:</div>\s*<div class='value'>([^<>]+)<",
+            page, 'creation time', fatal=False),
+            delimiter=' ', timezone=datetime.timedelta(hours=8))
+        view_count = str_to_int(self._html_search_regex(
+            r"<div class='title'>Views\s*:</div>\s*<div class='value'>([^<>]+)<",
+            page, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': oembed_obj['title'],
+            'thumbnail': thumb_url,
+            'description': self._html_search_meta('description', page),
+            'creator': oembed_obj['author_name'],
+            'duration': oembed_obj['duration'],
+            'timestamp': timestamp,
+            'view_count': view_count,
+        }
+
+
+class CamdemyFolderIE(InfoExtractor):
+    _VALID_URL = r'http://www.camdemy.com/folder/(?P<id>\d+)'
+    _TESTS = [{
+        # links with trailing slash
+        'url': 'http://www.camdemy.com/folder/450',
+        'info_dict': {
+            'id': '450',
+            'title': '信號與系統 2012 & 2011 (Signals and Systems)',
+        },
+        'playlist_mincount': 145
+    }, {
+        # links without trailing slash
+        # and multi-page
+        'url': 'http://www.camdemy.com/folder/853',
+        'info_dict': {
+            'id': '853',
+            'title': '科學計算 - 使用 Matlab'
+        },
+        'playlist_mincount': 20
+    }, {
+        # with displayMode parameter. For testing the codes to add parameters
+        'url': 'http://www.camdemy.com/folder/853/?displayMode=defaultOrderByOrg',
+        'info_dict': {
+            'id': '853',
+            'title': '科學計算 - 使用 Matlab'
+        },
+        'playlist_mincount': 20
+    }]
+
+    def _real_extract(self, url):
+        folder_id = self._match_id(url)
+
+        # Add displayMode=list so that all links are displayed in a single page
+        parsed_url = list(compat_urlparse.urlparse(url))
+        query = dict(compat_urlparse.parse_qsl(parsed_url[4]))
+        query.update({'displayMode': 'list'})
+        parsed_url[4] = compat_urllib_parse.urlencode(query)
+        final_url = compat_urlparse.urlunparse(parsed_url)
+
+        page = self._download_webpage(final_url, folder_id)
+        matches = re.findall(r"href='(/media/\d+/?)'", page)
+
+        entries = [self.url_result('http://www.camdemy.com' + media_path)
+                   for media_path in matches]
+
+        folder_title = self._html_search_meta('keywords', page)
+
+        return self.playlist_result(entries, folder_id, folder_title)

youtube_dl/extractor/canalplus.py

@@ -15,12 +15,13 @@ from ..utils import (
 
 class CanalplusIE(InfoExtractor):
     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
-    _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
+    _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
     _SITE_ID_MAP = {
         'canalplus.fr': 'cplus',
         'piwiplus.fr': 'teletoon',
         'd8.tv': 'd8',
+        'itele.fr': 'itele',
     }
 
     _TESTS = [{
@@ -53,6 +54,16 @@ class CanalplusIE(InfoExtractor):
             'upload_date': '20131108',
         },
         'skip': 'videos get deleted after a while',
+    }, {
+        'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
+        'md5': '65aa83ad62fe107ce29e564bb8712580',
+        'info_dict': {
+            'id': '1213714',
+            'ext': 'flv',
+            'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
+            'description': 'md5:8216206ec53426ea6321321f3b3c16db',
+            'upload_date': '20150211',
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/ccc.py

@@ -0,0 +1,99 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    qualities,
+    unified_strdate,
+)
+
+
+class CCCIE(InfoExtractor):
+    IE_NAME = 'media.ccc.de'
+    _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/[^?#]+/[^?#/]*?_(?P<id>[0-9]{8,})._[^?#/]*\.html'
+
+    _TEST = {
+        'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video',
+        'md5': '205a365d0d57c0b1e43a12c9ffe8f9be',
+        'info_dict': {
+            'id': '20131228183',
+            'ext': 'mp4',
+            'title': 'Introduction to Processor Design',
+            'description': 'md5:5ddbf8c734800267f2cee4eab187bc1b',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'view_count': int,
+            'upload_date': '20131229',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        if self._downloader.params.get('prefer_free_formats'):
+            preference = qualities(['mp3', 'opus', 'mp4-lq', 'webm-lq', 'h264-sd', 'mp4-sd', 'webm-sd', 'mp4', 'webm', 'mp4-hd', 'h264-hd', 'webm-hd'])
+        else:
+            preference = qualities(['opus', 'mp3', 'webm-lq', 'mp4-lq', 'webm-sd', 'h264-sd', 'mp4-sd', 'webm', 'mp4', 'webm-hd', 'mp4-hd', 'h264-hd'])
+
+        title = self._html_search_regex(
+            r'(?s)<h1>(.*?)</h1>', webpage, 'title')
+        description = self._html_search_regex(
+            r"(?s)<p class='description'>(.*?)</p>",
+            webpage, 'description', fatal=False)
+        upload_date = unified_strdate(self._html_search_regex(
+            r"(?s)<span class='[^']*fa-calendar-o'></span>(.*?)</li>",
+            webpage, 'upload date', fatal=False))
+        view_count = int_or_none(self._html_search_regex(
+            r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
+            webpage, 'view count', fatal=False))
+
+        matches = re.finditer(r'''(?xs)
+            <(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s*
+            <a\s+href='(?P<http_url>[^']+)'>\s*
+            (?:
+                .*?
+                <a\s+href='(?P<torrent_url>[^']+\.torrent)'
+            )?''', webpage)
+        formats = []
+        for m in matches:
+            format = m.group('format')
+            format_id = self._search_regex(
+                r'.*/([a-z0-9_-]+)/[^/]*$',
+                m.group('http_url'), 'format id', default=None)
+            vcodec = 'h264' if 'h264' in format_id else (
+                'none' if format_id in ('mp3', 'opus') else None
+            )
+            formats.append({
+                'format_id': format_id,
+                'format': format,
+                'url': m.group('http_url'),
+                'vcodec': vcodec,
+                'preference': preference(format_id),
+            })
+
+            if m.group('torrent_url'):
+                formats.append({
+                    'format_id': 'torrent-%s' % (format if format_id is None else format_id),
+                    'format': '%s (torrent)' % format,
+                    'proto': 'torrent',
+                    'format_note': '(unsupported; will just download the .torrent file)',
+                    'vcodec': vcodec,
+                    'preference': -100 + preference(format_id),
+                    'url': m.group('torrent_url'),
+                })
+        self._sort_formats(formats)
+
+        thumbnail = self._html_search_regex(
+            r"<video.*?poster='([^']+)'", webpage, 'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+            'upload_date': upload_date,
+            'formats': formats,
+        }

youtube_dl/extractor/cinchcast.py

@@ -28,12 +28,10 @@ class CinchcastIE(InfoExtractor):
             item, './{http://developer.longtailvideo.com/trac/}date')
         upload_date = unified_strdate(date_str, day_first=False)
         # duration is present but wrong
-        formats = []
-        formats.append({
+        formats = [{
             'format_id': 'main',
-            'url': item.find(
-                './{http://search.yahoo.com/mrss/}content').attrib['url'],
-        })
+            'url': item.find('./{http://search.yahoo.com/mrss/}content').attrib['url'],
+        }]
         backup_url = xpath_text(
             item, './{http://developer.longtailvideo.com/trac/}backupContent')
         if backup_url:

youtube_dl/extractor/cliphunter.py

@@ -1,9 +1,7 @@
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
+from ..utils import determine_ext
 
 
 _translation_table = {
@@ -27,10 +25,10 @@ class CliphunterIE(InfoExtractor):
     '''
     _TEST = {
         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
-        'md5': 'a2ba71eebf523859fe527a61018f723e',
+        'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
         'info_dict': {
             'id': '1012420',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Fun Jynx Maze solo',
             'thumbnail': 're:^https?://.*\.jpg$',
             'age_limit': 18,
@@ -44,39 +42,31 @@ class CliphunterIE(InfoExtractor):
         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_url = _decode(pl_fiji)
-        formats = [{
-            'url': video_url,
-            'format_id': 'default-%s' % pl_c_qual,
-        }]
+        fmts = {}
+        for fmt in ('mp4', 'flv'):
+            fmt_list = self._parse_json(self._search_regex(
+                r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id)
+            for f in fmt_list:
+                fmts[f['fname']] = _decode(f['sUrl'])
 
-        qualities_json = self._search_regex(
-            r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
-        qualities_data = json.loads(qualities_json)
+        qualities = self._parse_json(self._search_regex(
+            r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id)
 
-        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)
+        formats = []
+        for fname, url in fmts.items():
             f = {
-                'format_id': quality_id,
-                'url': video_url,
-                'quality': i,
+                'url': url,
             }
-            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'))
+            if fname in qualities:
+                qual = qualities[fname]
+                f.update({
+                    'format_id': '%s_%sp' % (determine_ext(url), qual['h']),
+                    'width': qual['w'],
+                    'height': qual['h'],
+                    'tbr': qual['br'],
+                })
             formats.append(f)
+
         self._sort_formats(formats)
 
         thumbnail = self._search_regex(

youtube_dl/extractor/cnn.py

@@ -51,7 +51,7 @@ class CNNIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         path = mobj.group('path')
         page_title = mobj.group('title')
-        info_url = 'http://cnn.com/video/data/3.0/%s/index.xml' % path
+        info_url = 'http://edition.cnn.com/video/data/3.0/%s/index.xml' % path
         info = self._download_xml(info_url, page_title)
 
         formats = []
@@ -143,13 +143,13 @@ class CNNArticleIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
     _TEST = {
         'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
-        'md5': '275b326f85d80dff7592a9820f5dc887',
+        'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
         'info_dict': {
-            'id': 'bestoftv/2014/12/21/sotu-crowley-president-obama-north-korea-not-going-to-be-intimidated.cnn',
+            'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
             'ext': 'mp4',
-            'title': 'Obama: We\'re not going to be intimidated',
-            'description': 'md5:e735586f3dc936075fa654a4d91b21f9',
-            'upload_date': '20141220',
+            'title': 'Obama: Cyberattack not an act of war',
+            'description': 'md5:51ce6750450603795cad0cdfbd7d05c5',
+            'upload_date': '20141221',
         },
         'add_ie': ['CNN'],
     }

youtube_dl/extractor/collegerama.py

@@ -0,0 +1,92 @@
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_request
+from ..utils import (
+    float_or_none,
+    int_or_none,
+)
+
+
+class CollegeRamaIE(InfoExtractor):
+    _VALID_URL = r'https?://collegerama\.tudelft\.nl/Mediasite/Play/(?P<id>[\da-f]+)'
+    _TESTS = [
+        {
+            'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d',
+            'md5': '481fda1c11f67588c0d9d8fbdced4e39',
+            'info_dict': {
+                'id': '585a43626e544bdd97aeb71a0ec907a01d',
+                'ext': 'mp4',
+                'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
+                'description': '',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 7713.088,
+                'timestamp': 1413309600,
+                'upload_date': '20141014',
+            },
+        },
+        {
+            'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4',
+            'md5': 'ef1fdded95bdf19b12c5999949419c92',
+            'info_dict': {
+                'id': '86a9ea9f53e149079fbdb4202b521ed21d',
+                'ext': 'wmv',
+                'title': '64ste Vakantiecursus: Afvalwater',
+                'description': 'md5:7fd774865cc69d972f542b157c328305',
+                'duration': 10853,
+                'timestamp': 1326446400,
+                'upload_date': '20120113',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        player_options_request = {
+            "getPlayerOptionsRequest": {
+                "ResourceId": video_id,
+                "QueryString": "",
+            }
+        }
+
+        request = compat_urllib_request.Request(
+            'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
+            json.dumps(player_options_request))
+        request.add_header('Content-Type', 'application/json')
+
+        player_options = self._download_json(request, video_id)
+
+        presentation = player_options['d']['Presentation']
+        title = presentation['Title']
+        description = presentation.get('Description')
+        thumbnail = None
+        duration = float_or_none(presentation.get('Duration'), 1000)
+        timestamp = int_or_none(presentation.get('UnixTime'), 1000)
+
+        formats = []
+        for stream in presentation['Streams']:
+            for video in stream['VideoUrls']:
+                thumbnail_url = stream.get('ThumbnailUrl')
+                if thumbnail_url:
+                    thumbnail = 'http://collegerama.tudelft.nl' + thumbnail_url
+                format_id = video['MediaType']
+                if format_id == 'SS':
+                    continue
+                formats.append({
+                    'url': video['Location'],
+                    'format_id': format_id,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/comedycentral.py

@@ -34,12 +34,12 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
 
 class ComedyCentralShowsIE(MTVServicesInfoExtractor):
     IE_DESC = 'The Daily Show / The Colbert Report'
-    # urls can be abbreviations like :thedailyshow or :colbert
+    # urls can be abbreviations like :thedailyshow
     # urls for episodes like:
     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
     #                     or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
     #                     or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
-    _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
+    _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
                       |https?://(:www\.)?
                           (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
                          ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
@@ -49,7 +49,9 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
                               |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
                           )|
                           (?P<interview>
-                              extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
+                              extended-interviews/(?P<interID>[0-9a-z]+)/
+                              (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
+                              (?:/[^/?#]?|[?#]|$))))
                      '''
     _TESTS = [{
         'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
@@ -62,6 +64,38 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
             'uploader': 'thedailyshow',
             'title': 'thedailyshow kristen-stewart part 1',
         }
+    }, {
+        'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
+        'info_dict': {
+            'id': 'sarah-chayes-extended-interview',
+            'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+            'title': 'thedailyshow Sarah Chayes Extended Interview',
+        },
+        'playlist': [
+            {
+                'info_dict': {
+                    'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
+                    'ext': 'mp4',
+                    'upload_date': '20150129',
+                    'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+                    'uploader': 'thedailyshow',
+                    'title': 'thedailyshow sarah-chayes-extended-interview part 1',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
+                    'ext': 'mp4',
+                    'upload_date': '20150129',
+                    'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+                    'uploader': 'thedailyshow',
+                    'title': 'thedailyshow sarah-chayes-extended-interview part 2',
+                },
+            },
+        ],
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
         'only_matching': True,
@@ -230,6 +264,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
 
         return {
             '_type': 'playlist',
+            'id': epTitle,
             'entries': entries,
             'title': show_name + ' ' + title,
             'description': description,

youtube_dl/extractor/common.py

@@ -14,6 +14,7 @@ import xml.etree.ElementTree
 
 from ..compat import (
     compat_cookiejar,
+    compat_HTTPError,
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
@@ -21,10 +22,12 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
+    age_restricted,
     clean_html,
     compiled_regex_type,
     ExtractorError,
     float_or_none,
+    HEADRequest,
     int_or_none,
     RegexNotFoundError,
     sanitize_filename,
@@ -86,7 +89,8 @@ class InfoExtractor(object):
                     * player_url SWF Player URL (used for rtmpdump).
                     * protocol   The protocol that will be used for the actual
                                  download, lower-case.
-                                 "http", "https", "rtsp", "rtmp", "m3u8" or so.
+                                 "http", "https", "rtsp", "rtmp", "rtmpe",
+                                 "m3u8", or "m3u8_native".
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field, regardless of all other values.
@@ -107,12 +111,17 @@ class InfoExtractor(object):
                                   (quality takes higher priority)
                                  -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.
+                    * stretched_ratio  If given and not 1, indicates that the
+                                 video's pixels are not square.
+                                 width : height ratio as float.
+                    * no_resume  The server does not support resuming the
+                                 (HTTP or RTMP) download. Boolean.
+
     url:            Final video URL.
     ext:            Video filename extension.
     format:         The video format, defaults to ext (used for --get-format)
@@ -126,7 +135,9 @@ class InfoExtractor(object):
                     something like "4234987", title "Dancing naked mole rats",
                     and display_id "dancing-naked-mole-rats"
     thumbnails:     A list of dictionaries, with the following entries:
+                        * "id" (optional, string) - Thumbnail format ID
                         * "url"
+                        * "preference" (optional, int) - quality of the image
                         * "width" (optional, int)
                         * "height" (optional, int)
                         * "resolution" (optional, string "{width}x{height"},
@@ -134,6 +145,7 @@ class InfoExtractor(object):
     thumbnail:      Full URL to a video thumbnail image.
     description:    Full video description.
     uploader:       Full name of the video uploader.
+    creator:        The main artist who created the video.
     timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
@@ -145,7 +157,19 @@ class InfoExtractor(object):
     view_count:     How many users have watched the video on the platform.
     like_count:     Number of positive ratings of the video
     dislike_count:  Number of negative ratings of the video
+    average_rating: Average rating give by users, the scale used depends on the webpage
     comment_count:  Number of comments on the video
+    comments:       A list of comments, each with one or more of the following
+                    properties (all but one of text or html optional):
+                        * "author" - human-readable name of the comment author
+                        * "author_id" - user ID of the comment author
+                        * "id" - Comment ID
+                        * "html" - Comment as HTML
+                        * "text" - Plain text of the comment
+                        * "timestamp" - UNIX timestamp of comment
+                        * "parent" - ID of the comment this one is replying to.
+                                     Set to "root" to indicate that this is a
+                                     comment to the original video.
     age_limit:      Age restriction for the video, as an integer (years)
     webpage_url:    The url to the video webpage, if given to youtube-dl it
                     should allow to get the same result again. (It will be set
@@ -241,8 +265,15 @@ class InfoExtractor(object):
 
     def extract(self, url):
         """Extracts URL information and returns it in list of dicts."""
+        try:
             self.initialize()
             return self._real_extract(url)
+        except ExtractorError:
+            raise
+        except compat_http_client.IncompleteRead as e:
+            raise ExtractorError('A network error has occured.', cause=e, expected=True)
+        except (KeyError, StopIteration) as e:
+            raise ExtractorError('An extractor error has occured.', cause=e)
 
     def set_downloader(self, downloader):
         """Sets the downloader for this IE."""
@@ -364,9 +395,19 @@ class InfoExtractor(object):
 
         return content
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
         """ Returns the data of the page as a string """
+        success = False
+        try_count = 0
+        while success is False:
+            try:
                 res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+                success = True
+            except compat_http_client.IncompleteRead as e:
+                try_count += 1
+                if try_count >= tries:
+                    raise e
+                self._sleep(timeout, video_id)
         if res is False:
             return res
         else:
@@ -474,7 +515,7 @@ class InfoExtractor(object):
                 if mobj:
                     break
 
-        if os.name != 'nt' and sys.stderr.isatty():
+        if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty():
             _name = '\033[0;34m%s\033[0m' % name
         else:
             _name = name
@@ -593,7 +634,7 @@ class InfoExtractor(object):
         return self._html_search_regex(
             r'''(?isx)<meta
                     (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
-                    [^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name),
+                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
             html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
@@ -623,6 +664,21 @@ class InfoExtractor(object):
         }
         return RATING_TABLE.get(rating.lower(), None)
 
+    def _family_friendly_search(self, html):
+        # See http://schema.org/VideoObject
+        family_friendly = self._html_search_meta('isFamilyFriendly', html)
+
+        if not family_friendly:
+            return None
+
+        RATING_TABLE = {
+            '1': 0,
+            'true': 0,
+            '0': 18,
+            'false': 18,
+        }
+        return RATING_TABLE.get(family_friendly.lower(), None)
+
     def _twitter_search_player(self, html):
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
@@ -672,21 +728,40 @@ class InfoExtractor(object):
                 preference,
                 f.get('language_preference') if f.get('language_preference') is not None else -1,
                 f.get('quality') if f.get('quality') is not None else -1,
+                f.get('tbr') if f.get('tbr') is not None else -1,
+                f.get('filesize') if f.get('filesize') is not None else -1,
+                f.get('vbr') if f.get('vbr') is not None else -1,
                 f.get('height') if f.get('height') is not None else -1,
                 f.get('width') if f.get('width') is not None else -1,
                 ext_preference,
-                f.get('tbr') if f.get('tbr') is not None else -1,
-                f.get('vbr') if f.get('vbr') is not None else -1,
                 f.get('abr') if f.get('abr') is not None else -1,
                 audio_ext_preference,
                 f.get('fps') if f.get('fps') is not None else -1,
-                f.get('filesize') if f.get('filesize') is not None else -1,
                 f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
                 f.get('source_preference') if f.get('source_preference') is not None else -1,
                 f.get('format_id'),
             )
         formats.sort(key=_formats_key)
 
+    def _check_formats(self, formats, video_id):
+        if formats:
+            formats[:] = filter(
+                lambda f: self._is_valid_url(
+                    f['url'], video_id,
+                    item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
+                formats)
+
+    def _is_valid_url(self, url, video_id, item='video'):
+        try:
+            self._request_webpage(url, video_id, 'Checking %s URL' % item)
+            return True
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                self.report_warning(
+                    '%s URL is invalid, skipping' % item, video_id)
+                return False
+            raise
+
     def http_scheme(self):
         """ Either "http:" or "https:", depending on the user's preferences """
         return (
@@ -711,33 +786,41 @@ class InfoExtractor(object):
         self.to_screen(msg)
         time.sleep(timeout)
 
-    def _extract_f4m_formats(self, manifest_url, video_id):
+    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
         manifest = self._download_xml(
             manifest_url, video_id, 'Downloading f4m manifest',
             'Unable to download f4m manifest')
 
         formats = []
+        manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
+        if not media_nodes:
+            manifest_version = '2.0'
+            media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         for i, media_el in enumerate(media_nodes):
+            if manifest_version == '2.0':
+                manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/'
+                                + (media_el.attrib.get('href') or media_el.attrib.get('url')))
             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,
+                'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
                 'url': manifest_url,
                 'ext': 'flv',
                 'tbr': tbr,
                 'width': int_or_none(media_el.attrib.get('width')),
                 'height': int_or_none(media_el.attrib.get('height')),
+                'preference': preference,
             })
         self._sort_formats(formats)
 
         return formats
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
-                              entry_protocol='m3u8', preference=None):
+                              entry_protocol='m3u8', preference=None,
+                              m3u8_id=None):
 
         formats = [{
-            'format_id': 'm3u8-meta',
+            'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
             'url': m3u8_url,
             'ext': ext,
             'protocol': 'm3u8',
@@ -773,9 +856,8 @@ class InfoExtractor(object):
                     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)),
+                    'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
                     'url': format_url(line.strip()),
                     'tbr': tbr,
                     'ext': ext,
@@ -801,10 +883,13 @@ class InfoExtractor(object):
         return formats
 
     # TODO: improve extraction
-    def _extract_smil_formats(self, smil_url, video_id):
+    def _extract_smil_formats(self, smil_url, video_id, fatal=True):
         smil = self._download_xml(
             smil_url, video_id, 'Downloading SMIL file',
-            'Unable to download SMIL file')
+            'Unable to download SMIL file', fatal=fatal)
+        if smil is False:
+            assert not fatal
+            return []
 
         base = smil.find('./head/meta').get('base')
 
@@ -877,6 +962,35 @@ class InfoExtractor(object):
             None, '/', True, False, expire_time, '', None, None, None)
         self._downloader.cookiejar.set_cookie(cookie)
 
+    def get_testcases(self, include_onlymatching=False):
+        t = getattr(self, '_TEST', None)
+        if t:
+            assert not hasattr(self, '_TESTS'), \
+                '%s has _TEST and _TESTS' % type(self).__name__
+            tests = [t]
+        else:
+            tests = getattr(self, '_TESTS', [])
+        for t in tests:
+            if not include_onlymatching and t.get('only_matching', False):
+                continue
+            t['name'] = type(self).__name__[:-len('IE')]
+            yield t
+
+    def is_suitable(self, age_limit):
+        """ Test whether the extractor is generally suitable for the given
+        age limit (i.e. pornographic sites are not, all others usually are) """
+
+        any_restricted = False
+        for tc in self.get_testcases(include_onlymatching=False):
+            if 'playlist' in tc:
+                tc = tc['playlist'][0]
+            is_restricted = age_restricted(
+                tc.get('info_dict', {}).get('age_limit'), age_limit)
+            if not is_restricted:
+                return True
+            any_restricted = any_restricted or is_restricted
+        return not any_restricted
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/commonmistakes.py

@@ -24,6 +24,23 @@ class CommonMistakesIE(InfoExtractor):
             'That doesn\'t make any sense. '
             'Simply remove the parameter in your command or configuration.'
         ) % url
-        if self._downloader.params.get('verbose'):
+        if not self._downloader.params.get('verbose'):
             msg += ' Add -v to the command line to see what arguments and configuration youtube-dl got.'
         raise ExtractorError(msg, expected=True)
+
+
+class UnicodeBOMIE(InfoExtractor):
+        IE_DESC = False
+        _VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
+
+        _TESTS = [{
+            'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
+            'only_matching': True,
+        }]
+
+        def _real_extract(self, url):
+            real_url = self._match_id(url)
+            self.report_warning(
+                'Your URL starts with a Byte Order Mark (BOM). '
+                'Removing the BOM and looking for "%s" ...' % real_url)
+            return self.url_result(real_url)

youtube_dl/extractor/ctsnews.py

@@ -0,0 +1,93 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601, ExtractorError
+
+
+class CtsNewsIE(InfoExtractor):
+    # https connection failed (Connection reset)
+    _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
+    _TESTS = [{
+        'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
+        'md5': 'a9875cb790252b08431186d741beaabe',
+        'info_dict': {
+            'id': '201501291578109',
+            'ext': 'mp4',
+            'title': '以色列.真主黨交火 3人死亡',
+            'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
+            'timestamp': 1422528540,
+            'upload_date': '20150129',
+        }
+    }, {
+        # News count not appear on page but still available in database
+        'url': 'http://news.cts.com.tw/cts/international/201309/201309031304098.html',
+        'md5': '3aee7e0df7cdff94e43581f54c22619e',
+        'info_dict': {
+            'id': '201309031304098',
+            'ext': 'mp4',
+            'title': '韓國31歲童顏男 貌如十多歲小孩',
+            'description': 'md5:f183feeba3752b683827aab71adad584',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1378205880,
+            'upload_date': '20130903',
+        }
+    }, {
+        # With Youtube embedded video
+        'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
+        'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
+        'add_ie': ['Youtube'],
+        'info_dict': {
+            'id': 'OVbfO7d0_hQ',
+            'ext': 'mp4',
+            'title': 'iPhone6熱銷 蘋果財報亮眼',
+            'description': 'md5:f395d4f485487bb0f992ed2c4b07aa7d',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20150128',
+            'uploader_id': 'TBSCTS',
+            'uploader': '中華電視公司',
+        }
+    }]
+
+    def _real_extract(self, url):
+        news_id = self._match_id(url)
+        page = self._download_webpage(url, news_id)
+
+        if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
+            feed_url = self._html_search_regex(
+                r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
+                page, 'feed url')
+            video_url = self._download_webpage(
+                feed_url, news_id, note='Fetching feed')
+        else:
+            self.to_screen('Not CTSPlayer video, trying Youtube...')
+            youtube_url = self._search_regex(
+                r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
+                default=None)
+            if not youtube_url:
+                raise ExtractorError('The news includes no videos!', expected=True)
+
+            return {
+                '_type': 'url',
+                'url': youtube_url,
+                'ie_key': 'Youtube',
+            }
+
+        description = self._html_search_meta('description', page)
+        title = self._html_search_meta('title', page)
+        thumbnail = self._html_search_meta('image', page)
+
+        datetime_str = self._html_search_regex(
+            r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
+        # Transform into ISO 8601 format with timezone info
+        datetime_str = datetime_str.replace('/', '-') + ':00+0800'
+        timestamp = parse_iso8601(datetime_str, delimiter=' ')
+
+        return {
+            'id': news_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+        }

youtube_dl/extractor/dctp.py

@@ -0,0 +1,61 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+
+
+class DctpTvIE(InfoExtractor):
+    _VALID_URL = r'http://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
+    _TEST = {
+        'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
+        'info_dict': {
+            'id': '1324',
+            'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
+            'ext': 'flv',
+            'title': 'Videoinstallation für eine Kaufhausfassade'
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        base_url = 'http://dctp-ivms2-restapi.s3.amazonaws.com/'
+        version_json = self._download_json(
+            base_url + 'version.json',
+            video_id, note='Determining file version')
+        version = version_json['version_name']
+        info_json = self._download_json(
+            '{0}{1}/restapi/slugs/{2}.json'.format(base_url, version, video_id),
+            video_id, note='Fetching object ID')
+        object_id = compat_str(info_json['object_id'])
+        meta_json = self._download_json(
+            '{0}{1}/restapi/media/{2}.json'.format(base_url, version, object_id),
+            video_id, note='Downloading metadata')
+        uuid = meta_json['uuid']
+        title = meta_json['title']
+        wide = meta_json['is_wide']
+        if wide:
+            ratio = '16x9'
+        else:
+            ratio = '4x3'
+        play_path = 'mp4:{0}_dctp_0500_{1}.m4v'.format(uuid, ratio)
+
+        servers_json = self._download_json(
+            'http://www.dctp.tv/streaming_servers/',
+            video_id, note='Downloading server list')
+        url = servers_json[0]['endpoint']
+
+        return {
+            'id': object_id,
+            'title': title,
+            'format': 'rtmp',
+            'url': url,
+            'play_path': play_path,
+            'rtmp_real_time': True,
+            'ext': 'flv',
+            'display_id': video_id
+        }

youtube_dl/extractor/defense.py

@@ -1,39 +1,37 @@
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
 
 
 class DefenseGouvFrIE(InfoExtractor):
     IE_NAME = 'defense.gouv.fr'
-    _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
-                  r'ligthboxvideo/base-de-medias/webtv/(.*)')
+    _VALID_URL = r'http://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
 
     _TEST = {
         'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
-        'file': '11213.mp4',
         'md5': '75bba6124da7e63d2d60b5244ec9430c',
-        "info_dict": {
-            "title": "attaque-chimique-syrienne-du-21-aout-2013-1"
+        'info_dict': {
+            'id': '11213',
+            'ext': 'mp4',
+            'title': 'attaque-chimique-syrienne-du-21-aout-2013-1'
         }
     }
 
     def _real_extract(self, url):
-        title = re.match(self._VALID_URL, url).group(1)
+        title = self._match_id(url)
         webpage = self._download_webpage(url, title)
+
         video_id = self._search_regex(
             r"flashvars.pvg_id=\"(\d+)\";",
             webpage, 'ID')
 
         json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
                     + video_id)
-        info = self._download_webpage(json_url, title,
-                                      'Downloading JSON config')
-        video_url = json.loads(info)['renditions'][0]['url']
+        info = self._download_json(json_url, title, 'Downloading JSON config')
+        video_url = info['renditions'][0]['url']
 
-        return {'id': video_id,
+        return {
+            'id': video_id,
             'ext': 'mp4',
             'url': video_url,
             'title': title,

youtube_dl/extractor/discovery.py

@@ -1,47 +1,45 @@
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    int_or_none,
+)
 
 
 class DiscoveryIE(InfoExtractor):
-    _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
+    _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
     _TEST = {
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
-        'md5': 'e12614f9ee303a6ccef415cb0793eba2',
+        'md5': '3c69d77d9b0d82bfd5e5932a60f26504',
         'info_dict': {
-            'id': '614784',
-            'ext': 'mp4',
-            'title': 'MythBusters: Mission Impossible Outtakes',
+            'id': 'mission-impossible-outtakes',
+            'ext': 'flv',
+            'title': 'Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                             ' each other -- to the point of confusing Jamie\'s dog -- and '
                             'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
                             ' back.'),
             'duration': 156,
+            'timestamp': 1303099200,
+            'upload_date': '20110418',
         },
     }
 
     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)
 
-        video_list_json = self._search_regex(r'var videoListJSON = ({.*?});',
-                                             webpage, 'video list', flags=re.DOTALL)
-        video_list = json.loads(video_list_json)
-        info = video_list['clips'][0]
-        formats = []
-        for f in info['mp4']:
-            formats.append(
-                {'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])})
+        info = self._parse_json(self._search_regex(
+            r'(?s)<script type="application/ld\+json">(.*?)</script>',
+            webpage, 'video info'), video_id)
 
         return {
-            'id': info['contentId'],
-            'title': video_list['name'],
-            'formats': formats,
-            'description': info['videoCaption'],
-            'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'),
-            'duration': info['duration'],
+            'id': video_id,
+            'title': info['name'],
+            'url': info['contentURL'],
+            'description': info.get('description'),
+            'thumbnail': info.get('thumbnailUrl'),
+            'timestamp': parse_iso8601(info.get('uploadDate')),
+            'duration': int_or_none(info.get('duration')),
         }

youtube_dl/extractor/dotsub.py

@@ -1,13 +1,14 @@
 from __future__ import unicode_literals
 
-import re
-import time
-
 from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    int_or_none,
+)
 
 
 class DotsubIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
         'md5': '0914d4d69605090f623b7ac329fea66e',
@@ -15,28 +16,37 @@ class DotsubIE(InfoExtractor):
             'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
             'ext': 'flv',
             'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
+            'description': 'md5:699a0f7f50aeec6042cb3b1db2d0d074',
+            'thumbnail': 're:^https?://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
+            'duration': 3169,
             'uploader': '4v4l0n42',
-            'description': 'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
-            'thumbnail': 'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
+            'timestamp': 1292248482.625,
             'upload_date': '20101213',
+            'view_count': int,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        info_url = "https://dotsub.com/api/media/%s/metadata" % video_id
-        info = self._download_json(info_url, video_id)
-        date = time.gmtime(info['dateCreated'] / 1000)  # The timestamp is in miliseconds
+        video_id = self._match_id(url)
+
+        info = self._download_json(
+            'https://dotsub.com/api/media/%s/metadata' % video_id, video_id)
+        video_url = info.get('mediaURI')
+
+        if not video_url:
+            webpage = self._download_webpage(url, video_id)
+            video_url = self._search_regex(
+                r'"file"\s*:\s*\'([^\']+)', webpage, 'video url')
 
         return {
             'id': video_id,
-            'url': info['mediaURI'],
+            'url': video_url,
             'ext': 'flv',
             'title': info['title'],
-            'thumbnail': info['screenshotURI'],
-            'description': info['description'],
-            'uploader': info['user'],
-            'view_count': info['numberOfViews'],
-            'upload_date': '%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
+            'description': info.get('description'),
+            'thumbnail': info.get('screenshotURI'),
+            'duration': int_or_none(info.get('duration'), 1000),
+            'uploader': info.get('user'),
+            'timestamp': float_or_none(info.get('dateCreated'), 1000),
+            'view_count': int_or_none(info.get('numberOfViews')),
         }

youtube_dl/extractor/drbonanza.py

@@ -0,0 +1,131 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class DRBonanzaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)'
+
+    _TESTS = [{
+        'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
+        'md5': 'fe330252ddea607635cf2eb2c99a0af3',
+        'info_dict': {
+            'id': '65517',
+            'ext': 'mp4',
+            'title': 'Talkshowet - Leonard Cohen',
+            'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'timestamp': 1295537932,
+            'upload_date': '20110120',
+            'duration': 3664,
+        },
+    }, {
+        'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
+        'md5': '6dfe039417e76795fb783c52da3de11d',
+        'info_dict': {
+            'id': '59410',
+            'ext': 'mp3',
+            'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
+            'description': 'md5:501e5a195749480552e214fbbed16c4e',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'timestamp': 1223274900,
+            'upload_date': '20081006',
+            'duration': 7369,
+        },
+    }]
+
+    def _real_extract(self, url):
+        url_id = self._match_id(url)
+        webpage = self._download_webpage(url, url_id)
+
+        if url_id:
+            info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json'))
+        else:
+            # Just fetch the first video on that page
+            info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json'))
+
+        asset_id = str(info['AssetId'])
+        title = info['Title'].rstrip(' \'\"-,.:;!?')
+        duration = int_or_none(info.get('Duration'), scale=1000)
+        # First published online. "FirstPublished" contains the date for original airing.
+        timestamp = parse_iso8601(
+            re.sub(r'\.\d+$', '', info['Created']))
+
+        def parse_filename_info(url):
+            match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
+            if match:
+                return {
+                    'width': int(match.group('width')),
+                    'height': int(match.group('height')),
+                    'vbr': int(match.group('bitrate')),
+                    'ext': match.group('ext')
+                }
+            match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
+            if match:
+                return {
+                    'vbr': int(match.group('bitrate')),
+                    'ext': match.group(2)
+                }
+            return {}
+
+        video_types = ['VideoHigh', 'VideoMid', 'VideoLow']
+        preferencemap = {
+            'VideoHigh': -1,
+            'VideoMid': -2,
+            'VideoLow': -3,
+            'Audio': -4,
+        }
+
+        formats = []
+        for file in info['Files']:
+            if info['Type'] == "Video":
+                if file['Type'] in video_types:
+                    format = parse_filename_info(file['Location'])
+                    format.update({
+                        'url': file['Location'],
+                        'format_id': file['Type'].replace('Video', ''),
+                        'preference': preferencemap.get(file['Type'], -10),
+                    })
+                    formats.append(format)
+                elif file['Type'] == "Thumb":
+                    thumbnail = file['Location']
+            elif info['Type'] == "Audio":
+                if file['Type'] == "Audio":
+                    format = parse_filename_info(file['Location'])
+                    format.update({
+                        'url': file['Location'],
+                        'format_id': file['Type'],
+                        'vcodec': 'none',
+                    })
+                    formats.append(format)
+                elif file['Type'] == "Thumb":
+                    thumbnail = file['Location']
+
+        description = '%s\n%s\n%s\n' % (
+            info['Description'], info['Actors'], info['Colophon'])
+
+        for f in formats:
+            f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
+            f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
+        self._sort_formats(formats)
+
+        display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
+        display_id = re.sub(r'-+', '-', display_id)
+
+        return {
+            'id': asset_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+        }

youtube_dl/extractor/drtuber.py

@@ -15,7 +15,7 @@ class DrTuberIE(InfoExtractor):
             'id': '1740434',
             'display_id': 'hot-perky-blonde-naked-golf',
             'ext': 'mp4',
-            'title': 'Hot Perky Blonde Naked Golf',
+            'title': 'hot perky blonde naked golf',
             'like_count': int,
             'dislike_count': int,
             'comment_count': int,
@@ -36,7 +36,8 @@ class DrTuberIE(InfoExtractor):
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
+            [r'class="hd_title" style="[^"]+">([^<]+)</h1>', r'<title>([^<]+) - \d+'],
+            webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',

youtube_dl/extractor/drtv.py

@@ -6,7 +6,7 @@ from ..utils import parse_iso8601
 
 
 class DRTVIE(SubtitlesInfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
 
     _TEST = {
         'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
@@ -25,9 +25,15 @@ class DRTVIE(SubtitlesInfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        programcard = self._download_json(
-            'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON')
+        webpage = self._download_webpage(url, video_id)
 
+        video_id = self._search_regex(
+            r'data-(?:material-identifier|episode-slug)="([^"]+)"',
+            webpage, 'video id')
+
+        programcard = self._download_json(
+            'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
+            video_id, 'Downloading video JSON')
         data = programcard['Data'][0]
 
         title = data['Title']
@@ -48,14 +54,20 @@ class DRTVIE(SubtitlesInfoExtractor):
             elif asset['Kind'] == 'VideoResource':
                 duration = asset['DurationInMilliseconds'] / 1000.0
                 restricted_to_denmark = asset['RestrictedToDenmark']
+                spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
                 for link in asset['Links']:
                     target = link['Target']
                     uri = link['Uri']
+                    format_id = target
+                    preference = -1 if target == 'HDS' else -2
+                    if spoken_subtitles:
+                        preference -= 2
+                        format_id += '-spoken-subtitles'
                     formats.append({
                         'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
-                        'format_id': target,
+                        'format_id': format_id,
                         'ext': link['FileFormat'],
-                        'preference': -1 if target == 'HDS' else -2,
+                        'preference': preference,
                     })
                 subtitles_list = asset.get('SubtitlesList')
                 if isinstance(subtitles_list, list):

youtube_dl/extractor/eighttracks.py

@@ -9,6 +9,9 @@ from .common import InfoExtractor
 from ..compat import (
     compat_str,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class EightTracksIE(InfoExtractor):
@@ -112,14 +115,29 @@ class EightTracksIE(InfoExtractor):
         session = str(random.randint(0, 1000000000))
         mix_id = data['id']
         track_count = data['tracks_count']
+        duration = data['duration']
+        avg_song_duration = float(duration) / track_count
         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
         next_url = first_url
         entries = []
+
         for i in range(track_count):
+            api_json = None
+            download_tries = 0
+
+            while api_json is None:
+                try:
                     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')
+                except ExtractorError:
+                    if download_tries > 3:
+                        raise
+                    else:
+                        download_tries += 1
+                        self._sleep(avg_song_duration, playlist_id)
+
             api_data = json.loads(api_json)
             track_data = api_data['set']['track']
             info = {
@@ -131,6 +149,7 @@ class EightTracksIE(InfoExtractor):
                 'ext': 'm4a',
             }
             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 {

youtube_dl/extractor/elpais.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import unified_strdate
 
@@ -24,9 +22,7 @@ class ElPaisIE(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)
 
         prefix = self._html_search_regex(

youtube_dl/extractor/escapist.py

@@ -1,18 +1,17 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
 )
 from ..utils import (
     ExtractorError,
+    js_to_json,
 )
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-'
+    _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
     _TEST = {
         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
@@ -20,31 +19,30 @@ class EscapistIE(InfoExtractor):
             'id': '6618',
             'ext': 'mp4',
             'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
-            'uploader': 'the-escapist-presents',
+            'uploader_id': 'the-escapist-presents',
+            'uploader': 'The Escapist Presents',
             'title': "Breaking Down Baldur's Gate",
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        showName = mobj.group('showname')
-        video_id = mobj.group('id')
-
-        self.report_extraction(video_id)
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        videoDesc = self._html_search_regex(
-            r'<meta name="description" content="([^"]*)"',
-            webpage, 'description', fatal=False)
+        uploader_id = self._html_search_regex(
+            r"<h1 class='headline'><a href='/videos/view/(.*?)'",
+            webpage, 'uploader ID', fatal=False)
+        uploader = self._html_search_regex(
+            r"<h1 class='headline'>(.*?)</a>",
+            webpage, 'uploader', fatal=False)
+        description = self._html_search_meta('description', webpage)
 
-        playerUrl = self._og_search_video_url(webpage, name='player URL')
+        raw_title = self._html_search_meta('title', webpage, fatal=True)
+        title = raw_title.partition(' : ')[2]
 
-        title = self._html_search_regex(
-            r'<meta name="title" content="([^"]*)"',
-            webpage, 'title').split(' : ')[-1]
-
-        configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
-        configUrl = compat_urllib_parse.unquote(configUrl)
+        player_url = self._og_search_video_url(webpage, name='player URL')
+        config_url = compat_urllib_parse.unquote(self._search_regex(
+            r'config=(.*)$', player_url, 'config URL'))
 
         formats = []
 
@@ -53,18 +51,21 @@ class EscapistIE(InfoExtractor):
                 cfgurl, video_id,
                 'Downloading ' + name + ' configuration',
                 'Unable to download ' + name + ' configuration',
-                transform_source=lambda s: s.replace("'", '"'))
+                transform_source=js_to_json)
 
             playlist = config['playlist']
+            video_url = next(
+                p['url'] for p in playlist
+                if p.get('eventCategory') == 'Video')
             formats.append({
-                'url': playlist[1]['url'],
+                'url': video_url,
                 'format_id': name,
                 'quality': quality,
             })
 
-        _add_format('normal', configUrl, quality=0)
-        hq_url = (configUrl +
-                  ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
+        _add_format('normal', config_url, quality=0)
+        hq_url = (config_url +
+                  ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
         try:
             _add_format('hq', hq_url, quality=1)
         except ExtractorError:
@@ -75,9 +76,10 @@ class EscapistIE(InfoExtractor):
         return {
             'id': video_id,
             'formats': formats,
-            'uploader': showName,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
             'title': title,
             'thumbnail': self._og_search_thumbnail(webpage),
-            'description': videoDesc,
-            'player_url': playerUrl,
+            'description': description,
+            'player_url': player_url,
         }

youtube_dl/extractor/fc2.py

@@ -5,6 +5,7 @@ import hashlib
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
 )
@@ -16,7 +17,8 @@ from ..utils import (
 class FC2IE(InfoExtractor):
     _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)'
     IE_NAME = 'fc2'
-    _TEST = {
+    _NETRC_MACHINE = 'fc2'
+    _TESTS = [{
         'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
         'md5': 'a6ebe8ebe0396518689d963774a54eb7',
         'info_dict': {
@@ -24,12 +26,57 @@ class FC2IE(InfoExtractor):
             'ext': 'flv',
             'title': 'Boxing again with Puff',
         },
+    }, {
+        'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/',
+        'info_dict': {
+            'id': '20150125cEva0hDn',
+            'ext': 'mp4',
+        },
+        'params': {
+            'username': 'ytdl@yt-dl.org',
+            'password': '(snip)',
+            'skip': 'requires actual password'
         }
+    }]
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None or password is None:
+            return False
+
+        # Log in
+        login_form_strs = {
+            'email': username,
+            'password': password,
+            'done': 'video',
+            'Submit': ' Login ',
+        }
+
+        # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
+        # chokes on unicode
+        login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
+        login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
+        request = compat_urllib_request.Request(
+            'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
+
+        login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
+        if 'mode=redirect&login=done' not in login_results:
+            self.report_warning('unable to log in: bad username or password')
+            return False
+
+        # this is also needed
+        login_redir = compat_urllib_request.Request('http://id.fc2.com/?mode=redirect&login=done')
+        self._download_webpage(
+            login_redir, None, note='Login redirect', errnote='Login redirect failed')
+
+        return True
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        self._login()
         webpage = self._download_webpage(url, video_id)
         self._downloader.cookiejar.clear_session_cookies()  # must clear
+        self._login()
 
         title = self._og_search_title(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
@@ -46,7 +93,12 @@ class FC2IE(InfoExtractor):
         info = compat_urlparse.parse_qs(info_webpage)
 
         if 'err_code' in info:
-            raise ExtractorError('Error code: %s' % info['err_code'][0])
+            # most of the time we can still download wideo even if err_code is 403 or 602
+            self.report_warning(
+                'Error code was: %s... but still trying' % info['err_code'][0])
+
+        if 'filepath' not in info:
+            raise ExtractorError('Cannot download file. Are you logged in?')
 
         video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
         title_info = info.get('title')

youtube_dl/extractor/firstpost.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -20,11 +18,10 @@ class FirstpostIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         page = self._download_webpage(url, video_id)
-        title = self._html_search_meta('twitter:title', page, 'title')
+
+        title = self._html_search_meta('twitter:title', page, 'title', fatal=True)
         description = self._html_search_meta('twitter:description', page, 'title')
 
         data = self._download_xml(
@@ -42,6 +39,7 @@ class FirstpostIE(InfoExtractor):
                 'height': int(details.find('./height').text.strip()),
             } for details in item.findall('./source/file_details') if details.find('./file').text
         ]
+        self._sort_formats(formats)
 
         return {
             'id': video_id,

youtube_dl/extractor/firsttv.py

@@ -1,52 +1,71 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import int_or_none
 
 
 class FirstTVIE(InfoExtractor):
-    IE_NAME = 'firsttv'
-    IE_DESC = 'Видеоархив - Первый канал'
-    _VALID_URL = r'http://(?:www\.)?1tv\.ru/videoarchive/(?P<id>\d+)'
+    IE_NAME = '1tv'
+    IE_DESC = 'Первый канал'
+    _VALID_URL = r'http://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>.+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.1tv.ru/videoarchive/73390',
-        'md5': '3de6390cf0cca4a5eae1d1d83895e5ad',
+        'md5': '777f525feeec4806130f4f764bc18a4f',
         'info_dict': {
             'id': '73390',
             'ext': 'mp4',
             'title': 'Олимпийские канатные дороги',
-            'description': 'md5:cc730d2bf4215463e37fff6a1e277b13',
-            'thumbnail': 'http://img1.1tv.ru/imgsize640x360/PR20140210114657.JPG',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'duration': 149,
+            'like_count': int,
+            'dislike_count': int,
         },
         'skip': 'Only works from Russia',
-    }
+    }, {
+        'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930',
+        'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
+        'info_dict': {
+            'id': '35930',
+            'ext': 'mp4',
+            'title': 'Наедине со всеми. Людмила Сенчина',
+            'description': 'md5:89553aed1d641416001fe8d450f06cb9',
+            'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
+            'duration': 2694,
+        },
+        'skip': 'Only works from Russia',
+    }]
 
     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, 'Downloading page')
 
         video_url = self._html_search_regex(
-            r'''(?s)jwplayer\('flashvideoportal_1'\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video URL')
+            r'''(?s)(?:jwplayer\('flashvideoportal_1'\)\.setup\({|var\s+playlistObj\s*=).*?'file'\s*:\s*'([^']+)'.*?}\);''',
+            webpage, 'video URL')
 
         title = self._html_search_regex(
-            r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>', webpage, 'title')
+            [r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
+             r"'title'\s*:\s*'([^']+)'"], webpage, 'title')
         description = self._html_search_regex(
-            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>', webpage, 'description', fatal=False)
+            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
+            webpage, 'description', default=None) or self._html_search_meta(
+                'description', webpage, 'description')
 
         thumbnail = self._og_search_thumbnail(webpage)
-        duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False)
+        duration = self._og_search_property(
+            'video:duration', webpage,
+            'video duration', fatal=False)
 
-        like_count = self._html_search_regex(r'title="Понравилось".*?/></label> \[(\d+)\]',
-                                             webpage, 'like count', fatal=False)
-        dislike_count = self._html_search_regex(r'title="Не понравилось".*?/></label> \[(\d+)\]',
-                                                webpage, 'dislike count', fatal=False)
+        like_count = self._html_search_regex(
+            r'title="Понравилось".*?/></label> \[(\d+)\]',
+            webpage, 'like count', default=None)
+        dislike_count = self._html_search_regex(
+            r'title="Не понравилось".*?/></label> \[(\d+)\]',
+            webpage, 'dislike count', default=None)
 
         return {
             'id': video_id,

youtube_dl/extractor/fktv.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class FKTVIE(InfoExtractor):
     IE_NAME = 'fernsehkritik.tv'
-    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
+    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
 
     _TEST = {
         'url': 'http://fernsehkritik.tv/folge-1',
@@ -26,29 +26,32 @@ class FKTVIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        episode = int(mobj.group('ep'))
+        episode = int(self._match_id(url))
 
-        server = random.randint(2, 4)
-        video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode
-        start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
+        video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%s.jpg' % episode
+        start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/Start' % episode,
                                                episode)
         playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
                                       'playlist', flags=re.DOTALL)
         files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
-        # TODO: return a single multipart video
+
         videos = []
         for i, _ in enumerate(files, 1):
             video_id = '%04d%d' % (episode, i)
-            video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i)
+            video_url = 'http://fernsehkritik.tv/js/directme.php?file=%s%s.flv' % (episode, '' if i == 1 else '-%d' % i)
             videos.append({
+                'ext': 'flv',
                 'id': video_id,
                 'url': video_url,
                 'title': clean_html(get_element_by_id('eptitle', start_webpage)),
                 'description': clean_html(get_element_by_id('contentlist', start_webpage)),
                 'thumbnail': video_thumbnail
             })
-        return videos
+        return {
+            '_type': 'multi_video',
+            'entries': videos,
+            'id': 'folge-%s' % episode,
+        }
 
 
 class FKTVPosteckeIE(InfoExtractor):

youtube_dl/extractor/folketinget.py

@@ -16,6 +16,7 @@ class FolketingetIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?ft\.dk/webtv/video/[^?#]*?\.(?P<id>[0-9]+)\.aspx'
     _TEST = {
         'url': 'http://www.ft.dk/webtv/video/20141/eru/td.1165642.aspx?as=1#player',
+        'md5': '6269e8626fa1a891bf5369b386ae996a',
         'info_dict': {
             'id': '1165642',
             'ext': 'mp4',
@@ -29,9 +30,6 @@ class FolketingetIE(InfoExtractor):
             'upload_date': '20141120',
             'duration': 3960,
         },
-        'params': {
-            'skip_download': 'rtmpdump required',
-        }
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/fourtube.py

@@ -7,10 +7,9 @@ from ..compat import (
     compat_urllib_request,
 )
 from ..utils import (
-    clean_html,
     parse_duration,
+    parse_iso8601,
     str_to_int,
-    unified_strdate,
 )
 
 
@@ -28,68 +27,81 @@ class FourTubeIE(InfoExtractor):
             'uploader': 'WCP Club',
             'uploader_id': 'wcp-club',
             'upload_date': '20131031',
+            'timestamp': 1383263892,
             'duration': 583,
+            'view_count': int,
+            'like_count': int,
+            'categories': list,
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage_url = 'http://www.4tube.com/videos/' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
+        webpage = self._download_webpage(url, video_id)
 
-        self.report_extraction(video_id)
+        title = self._html_search_meta('name', webpage)
+        timestamp = parse_iso8601(self._html_search_meta(
+            'uploadDate', webpage))
+        thumbnail = self._html_search_meta('thumbnailUrl', webpage)
+        uploader_id = self._html_search_regex(
+            r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
+            webpage, 'uploader id')
+        uploader = self._html_search_regex(
+            r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
+            webpage, 'uploader')
 
-        playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
-        media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
-        sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
-        title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
-        thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
+        categories_html = self._search_regex(
+            r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
+            webpage, 'categories', fatal=False)
+        categories = None
+        if categories_html:
+            categories = [
+                c.strip() for c in re.findall(
+                    r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
 
-        uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
-        mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
-        (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
+        view_count = str_to_int(self._search_regex(
+            r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">',
+            webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._search_regex(
+            r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">',
+            webpage, 'like count', fatal=False))
+        duration = parse_duration(self._html_search_meta('duration', webpage))
 
-        upload_date = None
-        view_count = None
-        duration = None
-        description = self._html_search_meta('description', webpage, 'description')
-        if description:
-            upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
-                                             fatal=False)
-            if upload_date:
-                upload_date = unified_strdate(upload_date)
-            view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
-            if view_count:
-                view_count = str_to_int(view_count)
-            duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
+        params_js = self._search_regex(
+            r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
+            webpage, 'initialization parameters'
+        )
+        params = self._parse_json('[%s]' % params_js, video_id)
+        media_id = params[0]
+        sources = ['%s' % p for p in params[2]]
 
-        token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
+        token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format(
+            media_id, '+'.join(sources))
         headers = {
             b'Content-Type': b'application/x-www-form-urlencoded',
             b'Origin': b'http://www.4tube.com',
         }
         token_req = compat_urllib_request.Request(token_url, b'{}', headers)
         tokens = self._download_json(token_req, video_id)
-
         formats = [{
             'url': tokens[format]['token'],
             'format_id': format + 'p',
             'resolution': format + 'p',
             'quality': int(format),
         } for format in sources]
-
         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
-            'thumbnail': thumbnail_url,
+            'categories': categories,
+            'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
+            'like_count': like_count,
             'view_count': view_count,
             'duration': duration,
             'age_limit': 18,
-            'webpage_url': webpage_url,
         }

youtube_dl/extractor/franceculture.py

@@ -1,77 +1,69 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_parse_qs,
     compat_urlparse,
 )
+from ..utils import (
+    determine_ext,
+    int_or_none,
+)
 
 
 class FranceCultureIE(InfoExtractor):
-    _VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
         'info_dict': {
             'id': '4795174',
             'ext': 'mp3',
             'title': 'Rendez-vous au pays des geeks',
+            'alt_title': 'Carnet nomade | 13-14',
             'vcodec': 'none',
-            'uploader': 'Colette Fellous',
             'upload_date': '20140301',
-            'duration': 3601,
             'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
-            'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...',
+            'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats',
+            'timestamp': 1393700400,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        baseurl = mobj.group('baseurl')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        params_code = self._search_regex(
-            r"<param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf\?([^']+)' />",
-            webpage, 'parameter code')
-        params = compat_parse_qs(params_code)
-        video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0])
+
+        video_path = self._search_regex(
+            r'<a id="player".*?href="([^"]+)"', webpage, 'video path')
+        video_url = compat_urlparse.urljoin(url, video_path)
+        timestamp = int_or_none(self._search_regex(
+            r'<a id="player".*?data-date="([0-9]+)"',
+            webpage, 'upload date', fatal=False))
+        thumbnail = self._search_regex(
+            r'<a id="player".*?>\s+<img src="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
 
         title = self._html_search_regex(
-            r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title')
+            r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
+        alt_title = self._html_search_regex(
+            r'<span class="title">(.*?)</span>',
+            webpage, 'alt_title', fatal=False)
+        description = self._html_search_regex(
+            r'<span class="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
+
         uploader = self._html_search_regex(
             r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
-            webpage, 'uploader', fatal=False)
-        thumbnail_part = self._html_search_regex(
-            r'(?s)<div id="emission".*?<img src="([^"]+)"', webpage,
-            'thumbnail', fatal=False)
-        if thumbnail_part is None:
-            thumbnail = None
-        else:
-            thumbnail = compat_urlparse.urljoin(baseurl, thumbnail_part)
-        description = self._html_search_regex(
-            r'(?s)<p class="desc">(.*?)</p>', webpage, 'description')
-
-        info = json.loads(params['infoData'][0])[0]
-        duration = info.get('media_length')
-        upload_date_candidate = info.get('media_section5')
-        upload_date = (
-            upload_date_candidate
-            if (upload_date_candidate is not None and
-                re.match(r'[0-9]{8}$', upload_date_candidate))
-            else None)
+            webpage, 'uploader', default=None)
+        vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
 
         return {
             'id': video_id,
             'url': video_url,
-            'vcodec': 'none' if video_url.lower().endswith('.mp3') else None,
-            'duration': duration,
+            'vcodec': vcodec,
             'uploader': uploader,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
             'title': title,
+            'alt_title': alt_title,
             'thumbnail': thumbnail,
             'description': description,
         }

youtube_dl/extractor/francetv.py

@@ -230,12 +230,13 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
 
 class GenerationQuoiIE(InfoExtractor):
     IE_NAME = 'france2.fr:generation-quoi'
-    _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
+    _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
 
     _TEST = {
         'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
-        'file': 'k7FJX8VBcvvLmX4wA5Q.mp4',
         'info_dict': {
+            'id': 'k7FJX8VBcvvLmX4wA5Q',
+            'ext': 'mp4',
             'title': 'Génération Quoi - Garde à Vous',
             'uploader': 'Génération Quoi',
         },
@@ -243,14 +244,12 @@ class GenerationQuoiIE(InfoExtractor):
             # It uses Dailymotion
             'skip_download': True,
         },
-        'skip': 'Only available from France',
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
-        info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % name)
-        info_json = self._download_webpage(info_url, name)
+        display_id = self._match_id(url)
+        info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
+        info_json = self._download_webpage(info_url, display_id)
         info = json.loads(info_json)
         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
                                ie='Dailymotion')

youtube_dl/extractor/gamekings.py

@@ -1,41 +1,67 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..utils import (
+    xpath_text,
+    xpath_with_ns,
+)
 
 
 class GamekingsIE(InfoExtractor):
-    _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
-    _TEST = {
+    _VALID_URL = r'http://www\.gamekings\.tv/(?:videos|nieuws)/(?P<id>[^/]+)'
+    _TESTS = [{
         'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
         # MD5 is flaky, seems to change regularly
         # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3',
         'info_dict': {
-            'id': '20130811',
+            'id': 'phoenix-wright-ace-attorney-dual-destinies-review',
             'ext': 'mp4',
             'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',
             'description': 'md5:36fd701e57e8c15ac8682a2374c99731',
-        }
-    }
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        # vimeo video
+        'url': 'http://www.gamekings.tv/videos/the-legend-of-zelda-majoras-mask/',
+        'md5': '12bf04dfd238e70058046937657ea68d',
+        'info_dict': {
+            'id': 'the-legend-of-zelda-majoras-mask',
+            'ext': 'mp4',
+            'title': 'The Legend of Zelda: Majora’s Mask',
+            'description': 'md5:9917825fe0e9f4057601fe1e38860de3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.gamekings.tv/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
+        video_id = self._match_id(url)
 
-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
-        webpage = self._download_webpage(url, name)
-        video_url = self._og_search_video_url(webpage)
+        webpage = self._download_webpage(url, video_id)
 
-        video = re.search(r'[0-9]+', video_url)
-        video_id = video.group(0)
+        playlist_id = self._search_regex(
+            r'gogoVideo\(\s*\d+\s*,\s*"([^"]+)', webpage, 'playlist id')
 
-        # Todo: add medium format
-        video_url = video_url.replace(video_id, 'large/' + video_id)
+        playlist = self._download_xml(
+            'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=%s' % playlist_id,
+            video_id)
+
+        NS_MAP = {
+            'jwplayer': 'http://rss.jwpcdn.com/'
+        }
+
+        item = playlist.find('./channel/item')
+
+        thumbnail = xpath_text(item, xpath_with_ns('./jwplayer:image', NS_MAP), 'thumbnail')
+        video_url = item.find(xpath_with_ns('./jwplayer:source', NS_MAP)).get('file')
 
         return {
             'id': video_id,
-            'ext': 'mp4',
             'url': video_url,
             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/gameone.py

@@ -57,8 +57,7 @@ class GameOneIE(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)
         og_video = self._og_search_video_url(webpage, secure=False)

youtube_dl/extractor/gamestar.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -29,9 +27,7 @@ class GameStarIE(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)
 
         og_title = self._og_search_title(webpage)

youtube_dl/extractor/gdcvault.py

@@ -39,7 +39,8 @@ class GDCVaultIE(InfoExtractor):
                 'id': '1015301',
                 'ext': 'flv',
                 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
-            }
+            },
+            'skip': 'Requires login',
         }
     ]
 

youtube_dl/extractor/generic.py

@@ -17,6 +17,7 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     HEADRequest,
+    is_html,
     orderedSet,
     parse_xml,
     smuggle_url,
@@ -139,6 +140,19 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Ooyala'],
         },
+        # multiple ooyala embeds on SBN network websites
+        {
+            'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
+            'info_dict': {
+                'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
+                'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
+            },
+            'playlist_mincount': 3,
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': ['Ooyala'],
+        },
         # google redirect
         {
             'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
@@ -361,7 +375,7 @@ class GenericIE(InfoExtractor):
             'info_dict': {
                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
                 'title': 'Zero Punctuation',
-                'description': 're:'
+                'description': 're:.*groundbreaking video review series.*'
             },
             'playlist_mincount': 11,
         },
@@ -488,6 +502,51 @@ class GenericIE(InfoExtractor):
                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
             }
         },
+        # Cinerama player
+        {
+            'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
+            'info_dict': {
+                'id': '730m_DandD_1901_512k',
+                'ext': 'mp4',
+                'uploader': 'www.abc.net.au',
+                'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
+            }
+        },
+        # embedded viddler video
+        {
+            'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
+            'info_dict': {
+                'id': '4d03aad9',
+                'ext': 'mp4',
+                'uploader': 'deadspin',
+                'title': 'WALL-TO-GORTAT',
+                'timestamp': 1422285291,
+                'upload_date': '20150126',
+            },
+            'add_ie': ['Viddler'],
+        },
+        # jwplayer YouTube
+        {
+            'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
+            'info_dict': {
+                'id': 'Mrj4DVp2zeA',
+                'ext': 'mp4',
+                'upload_date': '20150204',
+                'uploader': 'The National Archives UK',
+                'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
+                'uploader_id': 'NationalArchives08',
+                'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
+            },
+        },
+        # rtl.nl embed
+        {
+            'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
+            'playlist_mincount': 5,
+            'info_dict': {
+                'id': 'aanslagen-kopenhagen',
+                'title': 'Aanslagen Kopenhagen | RTL Nieuws',
+            }
+        }
     ]
 
     def report_following_redirect(self, new_url):
@@ -647,7 +706,7 @@ class GenericIE(InfoExtractor):
         # Maybe it's a direct link to a video?
         # Be careful not to download the whole thing!
         first_bytes = full_response.read(512)
-        if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')):
+        if not is_html(first_bytes):
             self._downloader.report_warning(
                 'URL could be a direct video link, returning it as such.')
             upload_date = unified_strdate(
@@ -732,6 +791,13 @@ class GenericIE(InfoExtractor):
                 'entries': entries,
             }
 
+        # Look for embedded rtl.nl player
+        matches = re.findall(
+            r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
+            webpage)
+        if matches:
+            return _playlist_from_matches(matches, ie='RtlNl')
+
         # Look for embedded (iframe) Vimeo player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
@@ -739,7 +805,6 @@ class GenericIE(InfoExtractor):
             player_url = unescapeHTML(mobj.group('url'))
             surl = smuggle_url(player_url, {'Referer': url})
             return self.url_result(surl)
-
         # Look for embedded (swf embed) Vimeo player
         mobj = re.search(
             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
@@ -849,12 +914,28 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
+        # Look for embedded Viddler player
+        mobj = re.search(
+            r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
         # Look for Ooyala videos
-        mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
-                re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+        mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
+                re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
+                re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage))
         if mobj is not None:
             return OoyalaIE._build_url_result(mobj.group('ec'))
 
+        # Look for multiple Ooyala embeds on SBN network websites
+        mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
+        if mobj is not None:
+            embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
+            if embeds:
+                return _playlist_from_matches(
+                    embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
+
         # Look for Aparat videos
         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
         if mobj is not None:
@@ -981,7 +1062,12 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded sbs.com.au player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1',
+            r'''(?x)
+            (?:
+                <meta\s+property="og:video"\s+content=|
+                <iframe[^>]+?src=
+            )
+            (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
             webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'SBS')
@@ -1012,6 +1098,8 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'Livestream')
 
         def check_video(vurl):
+            if YoutubeIE.suitable(vurl):
+                return True
             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')
@@ -1029,7 +1117,8 @@ class GenericIE(InfoExtractor):
                     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 = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
@@ -1042,9 +1131,13 @@ class GenericIE(InfoExtractor):
             found = filter_video(re.findall(r'''(?xs)
                 flowplayer\("[^"]+",\s*
                     \{[^}]+?\}\s*,
-                    \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
+                    \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
                         ["']?url["']?\s*:\s*["']([^"']+)["']
             ''', webpage))
+        if not found:
+            # Cinerama player
+            found = re.findall(
+                r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
         if not found:
             # Try to find twitter cards info
             found = filter_video(re.findall(

youtube_dl/extractor/globo.py

@@ -70,6 +70,19 @@ class GloboIE(InfoExtractor):
                 'like_count': int,
             }
         },
+        {
+            'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
+            'md5': 'c1defca721ce25b2354e927d3e4b3dec',
+            'info_dict': {
+                'id': '3928201',
+                'ext': 'mp4',
+                'title': 'Ator e diretor argentino, Ricado Darín fala sobre utopias e suas perdas',
+                'duration': 1472.906,
+                'uploader': 'Canal Brasil',
+                'uploader_id': 705,
+                'like_count': int,
+            }
+        },
     ]
 
     class MD5():
@@ -381,10 +394,15 @@ class GloboIE(InfoExtractor):
             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
 
+            resource_url = resource['url']
+            signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
+            if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
+                formats.extend(self._extract_m3u8_formats(signed_url, resource_id, 'mp4'))
+            else:
                 formats.append({
-                'url': '%s?h=%s&k=%s' % (resource['url'], signed_hash, 'flash'),
+                    'url': signed_url,
                     'format_id': resource_id,
-                'height': resource['height']
+                    'height': resource.get('height'),
                 })
 
         self._sort_formats(formats)

youtube_dl/extractor/goshgay.py

@@ -34,8 +34,6 @@ class GoshgayIE(InfoExtractor):
         duration = parse_duration(self._html_search_regex(
             r'<span class="duration">\s*-?\s*(.*?)</span>',
             webpage, 'duration', fatal=False))
-        family_friendly = self._html_search_meta(
-            'isFamilyFriendly', webpage, default='false')
 
         flashvars = compat_parse_qs(self._html_search_regex(
             r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"',
@@ -49,5 +47,5 @@ class GoshgayIE(InfoExtractor):
             'title': title,
             'thumbnail': thumbnail,
             'duration': duration,
-            'age_limit': 0 if family_friendly == 'true' else 18,
+            'age_limit': self._family_friendly_search(webpage),
         }

youtube_dl/extractor/grooveshark.py

@@ -83,7 +83,7 @@ class GroovesharkIE(InfoExtractor):
         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] \
+        return re.split('(?m)^\s*try\s*\{', js)[0] \
                  .split(' = ', 1)[1].strip().rstrip(';')
 
     def _transform_meta(self, js):

youtube_dl/extractor/hearthisat.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
+    HEADRequest,
+    str_to_int,
+    urlencode_postdata,
+    urlhandle_detect_ext,
+)
+
+
+class HearThisAtIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
+    _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
+    _TEST = {
+        'url': 'https://hearthis.at/moofi/dr-kreep',
+        'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
+        'info_dict': {
+            'id': '150939',
+            'ext': 'wav',
+            'title': 'Moofi - Dr. Kreep',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1421564134,
+            'description': 'Creepy Patch. Mutable Instruments Braids Vowel + Formant Mode.',
+            'upload_date': '20150118',
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'duration': 71,
+            'categories': ['Experimental'],
+        }
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
+
+        webpage = self._download_webpage(url, display_id)
+        track_id = self._search_regex(
+            r'intTrackId\s*=\s*(\d+)', webpage, 'track ID')
+
+        payload = urlencode_postdata({'tracks[]': track_id})
+        req = compat_urllib_request.Request(self._PLAYLIST_URL, payload)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+        track = self._download_json(req, track_id, 'Downloading playlist')[0]
+        title = '{artist:s} - {title:s}'.format(**track)
+
+        categories = None
+        if track.get('category'):
+            categories = [track['category']]
+
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        meta_span = r'<span[^>]+class="%s".*?</i>([^<]+)</span>'
+        view_count = str_to_int(self._search_regex(
+            meta_span % 'plays_count', webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._search_regex(
+            meta_span % 'likes_count', webpage, 'like count', fatal=False))
+        comment_count = str_to_int(self._search_regex(
+            meta_span % 'comment_count', webpage, 'comment count', fatal=False))
+        duration = str_to_int(self._search_regex(
+            r'data-length="(\d+)', webpage, 'duration', fatal=False))
+        timestamp = str_to_int(self._search_regex(
+            r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False))
+
+        formats = []
+        mp3_url = self._search_regex(
+            r'(?s)<a class="player-link"\s+(?:[a-zA-Z0-9_:-]+="[^"]+"\s+)*?data-mp3="([^"]+)"',
+            webpage, 'mp3 URL', fatal=False)
+        if mp3_url:
+            formats.append({
+                'format_id': 'mp3',
+                'vcodec': 'none',
+                'acodec': 'mp3',
+                'url': mp3_url,
+            })
+        download_path = self._search_regex(
+            r'<a class="[^"]*download_fct[^"]*"\s+href="([^"]+)"',
+            webpage, 'download URL', default=None)
+        if download_path:
+            download_url = compat_urlparse.urljoin(url, download_path)
+            ext_req = HEADRequest(download_url)
+            ext_handle = self._request_webpage(
+                ext_req, display_id, note='Determining extension')
+            ext = urlhandle_detect_ext(ext_handle)
+            formats.append({
+                'format_id': 'download',
+                'vcodec': 'none',
+                'ext': ext,
+                'url': download_url,
+                'preference': 2,  # Usually better quality
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': track_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'like_count': like_count,
+            'categories': categories,
+        }

youtube_dl/extractor/historicfilms.py

@@ -0,0 +1,46 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class HistoricFilmsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?historicfilms\.com/(?:tapes/|play)(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.historicfilms.com/tapes/4728',
+        'md5': 'd4a437aec45d8d796a38a215db064e9a',
+        'info_dict': {
+            'id': '4728',
+            'ext': 'mov',
+            'title': 'Historic Films: GP-7',
+            'description': 'md5:1a86a0f3ac54024e419aba97210d959a',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 2096,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        tape_id = self._search_regex(
+            r'class="tapeId">([^<]+)<', webpage, 'tape id')
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._html_search_meta(
+            'thumbnailUrl', webpage, 'thumbnails') or self._og_search_thumbnail(webpage)
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration'))
+
+        video_url = 'http://www.historicfilms.com/video/%s_%s_web.mov' % (tape_id, video_id)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+        }

youtube_dl/extractor/history.py

@@ -0,0 +1,31 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class HistoryIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?history\.com/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
+
+    _TESTS = [{
+        'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
+        'md5': '6fe632d033c92aa10b8d4a9be047a7c5',
+        'info_dict': {
+            'id': 'bLx5Dv5Aka1G',
+            'ext': 'mp4',
+            'title': "Bet You Didn't Know: Valentine's Day",
+            'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
+        },
+        'add_ie': ['ThePlatform'],
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
+            webpage, 'video url')
+
+        return self.url_result(smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}))

youtube_dl/extractor/huffpost.py

@@ -39,8 +39,9 @@ class HuffPostIE(InfoExtractor):
         data = self._download_json(api_url, video_id)['data']
 
         video_title = data['title']
-        duration = parse_duration(data['running_time'])
-        upload_date = unified_strdate(data['schedule']['starts_at'])
+        duration = parse_duration(data.get('running_time'))
+        upload_date = unified_strdate(
+            data.get('schedule', {}).get('starts_at') or data.get('segment_start_date_time'))
         description = data.get('description')
 
         thumbnails = []
@@ -59,16 +60,11 @@ class HuffPostIE(InfoExtractor):
             'ext': 'mp4',
             'url': url,
             'vcodec': 'none' if key.startswith('audio/') else None,
-        } for key, url in data['sources']['live'].items()]
-        if data.get('fivemin_id'):
-            fid = data['fivemin_id']
-            fcat = str(int(fid) // 100 + 1)
-            furl = 'http://avideos.5min.com/2/' + fcat[-3:] + '/' + fcat + '/' + fid + '.mp4'
-            formats.append({
-                'format': 'fivemin',
-                'url': furl,
-                'preference': 1,
-            })
+        } for key, url in data.get('sources', {}).get('live', {}).items()]
+
+        if not formats and data.get('fivemin_id'):
+            return self.url_result('5min:%s' % data['fivemin_id'])
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/imdb.py

@@ -16,7 +16,6 @@ class ImdbIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
-        'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
         'info_dict': {
             'id': '2524815897',
             'ext': 'mp4',

youtube_dl/extractor/ivi.py

@@ -16,7 +16,7 @@ from ..utils import (
 class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'
-    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
 
     _TESTS = [
         # Single movie
@@ -63,13 +63,15 @@ class IviIE(InfoExtractor):
         return int(m.group('commentcount')) if m is not None else 0
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
+        video_id = self._match_id(url)
 
         api_url = 'http://api.digitalaccess.ru/api/json/'
 
-        data = {'method': 'da.content.get',
-                'params': [video_id, {'site': 's183',
+        data = {
+            'method': 'da.content.get',
+            'params': [
+                video_id, {
+                    'site': 's183',
                     'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
                     'contentid': video_id
                 }
@@ -78,14 +80,17 @@ class IviIE(InfoExtractor):
 
         request = compat_urllib_request.Request(api_url, json.dumps(data))
 
-        video_json_page = self._download_webpage(request, video_id, 'Downloading video JSON')
+        video_json_page = self._download_webpage(
+            request, video_id, 'Downloading video JSON')
         video_json = json.loads(video_json_page)
 
         if 'error' in video_json:
             error = video_json['error']
             if error['origin'] == 'NoRedisValidData':
                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
-            raise ExtractorError('Unable to download video %s: %s' % (video_id, error['message']), expected=True)
+            raise ExtractorError(
+                'Unable to download video %s: %s' % (video_id, error['message']),
+                expected=True)
 
         result = video_json['result']
 

youtube_dl/extractor/izlesene.py

@@ -80,9 +80,6 @@ class IzleseneIE(InfoExtractor):
             r'comment_count\s*=\s*\'([^\']+)\';',
             webpage, 'comment_count', fatal=False)
 
-        family_friendly = self._html_search_meta(
-            'isFamilyFriendly', webpage, 'age limit', fatal=False)
-
         content_url = self._html_search_meta(
             'contentURL', webpage, 'content URL', fatal=False)
         ext = determine_ext(content_url, 'mp4')
@@ -120,6 +117,6 @@ class IzleseneIE(InfoExtractor):
             'duration': duration,
             'view_count': int_or_none(view_count),
             'comment_count': int_or_none(comment_count),
-            'age_limit': 18 if family_friendly == 'False' else 0,
+            'age_limit': self._family_friendly_search(webpage),
             'formats': formats,
         }

youtube_dl/extractor/kankan.py

@@ -13,17 +13,17 @@ class KankanIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',
-        'file': '48863.flv',
         'md5': '29aca1e47ae68fc28804aca89f29507e',
         'info_dict': {
+            'id': '48863',
+            'ext': 'flv',
             'title': 'Ready To Go',
         },
         'skip': 'Only available from China',
     }
 
     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)
 
         title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')

youtube_dl/extractor/karaoketv.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse
+from ..utils import (
+    js_to_json,
+)
+
+
+class KaraoketvIE(InfoExtractor):
+    _VALID_URL = r'http://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://karaoketv.co.il/?container=songs&id=171568',
+        'info_dict': {
+            'id': '171568',
+            'ext': 'mp4',
+            'title': 'אל העולם שלך - רותם כהן - שרים קריוקי',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        page_video_url = self._og_search_video_url(webpage, video_id)
+        config_json = compat_urllib_parse.unquote_plus(self._search_regex(
+            r'config=(.*)', page_video_url, 'configuration'))
+
+        urls_info_json = self._download_json(
+            config_json, video_id, 'Downloading configuration',
+            transform_source=js_to_json)
+
+        url = urls_info_json['playlist'][0]['url']
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'url': url,
+        }