release 2013.12.23.1

For context, refer to the http://de.wikipedia.org/wiki/Depublizieren

.travis.yml

@@ -3,9 +3,6 @@ python:
   - "2.6"
   - "2.7"
   - "3.3"
-before_install:
-  - sudo apt-get update -qq
-  - sudo apt-get install -qq rtmpdump
 script: nosetests test --verbose
 notifications:
   email:

README.md

@@ -30,13 +30,17 @@ which means you can modify it, redistribute it or use it however you like.
     --list-extractors          List all supported extractors and the URLs they
                                would handle
     --extractor-descriptions   Output descriptions of all supported extractors
-    --proxy URL                Use the specified HTTP/HTTPS proxy
+    --proxy URL                Use the specified HTTP/HTTPS proxy. Pass in an
+                               empty string (--proxy "") for direct connection
     --no-check-certificate     Suppress HTTPS certificate validation.
     --cache-dir DIR            Location in the filesystem where youtube-dl can
                                store downloaded information permanently. By
                                default $XDG_CACHE_HOME/youtube-dl or ~/.cache
                                /youtube-dl .
     --no-cache-dir             Disable filesystem caching
+    --bidi-workaround          Work around terminals that lack bidirectional
+                               text support. Requires bidiv or fribidi
+                               executable in PATH
 
 ## Video Selection:
     --playlist-start NUMBER    playlist video to start at (default is 1)
@@ -53,10 +57,15 @@ which means you can modify it, redistribute it or use it however you like.
     --date DATE                download only videos uploaded in this date
     --datebefore DATE          download only videos uploaded before this date
     --dateafter DATE           download only videos uploaded after this date
+    --min-views COUNT          Do not download any videos with less than COUNT
+                               views
+    --max-views COUNT          Do not download any videos with more than COUNT
+                               views
     --no-playlist              download only the currently playing video
     --age-limit YEARS          download only videos suitable for the given age
-    --download-archive FILE    Download only videos not present in the archive
-                               file. Record all downloaded videos in it.
+    --download-archive FILE    Download only videos not listed in the archive
+                               file. Record the IDs of all downloaded videos in
+                               it.
 
 ## Download Options:
     -r, --rate-limit LIMIT     maximum download rate in bytes per second (e.g.
@@ -96,6 +105,8 @@ which means you can modify it, redistribute it or use it however you like.
     --restrict-filenames       Restrict filenames to only ASCII characters, and
                                avoid "&" and spaces in filenames
     -a, --batch-file FILE      file containing URLs to download ('-' for stdin)
+    --load-info FILE           json file containing the video information
+                               (created with the "--write-json" option
     -w, --no-overwrites        do not overwrite files
     -c, --continue             force resume of partially downloaded files. By
                                default, youtube-dl will resume downloads if
@@ -121,6 +132,7 @@ which means you can modify it, redistribute it or use it however you like.
     --get-id                   simulate, quiet but print id
     --get-thumbnail            simulate, quiet but print thumbnail URL
     --get-description          simulate, quiet but print video description
+    --get-duration             simulate, quiet but print video length
     --get-filename             simulate, quiet but print output filename
     --get-format               simulate, quiet but print output format
     -j, --dump-json            simulate, quiet but print JSON information
@@ -130,11 +142,11 @@ which means you can modify it, redistribute it or use it however you like.
     -v, --verbose              print various debugging information
     --dump-intermediate-pages  print downloaded pages to debug problems(very
                                verbose)
-    --write-pages              Write downloaded pages to files in the current
-                               directory
+    --write-pages              Write downloaded intermediary pages to files in
+                               the current directory to debug problems
 
 ## Video Format Options:
-    -f, --format FORMAT        video format code, specifiy the order of
+    -f, --format FORMAT        video format code, specify the order of
                                preference using slashes: "-f 22/17/18". "-f mp4"
                                and "-f flv" are also supported
     --all-formats              download all available video formats
@@ -182,7 +194,7 @@ 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.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.conf`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -272,14 +284,54 @@ This README file was originally written by Daniel Bolton (<https://github.com/db
 
 # BUGS
 
-Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>
+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.
 
-Please include:
-
-* Your exact command line, like `youtube-dl -t "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"`. A common mistake is not to escape the `&`. Putting URLs in quotes should solve this problem.
-* If possible re-run the command with `--verbose`, and include the full output, it is really helpful to us.
-* The output of `youtube-dl --version`
-* The output of `python --version`
-* The name and version of your Operating System ("Ubuntu 11.04 x64" or "Windows 7 x64" is usually enough).
+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.
 
 For discussions, join us in the irc channel #youtube-dl on freenode.
+
+When you submit a request, please re-read it once to avoid a couple of mistakes (you can and should use this as a checklist):
+
+### Is the description of the issue itself sufficient?
+
+We often get issue reports that we cannot really decipher. While in most cases we eventually get the required information after asking back multiple times, this poses an unnecessary drain on our resources. Many contributors, including myself, are also not native speakers, so we may misread some parts.
+
+So please elaborate on what feature you are requesting, or what bug you want to be fixed. Make sure that it's obvious
+
+- What the problem is
+- How it could be fixed
+- How your proposed solution would look like
+
+If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
+
+For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
+
+Site support requests must contain an example URL. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+
+###  Are you using the latest version?
+
+Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. Ábout 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
+
+###  Is the issue already documented?
+
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+
+###  Why are existing options not enough?
+
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+
+###  Is there enough context in your bug report?
+
+People want to solve problems, and often think they do us a favor by breaking down their larger problems (e.g. wanting to skip already downloaded files) to a specific request (e.g. requesting us to look whether the file exists before downloading the info page). However, what often happens is that they break down the problem into two steps: One simple, and one impossible (or extremely complicated one).
+
+We are then presented with a very complicated request when the original problem could be solved far easier, e.g. by recording the downloaded video IDs in a separate file. To avoid this, you must include the greater context where it is non-obvious. In particular, every feature request that does not consist of adding support for a new site should contain a use case scenario that explains in what situation the missing feature would be useful.
+
+###  Does the issue involve one problem, and one problem only?
+
+Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
+
+In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
+
+###  Is anyone going to need the feature?
+
+Only post features that you (or an 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.

devscripts/bash-completion.in

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

test/parameters.json

@@ -39,5 +39,6 @@
     "writeinfojson": true, 
     "writesubtitles": false,
     "allsubtitles": false,
-    "listssubtitles": false
+    "listssubtitles": false,
+    "socket_timeout": 20
 }

test/test_YoutubeDL.py

@@ -7,6 +7,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import FakeYDL
+from youtube_dl import YoutubeDL
 
 
 class YDL(FakeYDL):
@@ -140,6 +141,20 @@ class TestFormatSelection(unittest.TestCase):
         self.assertEqual(test_dict['extractor'], 'Foo')
         self.assertEqual(test_dict['playlist'], 'funny videos')
 
+    def test_prepare_filename(self):
+        info = {
+            u'id': u'1234',
+            u'ext': u'mp4',
+            u'width': None,
+        }
+        def fname(templ):
+            ydl = YoutubeDL({'outtmpl': templ})
+            return ydl.prepare_filename(info)
+        self.assertEqual(fname(u'%(id)s.%(ext)s'), u'1234.mp4')
+        self.assertEqual(fname(u'%(id)s-%(width)s.%(ext)s'), u'1234-NA.mp4')
+        # Replace missing fields with 'NA'
+        self.assertEqual(fname(u'%(uploader_date)s-%(id)s.%(ext)s'), u'NA-1234.mp4')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_all_urls.py

@@ -10,6 +10,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from test.helper import get_testcases
 
 from youtube_dl.extractor import (
+    FacebookIE,
     gen_extractors,
     JustinTVIE,
     YoutubeIE,
@@ -87,12 +88,15 @@ class TestAllURLsMatching(unittest.TestCase):
         assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
         assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
 
+    def test_facebook_matching(self):
+        self.assertTrue(FacebookIE.suitable(u'https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
+
     def test_no_duplicates(self):
         ies = gen_extractors()
         for tc in get_testcases():
             url = tc['url']
             for ie in ies:
-                if type(ie).__name__ in ['GenericIE', tc['name'] + 'IE']:
+                if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
                     self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
                 else:
                     self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
@@ -106,6 +110,13 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':colbertreport', ['ComedyCentralShows'])
         self.assertMatch(':cr', ['ComedyCentralShows'])
 
+    def test_vimeo_matching(self):
+        self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
+        self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
+
+    # https://github.com/rg3/youtube-dl/issues/1930
+    def test_soundcloud_not_matching_sets(self):
+        self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
 
 if __name__ == '__main__':
     unittest.main()

test/test_playlists.py

@@ -12,16 +12,23 @@ from test.helper import FakeYDL
 
 
 from youtube_dl.extractor import (
+    AcademicEarthCourseIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
     VimeoChannelIE,
+    VimeoUserIE,
+    VimeoAlbumIE,
+    VimeoGroupsIE,
     UstreamChannelIE,
     SoundcloudSetIE,
     SoundcloudUserIE,
     LivestreamIE,
     NHLVideocenterIE,
     BambuserChannelIE,
-    BandcampAlbumIE
+    BandcampAlbumIE,
+    SmotriCommunityIE,
+    SmotriUserIE,
+    IviCompilationIE
 )
 
 
@@ -54,6 +61,30 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], u'Vimeo Tributes')
         self.assertTrue(len(result['entries']) > 24)
 
+    def test_vimeo_user(self):
+        dl = FakeYDL()
+        ie = VimeoUserIE(dl)
+        result = ie.extract('http://vimeo.com/nkistudio/videos')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Nki')
+        self.assertTrue(len(result['entries']) > 65)
+
+    def test_vimeo_album(self):
+        dl = FakeYDL()
+        ie = VimeoAlbumIE(dl)
+        result = ie.extract('http://vimeo.com/album/2632481')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Staff Favorites: November 2013')
+        self.assertTrue(len(result['entries']) > 12)
+
+    def test_vimeo_groups(self):
+        dl = FakeYDL()
+        ie = VimeoGroupsIE(dl)
+        result = ie.extract('http://vimeo.com/groups/rolexawards')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Rolex Awards for Enterprise')
+        self.assertTrue(len(result['entries']) > 72)
+
     def test_ustream_channel(self):
         dl = FakeYDL()
         ie = UstreamChannelIE(dl)
@@ -110,6 +141,53 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], u'Nightmare Night EP')
         self.assertTrue(len(result['entries']) >= 4)
+        
+    def test_smotri_community(self):
+        dl = FakeYDL()
+        ie = SmotriCommunityIE(dl)
+        result = ie.extract('http://smotri.com/community/video/kommuna')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'kommuna')
+        self.assertEqual(result['title'], u'КПРФ')
+        self.assertTrue(len(result['entries']) >= 4)
+        
+    def test_smotri_user(self):
+        dl = FakeYDL()
+        ie = SmotriUserIE(dl)
+        result = ie.extract('http://smotri.com/user/inspector')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'inspector')
+        self.assertEqual(result['title'], u'Inspector')
+        self.assertTrue(len(result['entries']) >= 9)
+
+    def test_AcademicEarthCourse(self):
+        dl = FakeYDL()
+        ie = AcademicEarthCourseIE(dl)
+        result = ie.extract(u'http://academicearth.org/courses/building-dynamic-websites/')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'building-dynamic-websites')
+        self.assertEqual(result['title'], u'Building Dynamic Websites')
+        self.assertEqual(result['description'], u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
+        self.assertEqual(len(result['entries']), 10)
+        
+    def test_ivi_compilation(self):
+        dl = FakeYDL()
+        ie = IviCompilationIE(dl)
+        result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'dezhurnyi_angel')
+        self.assertEqual(result['title'], u'Дежурный ангел (2010 - 2012)')
+        self.assertTrue(len(result['entries']) >= 36)
+        
+    def test_ivi_compilation_season(self):
+        dl = FakeYDL()
+        ie = IviCompilationIE(dl)
+        result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'dezhurnyi_angel/season2')
+        self.assertEqual(result['title'], u'Дежурный ангел (2010 - 2012) 2 сезон')
+        self.assertTrue(len(result['entries']) >= 20)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_subtitles.py

@@ -72,7 +72,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
         self.DL.params['writesubtitles'] = True
         self.DL.params['subtitlesformat'] = 'vtt'
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7')
+        self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
 
     def test_youtube_list_subtitles(self):
         self.DL.expect_warning(u'Video doesn\'t have automatic captions')

test/test_utils.py

@@ -13,19 +13,21 @@ import xml.etree.ElementTree
 
 #from youtube_dl.utils import htmlentity_transform
 from youtube_dl.utils import (
-    timeconvert,
-    sanitize_filename,
-    unescapeHTML,
-    orderedSet,
     DateRange,
-    unified_strdate,
+    encodeFilename,
     find_xpath_attr,
     get_meta_content,
-    xpath_with_ns,
-    smuggle_url,
-    unsmuggle_url,
+    orderedSet,
+    sanitize_filename,
     shell_quote,
-    encodeFilename,
+    smuggle_url,
+    str_to_int,
+    timeconvert,
+    unescapeHTML,
+    unified_strdate,
+    unsmuggle_url,
+    url_basename,
+    xpath_with_ns,
 )
 
 if sys.version_info < (3, 0):
@@ -176,6 +178,19 @@ class TestUtil(unittest.TestCase):
         args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
         self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 
+    def test_str_to_int(self):
+        self.assertEqual(str_to_int('123,456'), 123456)
+        self.assertEqual(str_to_int('123.456'), 123456)
+
+    def test_url_basename(self):
+        self.assertEqual(url_basename(u'http://foo.de/'), u'')
+        self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz')
+        self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz')
+        self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz')
+        self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
+        self.assertEqual(
+            url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
+            u'trailer.mp4')
 
 if __name__ == '__main__':
     unittest.main()

test/test_write_info_json.py

@@ -33,6 +33,7 @@ TEST_ID = 'BaW_jenozKc'
 INFO_JSON_FILE = TEST_ID + '.info.json'
 DESCRIPTION_FILE = TEST_ID + '.mp4.description'
 EXPECTED_DESCRIPTION = u'''test chars:  "'/\ä↭𝕐
+test URL: https://github.com/rg3/youtube-dl/issues/1892
 
 This is a test video for youtube-dl.
 

test/test_youtube_lists.py

@@ -15,6 +15,7 @@ from youtube_dl.extractor import (
     YoutubeIE,
     YoutubeChannelIE,
     YoutubeShowIE,
+    YoutubeTopListIE,
 )
 
 
@@ -107,5 +108,21 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('http://www.youtube.com/show/airdisasters')
         self.assertTrue(len(result) >= 3)
 
+    def test_youtube_mix(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('http://www.youtube.com/watch?v=lLJf9qJHR3E&list=RDrjFaenf1T-Y')
+        entries = result['entries']
+        self.assertTrue(len(entries) >= 20)
+        original_video = entries[0]
+        self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
+
+    def test_youtube_toplist(self):
+        dl = FakeYDL()
+        ie = YoutubeTopListIE(dl)
+        result = ie.extract('yttoplist:music:Top Tracks')
+        entries = result['entries']
+        self.assertTrue(len(entries) >= 5)
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/FileDownloader.py

@@ -204,11 +204,27 @@ class FileDownloader(object):
         """Report destination filename."""
         self.to_screen(u'[download] Destination: ' + filename)
 
+    def _report_progress_status(self, msg, is_last_line=False):
+        fullmsg = u'[download] ' + msg
+        if self.params.get('progress_with_newline', False):
+            self.to_screen(fullmsg)
+        else:
+            if os.name == 'nt':
+                prev_len = getattr(self, '_report_progress_prev_line_length',
+                                   0)
+                if prev_len > len(fullmsg):
+                    fullmsg += u' ' * (prev_len - len(fullmsg))
+                self._report_progress_prev_line_length = len(fullmsg)
+                clear_line = u'\r'
+            else:
+                clear_line = (u'\r\x1b[K' if sys.stderr.isatty() else u'\r')
+            self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
+        self.to_console_title(u'youtube-dl ' + msg)
+
     def report_progress(self, percent, data_len_str, speed, eta):
         """Report download progress."""
         if self.params.get('noprogress', False):
             return
-        clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
         if eta is not None:
             eta_str = self.format_eta(eta)
         else:
@@ -218,14 +234,29 @@ class FileDownloader(object):
         else:
             percent_str = 'Unknown %'
         speed_str = self.format_speed(speed)
-        if self.params.get('progress_with_newline', False):
-            self.to_screen(u'[download] %s of %s at %s ETA %s' %
-                (percent_str, data_len_str, speed_str, eta_str))
+
+        msg = (u'%s of %s at %s ETA %s' %
+               (percent_str, data_len_str, speed_str, eta_str))
+        self._report_progress_status(msg)
+
+    def report_progress_live_stream(self, downloaded_data_len, speed, elapsed):
+        if self.params.get('noprogress', False):
+            return
+        downloaded_str = format_bytes(downloaded_data_len)
+        speed_str = self.format_speed(speed)
+        elapsed_str = FileDownloader.format_seconds(elapsed)
+        msg = u'%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
+        self._report_progress_status(msg)
+
+    def report_finish(self, data_len_str, tot_time):
+        """Report download finished."""
+        if self.params.get('noprogress', False):
+            self.to_screen(u'[download] Download completed')
         else:
-            self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' %
-                (clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
-        self.to_console_title(u'youtube-dl - %s of %s at %s ETA %s' %
-                (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
+            self._report_progress_status(
+                (u'100%% of %s in %s' %
+                 (data_len_str, self.format_seconds(tot_time))),
+                is_last_line=True)
 
     def report_resuming_byte(self, resume_len):
         """Report attempt to resume at given byte."""
@@ -246,16 +277,7 @@ class FileDownloader(object):
         """Report it was impossible to resume download."""
         self.to_screen(u'[download] Unable to resume')
 
-    def report_finish(self, data_len_str, tot_time):
-        """Report download finished."""
-        if self.params.get('noprogress', False):
-            self.to_screen(u'[download] Download completed')
-        else:
-            clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
-            self.to_screen(u'\r%s[download] 100%% of %s in %s' %
-                (clear_line, data_len_str, self.format_seconds(tot_time)))
-
-    def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url, live):
+    def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url, live, conn):
         def run_rtmpdump(args):
             start = time.time()
             resume_percent = None
@@ -301,11 +323,27 @@ class FileDownloader(object):
                         'eta': eta,
                         'speed': speed,
                     })
-                elif self.params.get('verbose', False):
-                    if not cursor_in_new_line:
-                        self.to_screen(u'')
-                    cursor_in_new_line = True
-                    self.to_screen(u'[rtmpdump] '+line)
+                else:
+                    # no percent for live streams
+                    mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
+                    if mobj:
+                        downloaded_data_len = int(float(mobj.group(1))*1024)
+                        time_now = time.time()
+                        speed = self.calc_speed(start, time_now, downloaded_data_len)
+                        self.report_progress_live_stream(downloaded_data_len, speed, time_now - start)
+                        cursor_in_new_line = False
+                        self._hook_progress({
+                            'downloaded_bytes': downloaded_data_len,
+                            'tmpfilename': tmpfilename,
+                            'filename': filename,
+                            'status': 'downloading',
+                            'speed': speed,
+                        })
+                    elif self.params.get('verbose', False):
+                        if not cursor_in_new_line:
+                            self.to_screen(u'')
+                        cursor_in_new_line = True
+                        self.to_screen(u'[rtmpdump] '+line)
             proc.wait()
             if not cursor_in_new_line:
                 self.to_screen(u'')
@@ -338,6 +376,8 @@ class FileDownloader(object):
             basic_args += ['--stop', '1']
         if live:
             basic_args += ['--live']
+        if conn:
+            basic_args += ['--conn', conn]
         args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)]
 
         if sys.platform == 'win32' and sys.version_info < (3, 0):
@@ -479,7 +519,8 @@ class FileDownloader(object):
                                                 info_dict.get('page_url', None),
                                                 info_dict.get('play_path', None),
                                                 info_dict.get('tc_url', None),
-                                                info_dict.get('rtmp_live', False))
+                                                info_dict.get('rtmp_live', False),
+                                                info_dict.get('rtmp_conn', None))
 
         # Attempt to download using mplayer
         if url.startswith('mms') or url.startswith('rtsp'):

youtube_dl/YoutubeDL.py

@@ -3,6 +3,7 @@
 
 from __future__ import absolute_import
 
+import collections
 import errno
 import io
 import json
@@ -22,7 +23,6 @@ if os.name == 'nt':
 from .utils import (
     compat_cookiejar,
     compat_http_client,
-    compat_print,
     compat_str,
     compat_urllib_error,
     compat_urllib_request,
@@ -34,6 +34,8 @@ from .utils import (
     encodeFilename,
     ExtractorError,
     format_bytes,
+    formatSeconds,
+    get_term_width,
     locked_file,
     make_HTTPS_handler,
     MaxDownloadsReached,
@@ -45,6 +47,7 @@ from .utils import (
     subtitles_filename,
     takewhile_inclusive,
     UnavailableVideoError,
+    url_basename,
     write_json_file,
     write_string,
     YoutubeDLHandler,
@@ -93,6 +96,7 @@ class YoutubeDL(object):
     forcethumbnail:    Force printing thumbnail URL.
     forcedescription:  Force printing description.
     forcefilename:     Force printing final filename.
+    forceduration:     Force printing duration.
     forcejson:         Force printing info_dict as JSON.
     simulate:          Do not download the video files.
     format:            Video format code.
@@ -126,12 +130,24 @@ class YoutubeDL(object):
     noplaylist:        Download single video instead of a playlist if in doubt.
     age_limit:         An integer representing the user's age in years.
                        Unsuitable videos for the given age are skipped.
-    download_archive:   File name of a file where all downloads are recorded.
+    min_views:         An integer representing the minimum view count the video
+                       must have in order to not be skipped.
+                       Videos without view count information are always
+                       downloaded. None for no limit.
+    max_views:         An integer representing the maximum view count.
+                       Videos that are more popular than that are not
+                       downloaded.
+                       Videos without view count information are always
+                       downloaded. None for no limit.
+    download_archive:  File name of a file where all downloads are recorded.
                        Videos already present in the file are not downloaded
                        again.
     cookiefile:        File name where cookies should be read from and dumped to.
     nocheckcertificate:Do not verify SSL certificates
     proxy:             URL of the proxy server to use
+    socket_timeout:    Time to wait for unresponsive hosts, in seconds
+    bidi_workaround:   Work around buggy terminals without bidirectional text
+                       support, using fridibi
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:
@@ -146,7 +162,7 @@ class YoutubeDL(object):
     _num_downloads = None
     _screen_file = None
 
-    def __init__(self, params={}):
+    def __init__(self, params=None):
         """Create a FileDownloader object with the given options."""
         self._ies = []
         self._ies_instances = {}
@@ -155,6 +171,36 @@ class YoutubeDL(object):
         self._download_retcode = 0
         self._num_downloads = 0
         self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
+        self._err_file = sys.stderr
+        self.params = {} if params is None else params
+
+        if params.get('bidi_workaround', False):
+            try:
+                import pty
+                master, slave = pty.openpty()
+                width = get_term_width()
+                if width is None:
+                    width_args = []
+                else:
+                    width_args = ['-w', str(width)]
+                sp_kwargs = dict(
+                    stdin=subprocess.PIPE,
+                    stdout=slave,
+                    stderr=self._err_file)
+                try:
+                    self._output_process = subprocess.Popen(
+                        ['bidiv'] + width_args, **sp_kwargs
+                    )
+                except OSError:
+                    print('Falling back to fribidi')
+                    self._output_process = subprocess.Popen(
+                        ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs)
+                self._output_channel = os.fdopen(master, 'rb')
+            except OSError as ose:
+                if ose.errno == 2:
+                    self.report_warning(u'Could not find fribidi executable, ignoring --bidi-workaround . Make sure that  fribidi  is an executable file in one of the directories in your $PATH.')
+                else:
+                    raise
 
         if (sys.version_info >= (3,) and sys.platform != 'win32' and
                 sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
@@ -164,9 +210,8 @@ class YoutubeDL(object):
                 u'Assuming --restrict-filenames since file system encoding '
                 u'cannot encode all charactes. '
                 u'Set the LC_ALL environment variable to fix this.')
-            params['restrictfilenames'] = True
+            self.params['restrictfilenames'] = True
 
-        self.params = params
         self.fd = FileDownloader(self, self.params)
 
         if '%(stitle)s' in self.params.get('outtmpl', ''):
@@ -204,13 +249,33 @@ class YoutubeDL(object):
         self._pps.append(pp)
         pp.set_downloader(self)
 
+    def _bidi_workaround(self, message):
+        if not hasattr(self, '_output_channel'):
+            print('WORKAROUND NOT ENABLED')
+            return message
+
+        assert hasattr(self, '_output_process')
+        assert type(message) == type(u'')
+        line_count = message.count(u'\n') + 1
+        self._output_process.stdin.write((message + u'\n').encode('utf-8'))
+        self._output_process.stdin.flush()
+        res = u''.join(self._output_channel.readline().decode('utf-8')
+                       for _ in range(line_count))
+        return res[:-len(u'\n')]
+
     def to_screen(self, message, skip_eol=False):
+        """Print message to stdout if not in quiet mode."""
+        return self.to_stdout(message, skip_eol, check_quiet=True)
+
+    def to_stdout(self, message, skip_eol=False, check_quiet=False):
         """Print message to stdout if not in quiet mode."""
         if self.params.get('logger'):
             self.params['logger'].debug(message)
-        elif not self.params.get('quiet', False):
+        elif not check_quiet or not self.params.get('quiet', False):
+            message = self._bidi_workaround(message)
             terminator = [u'\n', u''][skip_eol]
             output = message + terminator
+
             write_string(output, self._screen_file)
 
     def to_stderr(self, message):
@@ -219,10 +284,9 @@ class YoutubeDL(object):
         if self.params.get('logger'):
             self.params['logger'].error(message)
         else:
+            message = self._bidi_workaround(message)
             output = message + u'\n'
-            if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
-                output = output.encode(preferredencoding())
-            sys.stderr.write(output)
+            write_string(output, self._err_file)
 
     def to_console_title(self, message):
         if not self.params.get('consoletitle', False):
@@ -293,7 +357,7 @@ class YoutubeDL(object):
         Print the message to stderr, it will be prefixed with 'WARNING:'
         If stderr is a tty file the 'WARNING:' will be colored
         '''
-        if sys.stderr.isatty() and os.name != 'nt':
+        if self._err_file.isatty() and os.name != 'nt':
             _msg_header = u'\033[0;33mWARNING:\033[0m'
         else:
             _msg_header = u'WARNING:'
@@ -305,29 +369,13 @@ class YoutubeDL(object):
         Do the same as trouble, but prefixes the message with 'ERROR:', colored
         in red if stderr is a tty file.
         '''
-        if sys.stderr.isatty() and os.name != 'nt':
+        if self._err_file.isatty() and os.name != 'nt':
             _msg_header = u'\033[0;31mERROR:\033[0m'
         else:
             _msg_header = u'ERROR:'
         error_message = u'%s %s' % (_msg_header, message)
         self.trouble(error_message, tb)
 
-    def report_writedescription(self, descfn):
-        """ Report that the description file is being written """
-        self.to_screen(u'[info] Writing video description to: ' + descfn)
-
-    def report_writesubtitles(self, sub_filename):
-        """ Report that the subtitles file is being written """
-        self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename)
-
-    def report_writeinfojson(self, infofn):
-        """ Report that the metadata file has been written """
-        self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
-
-    def report_writeannotations(self, annofn):
-        """ Report that the annotations file has been written. """
-        self.to_screen(u'[info] Writing video annotations to: ' + annofn)
-
     def report_file_already_downloaded(self, file_name):
         """Report file has already been fully downloaded."""
         try:
@@ -354,18 +402,17 @@ class YoutubeDL(object):
                 template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index']
 
             sanitize = lambda k, v: sanitize_filename(
-                u'NA' if v is None else compat_str(v),
+                compat_str(v),
                 restricted=self.params.get('restrictfilenames'),
                 is_id=(k == u'id'))
             template_dict = dict((k, sanitize(k, v))
-                                 for k, v in template_dict.items())
+                                 for k, v in template_dict.items()
+                                 if v is not None)
+            template_dict = collections.defaultdict(lambda: u'NA', template_dict)
 
             tmpl = os.path.expanduser(self.params['outtmpl'])
             filename = tmpl % template_dict
             return filename
-        except KeyError as err:
-            self.report_error(u'Erroneous output template')
-            return None
         except ValueError as err:
             self.report_error(u'Error in output template: ' + str(err) + u' (encoding: ' + repr(preferredencoding()) + ')')
             return None
@@ -373,13 +420,14 @@ class YoutubeDL(object):
     def _match_entry(self, info_dict):
         """ Returns None iff the file should be downloaded """
 
+        video_title = info_dict.get('title', info_dict.get('id', u'video'))
         if 'title' in info_dict:
             # This can happen when we're just evaluating the playlist
             title = info_dict['title']
             matchtitle = self.params.get('matchtitle', False)
             if matchtitle:
                 if not re.search(matchtitle, title, re.IGNORECASE):
-                    return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+                    return u'"' + title + '" title did not match pattern "' + matchtitle + '"'
             rejecttitle = self.params.get('rejecttitle', False)
             if rejecttitle:
                 if re.search(rejecttitle, title, re.IGNORECASE):
@@ -388,14 +436,21 @@ class YoutubeDL(object):
         if date is not None:
             dateRange = self.params.get('daterange', DateRange())
             if date not in dateRange:
-                return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
+                return u'%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
+        view_count = info_dict.get('view_count', None)
+        if view_count is not None:
+            min_views = self.params.get('min_views')
+            if min_views is not None and view_count < min_views:
+                return u'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views)
+            max_views = self.params.get('max_views')
+            if max_views is not None and view_count > max_views:
+                return u'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
         age_limit = self.params.get('age_limit')
         if age_limit is not None:
             if age_limit < info_dict.get('age_limit', 0):
                 return u'Skipping "' + title + '" because it is age restricted'
         if self.in_download_archive(info_dict):
-            return (u'%s has already been recorded in archive'
-                    % info_dict.get('title', info_dict.get('id', u'video')))
+            return u'%s has already been recorded in archive' % video_title
         return None
 
     @staticmethod
@@ -404,7 +459,8 @@ class YoutubeDL(object):
         for key, value in extra_info.items():
             info_dict.setdefault(key, value)
 
-    def extract_info(self, url, download=True, ie_key=None, extra_info={}):
+    def extract_info(self, url, download=True, ie_key=None, extra_info={},
+                     process=True):
         '''
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
@@ -438,9 +494,13 @@ class YoutubeDL(object):
                     {
                         'extractor': ie.IE_NAME,
                         'webpage_url': url,
+                        'webpage_url_basename': url_basename(url),
                         'extractor_key': ie.ie_key(),
                     })
-                return self.process_ie_result(ie_result, download, extra_info)
+                if process:
+                    return self.process_ie_result(ie_result, download, extra_info)
+                else:
+                    return ie_result
             except ExtractorError as de: # An error we somewhat expected
                 self.report_error(compat_str(de), de.format_traceback())
                 break
@@ -473,8 +533,33 @@ class YoutubeDL(object):
                                      download,
                                      ie_key=ie_result.get('ie_key'),
                                      extra_info=extra_info)
-        elif result_type == 'playlist':
+        elif result_type == 'url_transparent':
+            # Use the information from the embedding page
+            info = self.extract_info(
+                ie_result['url'], ie_key=ie_result.get('ie_key'),
+                extra_info=extra_info, download=False, process=False)
 
+            def make_result(embedded_info):
+                new_result = ie_result.copy()
+                for f in ('_type', 'url', 'ext', 'player_url', 'formats',
+                          'entries', 'urlhandle', 'ie_key', 'duration',
+                          'subtitles', 'annotations', 'format',
+                          'thumbnail', 'thumbnails'):
+                    if f in new_result:
+                        del new_result[f]
+                    if f in embedded_info:
+                        new_result[f] = embedded_info[f]
+                return new_result
+            new_result = make_result(info)
+
+            assert new_result.get('_type') != 'url_transparent'
+            if new_result.get('_type') == 'compat_list':
+                new_result['entries'] = [
+                    make_result(e) for e in new_result['entries']]
+
+            return self.process_ie_result(
+                new_result, download=download, extra_info=extra_info)
+        elif result_type == 'playlist':
             # We process each entry in the playlist
             playlist = ie_result.get('title', None) or ie_result.get('id', None)
             self.to_screen(u'[download] Downloading playlist: %s' % playlist)
@@ -483,16 +568,16 @@ class YoutubeDL(object):
 
             n_all_entries = len(ie_result['entries'])
             playliststart = self.params.get('playliststart', 1) - 1
-            playlistend = self.params.get('playlistend', -1)
-
+            playlistend = self.params.get('playlistend', None)
+            # For backwards compatibility, interpret -1 as whole list
             if playlistend == -1:
-                entries = ie_result['entries'][playliststart:]
-            else:
-                entries = ie_result['entries'][playliststart:playlistend]
+                playlistend = None
 
+            entries = ie_result['entries'][playliststart:playlistend]
             n_entries = len(entries)
 
-            self.to_screen(u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
+            self.to_screen(
+                u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
                 (ie_result['extractor'], playlist, n_all_entries, n_entries))
 
             for i, entry in enumerate(entries, 1):
@@ -502,6 +587,7 @@ class YoutubeDL(object):
                     'playlist_index': i + playliststart,
                     'extractor': ie_result['extractor'],
                     'webpage_url': ie_result['webpage_url'],
+                    'webpage_url_basename': url_basename(ie_result['webpage_url']),
                     'extractor_key': ie_result['extractor_key'],
                 }
 
@@ -522,6 +608,7 @@ class YoutubeDL(object):
                     {
                         'extractor': ie_result['extractor'],
                         'webpage_url': ie_result['webpage_url'],
+                        'webpage_url_basename': url_basename(ie_result['webpage_url']),
                         'extractor_key': ie_result['extractor_key'],
                     })
                 return r
@@ -665,22 +752,25 @@ class YoutubeDL(object):
 
         # Forced printings
         if self.params.get('forcetitle', False):
-            compat_print(info_dict['fulltitle'])
+            self.to_stdout(info_dict['fulltitle'])
         if self.params.get('forceid', False):
-            compat_print(info_dict['id'])
+            self.to_stdout(info_dict['id'])
         if self.params.get('forceurl', False):
             # For RTMP URLs, also include the playpath
-            compat_print(info_dict['url'] + info_dict.get('play_path', u''))
+            self.to_stdout(info_dict['url'] + info_dict.get('play_path', u''))
         if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:
-            compat_print(info_dict['thumbnail'])
+            self.to_stdout(info_dict['thumbnail'])
         if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
-            compat_print(info_dict['description'])
+            self.to_stdout(info_dict['description'])
         if self.params.get('forcefilename', False) and filename is not None:
-            compat_print(filename)
+            self.to_stdout(filename)
+        if self.params.get('forceduration', False) and info_dict.get('duration') is not None:
+            self.to_stdout(formatSeconds(info_dict['duration']))
         if self.params.get('forceformat', False):
-            compat_print(info_dict['format'])
+            self.to_stdout(info_dict['format'])
         if self.params.get('forcejson', False):
-            compat_print(json.dumps(info_dict))
+            info_dict['_filename'] = filename
+            self.to_stdout(json.dumps(info_dict))
 
         # Do nothing else if in simulate mode
         if self.params.get('simulate', False):
@@ -698,28 +788,34 @@ class YoutubeDL(object):
             return
 
         if self.params.get('writedescription', False):
-            try:
-                descfn = filename + u'.description'
-                self.report_writedescription(descfn)
-                with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
-                    descfile.write(info_dict['description'])
-            except (KeyError, TypeError):
-                self.report_warning(u'There\'s no description to write.')
-            except (OSError, IOError):
-                self.report_error(u'Cannot write description file ' + descfn)
-                return
+            descfn = filename + u'.description'
+            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
+                self.to_screen(u'[info] Video description is already present')
+            else:
+                try:
+                    self.to_screen(u'[info] Writing video description to: ' + descfn)
+                    with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
+                        descfile.write(info_dict['description'])
+                except (KeyError, TypeError):
+                    self.report_warning(u'There\'s no description to write.')
+                except (OSError, IOError):
+                    self.report_error(u'Cannot write description file ' + descfn)
+                    return
 
         if self.params.get('writeannotations', False):
-            try:
-                annofn = filename + u'.annotations.xml'
-                self.report_writeannotations(annofn)
-                with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
-                    annofile.write(info_dict['annotations'])
-            except (KeyError, TypeError):
-                self.report_warning(u'There are no annotations to write.')
-            except (OSError, IOError):
-                self.report_error(u'Cannot write annotations file: ' + annofn)
-                return
+            annofn = filename + u'.annotations.xml'
+            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)):
+                self.to_screen(u'[info] Video annotations are already present')
+            else:
+                try:
+                    self.to_screen(u'[info] Writing video annotations to: ' + annofn)
+                    with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
+                        annofile.write(info_dict['annotations'])
+                except (KeyError, TypeError):
+                    self.report_warning(u'There are no annotations to write.')
+                except (OSError, IOError):
+                    self.report_error(u'Cannot write annotations file: ' + annofn)
+                    return
 
         subtitles_are_requested = any([self.params.get('writesubtitles', False),
                                        self.params.get('writeautomaticsub')])
@@ -735,38 +831,48 @@ class YoutubeDL(object):
                     continue
                 try:
                     sub_filename = subtitles_filename(filename, sub_lang, sub_format)
-                    self.report_writesubtitles(sub_filename)
-                    with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
-                            subfile.write(sub)
+                    if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
+                        self.to_screen(u'[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format))
+                    else:
+                        self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename)
+                        with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
+                                subfile.write(sub)
                 except (OSError, IOError):
                     self.report_error(u'Cannot write subtitles file ' + descfn)
                     return
 
         if self.params.get('writeinfojson', False):
             infofn = os.path.splitext(filename)[0] + u'.info.json'
-            self.report_writeinfojson(infofn)
-            try:
-                json_info_dict = dict((k, v) for k, v in info_dict.items() if not k in ['urlhandle'])
-                write_json_file(json_info_dict, encodeFilename(infofn))
-            except (OSError, IOError):
-                self.report_error(u'Cannot write metadata to JSON file ' + infofn)
-                return
+            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
+                self.to_screen(u'[info] Video description metadata is already present')
+            else:
+                self.to_screen(u'[info] Writing video description metadata as JSON to: ' + infofn)
+                try:
+                    json_info_dict = dict((k, v) for k, v in info_dict.items() if not k in ['urlhandle'])
+                    write_json_file(json_info_dict, encodeFilename(infofn))
+                except (OSError, IOError):
+                    self.report_error(u'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'], u'jpg')
-                thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
-                self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
-                               (info_dict['extractor'], info_dict['id']))
-                try:
-                    uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
-                    with open(thumb_filename, 'wb') as thumbf:
-                        shutil.copyfileobj(uf, thumbf)
-                    self.to_screen(u'[%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(u'Unable to download thumbnail "%s": %s' %
-                        (info_dict['thumbnail'], compat_str(err)))
+                thumb_filename = os.path.splitext(filename)[0] + u'.' + thumb_format
+                if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
+                    self.to_screen(u'[%s] %s: Thumbnail is already present' %
+                                   (info_dict['extractor'], info_dict['id']))
+                else:
+                    self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
+                                   (info_dict['extractor'], info_dict['id']))
+                    try:
+                        uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
+                        with open(thumb_filename, 'wb') as thumbf:
+                            shutil.copyfileobj(uf, thumbf)
+                        self.to_screen(u'[%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(u'Unable to download thumbnail "%s": %s' %
+                            (info_dict['thumbnail'], compat_str(err)))
 
         if not self.params.get('skip_download', False):
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
@@ -811,6 +917,20 @@ class YoutubeDL(object):
 
         return self._download_retcode
 
+    def download_with_info_file(self, info_filename):
+        with io.open(info_filename, 'r', encoding='utf-8') as f:
+            info = json.load(f)
+        try:
+            self.process_ie_result(info, download=True)
+        except DownloadError:
+            webpage_url = info.get('webpage_url')
+            if webpage_url is not None:
+                self.report_warning(u'The info failed to download, trying with "%s"' % webpage_url)
+                return self.download([webpage_url])
+            else:
+                raise
+        return self._download_retcode
+
     def post_process(self, filename, ie_info):
         """Run all the postprocessors on the given file."""
         info = dict(ie_info)
@@ -969,7 +1089,10 @@ class YoutubeDL(object):
                 proxy_map.update(handler.proxies)
         write_string(u'[debug] Proxy map: ' + compat_str(proxy_map) + u'\n')
 
-    def _setup_opener(self, timeout=20):
+    def _setup_opener(self):
+        timeout_val = self.params.get('socket_timeout')
+        timeout = 600 if timeout_val is None else float(timeout_val)
+
         opts_cookiefile = self.params.get('cookiefile')
         opts_proxy = self.params.get('proxy')
 

youtube_dl/__init__.py

@@ -36,6 +36,8 @@ __authors__  = (
     'Marcin Cieślak',
     'Anton Larionov',
     'Takuya Tsuchida',
+    'Sergey M.',
+    'Michael Orlitzky',
 )
 
 __license__ = 'Public Domain'
@@ -47,7 +49,6 @@ import os
 import random
 import re
 import shlex
-import subprocess
 import sys
 
 
@@ -55,12 +56,13 @@ from .utils import (
     compat_print,
     DateRange,
     decodeOption,
-    determine_ext,
+    get_term_width,
     DownloadError,
     get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
     SameFileError,
+    setproctitle,
     std_headers,
     write_string,
 )
@@ -80,11 +82,11 @@ from .PostProcessor import (
 
 
 def parseOpts(overrideArguments=None):
-    def _readOptions(filename_bytes):
+    def _readOptions(filename_bytes, default=[]):
         try:
             optionf = open(filename_bytes)
         except IOError:
-            return [] # silently skip if file is not present
+            return default  # silently skip if file is not present
         try:
             res = []
             for l in optionf:
@@ -112,19 +114,6 @@ def parseOpts(overrideArguments=None):
     def _comma_separated_values_options_callback(option, opt_str, value, parser):
         setattr(parser.values, option.dest, value.split(','))
 
-    def _find_term_columns():
-        columns = os.environ.get('COLUMNS', None)
-        if columns:
-            return int(columns)
-
-        try:
-            sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-            out,err = sp.communicate()
-            return int(out.split()[1])
-        except:
-            pass
-        return None
-
     def _hide_login_info(opts):
         opts = list(opts)
         for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
@@ -139,7 +128,7 @@ def parseOpts(overrideArguments=None):
     max_help_position = 80
 
     # No need to wrap help messages if we're on a wide console
-    columns = _find_term_columns()
+    columns = get_term_width()
     if columns: max_width = columns
 
     fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
@@ -190,7 +179,9 @@ def parseOpts(overrideArguments=None):
     general.add_option('--extractor-descriptions',
             action='store_true', dest='list_extractor_descriptions',
             help='Output descriptions of all supported extractors', default=False)
-    general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
+    general.add_option(
+        '--proxy', dest='proxy', default=None, metavar='URL',
+        help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
     general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
     general.add_option(
         '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
@@ -198,12 +189,22 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--no-cache-dir', action='store_const', const=None, dest='cachedir',
         help='Disable filesystem caching')
+    general.add_option(
+        '--socket-timeout', dest='socket_timeout',
+        type=float, default=None, help=optparse.SUPPRESS_HELP)
+    general.add_option(
+        '--bidi-workaround', dest='bidi_workaround', action='store_true',
+        help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
 
 
-    selection.add_option('--playlist-start',
-            dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1)
-    selection.add_option('--playlist-end',
-            dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+    selection.add_option(
+        '--playlist-start',
+        dest='playliststart', metavar='NUMBER', default=1, type=int,
+        help='playlist video to start at (default is %default)')
+    selection.add_option(
+        '--playlist-end',
+        dest='playlistend', metavar='NUMBER', default=None, type=int,
+        help='playlist video to end at (default is last)')
     selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
     selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
     selection.add_option('--max-downloads', metavar='NUMBER',
@@ -214,13 +215,21 @@ def parseOpts(overrideArguments=None):
     selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
     selection.add_option('--datebefore', metavar='DATE', dest='datebefore', help='download only videos uploaded before this date', default=None)
     selection.add_option('--dateafter', metavar='DATE', dest='dateafter', help='download only videos uploaded after this date', default=None)
+    selection.add_option(
+        '--min-views', metavar='COUNT', dest='min_views',
+        default=None, type=int,
+        help="Do not download any videos with less than COUNT views",)
+    selection.add_option(
+        '--max-views', metavar='COUNT', dest='max_views',
+        default=None, type=int,
+        help="Do not download any videos with more than COUNT views",)
     selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False)
     selection.add_option('--age-limit', metavar='YEARS', dest='age_limit',
                          help='download only videos suitable for the given age',
                          default=None, type=int)
     selection.add_option('--download-archive', metavar='FILE',
                          dest='download_archive',
-                         help='Download only videos not present in the archive file. Record all downloaded videos in it.')
+                         help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.')
 
 
     authentication.add_option('-u', '--username',
@@ -235,7 +244,7 @@ def parseOpts(overrideArguments=None):
 
     video_format.add_option('-f', '--format',
             action='store', dest='format', metavar='FORMAT', default='best',
-            help='video format code, specifiy the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
+            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
     video_format.add_option('--all-formats',
             action='store_const', dest='format', help='download all available video formats', const='all')
     video_format.add_option('--prefer-free-formats',
@@ -294,6 +303,9 @@ def parseOpts(overrideArguments=None):
     verbosity.add_option('--get-description',
             action='store_true', dest='getdescription',
             help='simulate, quiet but print video description', default=False)
+    verbosity.add_option('--get-duration',
+            action='store_true', dest='getduration',
+            help='simulate, quiet but print video length', default=False)
     verbosity.add_option('--get-filename',
             action='store_true', dest='getfilename',
             help='simulate, quiet but print output filename', default=False)
@@ -317,7 +329,7 @@ def parseOpts(overrideArguments=None):
             help='print downloaded pages to debug problems(very verbose)')
     verbosity.add_option('--write-pages',
             action='store_true', dest='write_pages', default=False,
-            help='Write downloaded pages to files in the current directory')
+            help='Write downloaded intermediary pages to files in the current directory to debug problems')
     verbosity.add_option('--youtube-print-sig-code',
             action='store_true', dest='youtube_print_sig_code', default=False,
             help=optparse.SUPPRESS_HELP)
@@ -354,6 +366,9 @@ def parseOpts(overrideArguments=None):
             help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
     filesystem.add_option('-a', '--batch-file',
             dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
+    filesystem.add_option('--load-info',
+            dest='load_info_filename', metavar='FILE',
+            help='json file containing the video information (created with the "--write-json" option')
     filesystem.add_option('-w', '--no-overwrites',
             action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
     filesystem.add_option('-c', '--continue',
@@ -415,6 +430,8 @@ def parseOpts(overrideArguments=None):
         if opts.verbose:
             write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
     else:
+        systemConf = _readOptions('/etc/youtube-dl.conf')
+
         xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
         if xdg_config_home:
             userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
@@ -424,8 +441,31 @@ def parseOpts(overrideArguments=None):
             userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
             if not os.path.isfile(userConfFile):
                 userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
-        systemConf = _readOptions('/etc/youtube-dl.conf')
-        userConf = _readOptions(userConfFile)
+        userConf = _readOptions(userConfFile, None)
+
+        if userConf is None:
+            appdata_dir = os.environ.get('appdata')
+            if appdata_dir:
+                userConf = _readOptions(
+                    os.path.join(appdata_dir, 'youtube-dl', 'config'),
+                    default=None)
+                if userConf is None:
+                    userConf = _readOptions(
+                        os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
+                        default=None)
+
+        if userConf is None:
+            userConf = _readOptions(
+                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
+                default=None)
+        if userConf is None:
+            userConf = _readOptions(
+                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
+                default=None)
+
+        if userConf is None:
+            userConf = []
+
         commandLineConf = sys.argv[1:]
         argv = systemConf + userConf + commandLineConf
         opts, args = parser.parse_args(argv)
@@ -436,12 +476,15 @@ def parseOpts(overrideArguments=None):
 
     return parser, opts, args
 
+
 def _real_main(argv=None):
     # Compatibility fixes for Windows
     if sys.platform == 'win32':
         # https://github.com/rg3/youtube-dl/issues/820
         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
 
+    setproctitle(u'youtube-dl')
+
     parser, opts, args = parseOpts(argv)
 
     # Set user agent
@@ -481,7 +524,6 @@ def _real_main(argv=None):
         for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
             compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
-            all_urls = [url for url in all_urls if url not in matchedUrls]
             for mu in matchedUrls:
                 compat_print(u'  ' + mu)
         sys.exit(0)
@@ -536,18 +578,10 @@ def _real_main(argv=None):
         if numeric_buffersize is None:
             parser.error(u'invalid buffer size specified')
         opts.buffersize = numeric_buffersize
-    try:
-        opts.playliststart = int(opts.playliststart)
-        if opts.playliststart <= 0:
-            raise ValueError(u'Playlist start must be positive')
-    except (TypeError, ValueError):
-        parser.error(u'invalid playlist start number specified')
-    try:
-        opts.playlistend = int(opts.playlistend)
-        if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
-            raise ValueError(u'Playlist end must be greater than playlist start')
-    except (TypeError, ValueError):
-        parser.error(u'invalid playlist end number specified')
+    if opts.playliststart <= 0:
+        raise ValueError(u'Playlist start must be positive')
+    if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
+        raise ValueError(u'Playlist end must be greater than playlist start')
     if opts.extractaudio:
         if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
             parser.error(u'invalid audio format specified')
@@ -580,27 +614,30 @@ def _real_main(argv=None):
             or (opts.useid and u'%(id)s.%(ext)s')
             or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
             or u'%(title)s-%(id)s.%(ext)s')
-    if '%(ext)s' not in outtmpl and opts.extractaudio:
+    if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
         parser.error(u'Cannot download a video and extract audio into the same'
-                     u' file! Use "%%(ext)s" instead of %r' %
-                     determine_ext(outtmpl, u''))
+                     u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
+                     u' 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
 
     ydl_opts = {
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
         'videopassword': opts.videopassword,
-        'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.dumpjson),
+        'quiet': (opts.quiet or any_printing),
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
         'forceid': opts.getid,
         'forcethumbnail': opts.getthumbnail,
         'forcedescription': opts.getdescription,
+        'forceduration': opts.getduration,
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,
         'forcejson': opts.dumpjson,
         'simulate': opts.simulate,
-        'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.dumpjson),
+        'skip_download': (opts.skip_download or opts.simulate or any_printing),
         'format': opts.format,
         'format_limit': opts.format_limit,
         'listformats': opts.listformats,
@@ -644,6 +681,8 @@ def _real_main(argv=None):
         'keepvideo': opts.keepvideo,
         'min_filesize': opts.min_filesize,
         'max_filesize': opts.max_filesize,
+        'min_views': opts.min_views,
+        'max_views': opts.max_views,
         'daterange': date,
         'cachedir': opts.cachedir,
         'youtube_print_sig_code': opts.youtube_print_sig_code,
@@ -651,6 +690,9 @@ def _real_main(argv=None):
         'download_archive': opts.download_archive,
         'cookiefile': opts.cookiefile,
         'nocheckcertificate': opts.no_check_certificate,
+        'proxy': opts.proxy,
+        'socket_timeout': opts.socket_timeout,
+        'bidi_workaround': opts.bidi_workaround,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -673,14 +715,17 @@ def _real_main(argv=None):
             update_self(ydl.to_screen, opts.verbose)
 
         # Maybe do nothing
-        if len(all_urls) < 1:
+        if (len(all_urls) < 1) and (opts.load_info_filename is None):
             if not opts.update_self:
                 parser.error(u'you must provide at least one URL')
             else:
                 sys.exit()
 
         try:
-            retcode = ydl.download(all_urls)
+            if opts.load_info_filename is not None:
+                retcode = ydl.download_with_info_file(opts.load_info_filename)
+            else:
+                retcode = ydl.download(all_urls)
         except MaxDownloadsReached:
             ydl.to_screen(u'--max-download limit reached, aborting.')
             retcode = 101

youtube_dl/aes.py

@@ -1,4 +1,4 @@
-__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_decrypt_text']
+__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']
 
 import base64
 from math import ceil
@@ -32,6 +32,31 @@ def aes_ctr_decrypt(data, key, counter):
     
     return decrypted_data
 
+def aes_cbc_decrypt(data, key, iv):
+    """
+    Decrypt with aes in CBC mode
+    
+    @param {int[]} data        cipher
+    @param {int[]} key         16/24/32-Byte cipher key
+    @param {int[]} iv          16-Byte IV
+    @returns {int[]}           decrypted data
+    """
+    expanded_key = key_expansion(key)
+    block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
+    
+    decrypted_data=[]
+    previous_cipher_block = iv
+    for i in range(block_count):
+        block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]
+        block += [0]*(BLOCK_SIZE_BYTES - len(block))
+        
+        decrypted_block = aes_decrypt(block, expanded_key)
+        decrypted_data += xor(decrypted_block, previous_cipher_block)
+        previous_cipher_block = block
+    decrypted_data = decrypted_data[:len(data)]
+    
+    return decrypted_data
+
 def key_expansion(data):
     """
     Generate key schedule
@@ -75,7 +100,7 @@ def aes_encrypt(data, expanded_key):
     @returns {int[]}             16-Byte cipher
     """
     rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
-    
+
     data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
     for i in range(1, rounds+1):
         data = sub_bytes(data)
@@ -83,6 +108,26 @@ def aes_encrypt(data, expanded_key):
         if i != rounds:
             data = mix_columns(data)
         data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
+
+    return data
+
+def aes_decrypt(data, expanded_key):
+    """
+    Decrypt one block with aes
+    
+    @param {int[]} data          16-Byte cipher
+    @param {int[]} expanded_key  176/208/240-Byte expanded key
+    @returns {int[]}             16-Byte state
+    """
+    rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
+    
+    for i in range(rounds, 0, -1):
+        data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
+        if i != rounds:
+            data = mix_columns_inv(data)
+        data = shift_rows_inv(data)
+        data = sub_bytes_inv(data)
+    data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
     
     return data
 
@@ -139,14 +184,69 @@ SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B,
         0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
         0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
         0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16)
-MIX_COLUMN_MATRIX = ((2,3,1,1),
-                     (1,2,3,1),
-                     (1,1,2,3),
-                     (3,1,1,2))
+SBOX_INV = (0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
+            0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
+            0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
+            0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
+            0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
+            0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
+            0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
+            0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
+            0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
+            0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
+            0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
+            0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
+            0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
+            0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
+            0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
+            0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d)
+MIX_COLUMN_MATRIX = ((0x2,0x3,0x1,0x1),
+                     (0x1,0x2,0x3,0x1),
+                     (0x1,0x1,0x2,0x3),
+                     (0x3,0x1,0x1,0x2))
+MIX_COLUMN_MATRIX_INV = ((0xE,0xB,0xD,0x9),
+                         (0x9,0xE,0xB,0xD),
+                         (0xD,0x9,0xE,0xB),
+                         (0xB,0xD,0x9,0xE))
+RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35,
+                      0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA,
+                      0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31,
+                      0x53, 0xF5, 0x04, 0x0C, 0x14, 0x3C, 0x44, 0xCC, 0x4F, 0xD1, 0x68, 0xB8, 0xD3, 0x6E, 0xB2, 0xCD,
+                      0x4C, 0xD4, 0x67, 0xA9, 0xE0, 0x3B, 0x4D, 0xD7, 0x62, 0xA6, 0xF1, 0x08, 0x18, 0x28, 0x78, 0x88,
+                      0x83, 0x9E, 0xB9, 0xD0, 0x6B, 0xBD, 0xDC, 0x7F, 0x81, 0x98, 0xB3, 0xCE, 0x49, 0xDB, 0x76, 0x9A,
+                      0xB5, 0xC4, 0x57, 0xF9, 0x10, 0x30, 0x50, 0xF0, 0x0B, 0x1D, 0x27, 0x69, 0xBB, 0xD6, 0x61, 0xA3,
+                      0xFE, 0x19, 0x2B, 0x7D, 0x87, 0x92, 0xAD, 0xEC, 0x2F, 0x71, 0x93, 0xAE, 0xE9, 0x20, 0x60, 0xA0,
+                      0xFB, 0x16, 0x3A, 0x4E, 0xD2, 0x6D, 0xB7, 0xC2, 0x5D, 0xE7, 0x32, 0x56, 0xFA, 0x15, 0x3F, 0x41,
+                      0xC3, 0x5E, 0xE2, 0x3D, 0x47, 0xC9, 0x40, 0xC0, 0x5B, 0xED, 0x2C, 0x74, 0x9C, 0xBF, 0xDA, 0x75,
+                      0x9F, 0xBA, 0xD5, 0x64, 0xAC, 0xEF, 0x2A, 0x7E, 0x82, 0x9D, 0xBC, 0xDF, 0x7A, 0x8E, 0x89, 0x80,
+                      0x9B, 0xB6, 0xC1, 0x58, 0xE8, 0x23, 0x65, 0xAF, 0xEA, 0x25, 0x6F, 0xB1, 0xC8, 0x43, 0xC5, 0x54,
+                      0xFC, 0x1F, 0x21, 0x63, 0xA5, 0xF4, 0x07, 0x09, 0x1B, 0x2D, 0x77, 0x99, 0xB0, 0xCB, 0x46, 0xCA,
+                      0x45, 0xCF, 0x4A, 0xDE, 0x79, 0x8B, 0x86, 0x91, 0xA8, 0xE3, 0x3E, 0x42, 0xC6, 0x51, 0xF3, 0x0E,
+                      0x12, 0x36, 0x5A, 0xEE, 0x29, 0x7B, 0x8D, 0x8C, 0x8F, 0x8A, 0x85, 0x94, 0xA7, 0xF2, 0x0D, 0x17,
+                      0x39, 0x4B, 0xDD, 0x7C, 0x84, 0x97, 0xA2, 0xFD, 0x1C, 0x24, 0x6C, 0xB4, 0xC7, 0x52, 0xF6, 0x01)
+RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7, 0x1b, 0x68, 0x33, 0xee, 0xdf, 0x03,
+                      0x64, 0x04, 0xe0, 0x0e, 0x34, 0x8d, 0x81, 0xef, 0x4c, 0x71, 0x08, 0xc8, 0xf8, 0x69, 0x1c, 0xc1,
+                      0x7d, 0xc2, 0x1d, 0xb5, 0xf9, 0xb9, 0x27, 0x6a, 0x4d, 0xe4, 0xa6, 0x72, 0x9a, 0xc9, 0x09, 0x78,
+                      0x65, 0x2f, 0x8a, 0x05, 0x21, 0x0f, 0xe1, 0x24, 0x12, 0xf0, 0x82, 0x45, 0x35, 0x93, 0xda, 0x8e,
+                      0x96, 0x8f, 0xdb, 0xbd, 0x36, 0xd0, 0xce, 0x94, 0x13, 0x5c, 0xd2, 0xf1, 0x40, 0x46, 0x83, 0x38,
+                      0x66, 0xdd, 0xfd, 0x30, 0xbf, 0x06, 0x8b, 0x62, 0xb3, 0x25, 0xe2, 0x98, 0x22, 0x88, 0x91, 0x10,
+                      0x7e, 0x6e, 0x48, 0xc3, 0xa3, 0xb6, 0x1e, 0x42, 0x3a, 0x6b, 0x28, 0x54, 0xfa, 0x85, 0x3d, 0xba,
+                      0x2b, 0x79, 0x0a, 0x15, 0x9b, 0x9f, 0x5e, 0xca, 0x4e, 0xd4, 0xac, 0xe5, 0xf3, 0x73, 0xa7, 0x57,
+                      0xaf, 0x58, 0xa8, 0x50, 0xf4, 0xea, 0xd6, 0x74, 0x4f, 0xae, 0xe9, 0xd5, 0xe7, 0xe6, 0xad, 0xe8,
+                      0x2c, 0xd7, 0x75, 0x7a, 0xeb, 0x16, 0x0b, 0xf5, 0x59, 0xcb, 0x5f, 0xb0, 0x9c, 0xa9, 0x51, 0xa0,
+                      0x7f, 0x0c, 0xf6, 0x6f, 0x17, 0xc4, 0x49, 0xec, 0xd8, 0x43, 0x1f, 0x2d, 0xa4, 0x76, 0x7b, 0xb7,
+                      0xcc, 0xbb, 0x3e, 0x5a, 0xfb, 0x60, 0xb1, 0x86, 0x3b, 0x52, 0xa1, 0x6c, 0xaa, 0x55, 0x29, 0x9d,
+                      0x97, 0xb2, 0x87, 0x90, 0x61, 0xbe, 0xdc, 0xfc, 0xbc, 0x95, 0xcf, 0xcd, 0x37, 0x3f, 0x5b, 0xd1,
+                      0x53, 0x39, 0x84, 0x3c, 0x41, 0xa2, 0x6d, 0x47, 0x14, 0x2a, 0x9e, 0x5d, 0x56, 0xf2, 0xd3, 0xab,
+                      0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
+                      0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07)
 
 def sub_bytes(data):
     return [SBOX[x] for x in data]
 
+def sub_bytes_inv(data):
+    return [SBOX_INV[x] for x in data]
+
 def rotate(data):
     return data[1:] + [data[0]]
 
@@ -160,30 +260,31 @@ def key_schedule_core(data, rcon_iteration):
 def xor(data1, data2):
     return [x^y for x, y in zip(data1, data2)]
 
-def mix_column(data):
+def rijndael_mul(a, b):
+    if(a==0 or b==0):
+        return 0
+    return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]
+
+def mix_column(data, matrix):
     data_mixed = []
     for row in range(4):
         mixed = 0
         for column in range(4):
-            addend = data[column]
-            if MIX_COLUMN_MATRIX[row][column] in (2,3):
-                addend <<= 1
-                if addend > 0xff:
-                    addend &= 0xff
-                    addend ^= 0x1b
-                if MIX_COLUMN_MATRIX[row][column] == 3:
-                    addend ^= data[column]
-            mixed ^= addend & 0xff
+            # xor is (+) and (-)
+            mixed ^= rijndael_mul(data[column], matrix[row][column])
         data_mixed.append(mixed)
     return data_mixed
 
-def mix_columns(data):
+def mix_columns(data, matrix=MIX_COLUMN_MATRIX):
     data_mixed = []
     for i in range(4):
         column = data[i*4 : (i+1)*4]
-        data_mixed += mix_column(column)
+        data_mixed += mix_column(column, matrix)
     return data_mixed
 
+def mix_columns_inv(data):
+    return mix_columns(data, MIX_COLUMN_MATRIX_INV)
+
 def shift_rows(data):
     data_shifted = []
     for column in range(4):
@@ -191,6 +292,13 @@ def shift_rows(data):
             data_shifted.append( data[((column + row) & 0b11) * 4 + row] )
     return data_shifted
 
+def shift_rows_inv(data):
+    data_shifted = []
+    for column in range(4):
+        for row in range(4):
+            data_shifted.append( data[((column - row) & 0b11) * 4 + row] )
+    return data_shifted
+
 def inc(data):
     data = data[:] # copy
     for i in range(len(data)-1,-1,-1):

youtube_dl/extractor/__init__.py

@@ -1,6 +1,8 @@
-from .appletrailers import AppleTrailersIE
+from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
 from .anitube import AnitubeIE
+from .aparat import AparatIE
+from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
 from .ard import ARDIE
 from .arte import (
@@ -8,10 +10,12 @@ from .arte import (
     ArteTVPlus7IE,
     ArteTVCreativeIE,
     ArteTVFutureIE,
+    ArteTVDDCIE,
 )
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
+from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
 from .breakcom import BreakIE
@@ -19,13 +23,17 @@ from .brightcove import BrightcoveIE
 from .c56 import C56IE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
+from .cbs import CBSIE
+from .channel9 import Channel9IE
 from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
+from .clipsyndicate import ClipsyndicateIE
 from .cnn import CNNIE
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
 from .criterion import CriterionIE
+from .crunchyroll import CrunchyrollIE
 from .cspan import CSpanIE
 from .d8 import D8IE
 from .dailymotion import (
@@ -55,7 +63,7 @@ from .flickr import FlickrIE
 from .francetv import (
     PluzzIE,
     FranceTvInfoIE,
-    France2IE,
+    FranceTVIE,
     GenerationQuoiIE
 )
 from .freesound import FreesoundIE
@@ -71,10 +79,15 @@ from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .hypem import HypemIE
 from .ign import IGNIE, OneUPIE
+from .imdb import ImdbIE
 from .ina import InaIE
 from .infoq import InfoQIE
 from .instagram import InstagramIE
 from .internetvideoarchive import InternetVideoArchiveIE
+from .ivi import (
+    IviIE,
+    IviCompilationIE
+)
 from .jeuxvideo import JeuxVideoIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
@@ -84,6 +97,7 @@ from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .liveleak import LiveLeakIE
 from .livestream import LivestreamIE, LivestreamOriginalIE
+from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mit import TechTVMITIE, MITIE
@@ -97,16 +111,22 @@ from .myvideo import MyVideoIE
 from .naver import NaverIE
 from .nba import NBAIE
 from .nbc import NBCNewsIE
+from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
+from .ninegag import NineGagIE
 from .nowvideo import NowVideoIE
 from .ooyala import OoyalaIE
 from .orf import ORFIE
 from .pbs import PBSIE
 from .photobucket import PhotobucketIE
+from .podomatic import PodomaticIE
+from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
+from .pyvideo import PyvideoIE
+from .radiofrance import RadioFranceIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
 from .ringtv import RingTVIE
@@ -118,6 +138,12 @@ from .rutube import RutubeIE
 from .sina import SinaIE
 from .slashdot import SlashdotIE
 from .slideshare import SlideshareIE
+from .smotri import (
+    SmotriIE,
+    SmotriCommunityIE,
+    SmotriUserIE,
+    SmotriBroadcastIE,
+)
 from .sohu import SohuIE
 from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
 from .southparkstudios import (
@@ -136,6 +162,7 @@ from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
 from .tf1 import TF1IE
+from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .toutv import TouTvIE
 from .traileraddict import TrailerAddictIE
@@ -156,7 +183,13 @@ from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
 from .videopremium import VideoPremiumIE
-from .vimeo import VimeoIE, VimeoChannelIE
+from .vimeo import (
+    VimeoIE,
+    VimeoChannelIE,
+    VimeoUserIE,
+    VimeoAlbumIE,
+    VimeoGroupsIE,
+)
 from .vine import VineIE
 from .viki import VikiIE
 from .vk import VKIE
@@ -164,12 +197,17 @@ from .wat import WatIE
 from .websurg import WeBSurgIE
 from .weibo import WeiboIE
 from .wimp import WimpIE
+from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .xhamster import XHamsterIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .xtube import XTubeIE
-from .yahoo import YahooIE, YahooSearchIE
+from .yahoo import (
+    YahooIE,
+    YahooNewsIE,
+    YahooSearchIE,
+)
 from .youjizz import YouJizzIE
 from .youku import YoukuIE
 from .youporn import YouPornIE
@@ -187,6 +225,7 @@ from .youtube import (
     YoutubeWatchLaterIE,
     YoutubeFavouritesIE,
     YoutubeHistoryIE,
+    YoutubeTopListIE,
 )
 from .zdf import ZDFIE
 

youtube_dl/extractor/academicearth.py

@@ -0,0 +1,31 @@
+import re
+
+from .common import InfoExtractor
+
+
+class AcademicEarthCourseIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
+    IE_NAME = u'AcademicEarth:Course'
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        playlist_id = m.group('id')
+
+        webpage = self._download_webpage(url, playlist_id)
+        title = self._html_search_regex(
+            r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
+        description = self._html_search_regex(
+            r'<p class="excerpt">(.*?)</p>',
+            webpage, u'description', fatal=False)
+        urls = re.findall(
+            r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
+            webpage)
+        entries = [self.url_result(u) for u in urls]
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': title,
+            'description': description,
+            'entries': entries,
+        }

youtube_dl/extractor/addanime.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class AddAnimeIE(InfoExtractor):
 
-    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
+    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
     IE_NAME = u'AddAnime'
     _TEST = {
         u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',

youtube_dl/extractor/anitube.py

@@ -1,5 +1,4 @@
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 
@@ -28,9 +27,8 @@ class AnitubeIE(InfoExtractor):
         key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)',
                                       webpage, u'key')
 
-        webpage_config = self._download_webpage('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
+        config_xml = self._download_xml('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
                                                 key)
-        config_xml = xml.etree.ElementTree.fromstring(webpage_config.encode('utf-8'))
 
         video_title = config_xml.find('title').text
 

youtube_dl/extractor/aparat.py

@@ -0,0 +1,56 @@
+#coding: utf-8
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    HEADRequest,
+)
+
+
+class AparatIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
+
+    _TEST = {
+        u'url': u'http://www.aparat.com/v/wP8On',
+        u'file': u'wP8On.mp4',
+        u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1',
+        u'info_dict': {
+            u"title": u"تیم گلکسی 11 - زومیت",
+        },
+        #u'skip': u'Extremely unreliable',
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        # Note: There is an easier-to-parse configuration at
+        # http://www.aparat.com/video/video/config/videohash/%video_id
+        # but the URL in there does not work
+        embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' +
+                     video_id + u'/vt/frame')
+        webpage = self._download_webpage(embed_url, video_id)
+
+        video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
+        for i, video_url in enumerate(video_urls):
+            req = HEADRequest(video_url)
+            res = self._request_webpage(
+                req, video_id, note=u'Testing video URL %d' % i, errnote=False)
+            if res:
+                break
+        else:
+            raise ExtractorError(u'No working video URLs found')
+
+        title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title')
+        thumbnail = self._search_regex(
+            r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'ext': 'mp4',
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/appletrailers.py

@@ -1,5 +1,4 @@
 import re
-import xml.etree.ElementTree
 import json
 
 from .common import InfoExtractor
@@ -10,7 +9,7 @@ from ..utils import (
 
 
 class AppleTrailersIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
     _TEST = {
         u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
         u"playlist": [
@@ -65,18 +64,18 @@ class AppleTrailersIE(InfoExtractor):
         uploader_id = mobj.group('company')
 
         playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc')
-        playlist_snippet = self._download_webpage(playlist_url, movie)
-        playlist_cleaned = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', playlist_snippet)
-        playlist_cleaned = re.sub(r'<img ([^<]*?)>', r'<img \1/>', playlist_cleaned)
-        # The ' in the onClick attributes are not escaped, it couldn't be parsed
-        # with xml.etree.ElementTree.fromstring
-        # like: http://trailers.apple.com/trailers/wb/gravity/
-        def _clean_json(m):
-            return u'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
-        playlist_cleaned = re.sub(self._JSON_RE, _clean_json, playlist_cleaned)
-        playlist_html = u'<html>' + playlist_cleaned + u'</html>'
+        def fix_html(s):
+            s = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', s)
+            s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
+            # The ' in the onClick attributes are not escaped, it couldn't be parsed
+            # like: http://trailers.apple.com/trailers/wb/gravity/
+            def _clean_json(m):
+                return u'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
+            s = re.sub(self._JSON_RE, _clean_json, s)
+            s = u'<html>' + s + u'</html>'
+            return s
+        doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
 
-        doc = xml.etree.ElementTree.fromstring(playlist_html)
         playlist = []
         for li in doc.findall('./div/ul/li'):
             on_click = li.find('.//a').attrib['onClick']
@@ -113,7 +112,7 @@ class AppleTrailersIE(InfoExtractor):
                 })
             formats = sorted(formats, key=lambda f: (f['height'], f['width']))
 
-            info = {
+            playlist.append({
                 '_type': 'video',
                 'id': video_id,
                 'title': title,
@@ -124,12 +123,7 @@ class AppleTrailersIE(InfoExtractor):
                 'upload_date': upload_date,
                 'uploader_id': uploader_id,
                 'user_agent': 'QuickTime compatible (youtube-dl)',
-            }
-            # TODO: Remove when #980 has been merged
-            info['url'] = formats[-1]['url']
-            info['ext'] = formats[-1]['ext']
-
-            playlist.append(info)
+            })
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/archiveorg.py

@@ -11,7 +11,7 @@ from ..utils import (
 class ArchiveOrgIE(InfoExtractor):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?archive.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
     _TEST = {
         u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
         u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
@@ -49,7 +49,7 @@ class ArchiveOrgIE(InfoExtractor):
         for f in formats:
             f['ext'] = determine_ext(f['url'])
 
-        info = {
+        return {
             '_type': 'video',
             'id': video_id,
             'title': title,
@@ -57,12 +57,5 @@ class ArchiveOrgIE(InfoExtractor):
             'description': description,
             'uploader': uploader,
             'upload_date': upload_date,
+            'thumbnail': data.get('misc', {}).get('image'),
         }
-        thumbnail = data.get('misc', {}).get('image')
-        if thumbnail:
-            info['thumbnail'] = thumbnail
-
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-
-        return info

youtube_dl/extractor/arte.py

@@ -1,7 +1,6 @@
 # encoding: utf-8
 import re
 import json
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -11,6 +10,7 @@ from ..utils import (
     determine_ext,
     get_element_by_id,
     compat_str,
+    get_element_by_attribute,
 )
 
 # There are different sources of video in arte.tv, the extraction process 
@@ -18,8 +18,8 @@ from ..utils import (
 # add tests.
 
 class ArteTvIE(InfoExtractor):
-    _VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?P<lang>fr|de)/.*-(?P<id>.*?).html'
-    _LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
+    _VIDEOS_URL = r'(?:http://)?videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
+    _LIVEWEB_URL = r'(?:http://)?liveweb\.arte\.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
     _LIVE_URL = r'index-[0-9]+\.html$'
 
     IE_NAME = u'arte.tv'
@@ -78,8 +78,7 @@ class ArteTvIE(InfoExtractor):
         """Extract from videos.arte.tv"""
         ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
         ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
-        ref_xml = self._download_webpage(ref_xml_url, video_id, note=u'Downloading metadata')
-        ref_xml_doc = xml.etree.ElementTree.fromstring(ref_xml)
+        ref_xml_doc = self._download_xml(ref_xml_url, video_id, note=u'Downloading metadata')
         config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
         config_xml_url = config_node.attrib['ref']
         config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')
@@ -109,9 +108,8 @@ class ArteTvIE(InfoExtractor):
         """Extract form http://liveweb.arte.tv/"""
         webpage = self._download_webpage(url, name)
         video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, u'event id')
-        config_xml = self._download_webpage('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
+        config_doc = self._download_xml('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
                                             video_id, u'Downloading information')
-        config_doc = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
         event_doc = config_doc.find('event')
         url_node = event_doc.find('video').find('urlHd')
         if url_node is None:
@@ -145,7 +143,9 @@ class ArteTVPlus7IE(InfoExtractor):
 
     def _extract_from_webpage(self, webpage, video_id, lang):
         json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+        return self._extract_from_json_url(json_url, video_id, lang)
 
+    def _extract_from_json_url(self, json_url, video_id, lang):
         json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
         self.report_extraction(video_id)
         info = json.loads(json_info)
@@ -260,3 +260,21 @@ class ArteTVFutureIE(ArteTVPlus7IE):
         webpage = self._download_webpage(url, anchor_id)
         row = get_element_by_id(anchor_id, webpage)
         return self._extract_from_webpage(row, anchor_id, lang)
+
+
+class ArteTVDDCIE(ArteTVPlus7IE):
+    IE_NAME = u'arte.tv:ddc'
+    _VALID_URL = r'http?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
+
+    def _real_extract(self, url):
+        video_id, lang = self._extract_url_info(url)
+        if lang == 'folge':
+            lang = 'de'
+        elif lang == 'emission':
+            lang = 'fr'
+        webpage = self._download_webpage(url, video_id)
+        scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
+        script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
+        javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
+        json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
+        return self._extract_from_json_url(json_url, video_id, lang)

youtube_dl/extractor/auengine.py

@@ -16,7 +16,7 @@ class AUEngineIE(InfoExtractor):
             u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]"
         }
     }
-    _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
+    _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/bambuser.py

@@ -54,7 +54,7 @@ class BambuserIE(InfoExtractor):
 
 class BambuserChannelIE(InfoExtractor):
     IE_NAME = u'bambuser:channel'
-    _VALID_URL = r'http://bambuser.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
+    _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
     # The maximum number we can get with each request
     _STEP = 50
 

youtube_dl/extractor/blinkx.py

@@ -0,0 +1,90 @@
+import datetime
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    remove_start,
+)
+
+
+class BlinkxIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
+    _IE_NAME = u'blinkx'
+
+    _TEST = {
+        u'url': u'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
+        u'file': u'8aQUy7GV.mp4',
+        u'md5': u'2e9a07364af40163a908edbf10bb2492',
+        u'info_dict': {
+            u"title": u"Police Car Rolls Away",
+            u"uploader": u"stupidvideos.com",
+            u"upload_date": u"20131215",
+            u"description": u"A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!",
+            u"duration": 14.886,
+            u"thumbnails": [{
+                "width": 100,
+                "height": 76,
+                "url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg",
+            }],
+        },
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+        display_id = video_id[:8]
+
+        api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' +
+                   u'video=%s' % video_id)
+        data_json = self._download_webpage(api_url, display_id)
+        data = json.loads(data_json)['api']['results'][0]
+        dt = datetime.datetime.fromtimestamp(data['pubdate_epoch'])
+        upload_date = dt.strftime('%Y%m%d')
+
+        duration = None
+        thumbnails = []
+        formats = []
+        for m in data['media']:
+            if m['type'] == 'jpg':
+                thumbnails.append({
+                    'url': m['link'],
+                    'width': int(m['w']),
+                    'height': int(m['h']),
+                })
+            elif m['type'] == 'original':
+                duration = m['d']
+            elif m['type'] == 'youtube':
+                yt_id = m['link']
+                self.to_screen(u'Youtube video detected: %s' % yt_id)
+                return self.url_result(yt_id, 'Youtube', video_id=yt_id)
+            elif m['type'] in ('flv', 'mp4'):
+                vcodec = remove_start(m['vcodec'], 'ff')
+                acodec = remove_start(m['acodec'], 'ff')
+                format_id = (u'%s-%sk-%s' %
+                             (vcodec,
+                              (int(m['vbr']) + int(m['abr'])) // 1000,
+                              m['w']))
+                formats.append({
+                    'format_id': format_id,
+                    'url': m['link'],
+                    'vcodec': vcodec,
+                    'acodec': acodec,
+                    'abr': int(m['abr']) // 1000,
+                    'vbr': int(m['vbr']) // 1000,
+                    'width': int(m['w']),
+                    'height': int(m['h']),
+                })
+        formats.sort(key=lambda f: (f['width'], f['vbr'], f['abr']))
+
+        return {
+            'id': display_id,
+            'fullid': video_id,
+            'title': data['title'],
+            'formats': formats,
+            'uploader': data['channel_name'],
+            'upload_date': upload_date,
+            'description': data.get('description'),
+            'thumbnails': thumbnails,
+            'duration': duration,
+        }

youtube_dl/extractor/bliptv.py

@@ -51,8 +51,7 @@ class BlipTVIE(InfoExtractor):
             url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id')
         urlp = compat_urllib_parse_urlparse(url)
         if urlp.path.startswith('/play/'):
-            request = compat_urllib_request.Request(url)
-            response = compat_urllib_request.urlopen(request)
+            response = self._request_webpage(url, None, False)
             redirecturl = response.geturl()
             rurlp = compat_urllib_parse_urlparse(redirecturl)
             file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2]
@@ -69,25 +68,23 @@ class BlipTVIE(InfoExtractor):
         request.add_header('User-Agent', 'iTunes/10.6.1')
         self.report_extraction(mobj.group(1))
         info = None
-        try:
-            urlh = compat_urllib_request.urlopen(request)
-            if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
-                basename = url.split('/')[-1]
-                title,ext = os.path.splitext(basename)
-                title = title.decode('UTF-8')
-                ext = ext.replace('.', '')
-                self.report_direct_download(title)
-                info = {
-                    'id': title,
-                    'url': url,
-                    'uploader': None,
-                    'upload_date': None,
-                    'title': title,
-                    'ext': ext,
-                    'urlhandle': urlh
-                }
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
+        urlh = self._request_webpage(request, None, False,
+            u'unable to download video info webpage')
+        if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
+            basename = url.split('/')[-1]
+            title,ext = os.path.splitext(basename)
+            title = title.decode('UTF-8')
+            ext = ext.replace('.', '')
+            self.report_direct_download(title)
+            info = {
+                'id': title,
+                'url': url,
+                'uploader': None,
+                'upload_date': None,
+                'title': title,
+                'ext': ext,
+                'urlhandle': urlh
+            }
         if info is None: # Regular URL
             try:
                 json_code_bytes = urlh.read()

youtube_dl/extractor/bloomberg.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?).html'
+    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
 
     _TEST = {
         u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',

youtube_dl/extractor/brightcove.py

@@ -26,7 +26,7 @@ class BrightcoveIE(InfoExtractor):
             # From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
             u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
             u'file': u'2371591881001.mp4',
-            u'md5': u'8eccab865181d29ec2958f32a6a754f5',
+            u'md5': u'5423e113865d26e40624dce2e4b45d95',
             u'note': u'Test Brightcove downloads and detection in GenericIE',
             u'info_dict': {
                 u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
@@ -55,6 +55,18 @@ class BrightcoveIE(InfoExtractor):
                 u'uploader': u'Mashable',
             },
         },
+        {
+            # test that the default referer works
+            # from http://national.ballet.ca/interact/video/Lost_in_Motion_II/
+            u'url': u'http://link.brightcove.com/services/player/bcpid756015033001?bckey=AQ~~,AAAApYJi_Ck~,GxhXCegT1Dp39ilhXuxMJxasUhVNZiil&bctid=2878862109001',
+            u'info_dict': {
+                u'id': u'2878862109001',
+                u'ext': u'mp4',
+                u'title': u'Lost in Motion II',
+                u'description': u'md5:363109c02998fee92ec02211bd8000df',
+                u'uploader': u'National Ballet of Canada',
+            },
+        },
     ]
 
     @classmethod
@@ -118,17 +130,21 @@ class BrightcoveIE(InfoExtractor):
 
         videoPlayer = query.get('@videoPlayer')
         if videoPlayer:
-            return self._get_video_info(videoPlayer[0], query_str, query)
+            return self._get_video_info(videoPlayer[0], query_str, query,
+                # We set the original url as the default 'Referer' header
+                referer=url)
         else:
             player_key = query['playerKey']
             return self._get_playlist_info(player_key[0])
 
-    def _get_video_info(self, video_id, query_str, query):
+    def _get_video_info(self, video_id, query_str, query, referer=None):
         request_url = self._FEDERATED_URL_TEMPLATE % query_str
         req = compat_urllib_request.Request(request_url)
         linkBase = query.get('linkBaseURL')
         if linkBase is not None:
-            req.add_header('Referer', linkBase[0])
+            referer = linkBase[0]
+        if referer is not None:
+            req.add_header('Referer', referer)
         webpage = self._download_webpage(req, video_id)
 
         self.report_extraction(video_id)

youtube_dl/extractor/canalplus.py

@@ -1,6 +1,5 @@
 # encoding: utf-8
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import unified_strdate
@@ -31,11 +30,10 @@ class CanalplusIE(InfoExtractor):
             webpage = self._download_webpage(url, mobj.group('path'))
             video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
         info_url = self._VIDEO_INFO_TEMPLATE % video_id
-        info_page = self._download_webpage(info_url,video_id, 
+        doc = self._download_xml(info_url,video_id, 
                                            u'Downloading video info')
 
         self.report_extraction(video_id)
-        doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
         video_info = [video for video in doc if video.find('ID').text == video_id][0]
         infos = video_info.find('INFOS')
         media = video_info.find('MEDIA')

youtube_dl/extractor/cbs.py

@@ -0,0 +1,30 @@
+import re
+
+from .common import InfoExtractor
+
+
+class CBSIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/video/(?P<id>[^/]+)/.*'
+
+    _TEST = {
+        u'url': u'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
+        u'file': u'4JUVEwq3wUT7.flv',
+        u'info_dict': {
+            u'title': u'Connect Chat feat. Garth Brooks',
+            u'description': u'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
+            u'duration': 1495,
+        },
+        u'params': {
+            # rtmp download
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        real_id = self._search_regex(
+            r"video\.settings\.pid\s*=\s*'([^']+)';",
+            webpage, u'real video ID')
+        return self.url_result(u'theplatform:%s' % real_id)

youtube_dl/extractor/channel9.py

@@ -0,0 +1,267 @@
+# encoding: utf-8
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+class Channel9IE(InfoExtractor):
+    '''
+    Common extractor for channel9.msdn.com.
+
+    The type of provided URL (video or playlist) is determined according to
+    meta Search.PageType from web page HTML rather than URL itself, as it is
+    not always possible to do.    
+    '''
+    IE_DESC = u'Channel 9'
+    IE_NAME = u'channel9'
+    _VALID_URL = r'^https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
+
+    _TESTS = [
+        {
+            u'url': u'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
+            u'file': u'Events_TechEd_Australia_2013_KOS002.mp4',
+            u'md5': u'bbd75296ba47916b754e73c3a4bbdf10',
+            u'info_dict': {
+                u'title': u'Developer Kick-Off Session: Stuff We Love',
+                u'description': u'md5:c08d72240b7c87fcecafe2692f80e35f',
+                u'duration': 4576,
+                u'thumbnail': u'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
+                u'session_code': u'KOS002',
+                u'session_day': u'Day 1',
+                u'session_room': u'Arena 1A',
+                u'session_speakers': [ u'Ed Blankenship', u'Andrew Coates', u'Brady Gaster', u'Patrick Klug', u'Mads Kristensen' ],
+            },
+        },
+        {
+            u'url': u'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
+            u'file': u'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4',
+            u'md5': u'b43ee4529d111bc37ba7ee4f34813e68',
+            u'info_dict': {
+                u'title': u'Self-service BI with Power BI - nuclear testing',
+                u'description': u'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
+                u'duration': 1540,
+                u'thumbnail': u'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
+                u'authors': [ u'Mike Wilmot' ],
+            },
+        }
+    ]
+
+    _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
+
+    # Sorted by quality
+    _known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4']
+
+    def _restore_bytes(self, formatted_size):
+        if not formatted_size:
+            return 0
+        m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
+        if not m:
+            return 0
+        units = m.group('units')
+        try:
+            exponent = [u'B', u'KB', u'MB', u'GB', u'TB', u'PB', u'EB', u'ZB', u'YB'].index(units.upper())
+        except ValueError:
+            return 0
+        size = float(m.group('size'))
+        return int(size * (1024 ** exponent))
+
+    def _formats_from_html(self, html):
+        FORMAT_REGEX = r'''
+            (?x)
+            <a\s+href="(?P<url>[^"]+)">(?P<quality>[^<]+)</a>\s*
+            <span\s+class="usage">\((?P<note>[^\)]+)\)</span>\s*
+            (?:<div\s+class="popup\s+rounded">\s*
+            <h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
+            </div>)?                                                # File size part may be missing
+        '''
+        # Extract known formats
+        formats = [{'url': x.group('url'),
+                 'format_id': x.group('quality'),
+                 'format_note': x.group('note'),
+                 'format': '%s (%s)' % (x.group('quality'), x.group('note')), 
+                 'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate
+                 } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
+        # Sort according to known formats list
+        formats.sort(key=lambda fmt: self._known_formats.index(fmt['format_id']))
+        return formats
+
+    def _extract_title(self, html):
+        title = self._html_search_meta(u'title', html, u'title')
+        if title is None:           
+            title = self._og_search_title(html)
+            TITLE_SUFFIX = u' (Channel 9)'
+            if title is not None and title.endswith(TITLE_SUFFIX):
+                title = title[:-len(TITLE_SUFFIX)]
+        return title
+
+    def _extract_description(self, html):
+        DESCRIPTION_REGEX = r'''(?sx)
+            <div\s+class="entry-content">\s*
+            <div\s+id="entry-body">\s*
+            (?P<description>.+?)\s*
+            </div>\s*
+            </div>
+        '''
+        m = re.search(DESCRIPTION_REGEX, html)
+        if m is not None:
+            return m.group('description')
+        return self._html_search_meta(u'description', html, u'description')
+
+    def _extract_duration(self, html):
+        m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
+        return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
+
+    def _extract_slides(self, html):
+        m = re.search(r'<a href="(?P<slidesurl>[^"]+)" class="slides">Slides</a>', html)
+        return m.group('slidesurl') if m is not None else None
+
+    def _extract_zip(self, html):
+        m = re.search(r'<a href="(?P<zipurl>[^"]+)" class="zip">Zip</a>', html)
+        return m.group('zipurl') if m is not None else None
+
+    def _extract_avg_rating(self, html):
+        m = re.search(r'<p class="avg-rating">Avg Rating: <span>(?P<avgrating>[^<]+)</span></p>', html)
+        return float(m.group('avgrating')) if m is not None else 0
+
+    def _extract_rating_count(self, html):
+        m = re.search(r'<div class="rating-count">\((?P<ratingcount>[^<]+)\)</div>', html)
+        return int(self._fix_count(m.group('ratingcount'))) if m is not None else 0
+
+    def _extract_view_count(self, html):
+        m = re.search(r'<li class="views">\s*<span class="count">(?P<viewcount>[^<]+)</span> Views\s*</li>', html)
+        return int(self._fix_count(m.group('viewcount'))) if m is not None else 0
+
+    def _extract_comment_count(self, html):
+        m = re.search(r'<li class="comments">\s*<a href="#comments">\s*<span class="count">(?P<commentcount>[^<]+)</span> Comments\s*</a>\s*</li>', html)
+        return int(self._fix_count(m.group('commentcount'))) if m is not None else 0
+
+    def _fix_count(self, count):
+        return int(str(count).replace(',', '')) if count is not None else None
+
+    def _extract_authors(self, html):
+        m = re.search(r'(?s)<li class="author">(.*?)</li>', html)
+        if m is None:
+            return None
+        return re.findall(r'<a href="/Niners/[^"]+">([^<]+)</a>', m.group(1))
+
+    def _extract_session_code(self, html):
+        m = re.search(r'<li class="code">\s*(?P<code>.+?)\s*</li>', html)
+        return m.group('code') if m is not None else None
+
+    def _extract_session_day(self, html):
+        m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
+        return m.group('day') if m is not None else None
+
+    def _extract_session_room(self, html):
+        m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
+        return m.group('room') if m is not None else None
+
+    def _extract_session_speakers(self, html):
+        return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
+
+    def _extract_content(self, html, content_path):
+        # Look for downloadable content        
+        formats = self._formats_from_html(html)
+        slides = self._extract_slides(html)
+        zip_ = self._extract_zip(html)
+
+        # Nothing to download
+        if len(formats) == 0 and slides is None and zip_ is None:
+            self._downloader.report_warning(u'None of recording, slides or zip are available for %s' % content_path)
+            return
+
+        # Extract meta
+        title = self._extract_title(html)
+        description = self._extract_description(html)
+        thumbnail = self._og_search_thumbnail(html)
+        duration = self._extract_duration(html)
+        avg_rating = self._extract_avg_rating(html)
+        rating_count = self._extract_rating_count(html)
+        view_count = self._extract_view_count(html)
+        comment_count = self._extract_comment_count(html)
+
+        common = {'_type': 'video',
+                  'id': content_path,
+                  'description': description,
+                  'thumbnail': thumbnail,
+                  'duration': duration,
+                  'avg_rating': avg_rating,
+                  'rating_count': rating_count,
+                  'view_count': view_count,
+                  'comment_count': comment_count,
+                }
+
+        result = []
+
+        if slides is not None:
+            d = common.copy()
+            d.update({ 'title': title + '-Slides', 'url': slides })
+            result.append(d)
+
+        if zip_ is not None:
+            d = common.copy()
+            d.update({ 'title': title + '-Zip', 'url': zip_ })
+            result.append(d)
+
+        if len(formats) > 0:
+            d = common.copy()
+            d.update({ 'title': title, 'formats': formats })
+            result.append(d)
+
+        return result
+
+    def _extract_entry_item(self, html, content_path):
+        contents = self._extract_content(html, content_path)
+        if contents is None:
+            return contents
+
+        authors = self._extract_authors(html)
+
+        for content in contents:
+            content['authors'] = authors
+
+        return contents
+
+    def _extract_session(self, html, content_path):
+        contents = self._extract_content(html, content_path)
+        if contents is None:
+            return contents
+
+        session_meta = {'session_code': self._extract_session_code(html),
+                        'session_day': self._extract_session_day(html),
+                        'session_room': self._extract_session_room(html),
+                        'session_speakers': self._extract_session_speakers(html),
+                        }
+
+        for content in contents:
+            content.update(session_meta)
+
+        return contents
+
+    def _extract_list(self, content_path):
+        rss = self._download_xml(self._RSS_URL % content_path, content_path, u'Downloading RSS')
+        entries = [self.url_result(session_url.text, 'Channel9')
+                   for session_url in rss.findall('./channel/item/link')]
+        title_text = rss.find('./channel/title').text
+        return self.playlist_result(entries, content_path, title_text)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        content_path = mobj.group('contentpath')
+
+        webpage = self._download_webpage(url, content_path, u'Downloading web page')
+
+        page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage)
+        if page_type_m is None:
+            raise ExtractorError(u'Search.PageType not found, don\'t know how to process this page', expected=True)
+
+        page_type = page_type_m.group('pagetype')
+        if page_type == 'List':         # List page, may contain list of 'item'-like objects
+            return self._extract_list(content_path)
+        elif page_type == 'Entry.Item': # Any 'item'-like page, may contain downloadable content
+            return self._extract_entry_item(webpage, content_path)
+        elif page_type == 'Session':    # Event session page, may contain downloadable content
+            return self._extract_session(webpage, content_path)
+        else:
+            raise ExtractorError(u'Unexpected Search.PageType %s' % page_type, expected=True)

youtube_dl/extractor/cinemassacre.py

@@ -12,21 +12,27 @@ class CinemassacreIE(InfoExtractor):
     _TESTS = [{
         u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
         u'file': u'19911.flv',
-        u'md5': u'f9bb7ede54d1229c9846e197b4737e06',
         u'info_dict': {
             u'upload_date': u'20121110',
             u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
             u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
-        }
+        },
+        u'params': {
+            # rtmp download
+            u'skip_download': True,
+        },
     },
     {
         u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
         u'file': u'521be8ef82b16.flv',
-        u'md5': u'9509ee44dcaa7c1068604817c19a9e50',
         u'info_dict': {
             u'upload_date': u'20131002',
             u'title': u'The Mummy’s Hand (1940)',
-        }
+        },
+        u'params': {
+            # rtmp download
+            u'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/clipfish.py

@@ -3,6 +3,7 @@ import time
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class ClipfishIE(InfoExtractor):
@@ -10,13 +11,14 @@ class ClipfishIE(InfoExtractor):
 
     _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
     _TEST = {
-        u'url': u'http://www.clipfish.de/special/supertalent/video/4028320/supertalent-2013-ivana-opacak-singt-nobodys-perfect/',
-        u'file': u'4028320.f4v',
-        u'md5': u'5e38bda8c329fbfb42be0386a3f5a382',
+        u'url': u'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
+        u'file': u'3966754.mp4',
+        u'md5': u'2521cd644e862936cf2e698206e47385',
         u'info_dict': {
-            u'title': u'Supertalent 2013: Ivana Opacak singt Nobody\'s Perfect',
-            u'duration': 399,
-        }
+            u'title': u'FIFA 14 - E3 2013 Trailer',
+            u'duration': 82,
+        },
+        u'skip': 'Blocked in the US'
     }
 
     def _real_extract(self, url):
@@ -25,11 +27,14 @@ class ClipfishIE(InfoExtractor):
 
         info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
                     (video_id, int(time.time())))
-        info_xml = self._download_webpage(
+        doc = self._download_xml(
             info_url, video_id, note=u'Downloading info page')
-        doc = xml.etree.ElementTree.fromstring(info_xml)
         title = doc.find('title').text
         video_url = doc.find('filename').text
+        if video_url is None:
+            xml_bytes = xml.etree.ElementTree.tostring(doc)
+            raise ExtractorError(u'Cannot find video URL in document %r' %
+                                 xml_bytes)
         thumbnail = doc.find('imageurl').text
         duration_str = doc.find('duration').text
         m = re.match(

youtube_dl/extractor/clipsyndicate.py

@@ -0,0 +1,50 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    find_xpath_attr,
+    fix_xml_all_ampersand,
+)
+
+
+class ClipsyndicateIE(InfoExtractor):
+    _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
+        u'md5': u'4d7d549451bad625e0ff3d7bd56d776c',
+        u'info_dict': {
+            u'id': u'4629301',
+            u'ext': u'mp4',
+            u'title': u'Brick Briscoe',
+            u'duration': 612,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        js_player = self._download_webpage(
+            'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
+            video_id, u'Downlaoding player')
+        # it includes a required token
+        flvars = self._search_regex(r'flvars: "(.*?)"', js_player, u'flvars')
+
+        pdoc = self._download_xml(
+            'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
+            video_id, u'Downloading video info',
+            transform_source=fix_xml_all_ampersand) 
+
+        track_doc = pdoc.find('trackList/track')
+        def find_param(name):
+            node = find_xpath_attr(track_doc, './/param', 'name', name)
+            if node is not None:
+                return node.attrib['value']
+
+        return {
+            'id': video_id,
+            'title': find_param('title'),
+            'url': track_doc.find('location').text,
+            'thumbnail': find_param('thumbnail'),
+            'duration': int(find_param('duration')),
+        }

youtube_dl/extractor/cnn.py

@@ -1,5 +1,4 @@
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import determine_ext
@@ -33,8 +32,7 @@ class CNNIE(InfoExtractor):
         path = mobj.group('path')
         page_title = mobj.group('title')
         info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
-        info_xml = self._download_webpage(info_url, page_title)
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+        info = self._download_xml(info_url, page_title)
 
         formats = []
         for f in info.findall('files/file'):

youtube_dl/extractor/comedycentral.py

@@ -1,8 +1,7 @@
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from .mtv import MTVIE, _media_xml_tag
+from .mtv import MTVServicesInfoExtractor
 from ..utils import (
     compat_str,
     compat_urllib_parse,
@@ -12,8 +11,8 @@ from ..utils import (
 )
 
 
-class ComedyCentralIE(MTVIE):
-    _VALID_URL = r'http://www.comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
+class ComedyCentralIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'https?://(?:www.)?comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
     _FEED_URL = u'http://comedycentral.com/feeds/mrss/'
 
     _TEST = {
@@ -26,12 +25,6 @@ class ComedyCentralIE(MTVIE):
             u'description': u'After a certain point, breastfeeding becomes c**kblocking.',
         },
     }
-    # Overwrite MTVIE properties we don't want
-    _TESTS = []
-
-    def _get_thumbnail_url(self, uri, itemdoc):
-        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
-        return itemdoc.find(search_path).attrib['url']
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -158,13 +151,12 @@ class ComedyCentralShowsIE(InfoExtractor):
 
         uri = mMovieParams[0][1]
         indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
-        indexXml = self._download_webpage(indexUrl, epTitle,
+        idoc = self._download_xml(indexUrl, epTitle,
                                           u'Downloading show index',
                                           u'unable to download episode index')
 
         results = []
 
-        idoc = xml.etree.ElementTree.fromstring(indexXml)
         itemEls = idoc.findall('.//item')
         for partNum,itemEl in enumerate(itemEls):
             mediaId = itemEl.findall('./guid')[0].text
@@ -175,10 +167,9 @@ class ComedyCentralShowsIE(InfoExtractor):
 
             configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
                         compat_urllib_parse.urlencode({'uri': mediaId}))
-            configXml = self._download_webpage(configUrl, epTitle,
+            cdoc = self._download_xml(configUrl, epTitle,
                                                u'Downloading configuration for %s' % shortMediaId)
 
-            cdoc = xml.etree.ElementTree.fromstring(configXml)
             turls = []
             for rendition in cdoc.findall('.//rendition'):
                 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
@@ -200,7 +191,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                 })
 
             effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
-            info = {
+            results.append({
                 'id': shortMediaId,
                 'formats': formats,
                 'uploader': showId,
@@ -208,11 +199,6 @@ class ComedyCentralShowsIE(InfoExtractor):
                 'title': effTitle,
                 'thumbnail': None,
                 'description': compat_str(officialTitle),
-            }
-
-            # TODO: Remove when #980 has been merged
-            info.update(info['formats'][-1])
-
-            results.append(info)
+            })
 
         return results

youtube_dl/extractor/common.py

@@ -18,6 +18,7 @@ from ..utils import (
     sanitize_filename,
     unescapeHTML,
 )
+_NO_DEFAULT = object()
 
 
 class InfoExtractor(object):
@@ -34,15 +35,39 @@ class InfoExtractor(object):
     The dictionaries must include the following fields:
 
     id:             Video identifier.
-    url:            Final video URL.
     title:          Video title, unescaped.
-    ext:            Video filename extension.
 
-    Instead of url and ext, formats can also specified.
+    Additionally, it must contain either a formats entry or url and ext:
+
+    formats:        A list of dictionaries for each format available, it must
+                    be ordered from worst to best quality. Potential fields:
+                    * url        Mandatory. The URL of the video file
+                    * ext        Will be calculated from url if missing
+                    * format     A human-readable description of the format
+                                 ("mp4 container with h264/opus").
+                                 Calculated from the format_id, width, height.
+                                 and format_note fields if missing.
+                    * format_id  A short description of the format
+                                 ("mp4_h264_opus" or "19")
+                    * format_note Additional info about the format
+                                 ("3D" or "DASH video")
+                    * width      Width of the video, if known
+                    * height     Height of the video, if known
+                    * abr        Average audio bitrate in KBit/s
+                    * acodec     Name of the audio codec in use
+                    * vbr        Average video bitrate in KBit/s
+                    * vcodec     Name of the video codec in use
+                    * filesize   The number of bytes, if known in advance
+                    * player_url SWF Player URL (used for rtmpdump).
+    url:            Final video URL.
+    ext:            Video filename extension.
+    format:         The video format, defaults to ext (used for --get-format)
+    player_url:     SWF Player URL (used for rtmpdump).
+    urlhandle:      [internal] The urlHandle to be used to download the file,
+                    like returned by urllib.request.urlopen
 
     The following fields are optional:
 
-    format:         The video format, defaults to ext (used for --get-format)
     thumbnails:     A list of dictionaries (with the entries "resolution" and
                     "url") for the varying thumbnails
     thumbnail:      Full URL to a video thumbnail image.
@@ -51,32 +76,14 @@ class InfoExtractor(object):
     upload_date:    Video upload date (YYYYMMDD).
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
-    player_url:     SWF Player URL (used for rtmpdump).
     subtitles:      The subtitle file contents as a dictionary in the format
                     {language: subtitles}.
+    duration:       Length of the video in seconds, as an integer.
     view_count:     How many users have watched the video on the platform.
-    urlhandle:      [internal] The urlHandle to be used to download the file,
-                    like returned by urllib.request.urlopen
+    like_count:     Number of positive ratings of the video
+    dislike_count:  Number of negative ratings of the video
+    comment_count:  Number of comments on the video
     age_limit:      Age restriction for the video, as an integer (years)
-    formats:        A list of dictionaries for each format available, it must
-                    be ordered from worst to best quality. Potential fields:
-                    * url       Mandatory. The URL of the video file
-                    * ext       Will be calculated from url if missing
-                    * format    A human-readable description of the format
-                                ("mp4 container with h264/opus").
-                                Calculated from the format_id, width, height.
-                                and format_note fields if missing.
-                    * format_id A short description of the format
-                                ("mp4_h264_opus" or "19")
-                    * format_note Additional info about the format
-                                ("3D" or "DASH video")
-                    * width     Width of the video, if known
-                    * height    Height of the video, if known
-                    * abr       Average audio bitrate in KBit/s
-                    * acodec    Name of the audio codec in use
-                    * vbr       Average video bitrate in KBit/s
-                    * vcodec    Name of the video codec in use
-                    * filesize  The number of bytes, if known in advance
     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
                     by YoutubeDL if it's missing)
@@ -151,27 +158,40 @@ class InfoExtractor(object):
     def IE_NAME(self):
         return type(self).__name__[:-2]
 
-    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
+    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns the response handle """
         if note is None:
             self.report_download_webpage(video_id)
         elif note is not False:
-            self.to_screen(u'%s: %s' % (video_id, note))
+            if video_id is None:
+                self.to_screen(u'%s' % (note,))
+            else:
+                self.to_screen(u'%s: %s' % (video_id, note))
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            if errnote is False:
+                return False
             if errnote is None:
                 errnote = u'Unable to download webpage'
-            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
+            errmsg = u'%s: %s' % (errnote, compat_str(err))
+            if fatal:
+                raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
+            else:
+                self._downloader.report_warning(errmsg)
+                return False
 
-    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
+    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns a tuple (page content as string, URL handle) """
 
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
 
-        urlh = self._request_webpage(url_or_request, video_id, note, errnote)
+        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal)
+        if urlh is False:
+            assert not fatal
+            return False
         content_type = urlh.headers.get('Content-Type', '')
         webpage_bytes = urlh.read()
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
@@ -206,13 +226,22 @@ class InfoExtractor(object):
         content = webpage_bytes.decode(encoding, 'replace')
         return (content, urlh)
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns the data of the page as a string """
-        return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
+        res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+        if res is False:
+            return res
+        else:
+            content, _ = res
+            return content
 
-    def _download_xml(self, url_or_request, video_id, note=u'Downloading XML', errnote=u'Unable to downloand XML'):
+    def _download_xml(self, url_or_request, video_id,
+                      note=u'Downloading XML', errnote=u'Unable to download XML',
+                      transform_source=None):
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        if transform_source:
+            xml_string = transform_source(xml_string)
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
 
     def to_screen(self, msg):
@@ -236,7 +265,8 @@ class InfoExtractor(object):
         self.to_screen(u'Logging in')
 
     #Methods for following #608
-    def url_result(self, url, ie=None, video_id=None):
+    @staticmethod
+    def url_result(url, ie=None, video_id=None):
         """Returns a url that points to a page that should be processed"""
         #TODO: ie should be the class used for getting the info
         video_info = {'_type': 'url',
@@ -245,7 +275,8 @@ class InfoExtractor(object):
         if video_id is not None:
             video_info['id'] = video_id
         return video_info
-    def playlist_result(self, entries, playlist_id=None, playlist_title=None):
+    @staticmethod
+    def playlist_result(entries, playlist_id=None, playlist_title=None):
         """Returns a playlist"""
         video_info = {'_type': 'playlist',
                       'entries': entries}
@@ -255,7 +286,7 @@ class InfoExtractor(object):
             video_info['title'] = playlist_title
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -269,7 +300,7 @@ class InfoExtractor(object):
                 mobj = re.search(p, string, flags)
                 if mobj: break
 
-        if sys.stderr.isatty() and os.name != 'nt':
+        if os.name != 'nt' and sys.stderr.isatty():
             _name = u'\033[0;34m%s\033[0m' % name
         else:
             _name = name
@@ -277,7 +308,7 @@ class InfoExtractor(object):
         if mobj:
             # return the first matching group
             return next(g for g in mobj.groups() if g is not None)
-        elif default is not None:
+        elif default is not _NO_DEFAULT:
             return default
         elif fatal:
             raise RegexNotFoundError(u'Unable to extract %s' % _name)
@@ -286,7 +317,7 @@ class InfoExtractor(object):
                 u'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
@@ -363,7 +394,8 @@ class InfoExtractor(object):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
-            r'''(?ix)<meta(?=[^>]+(?:name|property)=["\']%s["\'])
+            r'''(?ix)<meta
+                    (?=[^>]+(?:itemprop|name|property)=["\']%s["\'])
                     [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
             html, display_name, fatal=False)
 

youtube_dl/extractor/crunchyroll.py

@@ -0,0 +1,171 @@
+# encoding: utf-8
+import re, base64, zlib
+from hashlib import sha1
+from math import pow, sqrt, floor
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_parse,
+    compat_urllib_request,
+    bytes_to_intlist,
+    intlist_to_bytes,
+    unified_strdate,
+    clean_html,
+)
+from ..aes import (
+    aes_cbc_decrypt,
+    inc,
+)
+
+class CrunchyrollIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://)?(?:www\.)?(?P<url>crunchyroll\.com/[^/]*/[^/?&]*?(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _TESTS = [{
+        u'url': u'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
+        u'file': u'645513.flv',
+        #u'md5': u'b1639fd6ddfaa43788c85f6d1dddd412',
+        u'info_dict': {
+            u'title': u'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
+            u'description': u'md5:2d17137920c64f2f49981a7797d275ef',
+            u'thumbnail': u'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
+            u'uploader': u'Yomiuri Telecasting Corporation (YTV)',
+            u'upload_date': u'20131013',
+        },
+        u'params': {
+            # rtmp
+            u'skip_download': True,
+        },
+    }]
+
+    _FORMAT_IDS = {
+        u'360': (u'60', u'106'),
+        u'480': (u'61', u'106'),
+        u'720': (u'62', u'106'),
+        u'1080': (u'80', u'108'),
+    }
+
+    def _decrypt_subtitles(self, data, iv, id):
+        data = bytes_to_intlist(data)
+        iv = bytes_to_intlist(iv)
+        id = int(id)
+
+        def obfuscate_key_aux(count, modulo, start):
+            output = list(start)
+            for _ in range(count):
+                output.append(output[-1] + output[-2])
+            # cut off start values
+            output = output[2:]
+            output = list(map(lambda x: x % modulo + 33, output))
+            return output
+
+        def obfuscate_key(key):
+            num1 = int(floor(pow(2, 25) * sqrt(6.9)))
+            num2 = (num1 ^ key) << 5
+            num3 = key ^ num1
+            num4 = num3 ^ (num3 >> 3) ^ num2
+            prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
+            shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode(u'ascii')).digest())
+            # Extend 160 Bit hash to 256 Bit
+            return shaHash + [0] * 12
+        
+        key = obfuscate_key(id)
+        class Counter:
+            __value = iv
+            def next_value(self):
+                temp = self.__value
+                self.__value = inc(self.__value)
+                return temp
+        decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
+        return zlib.decompress(decrypted_data)
+
+    def _convert_subtitles_to_srt(self, subtitles):
+        i=1
+        output = u''
+        for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
+            start = start.replace(u'.', u',')
+            end = end.replace(u'.', u',')
+            text = clean_html(text)
+            text = text.replace(u'\\N', u'\n')
+            if not text:
+                continue
+            output += u'%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
+            i+=1
+        return output
+
+    def _real_extract(self,url):
+        mobj = re.match(self._VALID_URL, url)
+
+        webpage_url = u'http://www.' + mobj.group('url')
+        video_id = mobj.group(u'video_id')
+        webpage = self._download_webpage(webpage_url, video_id)
+        note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, u'trailer-notice', default=u'')
+        if note_m:
+            raise ExtractorError(note_m)
+
+        video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, u'video_title', flags=re.DOTALL)
+        video_title = re.sub(r' {2,}', u' ', video_title)
+        video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, u'video_description', default=u'')
+        if not video_description:
+            video_description = None
+        video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, u'video_upload_date', fatal=False, flags=re.DOTALL)
+        if video_upload_date:
+            video_upload_date = unified_strdate(video_upload_date)
+        video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, u'video_uploader', fatal=False, flags=re.DOTALL)
+
+        playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, u'playerdata_url'))
+        playerdata_req = compat_urllib_request.Request(playerdata_url)
+        playerdata_req.data = compat_urllib_parse.urlencode({u'current_page': webpage_url})
+        playerdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded')
+        playerdata = self._download_webpage(playerdata_req, video_id, note=u'Downloading media info')
+        
+        stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, u'stream_id')
+        video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, u'thumbnail', fatal=False)
+
+        formats = []
+        for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
+            stream_quality, stream_format = self._FORMAT_IDS[fmt]
+            video_format = fmt+u'p'
+            streamdata_req = compat_urllib_request.Request(u'http://www.crunchyroll.com/xml/')
+            # urlencode doesn't work!
+            streamdata_req.data = u'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+u'&media%5Fid='+stream_id+u'&video%5Fformat='+stream_format
+            streamdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded')
+            streamdata_req.add_header(u'Content-Length', str(len(streamdata_req.data)))
+            streamdata = self._download_webpage(streamdata_req, video_id, note=u'Downloading media info for '+video_format)
+            video_url = self._search_regex(r'<host>([^<]+)', streamdata, u'video_url')
+            video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, u'video_play_path')
+            formats.append({
+                u'url': video_url,
+                u'play_path':   video_play_path,
+                u'ext': 'flv',
+                u'format': video_format,
+                u'format_id': video_format,
+            })
+
+        subtitles = {}
+        for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
+            sub_page = self._download_webpage(u'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
+                                              video_id, note=u'Downloading subtitles for '+sub_name)
+            id = self._search_regex(r'id=\'([0-9]+)', sub_page, u'subtitle_id', fatal=False)
+            iv = self._search_regex(r'<iv>([^<]+)', sub_page, u'subtitle_iv', fatal=False)
+            data = self._search_regex(r'<data>([^<]+)', sub_page, u'subtitle_data', fatal=False)
+            if not id or not iv or not data:
+                continue
+            id = int(id)
+            iv = base64.b64decode(iv)
+            data = base64.b64decode(data)
+
+            subtitle = self._decrypt_subtitles(data, iv, id).decode(u'utf-8')
+            lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, u'subtitle_lang_code', fatal=False)
+            if not lang_code:
+                continue
+            subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+
+        return {
+            u'id':          video_id,
+            u'title':       video_title,
+            u'description': video_description,
+            u'thumbnail':   video_thumbnail,
+            u'uploader':    video_uploader,
+            u'upload_date': video_upload_date,
+            u'subtitles':   subtitles,
+            u'formats':     formats,
+        }

youtube_dl/extractor/cspan.py

@@ -6,7 +6,7 @@ from ..utils import (
 )
 
 class CSpanIE(InfoExtractor):
-    _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
+    _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
     _TEST = {
         u'url': u'http://www.c-spanvideo.org/program/HolderonV',
         u'file': u'315139.flv',

youtube_dl/extractor/dailymotion.py

@@ -11,6 +11,7 @@ from ..utils import (
     get_element_by_attribute,
     get_element_by_id,
     orderedSet,
+    str_to_int,
 
     ExtractorError,
 )
@@ -27,7 +28,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
 class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
     """Information Extractor for Dailymotion"""
 
-    _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
+    _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
     IE_NAME = u'dailymotion'
 
     _FORMATS = [
@@ -80,7 +81,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
         # Extract id and simplified title from URL
         mobj = re.match(self._VALID_URL, url)
 
-        video_id = mobj.group(1).split('_')[0].split('?')[0]
+        video_id = mobj.group('id')
 
         url = 'http://www.dailymotion.com/video/%s' % video_id
 
@@ -100,10 +101,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             self.to_screen(u'Vevo video detected: %s' % vevo_id)
             return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
 
-        video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
-                                             # Looking for official user
-                                             r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
-                                            webpage, 'video uploader', fatal=False)
         age_limit = self._rta_search(webpage)
 
         video_upload_date = None
@@ -146,15 +143,21 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             self._list_available_subtitles(video_id, webpage)
             return
 
+        view_count = self._search_regex(
+            r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False)
+        if view_count is not None:
+            view_count = str_to_int(view_count)
+
         return {
             'id':       video_id,
             'formats': formats,
-            'uploader': video_uploader,
+            'uploader': info['owner_screenname'],
             'upload_date':  video_upload_date,
             'title':    self._og_search_title(webpage),
             'subtitles':    video_subtitles,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
+            'view_count': view_count,
         }
 
     def _get_available_subtitles(self, video_id, webpage):

youtube_dl/extractor/daum.py

@@ -1,6 +1,5 @@
 # encoding: utf-8
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -10,7 +9,7 @@ from ..utils import (
 
 
 class DaumIE(InfoExtractor):
-    _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
     IE_NAME = u'daum.net'
 
     _TEST = {
@@ -29,17 +28,16 @@ class DaumIE(InfoExtractor):
         video_id = mobj.group(1)
         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)
-        full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
+        full_id = self._search_regex(
+            r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
             webpage, u'full id')
         query = compat_urllib_parse.urlencode({'vid': full_id})
-        info_xml = self._download_webpage(
+        info = self._download_xml(
             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
             u'Downloading video info')
-        urls_xml = self._download_webpage(
+        urls = self._download_xml(
             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
             video_id, u'Downloading video formats info')
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
-        urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
 
         self.to_screen(u'%s: Getting video urls' % video_id)
         formats = []
@@ -49,10 +47,9 @@ class DaumIE(InfoExtractor):
                 'vid': full_id,
                 'profile': profile,
             })
-            url_xml = self._download_webpage(
+            url_doc = self._download_xml(
                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
                 video_id, note=False)
-            url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8'))
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,
@@ -60,7 +57,7 @@ class DaumIE(InfoExtractor):
                 'format_id': profile,
             })
 
-        info = {
+        return {
             'id': video_id,
             'title': info.find('TITLE').text,
             'formats': formats,
@@ -69,6 +66,3 @@ class DaumIE(InfoExtractor):
             'duration': int(info.find('DURATION').text),
             'upload_date': info.find('REGDTTM').text[:8],
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info

youtube_dl/extractor/dreisat.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -12,7 +11,7 @@ from ..utils import (
 
 class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
-    _VALID_URL = r'(?:http://)?(?:www\.)?3sat.de/mediathek/index.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+    _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/index\.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TEST = {
         u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
         u'file': u'36983.webm',
@@ -30,8 +29,7 @@ class DreiSatIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
-        details_xml = self._download_webpage(details_url, video_id, note=u'Downloading video details')
-        details_doc = xml.etree.ElementTree.fromstring(details_xml.encode('utf-8'))
+        details_doc = self._download_xml(details_url, video_id, note=u'Downloading video details')
 
         thumbnail_els = details_doc.findall('.//teaserimage')
         thumbnails = [{
@@ -67,7 +65,7 @@ class DreiSatIE(InfoExtractor):
             return (qidx, prefer_http, format['video_bitrate'])
         formats.sort(key=_sortkey)
 
-        info = {
+        return {
             '_type': 'video',
             'id': video_id,
             'title': video_title,
@@ -78,8 +76,3 @@ class DreiSatIE(InfoExtractor):
             'uploader': video_uploader,
             'upload_date': upload_date,
         }
-
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-
-        return info

youtube_dl/extractor/ebaumsworld.py

@@ -1,5 +1,4 @@
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import determine_ext
@@ -21,9 +20,8 @@ class EbaumsWorldIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        config_xml = self._download_webpage(
+        config = self._download_xml(
             'http://www.ebaumsworld.com/video/player/%s' % video_id, video_id)
-        config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
         video_url = config.find('file').text
 
         return {

youtube_dl/extractor/eighttracks.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 class EightTracksIE(InfoExtractor):
     IE_NAME = '8tracks'
-    _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
+    _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
     _TEST = {
         u"name": u"EightTracks",
         u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a",

youtube_dl/extractor/exfm.py

@@ -8,7 +8,7 @@ class ExfmIE(InfoExtractor):
     IE_NAME = u'exfm'
     IE_DESC = u'ex.fm'
     _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
-    _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
+    _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
     _TESTS = [
         {
             u'url': u'http://ex.fm/song/eh359',

youtube_dl/extractor/facebook.py

@@ -17,7 +17,7 @@ from ..utils import (
 class FacebookIE(InfoExtractor):
     """Information Extractor for Facebook"""
 
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:[^#?]*#!/)?(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
@@ -27,7 +27,7 @@ class FacebookIE(InfoExtractor):
         u'file': u'120708114770723.mp4',
         u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
         u'info_dict': {
-            u"duration": 279, 
+            u"duration": 279,
             u"title": u"PEOPLE ARE AWESOME 2013"
         }
     }

youtube_dl/extractor/faz.py

@@ -1,6 +1,5 @@
 # encoding: utf-8
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -10,7 +9,7 @@ from ..utils import (
 
 class FazIE(InfoExtractor):
     IE_NAME = u'faz.net'
-    _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+).html'
+    _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
 
     _TEST = {
         u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
@@ -28,9 +27,8 @@ class FazIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
             u'config xml url')
-        config_xml = self._download_webpage(config_xml_url, video_id,
+        config = self._download_xml(config_xml_url, video_id,
             u'Downloading config xml')
-        config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
 
         encodings = config.find('ENCODINGS')
         formats = []
@@ -46,13 +44,10 @@ class FazIE(InfoExtractor):
             })
 
         descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
-        info = {
+        return {
             'id': video_id,
             'title': self._og_search_title(webpage),
             'formats': formats,
             'description': descr,
             'thumbnail': config.find('STILL/STILL_BIG').text,
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info

youtube_dl/extractor/fktv.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class FKTVIE(InfoExtractor):
     IE_NAME = u'fernsehkritik.tv'
-    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
+    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
 
     _TEST = {
         u'url': u'http://fernsehkritik.tv/folge-1',
@@ -52,7 +52,7 @@ class FKTVIE(InfoExtractor):
 
 class FKTVPosteckeIE(InfoExtractor):
     IE_NAME = u'fernsehkritik.tv:postecke'
-    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/inline-video/postecke.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
+    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
     _TEST = {
         u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
         u'file': u'0120.flv',

youtube_dl/extractor/francetv.py

@@ -1,6 +1,5 @@
 # encoding: utf-8
 import re
-import xml.etree.ElementTree
 import json
 
 from .common import InfoExtractor
@@ -11,11 +10,10 @@ from ..utils import (
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
     def _extract_video(self, video_id):
-        xml_desc = self._download_webpage(
+        info = self._download_xml(
             'http://www.francetvinfo.fr/appftv/webservices/video/'
             'getInfosOeuvre.php?id-diffusion='
             + video_id, video_id, 'Downloading XML config')
-        info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))
 
         manifest_url = info.find('videos/video/url').text
         video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
@@ -23,7 +21,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
         thumbnail_path = info.find('image').text
 
         return {'id': video_id,
-                'ext': 'mp4',
+                'ext': 'flv' if video_url.startswith('rtmp') else 'mp4',
                 'url': video_url,
                 'title': info.find('titre').text,
                 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
@@ -47,7 +45,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
     IE_NAME = u'francetvinfo.fr'
-    _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
+    _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html'
 
     _TEST = {
         u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
@@ -68,35 +66,101 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
         return self._extract_video(video_id)
 
 
-class France2IE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'france2.fr'
-    _VALID_URL = r'''(?x)https?://www\.france2\.fr/
+class FranceTVIE(FranceTVBaseInfoExtractor):
+    IE_NAME = u'francetv'
+    IE_DESC = u'France 2, 3, 4, 5 and Ô'
+    _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
         (?:
-            emissions/.*?/videos/(?P<id>\d+)
-        |   emission/(?P<key>[^/?]+)
+            emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
+        |   (emissions?|jt)/(?P<key>[^/?]+)
         )'''
 
-    _TEST = {
-        u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
-        u'file': u'75540104.mp4',
-        u'info_dict': {
-            u'title': u'13h15, le samedi...',
-            u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+    _TESTS = [
+        # france2
+        {
+            u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
+            u'file': u'75540104.mp4',
+            u'info_dict': {
+                u'title': u'13h15, le samedi...',
+                u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+            },
+            u'params': {
+                # m3u8 download
+                u'skip_download': True,
+            },
         },
-        u'params': {
-            u'skip_download': True,
+        # france3
+        {
+            u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
+            u'info_dict': {
+                u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
+                u'ext': u'flv',
+                u'title': u'Le scandale du prix des médicaments',
+                u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce',
+            },
+            u'params': {
+                # rtmp download
+                u'skip_download': True,
+            },
         },
-    }
+        # france4
+        {
+            u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+            u'info_dict': {
+                u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+                u'ext': u'flv',
+                u'title': u'Hero Corp Making of - Extrait 1',
+                u'description': u'md5:c87d54871b1790679aec1197e73d650a',
+            },
+            u'params': {
+                # rtmp download
+                u'skip_download': True,
+            },
+        },
+        # france5
+        {
+            u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+            u'info_dict': {
+                u'id': u'92837968',
+                u'ext': u'mp4',
+                u'title': u'C à dire ?!',
+                u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
+            },
+            u'params': {
+                # m3u8 download
+                u'skip_download': True,
+            },
+        },
+        # franceo
+        {
+            u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+            u'info_dict': {
+                u'id': u'92327925',
+                u'ext': u'mp4',
+                u'title': u'Infô-Afrique',
+                u'description': u'md5:ebf346da789428841bee0fd2a935ea55',
+            },
+            u'params': {
+                # m3u8 download
+                u'skip_download': True,
+            },
+            u'skip': u'The id changes frequently',
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj.group('key'):
             webpage = self._download_webpage(url, mobj.group('key'))
-            video_id = self._html_search_regex(
-                r'''(?x)<div\s+class="video-player">\s*
+            id_res = [
+                (r'''(?x)<div\s+class="video-player">\s*
                     <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
-                    class="francetv-video-player">''',
-                webpage, u'video ID')
+                    class="francetv-video-player">'''),
+                (r'<a id="player_direct" href="http://info\.francetelevisions'
+                 '\.fr/\?id-video=([^"/&]+)'),
+                (r'<a class="video" id="ftv_player_(.+?)"'),
+            ]
+            video_id = self._html_search_regex(id_res, webpage, u'video ID')
         else:
             video_id = mobj.group('id')
         return self._extract_video(video_id)

youtube_dl/extractor/gamekings.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class GamekingsIE(InfoExtractor):
-    _VALID_URL = r'http?://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
+    _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
     _TEST = {
         u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/",
         u'file': u'20130811.mp4',

youtube_dl/extractor/gamespot.py

@@ -47,13 +47,10 @@ class GameSpotIE(InfoExtractor):
                 'format_id': q,
             })
 
-        info = {
+        return {
             'id': data_video['guid'],
             'title': compat_urllib_parse.unquote(data_video['title']),
             'formats': formats,
             'description': get_meta_content('description', webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info

youtube_dl/extractor/gametrailers.py

@@ -1,13 +1,10 @@
 import re
 
-from .mtv import MTVIE, _media_xml_tag
+from .mtv import MTVServicesInfoExtractor
 
-class GametrailersIE(MTVIE):
-    """
-    Gametrailers use the same videos system as MTVIE, it just changes the feed
-    url, where the uri is and the method to get the thumbnails.
-    """
-    _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
+
+class GametrailersIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
     _TEST = {
         u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
         u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',
@@ -17,15 +14,9 @@ class GametrailersIE(MTVIE):
             u'description': u'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
         },
     }
-    # Overwrite MTVIE properties we don't want
-    _TESTS = []
 
     _FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
 
-    def _get_thumbnail_url(self, uri, itemdoc):
-        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
-        return itemdoc.find(search_path).attrib['url']
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')

youtube_dl/extractor/generic.py

@@ -11,10 +11,14 @@ from ..utils import (
     compat_urlparse,
 
     ExtractorError,
+    HEADRequest,
     smuggle_url,
     unescapeHTML,
+    unified_strdate,
+    url_basename,
 )
 from .brightcove import BrightcoveIE
+from .ooyala import OoyalaIE
 
 
 class GenericIE(InfoExtractor):
@@ -71,6 +75,27 @@ class GenericIE(InfoExtractor):
                 u'skip_download': True,
             },
         },
+        # Direct link to a video
+        {
+            u'url': u'http://media.w3.org/2010/05/sintel/trailer.mp4',
+            u'file': u'trailer.mp4',
+            u'md5': u'67d406c2bcb6af27fa886f31aa934bbe',
+            u'info_dict': {
+                u'id': u'trailer',
+                u'title': u'trailer',
+                u'upload_date': u'20100513',
+            }
+        },
+        # ooyala video
+        {
+            u'url': u'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
+            u'md5': u'5644c6ca5d5782c1d0d350dad9bd840c',
+            u'info_dict': {
+                u'id': u'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
+                u'ext': u'mp4',
+                u'title': u'2cc213299525360.mov', #that's what we get
+            },
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -83,23 +108,20 @@ class GenericIE(InfoExtractor):
         """Report information extraction."""
         self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
 
-    def _test_redirect(self, url):
+    def _send_head(self, url):
         """Check if it is a redirect, like url shorteners, in case return the new url."""
-        class HeadRequest(compat_urllib_request.Request):
-            def get_method(self):
-                return "HEAD"
 
         class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
             """
             Subclass the HTTPRedirectHandler to make it use our
-            HeadRequest also on the redirected URL
+            HEADRequest also on the redirected URL
             """
             def redirect_request(self, req, fp, code, msg, headers, newurl):
                 if code in (301, 302, 303, 307):
                     newurl = newurl.replace(' ', '%20')
                     newheaders = dict((k,v) for k,v in req.headers.items()
                                       if k.lower() not in ("content-length", "content-type"))
-                    return HeadRequest(newurl,
+                    return HEADRequest(newurl,
                                        headers=newheaders,
                                        origin_req_host=req.get_origin_req_host(),
                                        unverifiable=True)
@@ -128,32 +150,49 @@ class GenericIE(InfoExtractor):
                         compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
             opener.add_handler(handler())
 
-        response = opener.open(HeadRequest(url))
+        response = opener.open(HEADRequest(url))
         if response is None:
             raise ExtractorError(u'Invalid URL protocol')
-        new_url = response.geturl()
-
-        if url == new_url:
-            return False
-
-        self.report_following_redirect(new_url)
-        return new_url
+        return response
 
     def _real_extract(self, url):
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
             self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
             return self.url_result('http://' + url)
+        video_id = os.path.splitext(url.split('/')[-1])[0]
 
         try:
-            new_url = self._test_redirect(url)
-            if new_url:
-                return [self.url_result(new_url)]
+            response = self._send_head(url)
+
+            # Check for redirect
+            new_url = response.geturl()
+            if url != new_url:
+                self.report_following_redirect(new_url)
+                return self.url_result(new_url)
+
+            # Check for direct link to a video
+            content_type = response.headers.get('Content-Type', '')
+            m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
+            if m:
+                upload_date = response.headers.get('Last-Modified')
+                if upload_date:
+                    upload_date = unified_strdate(upload_date)
+                return {
+                    'id': video_id,
+                    'title': os.path.splitext(url_basename(url))[0],
+                    'formats': [{
+                        'format_id': m.group('format_id'),
+                        'url': url,
+                        'vcodec': u'none' if m.group('type') == 'audio' else None
+                    }],
+                    'upload_date': upload_date,
+                }
+
         except compat_urllib_error.HTTPError:
             # This may be a stupid server that doesn't like HEAD, our UA, or so
             pass
 
-        video_id = url.split('/')[-1]
         try:
             webpage = self._download_webpage(url, video_id)
         except ValueError:
@@ -169,8 +208,13 @@ class GenericIE(InfoExtractor):
         #   Site Name | Video Title
         #   Video Title - Tagline | Site Name
         # and so on and so forth; it's just not practical
-        video_title = self._html_search_regex(r'<title>(.*)</title>',
-            webpage, u'video title', default=u'video', flags=re.DOTALL)
+        video_title = self._html_search_regex(
+            r'(?s)<title>(.*?)</title>', webpage, u'video title',
+            default=u'video')
+
+        # video uploader is domain name
+        video_uploader = self._search_regex(
+            r'^(?:https?://)?([^/]*)/.*', url, u'video uploader')
 
         # Look for BrightCove:
         bc_url = BrightcoveIE._extract_brightcove_url(webpage)
@@ -178,7 +222,7 @@ class GenericIE(InfoExtractor):
             self.to_screen(u'Brightcove video detected.')
             return self.url_result(bc_url, 'Brightcove')
 
-        # Look for embedded Vimeo player
+        # Look for embedded (iframe) Vimeo player
         mobj = re.search(
             r'<iframe[^>]+?src="(https?://player.vimeo.com/video/.+?)"', webpage)
         if mobj:
@@ -186,15 +230,58 @@ class GenericIE(InfoExtractor):
             surl = smuggle_url(player_url, {'Referer': url})
             return self.url_result(surl, 'Vimeo')
 
+        # Look for embedded (swf embed) Vimeo player
+        mobj = re.search(
+            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo.com/moogaloop.swf.+?)"', webpage)
+        if mobj:
+            return self.url_result(mobj.group(1), 'Vimeo')
+
         # Look for embedded YouTube player
-        matches = re.findall(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube.com/embed/.+?)\1', webpage)
+        matches = re.findall(r'''(?x)
+            (?:<iframe[^>]+?src=|embedSWF\(\s*)
+            (["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+                (?:embed|v)/.+?)
+            \1''', webpage)
         if matches:
             urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
                      for tuppl in matches]
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
 
+        # Look for embedded Dailymotion player
+        matches = re.findall(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
+        if matches:
+            urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Dailymotion')
+                     for tuppl in matches]
+            return self.playlist_result(
+                urlrs, playlist_id=video_id, playlist_title=video_title)
+
+        # Look for embedded Wistia player
+        match = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
+        if match:
+            return {
+                '_type': 'url_transparent',
+                'url': unescapeHTML(match.group('url')),
+                'ie_key': 'Wistia',
+                'uploader': video_uploader,
+                'title': video_title,
+                'id': video_id,
+            }
+
+        # Look for embedded blip.tv player
+        mobj = re.search(r'<meta\s[^>]*https?://api.blip.tv/\w+/redirect/\w+/(\d+)', webpage)
+        if mobj:
+            return self.url_result('http://blip.tv/seo/-'+mobj.group(1), 'BlipTV')
+        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*https?://(?:\w+\.)?blip.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', webpage)
+        if mobj:
+            player_url = 'http://blip.tv/play/%s.x?p=1' % mobj.group(1)
+            player_page = self._download_webpage(player_url, mobj.group(1))
+            blip_video_id = self._search_regex(r'data-episode-id="(\d+)', player_page, u'blip_video_id', fatal=False)
+            if blip_video_id:
+                return self.url_result('http://blip.tv/seo/-'+blip_video_id, 'BlipTV')
+
         # Look for Bandcamp pages with custom domain
         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
         if mobj is not None:
@@ -202,6 +289,22 @@ class GenericIE(InfoExtractor):
             # Don't set the extractor because it can be a track url or an album
             return self.url_result(burl)
 
+        # Look for embedded Vevo player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\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)=([^"&]+)', webpage)
+        if mobj is not None:
+            return OoyalaIE._build_url_result(mobj.group(1))
+
+        # Look for Aparat videos
+        mobj = re.search(r'<iframe src="(http://www.aparat.com/video/[^"]+)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group(1), 'Aparat')
+
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None:
@@ -238,14 +341,9 @@ class GenericIE(InfoExtractor):
         # here's a fun little line of code for you:
         video_id = os.path.splitext(video_id)[0]
 
-        # video uploader is domain name
-        video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',
-            url, u'video uploader')
-
         return {
             'id':       video_id,
             'url':      video_url,
             'uploader': video_uploader,
-            'upload_date':  None,
             'title':    video_title,
         }

youtube_dl/extractor/hotnewhiphop.py

@@ -11,7 +11,7 @@ class HotNewHipHopIE(InfoExtractor):
         u'file': u'1435540.mp3',
         u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
         u'info_dict': {
-            u"title": u"Freddie Gibbs - Lay It Down"
+            u"title": u'Freddie Gibbs "Lay It Down"'
         }
     }
 

youtube_dl/extractor/ign.py

@@ -44,7 +44,7 @@ class IGNIE(InfoExtractor):
                 {
                     u'file': u'638672ee848ae4ff108df2a296418ee2.mp4',
                     u'info_dict': {
-                        u'title': u'GTA 5\'s Twisted Beauty in Super Slow Motion',
+                        u'title': u'26 Twisted Moments from GTA 5 in Slow Motion',
                         u'description': u'The twisted beauty of GTA 5 in stunning slow motion.',
                     },
                 },
@@ -103,7 +103,7 @@ class IGNIE(InfoExtractor):
 class OneUPIE(IGNIE):
     """Extractor for 1up.com, it uses the ign videos system."""
 
-    _VALID_URL = r'https?://gamevideos.1up.com/(?P<type>video)/id/(?P<name_or_id>.+)'
+    _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)'
     IE_NAME = '1up.com'
 
     _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'

youtube_dl/extractor/imdb.py

@@ -0,0 +1,57 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    get_element_by_attribute,
+)
+
+
+class ImdbIE(InfoExtractor):
+    IE_NAME = u'imdb'
+    IE_DESC = u'Internet Movie Database trailers'
+    _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.imdb.com/video/imdb/vi2524815897',
+        u'md5': u'9f34fa777ade3a6e57a054fdbcb3a068',
+        u'info_dict': {
+            u'id': u'2524815897',
+            u'ext': u'mp4',
+            u'title': u'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
+            u'description': u'md5:9061c2219254e5d14e03c25c98e96a81',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
+        descr = get_element_by_attribute('itemprop', 'description', webpage)
+        available_formats = re.findall(
+            r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
+            flags=re.MULTILINE)
+        formats = []
+        for f_id, f_path in available_formats:
+            f_path = f_path.strip()
+            format_page = self._download_webpage(
+                compat_urlparse.urljoin(url, f_path),
+                u'Downloading info for %s format' % f_id)
+            json_data = self._search_regex(
+                r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
+                format_page, u'json data', flags=re.DOTALL)
+            info = json.loads(json_data)
+            format_info = info['videoPlayerObject']['video']
+            formats.append({
+                'format_id': f_id,
+                'url': format_info['url'],
+            })
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'formats': formats,
+            'description': descr,
+            'thumbnail': format_info['slate'],
+        }

youtube_dl/extractor/instagram.py

@@ -3,7 +3,7 @@ import re
 from .common import InfoExtractor
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?instagram.com/p/(.*?)/'
+    _VALID_URL = r'(?:http://)?instagram\.com/p/(.*?)/'
     _TEST = {
         u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
         u'file': u'aye83DjauH.mp4',

youtube_dl/extractor/internetvideoarchive.py

@@ -1,5 +1,4 @@
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -43,9 +42,8 @@ class InternetVideoArchiveIE(InfoExtractor):
         video_id = query_dic['publishedid'][0]
         url = self._build_url(query)
 
-        flashconfiguration_xml = self._download_webpage(url, video_id,
+        flashconfiguration = self._download_xml(url, video_id,
             u'Downloading flash configuration')
-        flashconfiguration = xml.etree.ElementTree.fromstring(flashconfiguration_xml.encode('utf-8'))
         file_url = flashconfiguration.find('file').text
         file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx')
         # Replace some of the parameters in the query to get the best quality
@@ -53,9 +51,8 @@ class InternetVideoArchiveIE(InfoExtractor):
         file_url = re.sub(r'(?<=\?)(.+)$',
             lambda m: self._clean_query(m.group()),
             file_url)
-        info_xml = self._download_webpage(file_url, video_id,
+        info = self._download_xml(file_url, video_id,
             u'Downloading video info')
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
         item = info.find('channel/item')
 
         def _bp(p):

youtube_dl/extractor/ivi.py

@@ -0,0 +1,154 @@
+# encoding: utf-8
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    ExtractorError,
+)
+
+
+class IviIE(InfoExtractor):
+    IE_DESC = u'ivi.ru'
+    IE_NAME = u'ivi'
+    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
+
+    _TESTS = [
+        # Single movie
+        {
+            u'url': u'http://www.ivi.ru/watch/53141',
+            u'file': u'53141.mp4',
+            u'md5': u'6ff5be2254e796ed346251d117196cf4',
+            u'info_dict': {
+                u'title': u'Иван Васильевич меняет профессию',
+                u'description': u'md5:14d8eda24e9d93d29b5857012c6d6346',
+                u'duration': 5498,
+                u'thumbnail': u'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg',
+            },
+            u'skip': u'Only works from Russia',
+        },
+        # Serial's serie
+        {
+            u'url': u'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
+            u'file': u'74791.mp4',
+            u'md5': u'3e6cc9a848c1d2ebcc6476444967baa9',
+            u'info_dict': {
+                u'title': u'Дежурный ангел - 1 серия',
+                u'duration': 2490,
+                u'thumbnail': u'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
+            },
+            u'skip': u'Only works from Russia',
+         }
+    ]
+    
+    # Sorted by quality
+    _known_formats = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
+
+    # Sorted by size
+    _known_thumbnails = ['Thumb-120x90', 'Thumb-160', 'Thumb-640x480']
+
+    def _extract_description(self, html):
+        m = re.search(r'<meta name="description" content="(?P<description>[^"]+)"/>', html)
+        return m.group('description') if m is not None else None
+
+    def _extract_comment_count(self, html):
+        m = re.search(u'(?s)<a href="#" id="view-comments" class="action-button dim gradient">\s*Комментарии:\s*(?P<commentcount>\d+)\s*</a>', html)
+        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')
+
+        api_url = 'http://api.digitalaccess.ru/api/json/'
+
+        data = {u'method': u'da.content.get',
+                u'params': [video_id, {u'site': u's183',
+                                       u'referrer': u'http://www.ivi.ru/watch/%s' % video_id,
+                                       u'contentid': video_id
+                                    }
+                            ]
+                }
+
+        request = compat_urllib_request.Request(api_url, json.dumps(data))
+
+        video_json_page = self._download_webpage(request, video_id, u'Downloading video JSON')
+        video_json = json.loads(video_json_page)
+
+        if u'error' in video_json:
+            error = video_json[u'error']
+            if error[u'origin'] == u'NoRedisValidData':
+                raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+            raise ExtractorError(u'Unable to download video %s: %s' % (video_id, error[u'message']), expected=True)
+
+        result = video_json[u'result']
+
+        formats = [{'url': x[u'url'],
+                    'format_id': x[u'content_format']
+                    } for x in result[u'files'] if x[u'content_format'] in self._known_formats]
+        formats.sort(key=lambda fmt: self._known_formats.index(fmt['format_id']))
+
+        if len(formats) == 0:
+            self._downloader.report_warning(u'No media links available for %s' % video_id)
+            return
+
+        duration = result[u'duration']
+        compilation = result[u'compilation']
+        title = result[u'title']
+
+        title = '%s - %s' % (compilation, title) if compilation is not None else title  
+
+        previews = result[u'preview']
+        previews.sort(key=lambda fmt: self._known_thumbnails.index(fmt['content_format']))
+        thumbnail = previews[-1][u'url'] if len(previews) > 0 else None
+
+        video_page = self._download_webpage(url, video_id, u'Downloading video page')
+        description = self._extract_description(video_page)
+        comment_count = self._extract_comment_count(video_page)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+            'comment_count': comment_count,
+            'formats': formats,
+        }
+
+
+class IviCompilationIE(InfoExtractor):
+    IE_DESC = u'ivi.ru compilations'
+    IE_NAME = u'ivi:compilation'
+    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
+
+    def _extract_entries(self, html, compilation_id):
+        return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')
+                for serie in re.findall(r'<strong><a href="/watch/%s/(\d+)">(?:[^<]+)</a></strong>' % compilation_id, html)]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        compilation_id = mobj.group('compilationid')
+        season_id = mobj.group('seasonid')
+
+        if season_id is not None: # Season link
+            season_page = self._download_webpage(url, compilation_id, u'Downloading season %s web page' % season_id)
+            playlist_id = '%s/season%s' % (compilation_id, season_id)
+            playlist_title = self._html_search_meta(u'title', season_page, u'title')
+            entries = self._extract_entries(season_page, compilation_id)
+        else: # Compilation link            
+            compilation_page = self._download_webpage(url, compilation_id, u'Downloading compilation web page')
+            playlist_id = compilation_id
+            playlist_title = self._html_search_meta(u'title', compilation_page, u'title')
+            seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page)
+            if len(seasons) == 0: # No seasons in this compilation
+                entries = self._extract_entries(compilation_page, compilation_id)
+            else:
+                entries = []
+                for season_id in seasons:
+                    season_page = self._download_webpage('http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
+                                                         compilation_id, u'Downloading season %s web page' % season_id)
+                    entries.extend(self._extract_entries(season_page, compilation_id))
+
+        return self.playlist_result(entries, playlist_id, playlist_title)

youtube_dl/extractor/jeuxvideo.py

@@ -2,7 +2,6 @@
 
 import json
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 
@@ -32,12 +31,9 @@ class JeuxVideoIE(InfoExtractor):
             r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
             xml_link, u'video ID')
 
-        xml_config = self._download_webpage(
+        config = self._download_xml(
             xml_link, title, u'Downloading XML config')
-        config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
-        info_json = self._search_regex(
-            r'(?sm)<format\.json>(.*?)</format\.json>',
-            xml_config, u'JSON information')
+        info_json = config.find('format.json').text
         info = json.loads(info_json)['versions'][0]
         
         video_url = 'http://video720.jeuxvideo.com/' + info['file']

youtube_dl/extractor/jukebox.py

@@ -8,7 +8,7 @@ from ..utils import (
 )
 
 class JukeboxIE(InfoExtractor):
-    _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+).html'
+    _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+)\.html'
     _IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
     _VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
     _TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'

youtube_dl/extractor/justintv.py

@@ -1,7 +1,6 @@
 import json
 import os
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -94,10 +93,9 @@ class JustinTVIE(InfoExtractor):
             archive_id = m.group(1)
 
             api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
-            chapter_info_xml = self._download_webpage(api, chapter_id,
+            doc = self._download_xml(api, chapter_id,
                                              note=u'Downloading chapter information',
                                              errnote=u'Chapter information download failed')
-            doc = xml.etree.ElementTree.fromstring(chapter_info_xml)
             for a in doc.findall('.//archive'):
                 if archive_id == a.find('./id').text:
                     break

youtube_dl/extractor/liveleak.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 class LiveLeakIE(InfoExtractor):
 
-    _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+    _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
     IE_NAME = u'liveleak'
     _TEST = {
         u'url': u'http://www.liveleak.com/view?i=757_1364311680',

youtube_dl/extractor/livestream.py

@@ -1,6 +1,5 @@
 import re
 import json
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -12,7 +11,7 @@ from ..utils import (
 
 class LivestreamIE(InfoExtractor):
     IE_NAME = u'livestream'
-    _VALID_URL = r'http://new.livestream.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
+    _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
     _TEST = {
         u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         u'file': u'4719370.mp4',
@@ -80,8 +79,7 @@ class LivestreamOriginalIE(InfoExtractor):
         user = mobj.group('user')
         api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
 
-        api_response = self._download_webpage(api_url, video_id)
-        info = xml.etree.ElementTree.fromstring(api_response.encode('utf-8'))
+        info = self._download_xml(api_url, video_id)
         item = info.find('channel').find('item')
         ns = {'media': 'http://search.yahoo.com/mrss'}
         thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']

youtube_dl/extractor/mdr.py

@@ -0,0 +1,63 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class MDRIE(InfoExtractor):
+    _VALID_URL = r'^(?P<domain>(?:https?://)?(?:www\.)?mdr\.de)/mediathek/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)_.*'
+    
+    # No tests, MDR regularily deletes its videos
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('video_id')
+        domain = m.group('domain')
+
+        # determine title and media streams from webpage
+        html = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<h2>(.*?)</h2>', html, u'title')
+        xmlurl = self._search_regex(
+            r'(/mediathek/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, u'XML URL')
+
+        doc = self._download_xml(domain + xmlurl, video_id)
+        formats = []
+        for a in doc.findall('./assets/asset'):
+            url_el = a.find('.//progressiveDownloadUrl')
+            if url_el is None:
+                continue
+            abr = int(a.find('bitrateAudio').text) // 1000
+            media_type = a.find('mediaType').text
+            format = {
+                'abr': abr,
+                'filesize': int(a.find('fileSize').text),
+                'url': url_el.text,
+            }
+
+            vbr_el = a.find('bitrateVideo')
+            if vbr_el is None:
+                format.update({
+                    'vcodec': 'none',
+                    'format_id': u'%s-%d' % (media_type, abr),
+                })
+            else:
+                vbr = int(vbr_el.text) // 1000
+                format.update({
+                    'vbr': vbr,
+                    'width': int(a.find('frameWidth').text),
+                    'height': int(a.find('frameHeight').text),
+                    'format_id': u'%s-%d' % (media_type, vbr),
+                })
+            formats.append(format)
+        formats.sort(key=lambda f: (f.get('vbr'), f['abr']))
+        if not formats:
+            raise ExtractorError(u'Could not find any valid formats')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }

youtube_dl/extractor/metacafe.py

@@ -1,14 +1,10 @@
 import re
-import socket
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
     compat_parse_qs,
-    compat_urllib_error,
     compat_urllib_parse,
     compat_urllib_request,
-    compat_str,
     determine_ext,
     ExtractorError,
 )
@@ -69,6 +65,21 @@ class MetacafeIE(InfoExtractor):
             u'age_limit': 18,
         },
     },
+    # cbs video
+    {
+        u'url': u'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/',
+        u'info_dict': {
+            u'id': u'0rOxMBabDXN6',
+            u'ext': u'flv',
+            u'title': u'Samsung Galaxy Note 2: Samsung\'s next-generation phablet',
+            u'description': u'md5:54d49fac53d26d5a0aaeccd061ada09d',
+            u'duration': 129,
+        },
+        u'params': {
+            # rtmp download
+            u'skip_download': True,
+        },
+    },
     ]
 
 
@@ -78,12 +89,8 @@ class MetacafeIE(InfoExtractor):
 
     def _real_initialize(self):
         # Retrieve disclaimer
-        request = compat_urllib_request.Request(self._DISCLAIMER)
-        try:
-            self.report_disclaimer()
-            compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
+        self.report_disclaimer()
+        self._download_webpage(self._DISCLAIMER, None, False, u'Unable to retrieve disclaimer')
 
         # Confirm age
         disclaimer_form = {
@@ -92,11 +99,8 @@ class MetacafeIE(InfoExtractor):
             }
         request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        try:
-            self.report_age_confirmation()
-            compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
+        self.report_age_confirmation()
+        self._download_webpage(request, None, False, u'Unable to confirm age')
 
     def _real_extract(self, url):
         # Extract id and simplified title from URL
@@ -106,10 +110,16 @@ class MetacafeIE(InfoExtractor):
 
         video_id = mobj.group(1)
 
-        # Check if video comes from YouTube
-        mobj2 = re.match(r'^yt-(.*)$', video_id)
-        if mobj2 is not None:
-            return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
+        # the video may come from an external site
+        m_external = re.match('^(\w{2})-(.*)$', video_id)
+        if m_external is not None:
+            prefix, ext_id = m_external.groups()
+            # Check if video comes from YouTube
+            if prefix == 'yt':
+                return self.url_result('http://www.youtube.com/watch?v=%s' % ext_id, 'Youtube')
+            # CBS videos use theplatform.com
+            if prefix == 'cb':
+                return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 
         # Retrieve video webpage to extract further information
         req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)

youtube_dl/extractor/metacritic.py

@@ -1,8 +1,10 @@
 import re
-import xml.etree.ElementTree
 import operator
 
 from .common import InfoExtractor
+from ..utils import (
+    fix_xml_all_ampersand,
+)
 
 
 class MetacriticIE(InfoExtractor):
@@ -23,9 +25,8 @@ class MetacriticIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         # The xml is not well formatted, there are raw '&'
-        info_xml = self._download_webpage('http://www.metacritic.com/video_data?video=' + video_id,
-            video_id, u'Downloading info xml').replace('&', '&')
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+        info = self._download_xml('http://www.metacritic.com/video_data?video=' + video_id,
+            video_id, u'Downloading info xml', transform_source=fix_xml_all_ampersand)
 
         clip = next(c for c in info.findall('playList/clip') if c.find('id').text == video_id)
         formats = []
@@ -43,13 +44,10 @@ class MetacriticIE(InfoExtractor):
         description = self._html_search_regex(r'<b>Description:</b>(.*?)</p>',
             webpage, u'description', flags=re.DOTALL)
 
-        info = {
+        return {
             'id': video_id,
             'title': clip.find('title').text,
             'formats': formats,
             'description': description,
             'duration': int(clip.find('duration').text),
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info

youtube_dl/extractor/mixcloud.py

@@ -1,13 +1,10 @@
 import json
 import re
-import socket
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_urllib_error,
-    compat_urllib_request,
     unified_strdate,
+    ExtractorError,
 )
 
 
@@ -31,13 +28,18 @@ class MixcloudIE(InfoExtractor):
         """Returns 1st active url from list"""
         for url in url_list:
             try:
-                compat_urllib_request.urlopen(url)
+                # We only want to know if the request succeed
+                # don't download the whole file
+                self._request_webpage(url, None, False)
                 return url
-            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error):
+            except ExtractorError:
                 url = None
 
         return None
 
+    def _get_url(self, template_url):
+        return self.check_urls(template_url % i for i in range(30))
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
@@ -53,13 +55,18 @@ class MixcloudIE(InfoExtractor):
         preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
         song_url = preview_url.replace('/previews/', '/cloudcasts/originals/')
         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
-        final_song_url = self.check_urls(template_url % i for i in range(30))
+        final_song_url = self._get_url(template_url)
+        if final_song_url is None:
+            self.to_screen('Trying with m4a extension')
+            template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
+            final_song_url = self._get_url(template_url)
+        if final_song_url is None:
+            raise ExtractorError(u'Unable to extract track url')
 
         return {
             'id': track_id,
             'title': info['name'],
             'url': final_song_url,
-            'ext': 'mp3',
             'description': info.get('description'),
             'thumbnail': info['pictures'].get('extra_large'),
             'uploader': info['user']['name'],

youtube_dl/extractor/mtv.py

@@ -10,35 +10,8 @@ from ..utils import (
 def _media_xml_tag(tag):
     return '{http://search.yahoo.com/mrss/}%s' % tag
 
-class MTVIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$'
-
-    _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
-
-    _TESTS = [
-        {
-            u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
-            u'file': u'853555.mp4',
-            u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8',
-            u'info_dict': {
-                u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"',
-                u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
-            },
-        },
-        {
-            u'add_ie': ['Vevo'],
-            u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
-            u'file': u'USCJY1331283.mp4',
-            u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
-            u'info_dict': {
-                u'title': u'Everything Has Changed',
-                u'upload_date': u'20130606',
-                u'uploader': u'Taylor Swift',
-            },
-            u'skip': u'VEVO is only available in some countries',
-        },
-    ]
 
+class MTVServicesInfoExtractor(InfoExtractor):
     @staticmethod
     def _id_from_uri(uri):
         return uri.split(':')[-1]
@@ -53,7 +26,12 @@ class MTVIE(InfoExtractor):
         return base + m.group('finalid')
 
     def _get_thumbnail_url(self, uri, itemdoc):
-        return 'http://mtv.mtvnimages.com/uri/' + uri
+        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
+        thumb_node = itemdoc.find(search_path)
+        if thumb_node is None:
+            return None
+        else:
+            return thumb_node.attrib['url']
 
     def _extract_video_formats(self, metadataXml):
         if '/error_country_block.swf' in metadataXml:
@@ -93,7 +71,7 @@ class MTVIE(InfoExtractor):
         else:
             description = None
 
-        info = {
+        return {
             'title': itemdoc.find('title').text,
             'formats': self._extract_video_formats(mediagen_page),
             'id': video_id,
@@ -101,32 +79,67 @@ class MTVIE(InfoExtractor):
             'description': description,
         }
 
-        # TODO: Remove when #980 has been merged
-        info.update(info['formats'][-1])
-
-        return info
-
     def _get_videos_info(self, uri):
         video_id = self._id_from_uri(uri)
         data = compat_urllib_parse.urlencode({'uri': uri})
-        infoXml = self._download_webpage(self._FEED_URL +'?' + data, video_id,
-                                         u'Downloading info')
-        idoc = xml.etree.ElementTree.fromstring(infoXml.encode('utf-8'))
+
+        def fix_ampersand(s):
+            """ Fix unencoded ampersand in XML """
+            return s.replace(u'& ', '&amp; ')
+        idoc = self._download_xml(
+            self._FEED_URL + '?' + data, video_id,
+            u'Downloading info', transform_source=fix_ampersand)
         return [self._get_video_info(item) for item in idoc.findall('.//item')]
 
+
+class MTVIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'''(?x)^https?://
+        (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
+           m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''
+
+    _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
+
+    _TESTS = [
+        {
+            u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
+            u'file': u'853555.mp4',
+            u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8',
+            u'info_dict': {
+                u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"',
+                u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
+            },
+        },
+        {
+            u'add_ie': ['Vevo'],
+            u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
+            u'file': u'USCJY1331283.mp4',
+            u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
+            u'info_dict': {
+                u'title': u'Everything Has Changed',
+                u'upload_date': u'20130606',
+                u'uploader': u'Taylor Swift',
+            },
+            u'skip': u'VEVO is only available in some countries',
+        },
+    ]
+
+    def _get_thumbnail_url(self, uri, itemdoc):
+        return 'http://mtv.mtvnimages.com/uri/' + uri
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
-
-        webpage = self._download_webpage(url, video_id)
-
-        # Some videos come from Vevo.com
-        m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
-                           webpage, re.DOTALL)
-        if m_vevo:
-            vevo_id = m_vevo.group(1);
-            self.to_screen(u'Vevo video detected: %s' % vevo_id)
-            return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
-
-        uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
+        uri = mobj.group('mgid')
+        if uri is None:
+            webpage = self._download_webpage(url, video_id)
+    
+            # Some videos come from Vevo.com
+            m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
+                               webpage, re.DOTALL)
+            if m_vevo:
+                vevo_id = m_vevo.group(1);
+                self.to_screen(u'Vevo video detected: %s' % vevo_id)
+                return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+    
+            uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
         return self._get_videos_info(uri)

youtube_dl/extractor/muzu.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class MuzuTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www.muzu.tv/(.+?)/(.+?)/(?P<id>\d+)'
+    _VALID_URL = r'https?://www\.muzu\.tv/(.+?)/(.+?)/(?P<id>\d+)'
     IE_NAME = u'muzu.tv'
 
     _TEST = {

youtube_dl/extractor/myspass.py

@@ -1,5 +1,4 @@
 import os.path
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -10,7 +9,7 @@ from ..utils import (
 
 
 class MySpassIE(InfoExtractor):
-    _VALID_URL = r'http://www.myspass.de/.*'
+    _VALID_URL = r'http://www\.myspass\.de/.*'
     _TEST = {
         u'url': u'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
         u'file': u'11741.mp4',
@@ -33,8 +32,7 @@ class MySpassIE(InfoExtractor):
 
         # get metadata
         metadata_url = META_DATA_URL_TEMPLATE % video_id
-        metadata_text = self._download_webpage(metadata_url, video_id)
-        metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
+        metadata = self._download_xml(metadata_url, video_id)
 
         # extract values from metadata
         url_flv_el = metadata.find('url_flv')

youtube_dl/extractor/naver.py

@@ -1,6 +1,5 @@
 # encoding: utf-8
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -10,7 +9,7 @@ from ..utils import (
 
 
 class NaverIE(InfoExtractor):
-    _VALID_URL = r'https?://tvcast\.naver\.com/v/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
 
     _TEST = {
         u'url': u'http://tvcast.naver.com/v/81652',
@@ -38,14 +37,12 @@ class NaverIE(InfoExtractor):
             'protocol': 'p2p',
             'inKey': key,
         })
-        info_xml = self._download_webpage(
+        info = self._download_xml(
             'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
             video_id, u'Downloading video info')
-        urls_xml = self._download_webpage(
+        urls = self._download_xml(
             'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
             video_id, u'Downloading video formats info')
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
-        urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
 
         formats = []
         for format_el in urls.findall('EncodingOptions/EncodingOption'):
@@ -59,7 +56,7 @@ class NaverIE(InfoExtractor):
                 'height': int(format_el.find('height').text),
             })
 
-        info = {
+        return {
             'id': video_id,
             'title': info.find('Subject').text,
             'formats': formats,
@@ -68,6 +65,3 @@ class NaverIE(InfoExtractor):
             'upload_date': info.find('WriteDate').text.replace('.', ''),
             'view_count': int(info.find('PlayCount').text),
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info

youtube_dl/extractor/nbc.py

@@ -1,5 +1,4 @@
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import find_xpath_attr, compat_str
@@ -21,8 +20,8 @@ class NBCNewsIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video')
+        all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
+        info = all_info.find('video')
 
         return {'id': video_id,
                 'title': info.find('headline').text,

youtube_dl/extractor/ndtv.py

@@ -0,0 +1,64 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import month_by_name
+
+
+class NDTVIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)'
+
+    _TEST = {
+        u"url": u"http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710",
+        u"file": u"300710.mp4",
+        u"md5": u"39f992dbe5fb531c395d8bbedb1e5e88",
+        u"info_dict": {
+            u"title": u"NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
+            u"description": u"In an exclusive interview to NDTV, Aam Aadmi Party's Arvind Kejriwal says it makes no difference to him that Rahul Gandhi said the Congress needs to learn from his party.",
+            u"upload_date": u"20131208",
+            u"duration": 1327,
+            u"thumbnail": u"http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg",
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        filename = self._search_regex(
+            r"__filename='([^']+)'", webpage, u'video filename')
+        video_url = (u'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
+                     filename)
+
+        duration_str = filename = self._search_regex(
+            r"__duration='([^']+)'", webpage, u'duration', fatal=False)
+        duration = None if duration_str is None else int(duration_str)
+
+        date_m = re.search(r'''(?x)
+            <p\s+class="vod_dateline">\s*
+                Published\s+On:\s*
+                (?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+)
+            ''', webpage)
+        upload_date = None
+        assert date_m
+        if date_m is not None:
+            month = month_by_name(date_m.group('monthname'))
+            if month is not None:
+                upload_date = '%s%02d%02d' % (
+                    date_m.group('year'), month, int(date_m.group('day')))
+
+        description = self._og_search_description(webpage)
+        READ_MORE = u' (Read more)'
+        if description.endswith(READ_MORE):
+            description = description[:-len(READ_MORE)]
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
+            'description': description,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': duration,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/nhl.py

@@ -1,6 +1,5 @@
 import re
 import json
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -26,9 +25,8 @@ class NHLBaseInfoExtractor(InfoExtractor):
             'path': initial_video_url.replace('.mp4', '_sd.mp4'),
         })
         path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
-        path_response = self._download_webpage(path_url, video_id,
+        path_doc = self._download_xml(path_url, video_id,
             u'Downloading final video url')
-        path_doc = xml.etree.ElementTree.fromstring(path_response)
         video_url = path_doc.find('path').text
 
         join = compat_urlparse.urljoin

youtube_dl/extractor/niconico.py

@@ -2,7 +2,6 @@
 
 import re
 import socket
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -81,7 +80,7 @@ class NiconicoIE(InfoExtractor):
         # the cookies in order to be able to download the info webpage
         self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
 
-        video_info_webpage = self._download_webpage(
+        video_info = self._download_xml(
             'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
             note=u'Downloading video info page')
 
@@ -92,7 +91,6 @@ class NiconicoIE(InfoExtractor):
         video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
 
         # Start extracting information
-        video_info = xml.etree.ElementTree.fromstring(video_info_webpage)
         video_title = video_info.find('.//title').text
         video_extension = video_info.find('.//movie_type').text
         video_format = video_extension.upper()
@@ -107,13 +105,11 @@ class NiconicoIE(InfoExtractor):
         video_uploader = video_uploader_id
         url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id
         try:
-            user_info_webpage = self._download_webpage(
+            user_info = self._download_xml(
                 url, video_id, note=u'Downloading user information')
+            video_uploader = user_info.find('.//nickname').text
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err))
-        else:
-            user_info = xml.etree.ElementTree.fromstring(user_info_webpage)
-            video_uploader = user_info.find('.//nickname').text
 
         return {
             'id':          video_id,

youtube_dl/extractor/ninegag.py

@@ -0,0 +1,43 @@
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class NineGagIE(InfoExtractor):
+    IE_NAME = '9gag'
+    _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)'
+
+    _TEST = {
+        u"url": u"http://9gag.tv/v/1912",
+        u"file": u"1912.mp4",
+        u"info_dict": {
+            u"description": u"This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
+            u"title": u"\"People Are Awesome 2013\" Is Absolutely Awesome"
+        },
+        u'add_ie': [u'Youtube']
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        data_json = self._html_search_regex(r'''(?x)
+            <div\s*id="tv-video"\s*data-video-source="youtube"\s*
+                data-video-meta="([^"]+)"''', webpage, u'video metadata')
+
+        data = json.loads(data_json)
+
+        return {
+            '_type': 'url_transparent',
+            'url': data['youtubeVideoId'],
+            'ie_key': 'Youtube',
+            'id': video_id,
+            'title': data['title'],
+            'description': data['description'],
+            'view_count': int(data['view_count']),
+            'like_count': int(data['statistic']['like']),
+            'dislike_count': int(data['statistic']['dislike']),
+            'thumbnail': data['thumbnail_url'],
+        }

youtube_dl/extractor/ooyala.py

@@ -22,6 +22,11 @@ class OoyalaIE(InfoExtractor):
     def _url_for_embed_code(embed_code):
         return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
 
+    @classmethod
+    def _build_url_result(cls, embed_code):
+        return cls.url_result(cls._url_for_embed_code(embed_code),
+            ie=cls.ie_key())
+
     def _extract_result(self, info, more_info):
         return {'id': info['embedCode'],
                 'ext': 'mp4',

youtube_dl/extractor/orf.py

@@ -12,7 +12,7 @@ from ..utils import (
 )
 
 class ORFIE(InfoExtractor):
-    _VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
+    _VALID_URL = r'https?://tvthek\.orf\.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/pbs.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class PBSIE(InfoExtractor):
-    _VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
+    _VALID_URL = r'https?://video\.pbs\.org/video/(?P<id>\d+)/?'
 
     _TEST = {
         u'url': u'http://video.pbs.org/video/2365006249/',

youtube_dl/extractor/podomatic.py

@@ -0,0 +1,49 @@
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class PodomaticIE(InfoExtractor):
+    IE_NAME = 'podomatic'
+    _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
+
+    _TEST = {
+        u"url": u"http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00",
+        u"file": u"2009-01-02T16_03_35-08_00.mp3",
+        u"md5": u"84bb855fcf3429e6bf72460e1eed782d",
+        u"info_dict": {
+            u"uploader": u"Science Teaching Tips",
+            u"uploader_id": u"scienceteachingtips",
+            u"title": u"64.  When the Moon Hits Your Eye",
+            u"duration": 446,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        channel = mobj.group('channel')
+
+        json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
+                     '?permalink=true&rtmp=0') %
+                    (mobj.group('proto'), channel, video_id))
+        data_json = self._download_webpage(
+            json_url, video_id, note=u'Downloading video info')
+        data = json.loads(data_json)
+
+        video_url = data['downloadLink']
+        uploader = data['podcast']
+        title = data['title']
+        thumbnail = data['imageLocation']
+        duration = int(data['length'] / 1000.0)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'uploader': uploader,
+            'uploader_id': channel,
+            'thumbnail': thumbnail,
+            'duration': duration,
+        }

youtube_dl/extractor/pornhd.py

@@ -0,0 +1,38 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import compat_urllib_parse
+
+
+class PornHdIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+    _TEST = {
+        u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
+        u'file': u'1962.flv',
+        u'md5': u'35272469887dca97abd30abecc6cdf75',
+        u'info_dict': {
+            u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
+            u"age_limit": 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('video_id')
+        video_title = mobj.group('video_title')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(
+            r'&hd=(http.+?)&', webpage, u'video URL')
+        video_url = compat_urllib_parse.unquote(video_url)
+        age_limit = 18
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'flv',
+            'title': video_title,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/pornhub.py

@@ -12,7 +12,7 @@ from ..aes import (
 )
 
 class PornHubIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9]+))'
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))'
     _TEST = {
         u'url': u'http://www.pornhub.com/view_video.php?viewkey=648719015',
         u'file': u'648719015.mp4',

youtube_dl/extractor/pyvideo.py

@@ -0,0 +1,51 @@
+import re
+import os
+
+from .common import InfoExtractor
+
+
+class PyvideoIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
+    _TESTS = [{
+        u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
+        u'file': u'24_4WWkSmNo.mp4',
+        u'md5': u'de317418c8bc76b1fd8633e4f32acbc6',
+        u'info_dict': {
+            u"title": u"Become a logging expert in 30 minutes",
+            u"description": u"md5:9665350d466c67fb5b1598de379021f7",
+            u"upload_date": u"20130320",
+            u"uploader": u"NextDayVideo",
+            u"uploader_id": u"NextDayVideo",
+        },
+        u'add_ie': ['Youtube'],
+    },
+    {
+        u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
+        u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12',
+        u'info_dict': {
+            u'id': u'2542',
+            u'ext': u'm4v',
+            u'title': u'Gloriajw-SpotifyWithErikBernhardsson182',
+        },
+    },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
+
+        if m_youtube is not None:
+            return self.url_result(m_youtube.group(1), 'Youtube')
+
+        title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>',
+            webpage, u'title', flags=re.DOTALL)
+        video_url = self._search_regex([r'<source src="(.*?)"',
+            r'<dt>Download</dt>.*?<a href="(.+?)"'],
+            webpage, u'video url', flags=re.DOTALL)
+        return {
+            'id': video_id,
+            'title': os.path.splitext(title)[0],
+            'url': video_url,
+        }

youtube_dl/extractor/radiofrance.py

@@ -0,0 +1,55 @@
+# coding: utf-8
+import re
+
+from .common import InfoExtractor
+
+
+class RadioFranceIE(InfoExtractor):
+    _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
+    IE_NAME = u'radiofrance'
+
+    _TEST = {
+        u'url': u'http://maison.radiofrance.fr/radiovisions/one-one',
+        u'file': u'one-one.ogg',
+        u'md5': u'bdbb28ace95ed0e04faab32ba3160daf',
+        u'info_dict': {
+            u"title": u"One to one",
+            u"description": u"Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.",
+            u"uploader": u"Thomas Hercouët",
+        },
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, u'title')
+        description = self._html_search_regex(
+            r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>',
+            webpage, u'description', fatal=False)
+        uploader = self._html_search_regex(
+            r'<div class="credit">&nbsp;&nbsp;&copy;&nbsp;(.*?)</div>',
+            webpage, u'uploader', fatal=False)
+
+        formats_str = self._html_search_regex(
+            r'class="jp-jplayer[^"]*" data-source="([^"]+)">',
+            webpage, u'audio URLs')
+        formats = [
+            {
+                'format_id': fm[0],
+                'url': fm[1],
+                'vcodec': 'none',
+            }
+            for fm in
+            re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str)
+        ]
+        # No sorting, we don't know any more about these formats
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'uploader': uploader,
+        }

youtube_dl/extractor/redtube.py

@@ -30,7 +30,7 @@ class RedTubeIE(InfoExtractor):
             r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
 
         video_title = self._html_search_regex(
-            r'<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
+            r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
             webpage, u'title')
 
         # No self-labeling, but they describe themselves as

youtube_dl/extractor/rtlnow.py

@@ -7,14 +7,15 @@ from ..utils import (
     ExtractorError,
 )
 
+
 class RTLnowIE(InfoExtractor):
     """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
-    _VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?rtlnitronow\.de/|(?:www\.)?superrtlnow\.de/|(?:www\.)?n-tvnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
+    _VALID_URL = r'(?:http://)?(?P<url>(?P<domain>rtl-now\.rtl\.de|rtl2now\.rtl2\.de|(?:www\.)?voxnow\.de|(?:www\.)?rtlnitronow\.de|(?:www\.)?superrtlnow\.de|(?:www\.)?n-tvnow\.de)/+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
     _TESTS = [{
         u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
         u'file': u'90419.flv',
         u'info_dict': {
-            u'upload_date': u'20070416', 
+            u'upload_date': u'20070416',
             u'title': u'Ahornallee - Folge 1 - Der Einzug',
             u'description': u'Folge 1 - Der Einzug',
         },
@@ -81,7 +82,7 @@ class RTLnowIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         webpage_url = u'http://' + mobj.group('url')
-        video_page_url = u'http://' + mobj.group('base_url')
+        video_page_url = u'http://' + mobj.group('domain') + u'/'
         video_id = mobj.group(u'video_id')
 
         webpage = self._download_webpage(webpage_url, video_id)

youtube_dl/extractor/rutube.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class RutubeIE(InfoExtractor):
-    _VALID_URL = r'https?://rutube.ru/video/(?P<long_id>\w+)'
+    _VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)'
 
     _TEST = {
         u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',

youtube_dl/extractor/sina.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -35,12 +34,11 @@ class SinaIE(InfoExtractor):
 
     def _extract_video(self, video_id):
         data = compat_urllib_parse.urlencode({'vid': video_id})
-        url_page = self._download_webpage('http://v.iask.com/v_play.php?%s' % data,
+        url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,
             video_id, u'Downloading video url')
         image_page = self._download_webpage(
             'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,
             video_id, u'Downloading thumbnail info')
-        url_doc = xml.etree.ElementTree.fromstring(url_page.encode('utf-8'))
 
         return {'id': video_id,
                 'url': url_doc.find('./durl/url').text,

youtube_dl/extractor/slashdot.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class SlashdotIE(InfoExtractor):
-    _VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
+    _VALID_URL = r'https?://tv\.slashdot\.org/video/\?embed=(?P<id>.*?)(&|$)'
 
     _TEST = {
         u'add_ie': ['Ooyala'],

youtube_dl/extractor/smotri.py

@@ -0,0 +1,373 @@
+# encoding: utf-8
+
+import os.path
+import re
+import json
+import hashlib
+import uuid
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+    ExtractorError,
+    url_basename,
+)
+
+
+class SmotriIE(InfoExtractor):
+    IE_DESC = u'Smotri.com'
+    IE_NAME = u'smotri'
+    _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))'
+
+    _TESTS = [
+        # real video id 2610366
+        {
+            u'url': u'http://smotri.com/video/view/?id=v261036632ab',
+            u'file': u'v261036632ab.mp4',
+            u'md5': u'2a7b08249e6f5636557579c368040eb9',
+            u'info_dict': {
+                u'title': u'катастрофа с камер видеонаблюдения',
+                u'uploader': u'rbc2008',
+                u'uploader_id': u'rbc08',
+                u'upload_date': u'20131118',
+                u'description': u'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
+                u'thumbnail': u'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
+            },
+        },
+        # real video id 57591
+        {
+            u'url': u'http://smotri.com/video/view/?id=v57591cb20',
+            u'file': u'v57591cb20.flv',
+            u'md5': u'830266dfc21f077eac5afd1883091bcd',
+            u'info_dict': {
+                u'title': u'test',
+                u'uploader': u'Support Photofile@photofile',
+                u'uploader_id': u'support-photofile',
+                u'upload_date': u'20070704',
+                u'description': u'test, видео test',
+                u'thumbnail': u'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
+            },
+        },
+        # video-password
+        {
+            u'url': u'http://smotri.com/video/view/?id=v1390466a13c',
+            u'file': u'v1390466a13c.mp4',
+            u'md5': u'f6331cef33cad65a0815ee482a54440b',
+            u'info_dict': {
+                u'title': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
+                u'uploader': u'timoxa40',
+                u'uploader_id': u'timoxa40',
+                u'upload_date': u'20100404',
+                u'thumbnail': u'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
+                u'description': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
+            },
+            u'params': {
+                u'videopassword': u'qwerty',
+            },
+        },
+        # age limit + video-password
+        {
+            u'url': u'http://smotri.com/video/view/?id=v15408898bcf',
+            u'file': u'v15408898bcf.flv',
+            u'md5': u'91e909c9f0521adf5ee86fbe073aad70',
+            u'info_dict': {
+                u'title': u'этот ролик не покажут по ТВ',
+                u'uploader': u'zzxxx',
+                u'uploader_id': u'ueggb',
+                u'upload_date': u'20101001',
+                u'thumbnail': u'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
+                u'age_limit': 18,
+                u'description': u'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
+            },
+            u'params': {
+                u'videopassword': u'333'
+            }
+        }
+    ]
+    
+    _SUCCESS = 0
+    _PASSWORD_NOT_VERIFIED = 1
+    _PASSWORD_DETECTED = 2
+    _VIDEO_NOT_FOUND = 3
+
+    def _search_meta(self, name, html, display_name=None):
+        if display_name is None:
+            display_name = name
+        return self._html_search_regex(
+            r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
+            html, display_name, fatal=False)
+        return self._html_search_meta(name, html, display_name)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('videoid')
+        real_video_id = mobj.group('realvideoid')
+
+        # Download video JSON data
+        video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id
+        video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON')
+        video_json = json.loads(video_json_page)
+        
+        status = video_json['status']
+        if status == self._VIDEO_NOT_FOUND:
+            raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+        elif status == self._PASSWORD_DETECTED:  # The video is protected by a password, retry with
+                                                # video-password set
+            video_password = self._downloader.params.get('videopassword', None)
+            if not video_password:
+                raise ExtractorError(u'This video is protected by a password, use the --video-password option', expected=True)
+            video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest()
+            video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON (video-password set)')
+            video_json = json.loads(video_json_page)
+            status = video_json['status']
+            if status == self._PASSWORD_NOT_VERIFIED:
+                raise ExtractorError(u'Video password is invalid', expected=True)
+        
+        if status != self._SUCCESS:
+            raise ExtractorError(u'Unexpected status value %s' % status)
+        
+        # Extract the URL of the video
+        video_url = video_json['file_data']
+        
+        # Video JSON does not provide enough meta data
+        # We will extract some from the video web page instead
+        video_page_url = 'http://' + mobj.group('url')
+        video_page = self._download_webpage(video_page_url, video_id, u'Downloading video page')
+
+        # Warning if video is unavailable
+        warning = self._html_search_regex(
+            r'<div class="videoUnModer">(.*?)</div>', video_page,
+            u'warning messagef', default=None)
+        if warning is not None:
+            self._downloader.report_warning(
+                u'Video %s may not be available; smotri said: %s ' %
+                (video_id, warning))
+
+        # Adult content
+        if re.search(u'EroConfirmText">', video_page) is not None:
+            self.report_age_confirmation()
+            confirm_string = self._html_search_regex(
+                r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
+                video_page, u'confirm string')
+            confirm_url = video_page_url + '&confirm=%s' % confirm_string
+            video_page = self._download_webpage(confirm_url, video_id, u'Downloading video page (age confirmed)')
+            adult_content = True
+        else:
+            adult_content = False
+        
+        # Extract the rest of meta data
+        video_title = self._search_meta(u'name', video_page, u'title')
+        if not video_title:
+            video_title = os.path.splitext(url_basename(video_url))[0]
+
+        video_description = self._search_meta(u'description', video_page)
+        END_TEXT = u' на сайте Smotri.com'
+        if video_description and video_description.endswith(END_TEXT):
+            video_description = video_description[:-len(END_TEXT)]
+        START_TEXT = u'Смотреть онлайн ролик '
+        if video_description and video_description.startswith(START_TEXT):
+            video_description = video_description[len(START_TEXT):]
+        video_thumbnail = self._search_meta(u'thumbnail', video_page)
+
+        upload_date_str = self._search_meta(u'uploadDate', video_page, u'upload date')
+        if upload_date_str:
+            upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str)
+            video_upload_date = (
+                (
+                    upload_date_m.group('year') +
+                    upload_date_m.group('month') +
+                    upload_date_m.group('day')
+                )
+                if upload_date_m else None
+            )
+        else:
+            video_upload_date = None
+        
+        duration_str = self._search_meta(u'duration', video_page)
+        if duration_str:
+            duration_m = re.search(r'T(?P<hours>[0-9]{2})H(?P<minutes>[0-9]{2})M(?P<seconds>[0-9]{2})S', duration_str)
+            video_duration = (
+                (
+                    (int(duration_m.group('hours')) * 60 * 60) +
+                    (int(duration_m.group('minutes')) * 60) +
+                    int(duration_m.group('seconds'))
+                )
+                if duration_m else None
+            )
+        else:
+            video_duration = None
+        
+        video_uploader = self._html_search_regex(
+            u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
+            video_page, u'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
+        
+        video_uploader_id = self._html_search_regex(
+            u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
+            video_page, u'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
+        
+        video_view_count = self._html_search_regex(
+            u'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
+            video_page, u'view count', fatal=False, flags=re.MULTILINE|re.DOTALL)
+                
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
+            'thumbnail': video_thumbnail,
+            'description': video_description,
+            'uploader': video_uploader,
+            'upload_date': video_upload_date,
+            'uploader_id': video_uploader_id,
+            'duration': video_duration,
+            'view_count': video_view_count,
+            'age_limit': 18 if adult_content else 0,
+            'video_page_url': video_page_url
+        }
+
+
+class SmotriCommunityIE(InfoExtractor):
+    IE_DESC = u'Smotri.com community videos'
+    IE_NAME = u'smotri:community'
+    _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
+    
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        community_id = mobj.group('communityid')
+
+        url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
+        rss = self._download_xml(url, community_id, u'Downloading community RSS')
+
+        entries = [self.url_result(video_url.text, 'Smotri')
+                   for video_url in rss.findall('./channel/item/link')]
+
+        description_text = rss.find('./channel/description').text
+        community_title = self._html_search_regex(
+            u'^Видео сообщества "([^"]+)"$', description_text, u'community title')
+
+        return self.playlist_result(entries, community_id, community_title)
+
+
+class SmotriUserIE(InfoExtractor):
+    IE_DESC = u'Smotri.com user videos'
+    IE_NAME = u'smotri:user'
+    _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        user_id = mobj.group('userid')
+
+        url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
+        rss = self._download_xml(url, user_id, u'Downloading user RSS')
+
+        entries = [self.url_result(video_url.text, 'Smotri')
+                   for video_url in rss.findall('./channel/item/link')]
+
+        description_text = rss.find('./channel/description').text
+        user_nickname = self._html_search_regex(
+            u'^Видео режиссера (.*)$', description_text,
+            u'user nickname')
+
+        return self.playlist_result(entries, user_id, user_nickname)
+
+
+class SmotriBroadcastIE(InfoExtractor):
+    IE_DESC = u'Smotri.com broadcasts'
+    IE_NAME = u'smotri:broadcast'
+    _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        broadcast_id = mobj.group('broadcastid')
+
+        broadcast_url = 'http://' + mobj.group('url')
+        broadcast_page = self._download_webpage(broadcast_url, broadcast_id, u'Downloading broadcast page')
+
+        if re.search(u'>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
+            raise ExtractorError(u'Broadcast %s does not exist' % broadcast_id, expected=True)
+
+        # Adult content
+        if re.search(u'EroConfirmText">', broadcast_page) is not None:
+
+            (username, password) = self._get_login_info()
+            if username is None:
+                raise ExtractorError(u'Erotic broadcasts allowed only for registered users, '
+                    u'use --username and --password options to provide account credentials.', expected=True)
+
+            # Log in
+            login_form_strs = {
+                u'login-hint53': '1',
+                u'confirm_erotic': '1',
+                u'login': username,
+                u'password': password,
+            }
+            # 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')
+            login_url = broadcast_url + '/?no_redirect=1'
+            request = compat_urllib_request.Request(login_url, login_data)
+            request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+            broadcast_page = self._download_webpage(
+                request, broadcast_id, note=u'Logging in and confirming age')
+
+            if re.search(u'>Неверный логин или пароль<', broadcast_page) is not None:
+                raise ExtractorError(u'Unable to log in: bad username or password', expected=True)
+
+            adult_content = True
+        else:
+            adult_content = False
+
+        ticket = self._html_search_regex(
+            u'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
+            broadcast_page, u'broadcast ticket')
+
+        url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
+
+        broadcast_password = self._downloader.params.get('videopassword', None)
+        if broadcast_password:
+            url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
+
+        broadcast_json_page = self._download_webpage(url, broadcast_id, u'Downloading broadcast JSON')
+
+        try:
+            broadcast_json = json.loads(broadcast_json_page)
+
+            protected_broadcast = broadcast_json['_pass_protected'] == 1
+            if protected_broadcast and not broadcast_password:
+                raise ExtractorError(u'This broadcast is protected by a password, use the --video-password option', expected=True)
+
+            broadcast_offline = broadcast_json['is_play'] == 0
+            if broadcast_offline:
+                raise ExtractorError(u'Broadcast %s is offline' % broadcast_id, expected=True)
+
+            rtmp_url = broadcast_json['_server']
+            if not rtmp_url.startswith('rtmp://'):
+                raise ExtractorError(u'Unexpected broadcast rtmp URL')
+
+            broadcast_playpath = broadcast_json['_streamName']
+            broadcast_thumbnail = broadcast_json['_imgURL']
+            broadcast_title = broadcast_json['title']
+            broadcast_description = broadcast_json['description']
+            broadcaster_nick = broadcast_json['nick']
+            broadcaster_login = broadcast_json['login']
+            rtmp_conn = 'S:%s' % uuid.uuid4().hex
+        except KeyError:
+            if protected_broadcast:
+                raise ExtractorError(u'Bad broadcast password', expected=True)
+            raise ExtractorError(u'Unexpected broadcast JSON')
+
+        return {
+            'id': broadcast_id,
+            'url': rtmp_url,
+            'title': broadcast_title,
+            'thumbnail': broadcast_thumbnail,
+            'description': broadcast_description,
+            'uploader': broadcaster_nick,
+            'uploader_id': broadcaster_login,
+            'age_limit': 18 if adult_content else 0,
+            'ext': 'flv',
+            'play_path': broadcast_playpath,
+            'rtmp_live': True,
+            'rtmp_conn': rtmp_conn
+        }

youtube_dl/extractor/soundcloud.py

@@ -1,3 +1,4 @@
+# encoding: utf-8
 import json
 import re
 import itertools
@@ -23,9 +24,12 @@ class SoundcloudIE(InfoExtractor):
      """
 
     _VALID_URL = r'''^(?:https?://)?
-                    (?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
+                    (?:(?:(?:www\.|m\.)?soundcloud\.com/
+                            (?P<uploader>[\w\d-]+)/
+                            (?!sets/)(?P<title>[\w\d-]+)/?
+                            (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
-                       |(?P<widget>w.soundcloud.com/player/?.*?url=.*)
+                       |(?P<widget>w\.soundcloud\.com/player/?.*?url=.*)
                     )
                     '''
     IE_NAME = u'soundcloud'
@@ -56,6 +60,32 @@ class SoundcloudIE(InfoExtractor):
                 u'skip_download': True,
             },
         },
+        # private link
+        {
+            u'url': u'https://soundcloud.com/jaimemf/youtube-dl-test-video-a-y-baw/s-8Pjrp',
+            u'md5': u'aa0dd32bfea9b0c5ef4f02aacd080604',
+            u'info_dict': {
+                u'id': u'123998367',
+                u'ext': u'mp3',
+                u'title': u'Youtube - Dl Test Video \'\' Ä↭',
+                u'uploader': u'jaimeMF',
+                u'description': u'test chars:  \"\'/\\ä↭',
+                u'upload_date': u'20131209',
+            },
+        },
+        # downloadable song
+        {
+            u'url': u'https://soundcloud.com/simgretina/just-your-problem-baby-1',
+            u'md5': u'56a8b69568acaa967b4c49f9d1d52d19',
+            u'info_dict': {
+                u'id': u'105614606',
+                u'ext': u'wav',
+                u'title': u'Just Your Problem Baby (Acapella)',
+                u'description': u'Vocals',
+                u'uploader': u'Sim Gretina',
+                u'upload_date': u'20130815',
+            },
+        },
     ]
 
     _CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
@@ -73,7 +103,7 @@ class SoundcloudIE(InfoExtractor):
     def _resolv_url(cls, url):
         return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
 
-    def _extract_info_dict(self, info, full_title=None, quiet=False):
+    def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None):
         track_id = compat_str(info['id'])
         name = full_title or track_id
         if quiet:
@@ -82,7 +112,7 @@ class SoundcloudIE(InfoExtractor):
         thumbnail = info['artwork_url']
         if thumbnail is not None:
             thumbnail = thumbnail.replace('-large', '-t500x500')
-        ext = info.get('original_format', u'mp3')
+        ext = u'mp3'
         result = {
             'id': track_id,
             'uploader': info['user']['username'],
@@ -98,14 +128,16 @@ class SoundcloudIE(InfoExtractor):
                     track_id, self._CLIENT_ID))
             result['formats'] = [{
                 'format_id': 'download',
-                'ext': ext,
+                'ext': info.get('original_format', u'mp3'),
                 'url': format_url,
                 'vcodec': 'none',
             }]
         else:
             # We have to retrieve the url
+            streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?'
+                'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
             stream_json = self._download_webpage(
-                'http://api.soundcloud.com/i1/tracks/{0}/streams?client_id={1}'.format(track_id, self._IPHONE_CLIENT_ID),
+                streams_url,
                 track_id, u'Downloading track url')
 
             formats = []
@@ -157,6 +189,7 @@ class SoundcloudIE(InfoExtractor):
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         track_id = mobj.group('track_id')
+        token = None
         if track_id is not None:
             info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
             full_title = track_id
@@ -165,19 +198,22 @@ class SoundcloudIE(InfoExtractor):
             return self.url_result(query['url'][0], ie='Soundcloud')
         else:
             # extract uploader (which is in the url)
-            uploader = mobj.group(1)
+            uploader = mobj.group('uploader')
             # extract simple title (uploader + slug of song title)
-            slug_title =  mobj.group(2)
-            full_title = '%s/%s' % (uploader, slug_title)
+            slug_title =  mobj.group('title')
+            token = mobj.group('token')
+            full_title = resolve_title = '%s/%s' % (uploader, slug_title)
+            if token:
+                resolve_title += '/%s' % token
     
             self.report_resolve(full_title)
     
-            url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
+            url = 'http://soundcloud.com/%s' % resolve_title
             info_json_url = self._resolv_url(url)
         info_json = self._download_webpage(info_json_url, full_title, u'Downloading info JSON')
 
         info = json.loads(info_json)
-        return self._extract_info_dict(info, full_title)
+        return self._extract_info_dict(info, full_title, secret_token=token)
 
 class SoundcloudSetIE(SoundcloudIE):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
@@ -217,7 +253,7 @@ class SoundcloudSetIE(SoundcloudIE):
 
 
 class SoundcloudUserIE(SoundcloudIE):
-    _VALID_URL = r'https?://(www\.)?soundcloud.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
+    _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
     IE_NAME = u'soundcloud:user'
 
     # it's in tests/test_playlists.py

youtube_dl/extractor/southparkstudios.py

@@ -1,15 +1,14 @@
 import re
 
-from .mtv import MTVIE, _media_xml_tag
+from .mtv import MTVServicesInfoExtractor
 
 
-class SouthParkStudiosIE(MTVIE):
+class SouthParkStudiosIE(MTVServicesInfoExtractor):
     IE_NAME = u'southparkstudios.com'
     _VALID_URL = r'(https?://)?(www\.)?(?P<url>southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
 
     _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
 
-    # Overwrite MTVIE properties we don't want
     _TESTS = [{
         u'url': u'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured',
         u'file': u'a7bff6c2-ed00-11e0-aca6-0026b9414f30.mp4',
@@ -19,14 +18,6 @@ class SouthParkStudiosIE(MTVIE):
         },
     }]
 
-    def _get_thumbnail_url(self, uri, itemdoc):
-        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
-        thumb_node = itemdoc.find(search_path)
-        if thumb_node is None:
-            return None
-        else:
-            return thumb_node.attrib['url']
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         url = u'http://www.' + mobj.group(u'url')

youtube_dl/extractor/space.py

@@ -6,7 +6,7 @@ from ..utils import RegexNotFoundError, ExtractorError
 
 
 class SpaceIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video.html'
+    _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
     _TEST = {
         u'add_ie': ['Brightcove'],
         u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',

youtube_dl/extractor/spiegel.py

@@ -1,5 +1,4 @@
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 
@@ -33,12 +32,10 @@ class SpiegelIE(InfoExtractor):
             r'<div class="module-title">(.*?)</div>', webpage, u'title')
 
         xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
-        xml_code = self._download_webpage(
+        idoc = self._download_xml(
             xml_url, video_id,
             note=u'Downloading XML', errnote=u'Failed to download XML')
 
-        idoc = xml.etree.ElementTree.fromstring(xml_code)
-
         formats = [
             {
                 'format_id': n.tag.rpartition('type')[2],

youtube_dl/extractor/stanfordoc.py

@@ -1,14 +1,7 @@
 import re
-import socket
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_str,
-    compat_urllib_error,
-    compat_urllib_request,
-
     ExtractorError,
     orderedSet,
     unescapeHTML,
@@ -18,7 +11,7 @@ from ..utils import (
 class StanfordOpenClassroomIE(InfoExtractor):
     IE_NAME = u'stanfordoc'
     IE_DESC = u'Stanford Open ClassRoom'
-    _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
+    _VALID_URL = r'^(?:https?://)?openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
     _TEST = {
         u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
         u'file': u'PracticalUnix_intro-environment.mp4',
@@ -45,11 +38,7 @@ class StanfordOpenClassroomIE(InfoExtractor):
             self.report_extraction(info['id'])
             baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
             xmlUrl = baseUrl + video + '.xml'
-            try:
-                metaXml = compat_urllib_request.urlopen(xmlUrl).read()
-            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
-            mdoc = xml.etree.ElementTree.fromstring(metaXml)
+            mdoc = self._download_xml(xmlUrl, info['id'])
             try:
                 info['title'] = mdoc.findall('./title')[0].text
                 info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
@@ -95,12 +84,9 @@ class StanfordOpenClassroomIE(InfoExtractor):
                 'upload_date': None,
             }
 
-            self.report_download_webpage(info['id'])
             rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
-            try:
-                rootpage = compat_urllib_request.urlopen(rootURL).read()
-            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
+            rootpage = self._download_webpage(rootURL, info['id'],
+                errnote=u'Unable to download course info page')
 
             info['title'] = info['id']
 

youtube_dl/extractor/teamcoco.py

@@ -1,5 +1,4 @@
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -32,8 +31,7 @@ class TeamcocoIE(InfoExtractor):
         self.report_extraction(video_id)
 
         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
-        data_xml = self._download_webpage(data_url, video_id, 'Downloading data webpage')
-        data = xml.etree.ElementTree.fromstring(data_xml.encode('utf-8'))
+        data = self._download_xml(data_url, video_id, 'Downloading data webpage')
 
 
         qualities = ['500k', '480p', '1000k', '720p', '1080p']

youtube_dl/extractor/tf1.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""
-    _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
+    _VALID_URL = r'http://videos\.tf1\.fr/.*-(.*?)\.html'
     _TEST = {
         u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         u'file': u'10635995.mp4',

youtube_dl/extractor/theplatform.py

@@ -0,0 +1,80 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    xpath_with_ns,
+)
+
+_x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'})
+
+
+class ThePlatformIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://link\.theplatform\.com/s/[^/]+/|theplatform:)(?P<id>[^/\?]+)'
+
+    _TEST = {
+        # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
+        u'url': u'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true',
+        u'info_dict': {
+            u'id': u'e9I_cZgTgIPd',
+            u'ext': u'flv',
+            u'title': u'Blackberry\'s big, bold Z30',
+            u'description': u'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
+            u'duration': 247,
+        },
+        u'params': {
+            # rtmp download
+            u'skip_download': True,
+        },
+    }
+
+    def _get_info(self, video_id):
+        smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
+            'format=smil&mbr=true'.format(video_id))
+        meta = self._download_xml(smil_url, video_id)
+
+        try:
+            error_msg = next(
+                n.attrib['abstract']
+                for n in meta.findall(_x('.//smil:ref'))
+                if n.attrib.get('title') == u'Geographic Restriction')
+        except StopIteration:
+            pass
+        else:
+            raise ExtractorError(error_msg, expected=True)
+
+        info_url = 'http://link.theplatform.com/s/dJ5BDC/{0}?format=preview'.format(video_id)
+        info_json = self._download_webpage(info_url, video_id)
+        info = json.loads(info_json)
+
+        head = meta.find(_x('smil:head'))
+        body = meta.find(_x('smil:body'))
+        base_url = head.find(_x('smil:meta')).attrib['base']
+        switch = body.find(_x('smil:switch'))
+        formats = []
+        for f in switch.findall(_x('smil:video')):
+            attr = f.attrib
+            formats.append({
+                'url': base_url,
+                'play_path': 'mp4:' + attr['src'],
+                'ext': 'flv',
+                'width': int(attr['width']),
+                'height': int(attr['height']),
+                'vbr': int(attr['system-bitrate']),
+            })
+        formats.sort(key=lambda f: (f['height'], f['width'], f['vbr']))
+
+        return {
+            'id': video_id,
+            'title': info['title'],
+            'formats': formats,
+            'description': info['description'],
+            'thumbnail': info['defaultThumbnailUrl'],
+            'duration': info['duration']//1000,
+        }
+        
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        return self._get_info(video_id)