release 2014.09.06

Conflicts:
	youtube_dl/extractor/__init__.py

.gitignore

@@ -26,5 +26,6 @@ updates_key.pem
 *.m4a
 *.m4v
 *.part
+*.swp
 test/testdata
 .tox

Makefile

@@ -6,10 +6,10 @@ clean:
 cleanall: clean
 	rm -f youtube-dl youtube-dl.exe
 
-PREFIX=/usr/local
+PREFIX ?= /usr/local
-BINDIR=$(PREFIX)/bin
+BINDIR ?= $(PREFIX)/bin
-MANDIR=$(PREFIX)/man
+MANDIR ?= $(PREFIX)/man
-PYTHON=/usr/bin/env python
+PYTHON ?= /usr/bin/env python
 
 # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
 ifeq ($(PREFIX),/usr)

README.md

@@ -17,6 +17,14 @@ If you do not have curl, you can alternatively use a recent wget:
 
 Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29).
 
+OS X users can install **youtube-dl** with [Homebrew](http://brew.sh/).
+
+    brew install youtube-dl
+
+You can also use pip:
+
+    sudo pip install youtube-dl
+
 Alternatively, refer to the developer instructions below for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
 
 # DESCRIPTION
@@ -247,6 +255,7 @@ which means you can modify it, redistribute it or use it however you like.
 ## Authentication Options:
     -u, --username USERNAME          account username
     -p, --password PASSWORD          account password
+    -2, --twofactor TWOFACTOR        two-factor auth code
     -n, --netrc                      use .netrc authentication data
     --video-password PASSWORD        video password (vimeo, smotri)
 
@@ -279,6 +288,10 @@ which means you can modify it, redistribute it or use it however you like.
                                      postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
                                      postprocessors
+    --exec CMD                       Execute a command on the file after
+                                     downloading, similar to find's -exec
+                                     syntax. Example: --exec 'adb push {}
+                                     /sdcard/Music/ && rm {}'
 
 # CONFIGURATION
 
@@ -303,10 +316,12 @@ The current default template is `%(title)s-%(id)s.%(ext)s`.
 
 In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
 
-    $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc
+```bash
-    youtube-dl test video ''_ä↭𝕐.mp4    # All kinds of weird characters
+$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc
-    $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
+youtube-dl test video ''_ä↭𝕐.mp4    # All kinds of weird characters
-    youtube-dl_test_video_.mp4          # A simple file name
+$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
+youtube-dl_test_video_.mp4          # A simple file name
+```
 
 # VIDEO SELECTION
 
@@ -317,14 +332,16 @@ Videos can be filtered by their upload date using the options `--date`, `--dateb
  
 Examples:
 
-    # Download only the videos uploaded in the last 6 months
+```bash
-    $ youtube-dl --dateafter now-6months
+# Download only the videos uploaded in the last 6 months
+$ youtube-dl --dateafter now-6months
 
-    # Download only the videos uploaded on January 1, 1970
+# Download only the videos uploaded on January 1, 1970
-    $ youtube-dl --date 19700101
+$ youtube-dl --date 19700101
 
-    $ # will only download the videos uploaded in the 200x decade
+$ # will only download the videos uploaded in the 200x decade
-    $ youtube-dl --dateafter 20000101 --datebefore 20091231
+$ youtube-dl --dateafter 20000101 --datebefore 20091231
+```
 
 # FAQ
 
@@ -399,49 +416,49 @@ If you want to add support for a new site, you can follow this quick list (assum
 2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
 3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
 4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
+    ```python
+    # coding: utf-8
+    from __future__ import unicode_literals
 
-        # coding: utf-8
+    import re
-        from __future__ import unicode_literals
 
-        import re
+    from .common import InfoExtractor
 
-        from .common import InfoExtractor
+
-        
+    class YourExtractorIE(InfoExtractor):
-        
+        _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
-        class YourExtractorIE(InfoExtractor):
+        _TEST = {
-            _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
+            'url': 'http://yourextractor.com/watch/42',
-            _TEST = {
+            'md5': 'TODO: md5 sum of the first 10KiB of the video file',
-                'url': 'http://yourextractor.com/watch/42',
+            'info_dict': {
-                'md5': 'TODO: md5 sum of the first 10KiB of the video file',
+                'id': '42',
-                'info_dict': {
+                'ext': 'mp4',
-                    'id': '42',
+                'title': 'Video title goes here',
-                    'ext': 'mp4',
+                'thumbnail': 're:^https?://.*\.jpg$',
-                    'title': 'Video title goes here',
+                # TODO more properties, either as:
-                    # TODO more properties, either as:
+                # * A value
-                    # * A value
+                # * MD5 checksum; start the string with md5:
-                    # * MD5 checksum; start the string with md5:
+                # * A regular expression; start the string with re:
-                    # * A regular expression; start the string with re:
+                # * Any Python type (for example int or float)
-                    # * Any Python type (for example int or float)
-                }
             }
+        }
 
-            def _real_extract(self, url):
+        def _real_extract(self, url):
-                mobj = re.match(self._VALID_URL, url)
+            mobj = re.match(self._VALID_URL, url)
-                video_id = mobj.group('id')
+            video_id = mobj.group('id')
-
-                # TODO more code goes here, for example ...
-                webpage = self._download_webpage(url, video_id)
-                title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
-
-                return {
-                    'id': video_id,
-                    'title': title,
-                    # TODO more properties (see youtube_dl/extractor/common.py)
-                }
 
+            # TODO more code goes here, for example ...
+            webpage = self._download_webpage(url, video_id)
+            title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
 
+            return {
+                'id': video_id,
+                'title': title,
+                # TODO more properties (see youtube_dl/extractor/common.py)
+            }
+    ```
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
-6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done.
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
 8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
 9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this:

test/helper.py

@@ -102,7 +102,11 @@ def expect_info_dict(self, expected_dict, got_dict):
             match_rex = re.compile(match_str)
 
             self.assertTrue(
-                isinstance(got, compat_str) and match_rex.match(got),
+                isinstance(got, compat_str),
+                u'Expected a %s object, but got %s for field %s' % (
+                    compat_str.__name__, type(got).__name__, info_field))
+            self.assertTrue(
+                match_rex.match(got),
                 u'field %s (value: %r) should match %r' % (info_field, got, match_str))
         elif isinstance(expected, type):
             got = got_dict.get(info_field)
@@ -117,8 +121,9 @@ def expect_info_dict(self, expected_dict, got_dict):
                 u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
     # Check for the presence of mandatory fields
-    for key in ('id', 'url', 'title', 'ext'):
+    if got_dict.get('_type') != 'playlist':
-        self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
+        for key in ('id', 'url', 'title', 'ext'):
+            self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
     # Check for mandatory fields that are automatically set by YoutubeDL
     for key in ['webpage_url', 'extractor', 'extractor_key']:
         self.assertTrue(got_dict.get(key), u'Missing field: %s' % key)

test/parameters.json

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

test/test_YoutubeDL.py

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

test/test_all_urls.py

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

test/test_cache.py

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

test/test_download.py

@@ -7,6 +7,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
+    assertGreaterEqual,
     get_params,
     gettestcases,
     expect_info_dict,
@@ -27,6 +28,7 @@ from youtube_dl.utils import (
     compat_HTTPError,
     DownloadError,
     ExtractorError,
+    format_bytes,
     UnavailableVideoError,
 )
 from youtube_dl.extractor import get_info_extractor
@@ -63,15 +65,21 @@ def generator(test_case):
     def test_template(self):
         ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
         other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
+        is_playlist = any(k.startswith('playlist') for k in test_case)
+        test_cases = test_case.get(
+            'playlist', [] if is_playlist else [test_case])
+
         def print_skipping(reason):
             print('Skipping %s: %s' % (test_case['name'], reason))
         if not ie.working():
             print_skipping('IE marked as not _WORKING')
             return
-        if 'playlist' not in test_case:
+
-            info_dict = test_case.get('info_dict', {})
+        for tc in test_cases:
-            if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
+            info_dict = tc.get('info_dict', {})
+            if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
                 raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
+
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
             return
@@ -81,6 +89,9 @@ def generator(test_case):
                 return
 
         params = get_params(test_case.get('params', {}))
+        if is_playlist and 'playlist' not in test_case:
+            params.setdefault('extract_flat', True)
+            params.setdefault('skip_download', True)
 
         ydl = YoutubeDL(params)
         ydl.add_default_info_extractors()
@@ -93,9 +104,11 @@ def generator(test_case):
         def get_tc_filename(tc):
             return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
 
-        test_cases = test_case.get('playlist', [test_case])
+        res_dict = None
-        def try_rm_tcs_files():
+        def try_rm_tcs_files(tcs=None):
-            for tc in test_cases:
+            if tcs is None:
+                tcs = test_cases
+            for tc in tcs:
                 tc_filename = get_tc_filename(tc)
                 try_rm(tc_filename)
                 try_rm(tc_filename + '.part')
@@ -105,7 +118,10 @@ def generator(test_case):
             try_num = 1
             while True:
                 try:
-                    ydl.download([test_case['url']])
+                    # We're not using .download here sine that is just a shim
+                    # for outside error handling, and returns the exit code
+                    # instead of the result dict.
+                    res_dict = ydl.extract_info(test_case['url'])
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
                     if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
@@ -121,22 +137,62 @@ def generator(test_case):
                 else:
                     break
 
+            if is_playlist:
+                self.assertEqual(res_dict['_type'], 'playlist')
+                expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
+            if 'playlist_mincount' in test_case:
+                assertGreaterEqual(
+                    self,
+                    len(res_dict['entries']),
+                    test_case['playlist_mincount'],
+                    'Expected at least %d in playlist %s, but got only %d' % (
+                        test_case['playlist_mincount'], test_case['url'],
+                        len(res_dict['entries'])))
+            if 'playlist_count' in test_case:
+                self.assertEqual(
+                    len(res_dict['entries']),
+                    test_case['playlist_count'],
+                    'Expected %d entries in playlist %s, but got %d.' % (
+                        test_case['playlist_count'],
+                        test_case['url'],
+                        len(res_dict['entries']),
+                    ))
+            if 'playlist_duration_sum' in test_case:
+                got_duration = sum(e['duration'] for e in res_dict['entries'])
+                self.assertEqual(
+                    test_case['playlist_duration_sum'], got_duration)
+
             for tc in test_cases:
                 tc_filename = get_tc_filename(tc)
                 if not test_case.get('params', {}).get('skip_download', False):
                     self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
                     self.assertTrue(tc_filename in finished_hook_called)
+                    expected_minsize = tc.get('file_minsize', 10000)
+                    if expected_minsize is not None:
+                        if params.get('test'):
+                            expected_minsize = max(expected_minsize, 10000)
+                        got_fsize = os.path.getsize(tc_filename)
+                        assertGreaterEqual(
+                            self, got_fsize, expected_minsize,
+                            'Expected %s to be at least %s, but it\'s only %s ' %
+                            (tc_filename, format_bytes(expected_minsize),
+                                format_bytes(got_fsize)))
+                    if 'md5' in tc:
+                        md5_for_file = _file_md5(tc_filename)
+                        self.assertEqual(md5_for_file, tc['md5'])
                 info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
                 self.assertTrue(os.path.exists(info_json_fn))
-                if 'md5' in tc:
-                    md5_for_file = _file_md5(tc_filename)
-                    self.assertEqual(md5_for_file, tc['md5'])
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
 
                 expect_info_dict(self, tc.get('info_dict', {}), info_dict)
         finally:
             try_rm_tcs_files()
+            if is_playlist and res_dict is not None:
+                # Remove all other files that may have been extracted if the
+                # extractor returns full results even with extract_flat
+                res_tcs = [{'info_dict': e} for e in res_dict['entries']]
+                try_rm_tcs_files(res_tcs)
 
     return test_template
 

test/test_playlists.py

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

test/test_utils.py

@@ -1,6 +1,8 @@
 #!/usr/bin/env python
 # coding: utf-8
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
@@ -13,7 +15,6 @@ import io
 import json
 import xml.etree.ElementTree
 
-#from youtube_dl.utils import htmlentity_transform
 from youtube_dl.utils import (
     DateRange,
     encodeFilename,
@@ -41,11 +42,6 @@ from youtube_dl.utils import (
     uppercase_escape,
 )
 
-if sys.version_info < (3, 0):
-    _compat_str = lambda b: b.decode('unicode-escape')
-else:
-    _compat_str = lambda s: s
-
 
 class TestUtil(unittest.TestCase):
     def test_timeconvert(self):
@@ -67,9 +63,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('this - that', sanitize_filename('this: that'))
 
         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
-        aumlaut = _compat_str('\xe4')
+        aumlaut = 'ä'
         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
-        tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
+        tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
         self.assertEqual(sanitize_filename(tests), tests)
 
         forbidden = '"\0\\/'
@@ -91,9 +87,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 
-        tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
+        tests = 'a\xe4b\u4e2d\u56fd\u7684c'
         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
-        self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
+        self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 
         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
         for fc in forbidden:
@@ -101,8 +97,8 @@ class TestUtil(unittest.TestCase):
                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 
         # Handle a common case more neatly
-        self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
+        self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
-        self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
+        self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
         # .. but make sure the file name is never empty
         self.assertTrue(sanitize_filename('-', restricted=True) != '')
         self.assertTrue(sanitize_filename(':', restricted=True) != '')
@@ -120,7 +116,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 
     def test_unescape_html(self):
-        self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
+        self.assertEqual(unescapeHTML('%20;'), '%20;')
+        self.assertEqual(
+            unescapeHTML('&eacute;'), 'é')
         
     def test_daterange(self):
         _20century = DateRange("19000101","20000101")
@@ -138,7 +136,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 
     def test_find_xpath_attr(self):
-        testxml = u'''<root>
+        testxml = '''<root>
             <node/>
             <node x="a"/>
             <node x="a" y="c" />
@@ -151,18 +149,18 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 
     def test_meta_parser(self):
-        testhtml = u'''
+        testhtml = '''
         <head>
             <meta name="description" content="foo &amp; bar">
             <meta content='Plato' name='author'/>
         </head>
         '''
         get_meta = lambda name: get_meta_content(name, testhtml)
-        self.assertEqual(get_meta('description'), u'foo & bar')
+        self.assertEqual(get_meta('description'), 'foo & bar')
         self.assertEqual(get_meta('author'), 'Plato')
 
     def test_xpath_with_ns(self):
-        testxml = u'''<root xmlns:media="http://example.com/">
+        testxml = '''<root xmlns:media="http://example.com/">
             <media:song>
                 <media:author>The Author</media:author>
                 <url>http://server.com/download.mp3</url>
@@ -171,8 +169,8 @@ class TestUtil(unittest.TestCase):
         doc = xml.etree.ElementTree.fromstring(testxml)
         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
         self.assertTrue(find('media:song') is not None)
-        self.assertEqual(find('media:song/media:author').text, u'The Author')
+        self.assertEqual(find('media:song/media:author').text, 'The Author')
-        self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
+        self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
     def test_smuggle_url(self):
         data = {u"ö": u"ö", u"abc": [3]}
@@ -187,22 +185,22 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(res_data, None)
 
     def test_shell_quote(self):
-        args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
+        args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
-        self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
+        self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 
     def test_str_to_int(self):
         self.assertEqual(str_to_int('123,456'), 123456)
         self.assertEqual(str_to_int('123.456'), 123456)
 
     def test_url_basename(self):
-        self.assertEqual(url_basename(u'http://foo.de/'), u'')
+        self.assertEqual(url_basename('http://foo.de/'), '')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
-        self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
+        self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
         self.assertEqual(
-            url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
+            url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
-            u'trailer.mp4')
+            'trailer.mp4')
 
     def test_parse_duration(self):
         self.assertEqual(parse_duration(None), None)
@@ -213,12 +211,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('00:01:01'), 61)
         self.assertEqual(parse_duration('x:y'), None)
         self.assertEqual(parse_duration('3h11m53s'), 11513)
+        self.assertEqual(parse_duration('3h 11m 53s'), 11513)
+        self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
+        self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
         self.assertEqual(parse_duration('62m45s'), 3765)
         self.assertEqual(parse_duration('6m59s'), 419)
         self.assertEqual(parse_duration('49s'), 49)
         self.assertEqual(parse_duration('0h0m0s'), 0)
         self.assertEqual(parse_duration('0m0s'), 0)
         self.assertEqual(parse_duration('0s'), 0)
+        self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -255,16 +257,16 @@ class TestUtil(unittest.TestCase):
         testPL(5, 2, (20, 99), [])
 
     def test_struct_unpack(self):
-        self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
+        self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
 
     def test_read_batch_urls(self):
-        f = io.StringIO(u'''\xef\xbb\xbf foo
+        f = io.StringIO('''\xef\xbb\xbf foo
             bar\r
             baz
             # More after this line\r
             ; or after this
             bam''')
-        self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
+        self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 
     def test_urlencode_postdata(self):
         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
@@ -280,9 +282,9 @@ class TestUtil(unittest.TestCase):
         d = json.loads(stripped)
         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 
-    def test_uppercase_escpae(self):
+    def test_uppercase_escape(self):
-        self.assertEqual(uppercase_escape(u'aä'), u'aä')
+        self.assertEqual(uppercase_escape('aä'), 'aä')
-        self.assertEqual(uppercase_escape(u'\\U0001d550'), u'𝕐')
+        self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -57,6 +57,7 @@ from .utils import (
     YoutubeDLHandler,
     prepend_extension,
 )
+from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
 from .downloader import get_suitable_downloader
 from .postprocessor import FFmpegMergerPP
@@ -133,7 +134,7 @@ class YoutubeDL(object):
     daterange:         A DateRange object, download only if the upload_date is in the range.
     skip_download:     Skip the actual download of the video file
     cachedir:          Location of the cache files in the filesystem.
-                       None to disable filesystem cache.
+                       False to disable filesystem cache.
     noplaylist:        Download single video instead of a playlist if in doubt.
     age_limit:         An integer representing the user's age in years.
                        Unsuitable videos for the given age are skipped.
@@ -162,6 +163,7 @@ class YoutubeDL(object):
     default_search:    Prepend this string if an input url is not valid.
                        'auto' for elaborate guessing
     encoding:          Use this encoding instead of the system-specified.
+    extract_flat:      Do not resolve URLs, return the immediate result.
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:
@@ -171,6 +173,7 @@ class YoutubeDL(object):
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
+    exec_cmd:          Arbitrary command to run after downloading
     """
 
     params = None
@@ -193,6 +196,7 @@ class YoutubeDL(object):
         self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
         self._err_file = sys.stderr
         self.params = params
+        self.cache = Cache(self)
 
         if params.get('bidi_workaround', False):
             try:
@@ -423,7 +427,7 @@ class YoutubeDL(object):
             autonumber_templ = '%0' + str(autonumber_size) + 'd'
             template_dict['autonumber'] = autonumber_templ % self._num_downloads
             if template_dict.get('playlist_index') is not None:
-                template_dict['playlist_index'] = '%05d' % template_dict['playlist_index']
+                template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index'])
             if template_dict.get('resolution') is None:
                 if template_dict.get('width') and template_dict.get('height'):
                     template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
@@ -479,7 +483,10 @@ class YoutubeDL(object):
                 return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
         age_limit = self.params.get('age_limit')
         if age_limit is not None:
-            if age_limit < info_dict.get('age_limit', 0):
+            actual_age_limit = info_dict.get('age_limit')
+            if actual_age_limit is None:
+                actual_age_limit = 0
+            if age_limit < actual_age_limit:
                 return 'Skipping "' + title + '" because it is age restricted'
         if self.in_download_archive(info_dict):
             return '%s has already been recorded in archive' % video_title
@@ -558,7 +565,12 @@ class YoutubeDL(object):
         Returns the resolved ie_result.
         """
 
-        result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
+        result_type = ie_result.get('_type', 'video')
+
+        if self.params.get('extract_flat', False):
+            if result_type in ('url', 'url_transparent'):
+                return ie_result
+
         if result_type == 'video':
             self.add_extra_info(ie_result, extra_info)
             return self.process_video_result(ie_result, download=download)
@@ -627,6 +639,7 @@ class YoutubeDL(object):
             for i, entry in enumerate(entries, 1):
                 self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries))
                 extra = {
+                    'n_entries': n_entries,
                     'playlist': playlist,
                     'playlist_index': i + playliststart,
                     'extractor': ie_result['extractor'],

youtube_dl/__init__.py

@@ -66,6 +66,15 @@ __authors__  = (
     'Naglis Jonaitis',
     'Charles Chen',
     'Hassaan Ali',
+    'Dobrosław Żybort',
+    'David Fabijan',
+    'Sebastian Haas',
+    'Alexander Kirk',
+    'Erik Johnson',
+    'Keith Beckman',
+    'Ole Ernst',
+    'Aaron McDaniel (mcd1992)',
+    'Magnus Kolstad',
 )
 
 __license__ = 'Public Domain'
@@ -76,7 +85,6 @@ import optparse
 import os
 import random
 import shlex
-import shutil
 import sys
 
 
@@ -88,7 +96,6 @@ from .utils import (
     decodeOption,
     get_term_width,
     DownloadError,
-    get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,
@@ -112,6 +119,7 @@ from .postprocessor import (
     FFmpegExtractAudioPP,
     FFmpegEmbedSubtitlePP,
     XAttrMetadataPP,
+    ExecAfterDownloadPP,
 )
 
 
@@ -311,6 +319,8 @@ def parseOpts(overrideArguments=None):
             dest='username', metavar='USERNAME', help='account username')
     authentication.add_option('-p', '--password',
             dest='password', metavar='PASSWORD', help='account password')
+    authentication.add_option('-2', '--twofactor',
+            dest='twofactor', metavar='TWOFACTOR', help='two-factor auth code')
     authentication.add_option('-n', '--netrc',
             action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
     authentication.add_option('--video-password',
@@ -507,10 +517,10 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option('--cookies',
             dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
     filesystem.add_option(
-        '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
+        '--cache-dir', dest='cachedir', default=None, metavar='DIR',
         help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
     filesystem.add_option(
-        '--no-cache-dir', action='store_const', const=None, dest='cachedir',
+        '--no-cache-dir', action='store_const', const=False, dest='cachedir',
         help='Disable filesystem caching')
     filesystem.add_option(
         '--rm-cache-dir', action='store_true', dest='rm_cachedir',
@@ -541,7 +551,9 @@ def parseOpts(overrideArguments=None):
         help='Prefer avconv over ffmpeg for running the postprocessors (default)')
     postproc.add_option('--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg',
         help='Prefer ffmpeg over avconv for running the postprocessors')
-
+    postproc.add_option(
+        '--exec', metavar='CMD', dest='exec_cmd',
+        help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'' )
 
     parser.add_option_group(general)
     parser.add_option_group(selection)
@@ -745,6 +757,7 @@ def _real_main(argv=None):
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
+        'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
         'quiet': (opts.quiet or any_printing),
         'no_warnings': opts.no_warnings,
@@ -821,6 +834,7 @@ def _real_main(argv=None):
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
+        'exec_cmd': opts.exec_cmd,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -844,26 +858,20 @@ def _real_main(argv=None):
                 ydl.add_post_processor(FFmpegAudioFixPP())
             ydl.add_post_processor(AtomicParsleyPP())
 
+
+        # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
+        # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
+        if opts.exec_cmd:
+            ydl.add_post_processor(ExecAfterDownloadPP(
+                verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd))
+
         # Update version
         if opts.update_self:
             update_self(ydl.to_screen, opts.verbose)
 
         # Remove cache dir
         if opts.rm_cachedir:
-            if opts.cachedir is None:
+            ydl.cache.remove()
-                ydl.to_screen(u'No cache dir specified (Did you combine --no-cache-dir and --rm-cache-dir?)')
-            else:
-                if ('.cache' not in opts.cachedir) or ('youtube-dl' not in opts.cachedir):
-                    ydl.to_screen(u'Not removing directory %s - this does not look like a cache dir')
-                    retcode = 141
-                else:
-                    ydl.to_screen(
-                        u'Removing cache dir %s .' % opts.cachedir,
-                        skip_eol=True)
-                    if os.path.exists(opts.cachedir):
-                        ydl.to_screen(u'.', skip_eol=True)
-                        shutil.rmtree(opts.cachedir)
-                    ydl.to_screen(u'.')
 
         # Maybe do nothing
         if (len(all_urls) < 1) and (opts.load_info_filename is None):

youtube_dl/cache.py

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

youtube_dl/downloader/common.py

@@ -292,7 +292,7 @@ class FileDownloader(object):
 
     def real_download(self, filename, info_dict):
         """Real download process. Redefine in subclasses."""
-        raise NotImplementedError(u'This method must be implemented by sublcasses')
+        raise NotImplementedError(u'This method must be implemented by subclasses')
 
     def _hook_progress(self, status):
         for ph in self._progress_hooks:

youtube_dl/downloader/hls.py

@@ -3,6 +3,7 @@ import subprocess
 
 from .common import FileDownloader
 from ..utils import (
+    check_executable,
     encodeFilename,
 )
 
@@ -19,13 +20,11 @@ class HlsFD(FileDownloader):
             encodeFilename(tmpfilename, for_subprocess=True)]
 
         for program in ['avconv', 'ffmpeg']:
-            try:
+            if check_executable(program, ['-version']):
-                subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
                 break
-            except (OSError, IOError):
-                pass
         else:
             self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            return False
         cmd = [program] + args
 
         retval = subprocess.call(cmd)
@@ -42,5 +41,5 @@ class HlsFD(FileDownloader):
             return True
         else:
             self.to_stderr(u"\n")
-            self.report_error(u'ffmpeg exited with code %d' % retval)
+            self.report_error(u'%s exited with code %d' % (program, retval))
             return False

youtube_dl/downloader/http.py

@@ -27,8 +27,16 @@ class HttpFD(FileDownloader):
             headers['Youtubedl-user-agent'] = info_dict['user_agent']
         if 'http_referer' in info_dict:
             headers['Referer'] = info_dict['http_referer']
-        basic_request = compat_urllib_request.Request(url, None, headers)
+        add_headers = info_dict.get('http_headers')
-        request = compat_urllib_request.Request(url, None, headers)
+        if add_headers:
+            headers.update(add_headers)
+        data = info_dict.get('http_post_data')
+        http_method = info_dict.get('http_method')
+        basic_request = compat_urllib_request.Request(url, data, headers)
+        request = compat_urllib_request.Request(url, data, headers)
+        if http_method is not None:
+            basic_request.get_method = lambda: http_method
+            request.get_method = lambda: http_method
 
         is_test = self.params.get('test', False)
 
@@ -185,7 +193,8 @@ class HttpFD(FileDownloader):
             self.to_stderr(u"\n")
             self.report_error(u'Did not get any data blocks')
             return False
-        stream.close()
+        if tmpfilename != u'-':
+            stream.close()
         self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))

youtube_dl/downloader/rtmp.py

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

youtube_dl/extractor/__init__.py

@@ -4,12 +4,13 @@ from .addanime import AddAnimeIE
 from .adultswim import AdultSwimIE
 from .aftonbladet import AftonbladetIE
 from .anitube import AnitubeIE
+from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
-from .ard import ARDIE
+from .ard import ARDIE, ARDMediathekIE
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
@@ -23,6 +24,7 @@ from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
+from .beeg import BeegIE
 from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
@@ -65,10 +67,13 @@ from .dailymotion import (
     DailymotionUserIE,
 )
 from .daum import DaumIE
+from .dbtv import DBTVIE
 from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .drtuber import DrTuberIE
 from .drtv import DRTVIE
+from .dump import DumpIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE
@@ -77,12 +82,18 @@ from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
+from .ellentv import (
+    EllenTVIE,
+    EllenTVClipsIE,
+)
 from .elpais import ElPaisIE
-from .empflix import EmpflixIE
+from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
+from .eporner import EpornerIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
+from .expotv import ExpoTVIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
@@ -110,7 +121,10 @@ from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
-from .gameone import GameOneIE
+from .gameone import (
+    GameOneIE,
+    GameOnePlaylistIE,
+)
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gametrailers import GametrailersIE
@@ -121,11 +135,14 @@ from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
+from .grooveshark import GroovesharkIE
 from .hark import HarkIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .hornbunny import HornBunnyIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
+from .howstuffworks import HowStuffWorksIE
 from .huffpost import HuffPostIE
 from .hypem import HypemIE
 from .iconosquare import IconosquareIE
@@ -146,6 +163,7 @@ from .ivi import (
 from .izlesene import IzleseneIE
 from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
+from .jove import JoveIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
 from .jpopsukitv import JpopsukiIE
@@ -176,15 +194,19 @@ from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
+from .ministrygrid import MinistryGridIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
+from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
 from .mlb import MLBIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
+from .mojvideo import MojvideoIE
 from .mooshare import MooshareIE
 from .morningstar import MorningstarIE
 from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
+from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
 from .movshare import MovShareIE
 from .mtv import (
@@ -193,6 +215,7 @@ from .mtv import (
     MTVIggyIE,
 )
 from .musicplayon import MusicPlayOnIE
+from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE
 from .myspass import MySpassIE
@@ -213,6 +236,7 @@ from .niconico import NiconicoIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
+from .nosvideo import NosVideoIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
@@ -224,17 +248,23 @@ from .nrk import (
 from .ntv import NTVIE
 from .nytimes import NYTimesIE
 from .nuvid import NuvidIE
-from .oe1 import OE1IE
 from .ooyala import OoyalaIE
-from .orf import ORFIE
+from .orf import (
+    ORFTVthekIE,
+    ORFOE1IE,
+    ORFFM4IE,
+)
 from .parliamentliveuk import ParliamentLiveUKIE
+from .patreon import PatreonIE
 from .pbs import PBSIE
 from .photobucket import PhotobucketIE
+from .playfm import PlayFMIE
 from .playvid import PlayvidIE
 from .podomatic import PodomaticIE
 from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
+from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .radiofrance import RadioFranceIE
@@ -247,9 +277,10 @@ from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
+from .rtlnl import RtlXlIE
 from .rtlnow import RTLnowIE
 from .rts import RTSIE
-from .rtve import RTVEALaCartaIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE
 from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
@@ -260,6 +291,7 @@ from .rutube import (
 from .rutv import RUTVIE
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
+from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .servingsys import ServingSysIE
@@ -292,10 +324,12 @@ from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
+from .sportdeutschland import SportDeutschlandIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .sunporno import SunPornoIE
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
@@ -315,6 +349,7 @@ from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
+from .tnaflix import TNAFlixIE
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
@@ -327,7 +362,7 @@ from .tutv import TutvIE
 from .tvigle import TvigleIE
 from .tvp import TvpIE
 from .tvplay import TVPlayIE
-from.ubu import UbuIE
+from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
     UdemyCourseIE
@@ -367,11 +402,13 @@ from .vine import (
 from .viki import VikiIE
 from .vk import VKIE
 from .vodlocker import VodlockerIE
+from .vporn import VpornIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
 from .vulture import VultureIE
 from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
+from .wayofthemaster import WayOfTheMasterIE
 from .wdr import (
     WDRIE,
     WDRMobileIE,
@@ -383,6 +420,7 @@ from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .wrzuta import WrzutaIE
 from .xbef import XBefIE
+from .xboxclips import XboxClipsIE
 from .xhamster import XHamsterIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE

youtube_dl/extractor/academicearth.py

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

youtube_dl/extractor/anysex.py

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

youtube_dl/extractor/aol.py

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

youtube_dl/extractor/aparat.py

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

youtube_dl/extractor/appletrailers.py

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

youtube_dl/extractor/ard.py

@@ -10,10 +10,14 @@ from ..utils import (
     qualities,
     compat_urllib_parse_urlparse,
     compat_urllib_parse,
+    int_or_none,
+    parse_duration,
+    unified_strdate,
 )
 
 
-class ARDIE(InfoExtractor):
+class ARDMediathekIE(InfoExtractor):
+    IE_NAME = 'ARD:mediathek'
     _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
@@ -51,6 +55,9 @@ class ARDIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
+            raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
+
         title = self._html_search_regex(
             [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
              r'<meta name="dcterms.title" content="(.*?)"/>',
@@ -125,3 +132,60 @@ class ARDIE(InfoExtractor):
             'formats': formats,
             'thumbnail': thumbnail,
         }
+
+
+class ARDIE(InfoExtractor):
+    _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _TEST = {
+        'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
+        'md5': 'd216c3a86493f9322545e045ddc3eb35',
+        'info_dict': {
+            'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge',
+            'id': '100',
+            'ext': 'mp4',
+            'duration': 2600,
+            'title': 'Die Story im Ersten: Mission unter falscher Flagge',
+            'upload_date': '20140804',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+
+        player_url = mobj.group('mainurl') + '~playerXml.xml'
+        doc = self._download_xml(player_url, display_id)
+        video_node = doc.find('./video')
+        upload_date = unified_strdate(video_node.find('./broadcastDate').text)
+        thumbnail = video_node.find('.//teaserImage//variant/url').text
+
+        formats = []
+        for a in video_node.findall('.//asset'):
+            f = {
+                'format_id': a.attrib['type'],
+                'width': int_or_none(a.find('./frameWidth').text),
+                'height': int_or_none(a.find('./frameHeight').text),
+                'vbr': int_or_none(a.find('./bitrateVideo').text),
+                'abr': int_or_none(a.find('./bitrateAudio').text),
+                'vcodec': a.find('./codecVideo').text,
+                'tbr': int_or_none(a.find('./totalBitrate').text),
+            }
+            if a.find('./serverPrefix').text:
+                f['url'] = a.find('./serverPrefix').text
+                f['playpath'] = a.find('./fileName').text
+            else:
+                f['url'] = a.find('./fileName').text
+            formats.append(f)
+        self._sort_formats(formats)
+
+        return {
+            'id': mobj.group('id'),
+            'formats': formats,
+            'display_id': display_id,
+            'title': video_node.find('./title').text,
+            'duration': parse_duration(video_node.find('./duration').text),
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+        }
+

youtube_dl/extractor/arte.py

@@ -78,7 +78,8 @@ class ArteTVPlus7IE(InfoExtractor):
 
     def _extract_from_webpage(self, webpage, video_id, lang):
         json_url = self._html_search_regex(
-            r'arte_vp_url="(.*?)"', webpage, 'json vp url')
+            [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
+            webpage, 'json vp url')
         return self._extract_from_json_url(json_url, video_id, lang)
 
     def _extract_from_json_url(self, json_url, video_id, lang):
@@ -109,15 +110,19 @@ class ArteTVPlus7IE(InfoExtractor):
             regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
             return any(re.match(r, f['versionCode']) for r in regexes)
         # Some formats may not be in the same language as the url
+        # TODO: Might want not to drop videos that does not match requested language
+        # but to process those formats with lower precedence
         formats = filter(_match_lang, all_formats)
-        formats = list(formats) # in python3 filter returns an iterator
+        formats = list(formats)  # in python3 filter returns an iterator
         if not formats:
             # Some videos are only available in the 'Originalversion'
             # they aren't tagged as being in French or German
-            if all(f['versionCode'] == 'VO' or f['versionCode'] == 'VA' for f in all_formats):
+            # Sometimes there are neither videos of requested lang code
-                formats = all_formats
+            # nor original version videos available
-            else:
+            # For such cases we just take all_formats as is
-                raise ExtractorError(u'The formats list is empty')
+            formats = all_formats
+            if not formats:
+                raise ExtractorError('The formats list is empty')
 
         if re.match(r'[A-Z]Q', formats[0]['quality']) is not None:
             def sort_key(f):
@@ -173,16 +178,26 @@ class ArteTVPlus7IE(InfoExtractor):
 # It also uses the arte_vp_url url from the webpage to extract the information
 class ArteTVCreativeIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:creative'
-    _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/magazine?/(?P<id>.+)'
+    _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/(?:magazine?/)?(?P<id>[^?#]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
         'info_dict': {
-            'id': '050489-002',
+            'id': '72176',
             'ext': 'mp4',
-            'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design',
+            'title': 'Folge 2 - Corporate Design',
+            'upload_date': '20131004',
         },
-    }
+    }, {
+        'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
+        'info_dict': {
+            'id': '160676',
+            'ext': 'mp4',
+            'title': 'Monty Python live (mostly)',
+            'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n',
+            'upload_date': '20140805',
+        }
+    }]
 
 
 class ArteTVFutureIE(ArteTVPlus7IE):

youtube_dl/extractor/bambuser.py

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

youtube_dl/extractor/bandcamp.py

@@ -96,7 +96,7 @@ class BandcampAlbumIE(InfoExtractor):
     IE_NAME = 'Bandcamp:album'
     _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
         'playlist': [
             {
@@ -118,7 +118,13 @@ class BandcampAlbumIE(InfoExtractor):
             'playlistend': 2
         },
         'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
-    }
+    }, {
+        'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
+        'info_dict': {
+            'title': 'Hierophany of the Open Grave',
+        },
+        'playlist_mincount': 9,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/beeg.py

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

youtube_dl/extractor/bliptv.py

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

youtube_dl/extractor/brightcove.py

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

youtube_dl/extractor/cbs.py

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

youtube_dl/extractor/cliphunter.py

@@ -1,11 +1,13 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
-translation_table = {
+_translation_table = {
     'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
     'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
     'y': 'l', 'z': 'i',
@@ -13,6 +15,10 @@ translation_table = {
 }
 
 
+def _decode(s):
+    return ''.join(_translation_table.get(c, c) for c in s)
+
+
 class CliphunterIE(InfoExtractor):
     IE_NAME = 'cliphunter'
 
@@ -22,10 +28,14 @@ class CliphunterIE(InfoExtractor):
     '''
     _TEST = {
         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
-        'file': '1012420.flv',
+        'md5': 'a2ba71eebf523859fe527a61018f723e',
-        'md5': '15e7740f30428abf70f4223478dc1225',
         'info_dict': {
+            'id': '1012420',
+            'ext': 'mp4',
             'title': 'Fun Jynx Maze solo',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'age_limit': 18,
+            'duration': 1317,
         }
     }
 
@@ -35,22 +45,55 @@ class CliphunterIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        video_title = self._search_regex(
+            r'mediaTitle = "([^"]+)"', webpage, 'title')
+
         pl_fiji = self._search_regex(
             r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
         pl_c_qual = self._search_regex(
             r'pl_c_qual = "(.)"', webpage, 'video quality')
-        video_title = self._search_regex(
+        video_url = _decode(pl_fiji)
-            r'mediaTitle = "([^"]+)"', webpage, 'title')
-
-        video_url = ''.join(translation_table.get(c, c) for c in pl_fiji)
-
         formats = [{
             'url': video_url,
-            'format_id': pl_c_qual,
+            'format_id': 'default-%s' % pl_c_qual,
         }]
 
+        qualities_json = self._search_regex(
+            r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
+        qualities_data = json.loads(qualities_json)
+
+        for i, t in enumerate(
+                re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
+            quality_id, crypted_url = t
+            video_url = _decode(crypted_url)
+            f = {
+                'format_id': quality_id,
+                'url': video_url,
+                'quality': i,
+            }
+            if quality_id in qualities_data:
+                qd = qualities_data[quality_id]
+                m = re.match(
+                    r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
+                        \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
+                if m:
+                    f['width'] = int(m.group('width'))
+                    f['height'] = int(m.group('height'))
+                    f['tbr'] = int(m.group('tbr'))
+            formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = self._search_regex(
+            r"var\s+mov_thumb\s*=\s*'([^']+)';",
+            webpage, 'thumbnail', fatal=False)
+        duration = int_or_none(self._search_regex(
+            r'pl_dur\s*=\s*([0-9]+)', webpage, 'duration', fatal=False))
+
         return {
             'id': video_id,
             'title': video_title,
             'formats': formats,
+            'duration': duration,
+            'age_limit': self._rta_search(webpage),
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/comedycentral.py

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

youtube_dl/extractor/common.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import base64
 import hashlib
 import json
@@ -84,6 +86,12 @@ class InfoExtractor(object):
                                  format, irrespective of the file format.
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
+                    * http_referer  HTTP Referer header value to set.
+                    * http_method  HTTP method to use for the download.
+                    * http_headers  A dictionary of additional HTTP headers
+                                 to add to the request.
+                    * http_post_data  Additional data to send with a POST
+                                 request.
     url:            Final video URL.
     ext:            Video filename extension.
     format:         The video format, defaults to ext (used for --get-format)
@@ -108,7 +116,7 @@ class InfoExtractor(object):
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
-    location:       Physical location of the video.
+    location:       Physical location where the video was filmed.
     subtitles:      The subtitle file contents as a dictionary in the format
                     {language: subtitles}.
     duration:       Length of the video in seconds, as an integer.
@@ -196,17 +204,17 @@ class InfoExtractor(object):
             self.report_download_webpage(video_id)
         elif note is not False:
             if video_id is None:
-                self.to_screen(u'%s' % (note,))
+                self.to_screen('%s' % (note,))
             else:
-                self.to_screen(u'%s: %s' % (video_id, note))
+                self.to_screen('%s: %s' % (video_id, note))
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if errnote is False:
                 return False
             if errnote is None:
-                errnote = u'Unable to download webpage'
+                errnote = 'Unable to download webpage'
-            errmsg = u'%s: %s' % (errnote, compat_str(err))
+            errmsg = '%s: %s' % (errnote, compat_str(err))
             if fatal:
                 raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
             else:
@@ -243,7 +251,7 @@ class InfoExtractor(object):
                 url = url_or_request.get_full_url()
             except AttributeError:
                 url = url_or_request
-            self.to_screen(u'Dumping request to ' + url)
+            self.to_screen('Dumping request to ' + url)
             dump = base64.b64encode(webpage_bytes).decode('ascii')
             self._downloader.to_screen(dump)
         if self._downloader.params.get('write_pages', False):
@@ -253,11 +261,11 @@ class InfoExtractor(object):
                 url = url_or_request
             basen = '%s_%s' % (video_id, url)
             if len(basen) > 240:
-                h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
+                h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
                 basen = basen[:240 - len(h)] + h
             raw_filename = basen + '.dump'
             filename = sanitize_filename(raw_filename, restricted=True)
-            self.to_screen(u'Saving request to ' + filename)
+            self.to_screen('Saving request to ' + filename)
             with open(filename, 'wb') as outf:
                 outf.write(webpage_bytes)
 
@@ -266,14 +274,14 @@ class InfoExtractor(object):
         except LookupError:
             content = webpage_bytes.decode('utf-8', 'replace')
 
-        if (u'<title>Access to this site is blocked</title>' in content and
+        if ('<title>Access to this site is blocked</title>' in content and
-                u'Websense' in content[:512]):
+                'Websense' in content[:512]):
-            msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
+            msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
             blocked_iframe = self._html_search_regex(
                 r'<iframe src="([^"]+)"', content,
-                u'Websense information URL', default=None)
+                'Websense information URL', default=None)
             if blocked_iframe:
-                msg += u' Visit %s for more details' % blocked_iframe
+                msg += ' Visit %s for more details' % blocked_iframe
             raise ExtractorError(msg, expected=True)
 
         return (content, urlh)
@@ -288,7 +296,7 @@ class InfoExtractor(object):
             return content
 
     def _download_xml(self, url_or_request, video_id,
-                      note=u'Downloading XML', errnote=u'Unable to download XML',
+                      note='Downloading XML', errnote='Unable to download XML',
                       transform_source=None, fatal=True):
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(
@@ -300,8 +308,8 @@ class InfoExtractor(object):
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
 
     def _download_json(self, url_or_request, video_id,
-                       note=u'Downloading JSON metadata',
+                       note='Downloading JSON metadata',
-                       errnote=u'Unable to download JSON metadata',
+                       errnote='Unable to download JSON metadata',
                        transform_source=None,
                        fatal=True):
         json_string = self._download_webpage(
@@ -316,29 +324,29 @@ class InfoExtractor(object):
             raise ExtractorError('Failed to download JSON', cause=ve)
 
     def report_warning(self, msg, video_id=None):
-        idstr = u'' if video_id is None else u'%s: ' % video_id
+        idstr = '' if video_id is None else '%s: ' % video_id
         self._downloader.report_warning(
-            u'[%s] %s%s' % (self.IE_NAME, idstr, msg))
+            '[%s] %s%s' % (self.IE_NAME, idstr, msg))
 
     def to_screen(self, msg):
         """Print msg to screen, prefixing it with '[ie_name]'"""
-        self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
+        self._downloader.to_screen('[%s] %s' % (self.IE_NAME, msg))
 
     def report_extraction(self, id_or_name):
         """Report information extraction."""
-        self.to_screen(u'%s: Extracting information' % id_or_name)
+        self.to_screen('%s: Extracting information' % id_or_name)
 
     def report_download_webpage(self, video_id):
         """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
+        self.to_screen('%s: Downloading webpage' % video_id)
 
     def report_age_confirmation(self):
         """Report attempt to confirm age."""
-        self.to_screen(u'Confirming age')
+        self.to_screen('Confirming age')
 
     def report_login(self):
         """Report attempt to log in."""
-        self.to_screen(u'Logging in')
+        self.to_screen('Logging in')
 
     #Methods for following #608
     @staticmethod
@@ -378,7 +386,7 @@ class InfoExtractor(object):
                     break
 
         if os.name != 'nt' and sys.stderr.isatty():
-            _name = u'\033[0;34m%s\033[0m' % name
+            _name = '\033[0;34m%s\033[0m' % name
         else:
             _name = name
 
@@ -388,10 +396,10 @@ class InfoExtractor(object):
         elif default is not _NO_DEFAULT:
             return default
         elif fatal:
-            raise RegexNotFoundError(u'Unable to extract %s' % _name)
+            raise RegexNotFoundError('Unable to extract %s' % _name)
         else:
-            self._downloader.report_warning(u'unable to extract %s; '
+            self._downloader.report_warning('unable to extract %s; '
-                u'please report this issue on http://yt-dl.org/bug' % _name)
+                'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
     def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
@@ -430,10 +438,26 @@ class InfoExtractor(object):
                 else:
                     raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
             except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
+                self._downloader.report_warning('parsing .netrc: %s' % compat_str(err))
         
         return (username, password)
 
+    def _get_tfa_info(self):
+        """
+        Get the two-factor authentication info
+        TODO - asking the user will be required for sms/phone verify
+        currently just uses the command line option
+        If there's no info available, return None
+        """
+        if self._downloader is None:
+            return None
+        downloader_params = self._downloader.params
+
+        if downloader_params.get('twofactor', None) is not None:
+            return downloader_params['twofactor']
+
+        return None
+
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
@@ -454,7 +478,7 @@ class InfoExtractor(object):
         return unescapeHTML(escaped)
 
     def _og_search_thumbnail(self, html, **kargs):
-        return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)
+        return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs)
 
     def _og_search_description(self, html, **kargs):
         return self._og_search_property('description', html, fatal=False, **kargs)
@@ -463,8 +487,9 @@ class InfoExtractor(object):
         return self._og_search_property('title', html, **kargs)
 
     def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
-        regexes = self._og_regexes('video')
+        regexes = self._og_regexes('video') + self._og_regexes('video:url')
-        if secure: regexes = self._og_regexes('video:secure_url') + regexes
+        if secure:
+            regexes = self._og_regexes('video:secure_url') + regexes
         return self._html_search_regex(regexes, html, name, **kargs)
 
     def _og_search_url(self, html, **kargs):
@@ -512,7 +537,7 @@ class InfoExtractor(object):
 
     def _sort_formats(self, formats):
         if not formats:
-            raise ExtractorError(u'No video formats found')
+            raise ExtractorError('No video formats found')
 
         def _formats_key(f):
             # TODO remove the following workaround
@@ -532,9 +557,9 @@ class InfoExtractor(object):
 
             if f.get('vcodec') == 'none':  # audio only
                 if self._downloader.params.get('prefer_free_formats'):
-                    ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus']
+                    ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                 else:
-                    ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a']
+                    ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a']
                 ext_preference = 0
                 try:
                     audio_ext_preference = ORDER.index(f['ext'])
@@ -542,9 +567,9 @@ class InfoExtractor(object):
                     audio_ext_preference = -1
             else:
                 if self._downloader.params.get('prefer_free_formats'):
-                    ORDER = [u'flv', u'mp4', u'webm']
+                    ORDER = ['flv', 'mp4', 'webm']
                 else:
-                    ORDER = [u'webm', u'flv', u'mp4']
+                    ORDER = ['webm', 'flv', 'mp4']
                 try:
                     ext_preference = ORDER.index(f['ext'])
                 except ValueError:
@@ -586,7 +611,7 @@ class InfoExtractor(object):
 
     def _sleep(self, timeout, video_id, msg_template=None):
         if msg_template is None:
-            msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds'
+            msg_template = '%(video_id)s: Waiting for %(timeout)s seconds'
         msg = msg_template % {'video_id': video_id, 'timeout': timeout}
         self.to_screen(msg)
         time.sleep(timeout)
@@ -597,11 +622,15 @@ class InfoExtractor(object):
             'Unable to download f4m manifest')
 
         formats = []
-        for media_el in manifest.findall('{http://ns.adobe.com/f4m/1.0}media'):
+        media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
+        for i, media_el in enumerate(media_nodes):
+            tbr = int_or_none(media_el.attrib.get('bitrate'))
+            format_id = 'f4m-%d' % (i if tbr is None else tbr)
             formats.append({
+                'format_id': format_id,
                 'url': manifest_url,
                 'ext': 'flv',
-                'tbr': int_or_none(media_el.attrib.get('bitrate')),
+                'tbr': tbr,
                 'width': int_or_none(media_el.attrib.get('width')),
                 'height': int_or_none(media_el.attrib.get('height')),
             })
@@ -609,6 +638,61 @@ class InfoExtractor(object):
 
         return formats
 
+    def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None):
+        formats = [{
+            'format_id': 'm3u8-meta',
+            'url': m3u8_url,
+            'ext': ext,
+            'protocol': 'm3u8',
+            'preference': -1,
+            'resolution': 'multiple',
+            'format_note': 'Quality selection URL',
+        }]
+
+        m3u8_doc = self._download_webpage(m3u8_url, video_id)
+        last_info = None
+        kv_rex = re.compile(
+            r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')
+        for line in m3u8_doc.splitlines():
+            if line.startswith('#EXT-X-STREAM-INF:'):
+                last_info = {}
+                for m in kv_rex.finditer(line):
+                    v = m.group('val')
+                    if v.startswith('"'):
+                        v = v[1:-1]
+                    last_info[m.group('key')] = v
+            elif line.startswith('#') or not line.strip():
+                continue
+            else:
+                if last_info is None:
+                    formats.append({'url': line})
+                    continue
+                tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
+
+                f = {
+                    'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)),
+                    'url': line.strip(),
+                    'tbr': tbr,
+                    'ext': ext,
+                }
+                codecs = last_info.get('CODECS')
+                if codecs:
+                    # TODO: looks like video codec is not always necessarily goes first
+                    va_codecs = codecs.split(',')
+                    if va_codecs[0]:
+                        f['vcodec'] = va_codecs[0].partition('.')[0]
+                    if len(va_codecs) > 1 and va_codecs[1]:
+                        f['acodec'] = va_codecs[1].partition('.')[0]
+                resolution = last_info.get('RESOLUTION')
+                if resolution:
+                    width_str, height_str = resolution.split('x')
+                    f['width'] = int(width_str)
+                    f['height'] = int(height_str)
+                formats.append(f)
+                last_info = {}
+        self._sort_formats(formats)
+        return formats
+
 
 class SearchInfoExtractor(InfoExtractor):
     """
@@ -628,7 +712,7 @@ class SearchInfoExtractor(InfoExtractor):
     def _real_extract(self, query):
         mobj = re.match(self._make_valid_url(), query)
         if mobj is None:
-            raise ExtractorError(u'Invalid search query "%s"' % query)
+            raise ExtractorError('Invalid search query "%s"' % query)
 
         prefix = mobj.group('prefix')
         query = mobj.group('query')
@@ -639,9 +723,9 @@ class SearchInfoExtractor(InfoExtractor):
         else:
             n = int(prefix)
             if n <= 0:
-                raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
+                raise ExtractorError('invalid download number %s for query "%s"' % (n, query))
             elif n > self._MAX_RESULTS:
-                self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
+                self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
                 n = self._MAX_RESULTS
             return self._get_n_results(query, n)
 

youtube_dl/extractor/crunchyroll.py

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

youtube_dl/extractor/cspan.py

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

youtube_dl/extractor/dailymotion.py

@@ -1,3 +1,6 @@
+#coding: utf-8
+from __future__ import unicode_literals
+
 import re
 import json
 import itertools
@@ -28,51 +31,53 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
     """Information Extractor for Dailymotion"""
 
     _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
-    IE_NAME = u'dailymotion'
+    IE_NAME = 'dailymotion'
 
     _FORMATS = [
-        (u'stream_h264_ld_url', u'ld'),
+        ('stream_h264_ld_url', 'ld'),
-        (u'stream_h264_url', u'standard'),
+        ('stream_h264_url', 'standard'),
-        (u'stream_h264_hq_url', u'hq'),
+        ('stream_h264_hq_url', 'hq'),
-        (u'stream_h264_hd_url', u'hd'),
+        ('stream_h264_hd_url', 'hd'),
-        (u'stream_h264_hd1080_url', u'hd180'),
+        ('stream_h264_hd1080_url', 'hd180'),
     ]
 
     _TESTS = [
         {
-            u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
+            'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
-            u'file': u'x33vw9.mp4',
+            'md5': '392c4b85a60a90dc4792da41ce3144eb',
-            u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
+            'info_dict': {
-            u'info_dict': {
+                'id': 'x33vw9',
-                u"uploader": u"Amphora Alex and Van .", 
+                'ext': 'mp4',
-                u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
+                'uploader': 'Amphora Alex and Van .',
+                'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"',
             }
         },
         # Vevo video
         {
-            u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
+            'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
-            u'file': u'USUV71301934.mp4',
+            'info_dict': {
-            u'info_dict': {
+                'title': 'Roar (Official)',
-                u'title': u'Roar (Official)',
+                'id': 'USUV71301934',
-                u'uploader': u'Katy Perry',
+                'ext': 'mp4',
-                u'upload_date': u'20130905',
+                'uploader': 'Katy Perry',
+                'upload_date': '20130905',
             },
-            u'params': {
+            'params': {
-                u'skip_download': True,
+                'skip_download': True,
             },
-            u'skip': u'VEVO is only available in some countries',
+            'skip': 'VEVO is only available in some countries',
         },
         # age-restricted video
         {
-            u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
+            'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
-            u'file': u'xyh2zz.mp4',
+            'md5': '0d667a7b9cebecc3c89ee93099c4159d',
-            u'md5': u'0d667a7b9cebecc3c89ee93099c4159d',
+            'info_dict': {
-            u'info_dict': {
+                'id': 'xyh2zz',
-                u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
+                'ext': 'mp4',
-                u'uploader': 'HotWaves1012',
+                'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
-                u'age_limit': 18,
+                'uploader': 'HotWaves1012',
+                'age_limit': 18,
             }
-
         }
     ]
 
@@ -97,8 +102,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             webpage)
         if m_vevo is not None:
             vevo_id = m_vevo.group('id')
-            self.to_screen(u'Vevo video detected: %s' % vevo_id)
+            self.to_screen('Vevo video detected: %s' % vevo_id)
-            return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
+            return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 
         age_limit = self._rta_search(webpage)
 
@@ -109,7 +114,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
         embed_page = self._download_webpage(embed_url, video_id,
-                                            u'Downloading embed page')
+                                            'Downloading embed page')
         info = self._search_regex(r'var info = ({.*?}),$', embed_page,
             'video info', flags=re.MULTILINE)
         info = json.loads(info)
@@ -134,7 +139,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
                     'height': height,
                 })
         if not formats:
-            raise ExtractorError(u'Unable to extract video URL')
+            raise ExtractorError('Unable to extract video URL')
 
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, webpage)
@@ -143,7 +148,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             return
 
         view_count = self._search_regex(
-            r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False)
+            r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, 'view count', fatal=False)
         if view_count is not None:
             view_count = str_to_int(view_count)
 
@@ -165,28 +170,35 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
                 video_id, note=False)
         except ExtractorError as err:
-            self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+            self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
             return {}
         info = json.loads(sub_list)
         if (info['total'] > 0):
             sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
             return sub_lang_list
-        self._downloader.report_warning(u'video doesn\'t have subtitles')
+        self._downloader.report_warning('video doesn\'t have subtitles')
         return {}
 
 
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
-    IE_NAME = u'dailymotion:playlist'
+    IE_NAME = 'dailymotion:playlist'
     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
     _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
+    _TESTS = [{
+        'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
+        'info_dict': {
+            'title': 'SPORT',
+        },
+        'playlist_mincount': 20,
+    }]
 
     def _extract_entries(self, id):
         video_ids = []
         for pagenum in itertools.count(1):
             request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
             webpage = self._download_webpage(request,
-                                             id, u'Downloading page %s' % pagenum)
+                                             id, 'Downloading page %s' % pagenum)
 
             video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
 
@@ -209,9 +221,17 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 
 class DailymotionUserIE(DailymotionPlaylistIE):
-    IE_NAME = u'dailymotion:user'
+    IE_NAME = 'dailymotion:user'
     _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
+    _TESTS = [{
+        'url': 'https://www.dailymotion.com/user/nqtv',
+        'info_dict': {
+            'id': 'nqtv',
+            'title': 'Rémi Gaillard',
+        },
+        'playlist_mincount': 100,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -219,7 +239,7 @@ class DailymotionUserIE(DailymotionPlaylistIE):
         webpage = self._download_webpage(url, user)
         full_user = unescapeHTML(self._html_search_regex(
             r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
-            webpage, u'user', flags=re.DOTALL))
+            webpage, 'user'))
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/dbtv.py

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

youtube_dl/extractor/dfb.py

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

youtube_dl/extractor/dropbox.py

@@ -11,8 +11,7 @@ from ..utils import compat_urllib_parse_unquote
 class DropboxIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)'
     _TEST = {
-        'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4',
+        'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
-        'md5': '8a3d905427a6951ccb9eb292f154530b',
         'info_dict': {
             'id': 'nelirfsxnmcfbfh',
             'ext': 'mp4',
@@ -25,7 +24,9 @@ class DropboxIE(InfoExtractor):
         video_id = mobj.group('id')
         fn = compat_urllib_parse_unquote(mobj.group('title'))
         title = os.path.splitext(fn)[0]
-        video_url = url + '?dl=1'
+        video_url = (
+            re.sub(r'[?&]dl=0', '', url) +
+            ('?' if '?' in url else '&') + 'dl=1')
 
         return {
             'id': video_id,

youtube_dl/extractor/drtuber.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import str_to_int
+
+
+class DrTuberIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
+    _TEST = {
+        'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
+        'md5': '93e680cf2536ad0dfb7e74d94a89facd',
+        'info_dict': {
+            'id': '1740434',
+            'display_id': 'hot-perky-blonde-naked-golf',
+            'ext': 'mp4',
+            'title': 'Hot Perky Blonde Naked Golf',
+            'like_count': int,
+            'dislike_count': int,
+            'comment_count': int,
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._html_search_regex(
+            r'<source src="([^"]+)"', webpage, 'video URL')
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
+
+        thumbnail = self._html_search_regex(
+            r'poster="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        like_count = str_to_int(self._html_search_regex(
+            r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
+            webpage, 'like count', fatal=False))
+        dislike_count = str_to_int(self._html_search_regex(
+            r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
+            webpage, 'like count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<span class="comments_count">([\d,\.]+)</span>',
+            webpage, 'comment count', fatal=False))
+
+        cats_str = self._html_search_regex(
+            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
+        categories = None if cats_str is None else cats_str.split(' ')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
+            'categories': categories,
+            'age_limit': self._rta_search(webpage),
+        }

youtube_dl/extractor/dump.py

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

youtube_dl/extractor/ebaumsworld.py

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

youtube_dl/extractor/eighttracks.py

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

youtube_dl/extractor/ellentv.py

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

youtube_dl/extractor/empflix.py

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

youtube_dl/extractor/eporner.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    str_to_int,
+)
+
+
+class EpornerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)'
+    _TEST = {
+        'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
+        'md5': '3b427ae4b9d60619106de3185c2987cd',
+        'info_dict': {
+            'id': '95008',
+            'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
+            'ext': 'flv',
+            'title': 'Infamous Tiffany Teen Strip Tease Video',
+            'duration': 194,
+            'view_count': int,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+        title = self._html_search_regex(
+            r'<title>(.*?) - EPORNER', webpage, 'title')
+
+        redirect_code = self._html_search_regex(
+            r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
+            webpage, 'redirect_code')
+        redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
+        player_code = self._download_webpage(
+            redirect_url, display_id, note='Downloading player config')
+
+        sources = self._search_regex(
+            r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
+
+        formats = []
+        for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
+            fmt = {
+                'url': video_url,
+                'format_id': format_id,
+            }
+            m = re.search(r'^(\d+)', format_id)
+            if m:
+                fmt['height'] = int(m.group(1))
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        duration = parse_duration(self._search_regex(
+            r'class="mbtim">([0-9:]+)</div>', webpage, 'duration',
+            fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
+            webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': self._rta_search(webpage),
+        }

youtube_dl/extractor/escapist.py

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

youtube_dl/extractor/everyonesmixtape.py

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

youtube_dl/extractor/expotv.py

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

youtube_dl/extractor/facebook.py

@@ -20,15 +20,15 @@ from ..utils import (
 class FacebookIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         https?://(?:\w+\.)?facebook\.com/
-        (?:[^#?]*\#!/)?
+        (?:[^#]*?\#!/)?
-        (?:video/video\.php|photo\.php|video/embed)\?(?:.*?)
+        (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
         (?:v|video_id)=(?P<id>[0-9]+)
         (?:.*)'''
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
     IE_NAME = 'facebook'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.facebook.com/photo.php?v=120708114770723',
         'md5': '48975a41ccc4b7a581abd68651c1a5a8',
         'info_dict': {
@@ -37,7 +37,10 @@ class FacebookIE(InfoExtractor):
             'duration': 279,
             'title': 'PEOPLE ARE AWESOME 2013',
         }
-    }
+    }, {
+        'url': 'https://www.facebook.com/video.php?v=10204634152394104',
+        'only_matching': True,
+    }]
 
     def _login(self):
         (useremail, password) = self._get_login_info()
@@ -76,7 +79,8 @@ class FacebookIE(InfoExtractor):
 
             check_form = {
                 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'),
-                'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'),
+                'h': self._search_regex(
+                    r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
                 'name_action_selected': 'dont_save',
             }
             check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))

youtube_dl/extractor/firedrive.py

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

youtube_dl/extractor/gameone.py

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

youtube_dl/extractor/generic.py

@@ -8,18 +8,20 @@ import re
 from .common import InfoExtractor
 from .youtube import YoutubeIE
 from ..utils import (
-    compat_urllib_error,
     compat_urllib_parse,
-    compat_urllib_request,
     compat_urlparse,
     compat_xml_parse_error,
 
+    determine_ext,
     ExtractorError,
+    float_or_none,
     HEADRequest,
+    orderedSet,
     parse_xml,
     smuggle_url,
     unescapeHTML,
     unified_strdate,
+    unsmuggle_url,
     url_basename,
 )
 from .brightcove import BrightcoveIE
@@ -289,6 +291,97 @@ class GenericIE(InfoExtractor):
                 'description': 'Mario\'s life in the fast lane has never looked so good.',
             },
         },
+        # YouTube embed via <data-embed-url="">
+        {
+            'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
+            'info_dict': {
+                'id': 'jpSGZsgga_I',
+                'ext': 'mp4',
+                'title': 'Asphalt 8: Airborne - Launch Trailer',
+                'uploader': 'Gameloft',
+                'uploader_id': 'gameloft',
+                'upload_date': '20130821',
+                'description': 'md5:87bd95f13d8be3e7da87a5f2c443106a',
+            },
+            'params': {
+                'skip_download': True,
+            }
+        },
+        # Camtasia studio
+        {
+            'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
+            'playlist': [{
+                'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
+                'info_dict': {
+                    'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
+                    'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
+                    'ext': 'flv',
+                    'duration': 2235.90,
+                }
+            }, {
+                'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
+                'info_dict': {
+                    'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
+                    'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
+                    'ext': 'flv',
+                    'duration': 2235.93,
+                }
+            }],
+            'info_dict': {
+                'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
+            }
+        },
+        # Flowplayer
+        {
+            'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
+            'md5': '9d65602bf31c6e20014319c7d07fba27',
+            'info_dict': {
+                'id': '5123ea6d5e5a7',
+                'ext': 'mp4',
+                'age_limit': 18,
+                'uploader': 'www.handjobhub.com',
+                'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
+            }
+        },
+        # RSS feed
+        {
+            'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+            'info_dict': {
+                'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+                'title': 'Zero Punctuation',
+                'description': 're:'
+            },
+            'playlist_mincount': 11,
+        },
+        # Multiple brightcove videos
+        # https://github.com/rg3/youtube-dl/issues/2283
+        {
+            'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
+            'info_dict': {
+                'id': 'always-never',
+                'title': 'Always / Never - The New Yorker',
+            },
+            'playlist_count': 3,
+            'params': {
+                'extract_flat': False,
+                'skip_download': True,
+            }
+        },
+        # MLB embed
+        {
+            'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
+            'md5': '96f09a37e44da40dd083e12d9a683327',
+            'info_dict': {
+                'id': '33322633',
+                'ext': 'mp4',
+                'title': 'Ump changes call to ball',
+                'description': 'md5:71c11215384298a172a6dcb4c2e20685',
+                'duration': 48,
+                'timestamp': 1401537900,
+                'upload_date': '20140531',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -301,58 +394,6 @@ class GenericIE(InfoExtractor):
         """Report information extraction."""
         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
 
-    def _send_head(self, url):
-        """Check if it is a redirect, like url shorteners, in case return the new url."""
-
-        class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
-            """
-            Subclass the HTTPRedirectHandler to make it use our
-            HEADRequest also on the redirected URL
-            """
-            def redirect_request(self, req, fp, code, msg, headers, newurl):
-                if code in (301, 302, 303, 307):
-                    newurl = newurl.replace(' ', '%20')
-                    newheaders = dict((k,v) for k,v in req.headers.items()
-                                      if k.lower() not in ("content-length", "content-type"))
-                    try:
-                        # This function was deprecated in python 3.3 and removed in 3.4
-                        origin_req_host = req.get_origin_req_host()
-                    except AttributeError:
-                        origin_req_host = req.origin_req_host
-                    return HEADRequest(newurl,
-                                       headers=newheaders,
-                                       origin_req_host=origin_req_host,
-                                       unverifiable=True)
-                else:
-                    raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
-        class HTTPMethodFallback(compat_urllib_request.BaseHandler):
-            """
-            Fallback to GET if HEAD is not allowed (405 HTTP error)
-            """
-            def http_error_405(self, req, fp, code, msg, headers):
-                fp.read()
-                fp.close()
-
-                newheaders = dict((k,v) for k,v in req.headers.items()
-                                  if k.lower() not in ("content-length", "content-type"))
-                return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
-                                                 headers=newheaders,
-                                                 origin_req_host=req.get_origin_req_host(),
-                                                 unverifiable=True))
-
-        # Build our opener
-        opener = compat_urllib_request.OpenerDirector()
-        for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
-                        HTTPMethodFallback, HEADRedirectHandler,
-                        compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
-            opener.add_handler(handler())
-
-        response = opener.open(HEADRequest(url))
-        if response is None:
-            raise ExtractorError('Invalid URL protocol')
-        return response
-
     def _extract_rss(self, url, video_id, doc):
         playlist_title = doc.find('./channel/title').text
         playlist_desc_el = doc.find('./channel/description')
@@ -372,6 +413,43 @@ class GenericIE(InfoExtractor):
             'entries': entries,
         }
 
+    def _extract_camtasia(self, url, video_id, webpage):
+        """ Returns None if no camtasia video can be found. """
+
+        camtasia_cfg = self._search_regex(
+            r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
+            webpage, 'camtasia configuration file', default=None)
+        if camtasia_cfg is None:
+            return None
+
+        title = self._html_search_meta('DC.title', webpage, fatal=True)
+
+        camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
+        camtasia_cfg = self._download_xml(
+            camtasia_url, video_id,
+            note='Downloading camtasia configuration',
+            errnote='Failed to download camtasia configuration')
+        fileset_node = camtasia_cfg.find('./playlist/array/fileset')
+
+        entries = []
+        for n in fileset_node.getchildren():
+            url_n = n.find('./uri')
+            if url_n is None:
+                continue
+
+            entries.append({
+                'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
+                'title': '%s - %s' % (title, n.tag),
+                'url': compat_urlparse.urljoin(url, url_n.text),
+                'duration': float_or_none(n.find('./duration').text),
+            })
+
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            'title': title,
+        }
+
     def _real_extract(self, url):
         if url.startswith('//'):
             return {
@@ -408,17 +486,31 @@ class GenericIE(InfoExtractor):
             else:
                 assert ':' in default_search
                 return self.url_result(default_search + url)
-        video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
+
+        url, smuggled_data = unsmuggle_url(url)
+        force_videoid = None
+        if smuggled_data and 'force_videoid' in smuggled_data:
+            force_videoid = smuggled_data['force_videoid']
+            video_id = force_videoid
+        else:
+            video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
 
         self.to_screen('%s: Requesting header' % video_id)
 
-        try:
+        head_req = HEADRequest(url)
-            response = self._send_head(url)
+        response = self._request_webpage(
+            head_req, video_id,
+            note=False, errnote='Could not send HEAD request to %s' % url,
+            fatal=False)
 
+        if response is not False:
             # Check for redirect
             new_url = response.geturl()
             if url != new_url:
                 self.report_following_redirect(new_url)
+                if force_videoid:
+                    new_url = smuggle_url(
+                        new_url, {'force_videoid': force_videoid})
                 return self.url_result(new_url)
 
             # Check for direct link to a video
@@ -439,10 +531,6 @@ class GenericIE(InfoExtractor):
                     'upload_date': upload_date,
                 }
 
-        except compat_urllib_error.HTTPError:
-            # This may be a stupid server that doesn't like HEAD, our UA, or so
-            pass
-
         try:
             webpage = self._download_webpage(url, video_id)
         except ValueError:
@@ -460,6 +548,11 @@ class GenericIE(InfoExtractor):
         except compat_xml_parse_error:
             pass
 
+        # Is it a Camtasia project?
+        camtasia_res = self._extract_camtasia(url, video_id, webpage)
+        if camtasia_res is not None:
+            return camtasia_res
+
         # Sometimes embedded video player is hidden behind percent encoding
         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
         # Unescaping the whole page allows to handle those cases in a generic way
@@ -475,10 +568,26 @@ class GenericIE(InfoExtractor):
             r'(?s)<title>(.*?)</title>', webpage, 'video title',
             default='video')
 
+        # Try to detect age limit automatically
+        age_limit = self._rta_search(webpage)
+        # And then there are the jokers who advertise that they use RTA,
+        # but actually don't.
+        AGE_LIMIT_MARKERS = [
+            r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
+        ]
+        if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
+            age_limit = 18
+
         # video uploader is domain name
         video_uploader = self._search_regex(
             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
 
+        # Helper method
+        def _playlist_from_matches(matches, getter, ie=None):
+            urlrs = orderedSet(self.url_result(getter(m), ie) for m in matches)
+            return self.playlist_result(
+                urlrs, playlist_id=video_id, playlist_title=video_title)
+
         # Look for BrightCove:
         bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
         if bc_urls:
@@ -514,6 +623,7 @@ class GenericIE(InfoExtractor):
         matches = re.findall(r'''(?x)
             (?:
                 <iframe[^>]+?src=|
+                data-video-url=|
                 <embed[^>]+?src=|
                 embedSWF\(?:\s*
             )
@@ -522,19 +632,15 @@ class GenericIE(InfoExtractor):
                 (?:embed|v)/.+?)
             \1''', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
+            return _playlist_from_matches(
-                     for tuppl in matches]
+                matches, lambda m: unescapeHTML(m[1]), ie='Youtube')
-            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]))
+            return _playlist_from_matches(
-                     for tuppl in matches]
+                matches, lambda m: unescapeHTML(m[1]))
-            return self.playlist_result(
-                urlrs, playlist_id=video_id, playlist_title=video_title)
 
         # Look for embedded Wistia player
         match = re.search(
@@ -553,7 +659,7 @@ class GenericIE(InfoExtractor):
         mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
         if mobj:
             return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV')
-        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage)
+        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
         if mobj:
             return self.url_result(mobj.group(1), 'BlipTV')
 
@@ -648,10 +754,8 @@ class GenericIE(InfoExtractor):
         # Look for funnyordie embed
         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
+            return _playlist_from_matches(
-                     for eurl in matches]
+                matches, getter=unescapeHTML, ie='FunnyOrDie')
-            return self.playlist_result(
-                urlrs, playlist_id=video_id, playlist_title=video_title)
 
         # Look for embedded RUTV player
         rutv_url = RUTVIE._extract_url(webpage)
@@ -706,6 +810,26 @@ class GenericIE(InfoExtractor):
             url = unescapeHTML(mobj.group('url'))
             return self.url_result(url, ie='MTVServicesEmbedded')
 
+        # Look for embedded yahoo player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Yahoo')
+
+        # Look for embedded sbs.com.au player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'SBS')
+
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'MLB')
+
         # Start with something easy: JW Player in SWFObject
         found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if not found:
@@ -723,6 +847,14 @@ class GenericIE(InfoExtractor):
         if not found:
             # Broaden the findall a little bit: JWPlayer JS loader
             found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+        if not found:
+            # Flow player
+            found = re.findall(r'''(?xs)
+                flowplayer\("[^"]+",\s*
+                    \{[^}]+?\}\s*,
+                    \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
+                        ["']?url["']?\s*:\s*["']([^"']+)["']
+            ''', webpage)
         if not found:
             # Try to find twitter cards info
             found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@@ -732,10 +864,16 @@ class GenericIE(InfoExtractor):
             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
-                found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
+                def check_video(vurl):
+                    vpath = compat_urlparse.urlparse(vurl).path
+                    vext = determine_ext(vpath)
+                    return '.' in vpath and vext not in ('swf', 'png', 'jpg')
+                found = list(filter(
+                    check_video,
+                    re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)))
         if not found:
             # HTML5 video
-            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage)
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage)
         if not found:
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
@@ -769,6 +907,7 @@ class GenericIE(InfoExtractor):
                 'url': video_url,
                 'uploader': video_uploader,
                 'title': video_title,
+                'age_limit': age_limit,
             })
 
         if len(entries) == 1:

youtube_dl/extractor/googlesearch.py

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

youtube_dl/extractor/grooveshark.py

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

youtube_dl/extractor/hornbunny.py

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

youtube_dl/extractor/howstuffworks.py

@@ -0,0 +1,134 @@
+from __future__ import unicode_literals
+
+import re
+import json
+import random
+import string
+
+from .common import InfoExtractor
+from ..utils import find_xpath_attr
+
+
+class HowStuffWorksIE(InfoExtractor):
+    _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm'
+    _TESTS = [
+        {
+            'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm',
+            'info_dict': {
+                'id': '450221',
+                'display_id': 'cool-jobs-iditarod-musher',
+                'ext': 'flv',
+                'title': 'Cool Jobs - Iditarod Musher',
+                'description': 'md5:82bb58438a88027b8186a1fccb365f90',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                # md5 is not consistent
+                'skip_download': True
+            }
+        },
+        {
+            'url': 'http://adventure.howstuffworks.com/39516-deadliest-catch-jakes-farewell-pots-video.htm',
+            'info_dict': {
+                'id': '553470',
+                'display_id': 'deadliest-catch-jakes-farewell-pots',
+                'ext': 'mp4',
+                'title': 'Deadliest Catch: Jake\'s Farewell Pots',
+                'description': 'md5:9632c346d5e43ee238028c9cefd8dbbc',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                # md5 is not consistent
+                'skip_download': True
+            }
+        },
+        {
+            'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm',
+            'info_dict': {
+                'id': '440011',
+                'display_id': 'sword-swallowing-1-by-dan-meyer',
+                'ext': 'flv',
+                'title': 'Sword Swallowing #1 by Dan Meyer',
+                'description': 'md5:b2409e88172913e2e7d3d1159b0ef735',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                # md5 is not consistent
+                'skip_download': True
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        webpage = self._download_webpage(url, display_id)
+
+        content_id = self._search_regex(r'var siteSectionId="(\d+)";', webpage, 'content id')
+
+        mp4 = self._search_regex(
+            r'''(?xs)var\s+clip\s*=\s*{\s*
+                .+?\s*
+                content_id\s*:\s*%s\s*,\s*
+                .+?\s*
+                mp4\s*:\s*\[(.*?),?\]\s*
+                };\s*
+                videoData\.push\(clip\);''' % content_id,
+            webpage, 'mp4', fatal=False, default=None)
+
+        smil = self._download_xml(
+            'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % content_id,
+            content_id, 'Downloading video SMIL')
+
+        http_base = find_xpath_attr(
+            smil,
+            './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'),
+            'name',
+            'httpBase').get('content')
+
+        def random_string(str_len=0):
+            return ''.join([random.choice(string.ascii_uppercase) for _ in range(str_len)])
+
+        URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=%s&g=%s' % (random_string(5), random_string(12))
+
+        formats = []
+
+        if mp4:
+            for video in json.loads('[%s]' % mp4):
+                bitrate = video['bitrate']
+                fmt = {
+                    'url': video['src'].replace('http://pmd.video.howstuffworks.com', http_base) + URL_SUFFIX,
+                    'format_id': bitrate,
+                }
+                m = re.search(r'(?P<vbr>\d+)[Kk]', bitrate)
+                if m:
+                    fmt['vbr'] = int(m.group('vbr'))
+                formats.append(fmt)
+        else:
+            for video in smil.findall(
+                    './/{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')):
+                vbr = int(video.attrib['system-bitrate']) / 1000
+                formats.append({
+                    'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX),
+                    'format_id': '%dk' % vbr,
+                    'vbr': vbr,
+                })
+
+        self._sort_formats(formats)
+
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' : HowStuffWorks'
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
+
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        return {
+            'id': content_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/ign.py

@@ -18,6 +18,7 @@ class IGNIE(InfoExtractor):
     _DESCRIPTION_RE = [
         r'<span class="page-object-description">(.+?)</span>',
         r'id="my_show_video">.*?<p>(.*?)</p>',
+        r'<meta name="description" content="(.*?)"',
     ]
 
     _TESTS = [
@@ -55,6 +56,17 @@ class IGNIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
+            'md5': '4e9a0bda1e5eebd31ddcf86ec0b9b3c7',
+            'info_dict': {
+                'id': '078fdd005f6d3c02f63d795faa1b984f',
+                'ext': 'mp4',
+                'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
+                'description': 'Giant skeletons, bloody hunts, and captivating'
+                    ' natural beauty take our breath away.',
+            },
+        },
     ]
 
     def _find_video_id(self, webpage):
@@ -62,6 +74,7 @@ class IGNIE(InfoExtractor):
             r'data-video-id="(.+?)"',
             r'<object id="vid_(.+?)"',
             r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
+            r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
         ]
         return self._search_regex(res_id, webpage, 'video id')
 
@@ -70,10 +83,7 @@ class IGNIE(InfoExtractor):
         name_or_id = mobj.group('name_or_id')
         page_type = mobj.group('type')
         webpage = self._download_webpage(url, name_or_id)
-        if page_type == 'articles':
+        if page_type != 'video':
-            video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url')
-            return self.url_result(video_url, ie='IGN')
-        elif page_type != 'video':
             multiple_urls = re.findall(
                 '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
                 webpage)

youtube_dl/extractor/imdb.py

@@ -63,6 +63,14 @@ class ImdbListIE(InfoExtractor):
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
     _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+    _TEST = {
+        'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
+        'info_dict': {
+            'id': 'JFs9NWw6XI0',
+            'title': 'March 23, 2012 Releases',
+        },
+        'playlist_count': 7,
+    }
     
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/instagram.py

@@ -46,6 +46,30 @@ class InstagramUserIE(InfoExtractor):
     _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
     IE_DESC = 'Instagram user profile'
     IE_NAME = 'instagram:user'
+    _TEST = {
+        'url': 'http://instagram.com/porsche',
+        'info_dict': {
+            'id': 'porsche',
+            'title': 'porsche',
+        },
+        'playlist_mincount': 2,
+        'playlist': [{
+            'info_dict': {
+                'id': '614605558512799803_462752227',
+                'ext': 'mp4',
+                'title': '#Porsche Intelligent Performance.',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'uploader': 'Porsche',
+                'uploader_id': 'porsche',
+                'timestamp': 1387486713,
+                'upload_date': '20131219',
+            },
+        }],
+        'params': {
+            'extract_flat': True,
+            'skip_download': True,
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/ivi.py

@@ -127,6 +127,21 @@ class IviCompilationIE(InfoExtractor):
     IE_DESC = 'ivi.ru compilations'
     IE_NAME = 'ivi:compilation'
     _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
+    _TESTS = [{
+        'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
+        'info_dict': {
+            'id': 'dvoe_iz_lartsa',
+            'title': 'Двое из ларца (2006 - 2008)',
+        },
+        'playlist_mincount': 24,
+    }, {
+        'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
+        'info_dict': {
+            'id': 'dvoe_iz_lartsa/season1',
+            'title': 'Двое из ларца (2006 - 2008) 1 сезон',
+        },
+        'playlist_mincount': 12,
+    }]
 
     def _extract_entries(self, html, compilation_id):
         return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')

youtube_dl/extractor/jove.py

@@ -0,0 +1,80 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    unified_strdate
+)
+
+
+class JoveIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)'
+    _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}'
+    _TESTS = [
+        {
+            'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current',
+            'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b',
+            'info_dict': {
+                'id': '2744',
+                'ext': 'mp4',
+                'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation',
+                'description': 'md5:015dd4509649c0908bc27f049e0262c6',
+                'thumbnail': 're:^https?://.*\.png$',
+                'upload_date': '20110523',
+            }
+        },
+        {
+            'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation',
+            'md5': '914aeb356f416811d911996434811beb',
+            'info_dict': {
+                'id': '51796',
+                'ext': 'mp4',
+                'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment',
+                'description': 'md5:35ff029261900583970c4023b70f1dc9',
+                'thumbnail': 're:^https?://.*\.png$',
+                'upload_date': '20140802',
+            }
+        },
+
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        chapters_id = self._html_search_regex(
+            r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id')
+
+        chapters_xml = self._download_xml(
+            self._CHAPTERS_URL.format(video_id=chapters_id),
+            video_id, note='Downloading chapters XML',
+            errnote='Failed to download chapters XML')
+
+        video_url = chapters_xml.attrib.get('video')
+        if not video_url:
+            raise ExtractorError('Failed to get the video URL')
+
+        title = self._html_search_meta('citation_title', webpage, 'title')
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._html_search_regex(
+            r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>',
+            webpage, 'description', fatal=False)
+        publish_date = unified_strdate(self._html_search_meta(
+            'citation_publication_date', webpage, 'publish date', fatal=False))
+        comment_count = self._html_search_regex(
+            r'<meta name="num_comments" content="(\d+) Comments?"',
+            webpage, 'comment count', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'description': description,
+            'upload_date': publish_date,
+            'comment_count': comment_count,
+        }

youtube_dl/extractor/khanacademy.py

@@ -12,18 +12,27 @@ class KhanAcademyIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])'
     IE_NAME = 'KhanAcademy'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.khanacademy.org/video/one-time-pad',
-        'file': 'one-time-pad.mp4',
         'md5': '7021db7f2d47d4fff89b13177cb1e8f4',
         'info_dict': {
+            'id': 'one-time-pad',
+            'ext': 'mp4',
             'title': 'The one-time pad',
             'description': 'The perfect cipher',
             'duration': 176,
             'uploader': 'Brit Cruise',
             'upload_date': '20120411',
         }
-    }
+    }, {
+        'url': 'https://www.khanacademy.org/math/applied-math/cryptography',
+        'info_dict': {
+            'id': 'cryptography',
+            'title': 'Journey into cryptography',
+            'description': 'How have humans protected their secret messages through history? What has changed today?',
+        },
+        'playlist_mincount': 3,
+    }]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

youtube_dl/extractor/livestream.py

@@ -19,7 +19,7 @@ from ..utils import (
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
     _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',
         'info_dict': {
@@ -31,7 +31,13 @@ class LivestreamIE(InfoExtractor):
             'view_count': int,
             'thumbnail': 're:^http://.*\.jpg$'
         }
-    }
+    }, {
+        'url': 'http://new.livestream.com/tedx/cityenglish',
+        'info_dict': {
+            'title': 'TEDCity2.0 (English)',
+        },
+        'playlist_mincount': 4,
+    }]
 
     def _parse_smil(self, video_id, smil_url):
         formats = []
@@ -111,23 +117,37 @@ class LivestreamIE(InfoExtractor):
         event_name = mobj.group('event_name')
         webpage = self._download_webpage(url, video_id or event_name)
 
-        if video_id is None:
+        og_video = self._og_search_video_url(
-            # This is an event page:
+            webpage, 'player url', fatal=False, default=None)
-            config_json = self._search_regex(
+        if og_video is not None:
-                r'window.config = ({.*?});', webpage, 'window config')
-            info = json.loads(config_json)['event']
-            videos = [self._extract_video_info(video_data['data'])
-                for video_data in info['feed']['data']
-                if video_data['type'] == 'video']
-            return self.playlist_result(videos, info['id'], info['full_name'])
-        else:
-            og_video = self._og_search_video_url(webpage, 'player url')
             query_str = compat_urllib_parse_urlparse(og_video).query
             query = compat_urlparse.parse_qs(query_str)
-            api_url = query['play_url'][0].replace('.smil', '')
+            if 'play_url' in query:
-            info = json.loads(self._download_webpage(
+                api_url = query['play_url'][0].replace('.smil', '')
-                api_url, video_id, 'Downloading video info'))
+                info = json.loads(self._download_webpage(
-            return self._extract_video_info(info)
+                    api_url, video_id, 'Downloading video info'))
+                return self._extract_video_info(info)
+
+        config_json = self._search_regex(
+            r'window.config = ({.*?});', webpage, 'window config')
+        info = json.loads(config_json)['event']
+
+        def is_relevant(vdata, vid):
+            result = vdata['type'] == 'video'
+            if video_id is not None:
+                result = result and compat_str(vdata['data']['id']) == vid
+            return result
+
+        videos = [self._extract_video_info(video_data['data'])
+                  for video_data in info['feed']['data']
+                  if is_relevant(video_data, video_id)]
+        if video_id is None:
+            # This is an event page:
+            return self.playlist_result(videos, info['id'], info['full_name'])
+        else:
+            if not videos:
+                raise ExtractorError('Cannot find video %s' % video_id)
+            return videos[0]
 
 
 # The original version of Livestream uses a different system
@@ -137,7 +157,7 @@ class LivestreamOriginalIE(InfoExtractor):
         (?P<user>[^/]+)/(?P<type>video|folder)
         (?:\?.*?Id=|/)(?P<id>.*?)(&|$)
         '''
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
         'info_dict': {
             'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
@@ -148,7 +168,13 @@ class LivestreamOriginalIE(InfoExtractor):
             # rtmp
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
+        'info_dict': {
+            'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3',
+        },
+        'playlist_mincount': 4,
+    }]
 
     def _extract_video(self, user, video_id):
         api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
@@ -171,15 +197,19 @@ class LivestreamOriginalIE(InfoExtractor):
 
     def _extract_folder(self, url, folder_id):
         webpage = self._download_webpage(url, folder_id)
-        urls = orderedSet(re.findall(r'<a href="(https?://livestre\.am/.*?)"', webpage))
+        paths = orderedSet(re.findall(
+            r'''(?x)(?:
+                <li\s+class="folder">\s*<a\s+href="|
+                <a\s+href="(?=https?://livestre\.am/)
+            )([^"]+)"''', webpage))
 
         return {
             '_type': 'playlist',
             'id': folder_id,
             'entries': [{
                 '_type': 'url',
-                'url': video_url,
+                'url': compat_urlparse.urljoin(url, p),
-            } for video_url in urls],
+            } for p in paths],
         }
 
     def _real_extract(self, url):

youtube_dl/extractor/metacafe.py

@@ -9,6 +9,7 @@ from ..utils import (
     compat_urllib_request,
     determine_ext,
     ExtractorError,
+    int_or_none,
 )
 
 
@@ -83,6 +84,21 @@ class MetacafeIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # Movieclips.com video
+        {
+            'url': 'http://www.metacafe.com/watch/mv-Wy7ZU/my_week_with_marilyn_do_you_love_me/',
+            'info_dict': {
+                'id': 'mv-Wy7ZU',
+                'ext': 'mp4',
+                'title': 'My Week with Marilyn - Do You Love Me?',
+                'description': 'From the movie My Week with Marilyn - Colin (Eddie Redmayne) professes his love to Marilyn (Michelle Williams) and gets her to promise to return to set and finish the movie.',
+                'uploader': 'movie_trailers',
+                'duration': 176,
+            },
+            'params': {
+                'skip_download': 'requires rtmpdump',
+            }
+        }
     ]
 
     def report_disclaimer(self):
@@ -134,6 +150,7 @@ class MetacafeIE(InfoExtractor):
 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
+        video_url = None
         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
         if mobj is not None:
             mediaURL = compat_urllib_parse.unquote(mobj.group(1))
@@ -146,16 +163,17 @@ class MetacafeIE(InfoExtractor):
             else:
                 gdaKey = mobj.group(1)
                 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
-        else:
+        if video_url is None:
             mobj = re.search(r'<video src="([^"]+)"', webpage)
             if mobj:
                 video_url = mobj.group(1)
                 video_ext = 'mp4'
-            else:
+        if video_url is None:
-                mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+            flashvars = self._search_regex(
-                if mobj is None:
+                r' name="flashvars" value="(.*?)"', webpage, 'flashvars',
-                    raise ExtractorError('Unable to extract media URL')
+                default=None)
-                vardict = compat_parse_qs(mobj.group(1))
+            if flashvars:
+                vardict = compat_parse_qs(flashvars)
                 if 'mediaData' not in vardict:
                     raise ExtractorError('Unable to extract media URL')
                 mobj = re.search(
@@ -165,26 +183,68 @@ class MetacafeIE(InfoExtractor):
                 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
                 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
                 video_ext = determine_ext(video_url)
+        if video_url is None:
+            player_url = self._search_regex(
+                r"swfobject\.embedSWF\('([^']+)'",
+                webpage, 'config URL', default=None)
+            if player_url:
+                config_url = self._search_regex(
+                    r'config=(.+)$', player_url, 'config URL')
+                config_doc = self._download_xml(
+                    config_url, video_id,
+                    note='Downloading video config')
+                smil_url = config_doc.find('.//properties').attrib['smil_file']
+                smil_doc = self._download_xml(
+                    smil_url, video_id,
+                    note='Downloading SMIL document')
+                base_url = smil_doc.find('./head/meta').attrib['base']
+                video_url = []
+                for vn in smil_doc.findall('.//video'):
+                    br = int(vn.attrib['system-bitrate'])
+                    play_path = vn.attrib['src']
+                    video_url.append({
+                        'format_id': 'smil-%d' % br,
+                        'url': base_url,
+                        'play_path': play_path,
+                        'page_url': url,
+                        'player_url': player_url,
+                        'ext': play_path.partition(':')[0],
+                    })
 
-        video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title')
+        if video_url is None:
+            raise ExtractorError('Unsupported video type')
+
+        video_title = self._html_search_regex(
+            r'(?im)<title>(.*) - Video</title>', webpage, 'title')
         description = self._og_search_description(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
         video_uploader = self._html_search_regex(
                 r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
                 webpage, 'uploader nickname', fatal=False)
+        duration = int_or_none(
+            self._html_search_meta('video:duration', webpage))
 
-        if re.search(r'"contentRating":"restricted"', webpage) is not None:
+        age_limit = (
-            age_limit = 18
+            18
+            if re.search(r'"contentRating":"restricted"', webpage)
+            else 0)
+
+        if isinstance(video_url, list):
+            formats = video_url
         else:
-            age_limit = 0
+            formats = [{
+                'url': video_url,
+                'ext': video_ext,
+            }]
 
+        self._sort_formats(formats)
         return {
             'id': video_id,
-            'url': video_url,
             'description': description,
             'uploader': video_uploader,
             'title': video_title,
-            'thumbnail':thumbnail,
+            'thumbnail': thumbnail,
-            'ext': video_ext,
             'age_limit': age_limit,
+            'formats': formats,
+            'duration': duration,
         }

youtube_dl/extractor/ministrygrid.py

@@ -0,0 +1,57 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    smuggle_url,
+)
+
+
+class MinistryGridIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.ministrygrid.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
+
+    _TEST = {
+        'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers',
+        'md5': '844be0d2a1340422759c2a9101bab017',
+        'info_dict': {
+            'id': '3453494717001',
+            'ext': 'mp4',
+            'title': 'The Gospel by Numbers',
+            'description': 'Coming soon from T4G 2014!',
+            'uploader': 'LifeWay Christian Resources (MG)',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        portlets_json = self._search_regex(
+            r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list')
+        portlets = json.loads(portlets_json)
+        pl_id = self._search_regex(
+            r'<!--\s*p_l_id - ([0-9]+)<br>', webpage, 'p_l_id')
+
+        for i, portlet in enumerate(portlets):
+            portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet)
+            portlet_code = self._download_webpage(
+                portlet_url, video_id,
+                note='Looking in portlet %s (%d/%d)' % (portlet, i + 1, len(portlets)),
+                fatal=False)
+            video_iframe_url = self._search_regex(
+                r'<iframe.*?src="([^"]+)"', portlet_code, 'video iframe',
+                default=None)
+            if video_iframe_url:
+                surl = smuggle_url(
+                    video_iframe_url, {'force_videoid': video_id})
+                return {
+                    '_type': 'url',
+                    'id': video_id,
+                    'url': surl,
+                }
+
+        raise ExtractorError('Could not find video iframe in any portlets')

youtube_dl/extractor/mitele.py

@@ -0,0 +1,60 @@
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    get_element_by_attribute,
+    parse_duration,
+    strip_jsonp,
+)
+
+
+class MiTeleIE(InfoExtractor):
+    IE_NAME = 'mitele.es'
+    _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/'
+
+    _TEST = {
+        'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
+        'md5': '6a75fe9d0d3275bead0cb683c616fddb',
+        'info_dict': {
+            'id': '0fce117d',
+            'ext': 'mp4',
+            'title': 'Programa 144 - Tor, la web invisible',
+            'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
+            'display_id': 'programa-144',
+            'duration': 2913,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        episode = mobj.group('episode')
+        webpage = self._download_webpage(url, episode)
+        embed_data_json = self._search_regex(
+            r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
+            flags=re.DOTALL
+        ).replace('\'', '"')
+        embed_data = json.loads(embed_data_json)
+
+        info_url = embed_data['flashvars']['host']
+        info_el = self._download_xml(info_url, episode).find('./video/info')
+
+        video_link = info_el.find('videoUrl/link').text
+        token_query = compat_urllib_parse.urlencode({'id': video_link})
+        token_info = self._download_json(
+            'http://token.mitele.es/?' + token_query, episode,
+            transform_source=strip_jsonp
+        )
+
+        return {
+            'id': embed_data['videoId'],
+            'display_id': episode,
+            'title': info_el.find('title').text,
+            'url': token_info['tokenizedUrl'],
+            'description': get_element_by_attribute('class', 'text', webpage),
+            'thumbnail': info_el.find('thumb').text,
+            'duration': parse_duration(info_el.find('duration').text),
+        }

youtube_dl/extractor/mixcloud.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     ExtractorError,
+    HEADRequest,
     int_or_none,
     parse_iso8601,
 )
@@ -38,7 +39,7 @@ class MixcloudIE(InfoExtractor):
             try:
                 # We only want to know if the request succeed
                 # don't download the whole file
-                self._request_webpage(url, None, False)
+                self._request_webpage(HEADRequest(url), None, False)
                 return url
             except ExtractorError:
                 url = None

youtube_dl/extractor/mlb.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class MLBIE(InfoExtractor):
-    _VALID_URL = r'https?://m\.mlb\.com/(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)'
+    _VALID_URL = r'https?://m\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|shared/video/embed/embed\.html\?.*?\bcontent_id=)(?P<id>n?\d+)'
     _TESTS = [
         {
             'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
@@ -69,6 +69,10 @@ class MLBIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
+        {
+            'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/mofosex.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import re
 
@@ -8,15 +10,17 @@ from ..utils import (
     compat_urllib_parse,
 )
 
+
 class MofosexIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
+    _VALID_URL = r'^https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
     _TEST = {
-        u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
+        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
-        u'file': u'5018.mp4',
+        'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
-        u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a',
+        'info_dict': {
-        u'info_dict': {
+            'id': '5018',
-            u"title": u"Japanese Teen Music Video",
+            'ext': 'mp4',
-            u"age_limit": 18,
+            'title': 'Japanese Teen Music Video',
+            'age_limit': 18,
         }
     }
 
@@ -29,8 +33,8 @@ class MofosexIE(InfoExtractor):
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title')
+        video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url'))
+        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[5].split('_')[:2]

youtube_dl/extractor/mojvideo.py

@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_duration,
+)
+
+
+class MojvideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P<display_id>[^/]+)/(?P<id>[a-f0-9]+)'
+    _TEST = {
+        'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906',
+        'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7',
+        'info_dict': {
+            'id': '3d1ed4497707730b2906',
+            'display_id': 'v-avtu-pred-mano-rdecelaska-alfi-nipic',
+            'ext': 'mp4',
+            'title': 'V avtu pred mano rdečelaska - Alfi Nipič',
+            'thumbnail': 're:^http://.*\.jpg$',
+            'duration': 242,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        # XML is malformed
+        playerapi = self._download_webpage(
+            'http://www.mojvideo.com/playerapi.php?v=%s&t=1' % video_id, display_id)
+
+        if '<error>true</error>' in playerapi:
+            error_desc = self._html_search_regex(
+                r'<errordesc>([^<]*)</errordesc>', playerapi, 'error description', fatal=False)
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True)
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', playerapi, 'title')
+        video_url = self._html_search_regex(
+            r'<file>([^<]+)</file>', playerapi, 'video URL')
+        thumbnail = self._html_search_regex(
+            r'<preview>([^<]+)</preview>', playerapi, 'thumbnail', fatal=False)
+        duration = parse_duration(self._html_search_regex(
+            r'<duration>([^<]+)</duration>', playerapi, 'duration', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+        }

youtube_dl/extractor/movieclips.py

@@ -0,0 +1,78 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_str,
+    clean_html,
+)
+
+
+class MovieClipsIE(InfoExtractor):
+    _VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?'
+    _TEST = {
+        'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/',
+        'info_dict': {
+            'id': 'Wy7ZU',
+            'display_id': 'my-week-with-marilyn-movie-do-you-love-me',
+            'ext': 'mp4',
+            'title': 'My Week with Marilyn - Do You Love Me?',
+            'description': 'md5:e86795bd332fe3cff461e7c8dc542acb',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+        show_id = display_id or video_id
+
+        config = self._download_xml(
+            'http://config.movieclips.com/player/config/%s' % video_id,
+            show_id, 'Downloading player config')
+
+        if config.find('./country-region').text == 'false':
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True)
+
+        properties = config.find('./video/properties')
+        smil_file = properties.attrib['smil_file']
+
+        smil = self._download_xml(smil_file, show_id, 'Downloading SMIL')
+        base_url = smil.find('./head/meta').attrib['base']
+
+        formats = []
+        for video in smil.findall('./body/switch/video'):
+            vbr = int(video.attrib['system-bitrate']) / 1000
+            src = video.attrib['src']
+            formats.append({
+                'url': base_url,
+                'play_path': src,
+                'ext': src.split(':')[0],
+                'vbr': vbr,
+                'format_id': '%dk' % vbr,
+            })
+
+        self._sort_formats(formats)
+
+        title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title'])
+        description = clean_html(compat_str(properties.attrib['clip_description']))
+        thumbnail = properties.attrib['image']
+        categories = properties.attrib['clip_categories'].split(',')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'formats': formats,
+        }

youtube_dl/extractor/musicvault.py

@@ -0,0 +1,76 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+)
+
+
+class MusicVaultIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html'
+    _TEST = {
+        'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html',
+        'md5': '2cdbb3ae75f7fb3519821507d2fb3c15',
+        'info_dict': {
+            'id': '1010863',
+            'ext': 'mp4',
+            'uploader_id': 'the-allman-brothers-band',
+            'title': 'Straight from the Heart',
+            'duration': 244,
+            'uploader': 'The Allman Brothers Band',
+            'thumbnail': 're:^https?://.*/thumbnail/.*',
+            'upload_date': '19811216',
+            'location': 'Capitol Theatre (Passaic, NJ)',
+            'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+        webpage = self._download_webpage(url, display_id)
+
+        thumbnail = self._search_regex(
+            r'<meta itemprop="thumbnail" content="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        data_div = self._search_regex(
+            r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields')
+        uploader = self._html_search_regex(
+            r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False)
+        title = self._html_search_regex(
+            r'<h2.*?>(.*?)</h2>', data_div, 'title')
+        upload_date = unified_strdate(self._html_search_regex(
+            r'<h3.*?>(.*?)</h3>', data_div, 'uploader', fatal=False))
+        location = self._html_search_regex(
+            r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False)
+
+        duration = parse_duration(self._html_search_meta('duration', webpage))
+
+        VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http'
+        kaltura_id = self._search_regex(
+            r'<div id="video-detail-player" data-kaltura-id="([^"]+)"',
+            webpage, 'kaltura ID')
+        video_url = VIDEO_URL_TEMPLATE % {
+            'entry_id': kaltura_id,
+            'wid': self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid'),
+            'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'),
+        }
+
+        return {
+            'id': mobj.group('id'),
+            'url': video_url,
+            'ext': 'mp4',
+            'display_id': display_id,
+            'uploader_id': mobj.group('uploader_id'),
+            'thumbnail': thumbnail,
+            'description': self._html_search_meta('description', webpage),
+            'upload_date': upload_date,
+            'location': location,
+            'title': title,
+            'uploader': uploader,
+            'duration': duration,
+        }

youtube_dl/extractor/nba.py

@@ -3,18 +3,23 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    remove_end,
+    parse_duration,
+)
 
 
 class NBAIE(InfoExtractor):
     _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
     _TEST = {
         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
-        'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
+        'md5': 'c0edcfc37607344e2ff8f13c378c88a4',
         'info_dict': {
             'id': '0021200253-okc-bkn-recap.nba',
             'ext': 'mp4',
-            'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
             'title': 'Thunder vs. Nets',
+            'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
+            'duration': 181,
         },
     }
 
@@ -27,13 +32,18 @@ class NBAIE(InfoExtractor):
         video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
 
         shortened_video_id = video_id.rpartition('/')[2]
-        title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
+        title = remove_end(
+            self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
+
+        description = self._og_search_description(webpage)
+        duration = parse_duration(
+            self._html_search_meta('duration', webpage, 'duration', fatal=False))
 
-        description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
 
         return {
             'id': shortened_video_id,
             'url': video_url,
             'title': title,
             'description': description,
+            'duration': duration,
         }

youtube_dl/extractor/nhl.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -25,8 +27,8 @@ class NHLBaseInfoExtractor(InfoExtractor):
             'path': initial_video_url.replace('.mp4', '_sd.mp4'),
         })
         path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
-        path_doc = self._download_xml(path_url, video_id,
+        path_doc = self._download_xml(
-            u'Downloading final video url')
+            path_url, video_id, 'Downloading final video url')
         video_url = path_doc.find('path').text
 
         join = compat_urlparse.urljoin
@@ -43,17 +45,18 @@ class NHLBaseInfoExtractor(InfoExtractor):
 
 
 class NHLIE(NHLBaseInfoExtractor):
-    IE_NAME = u'nhl.com'
+    IE_NAME = 'nhl.com'
-    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?<=[?&])id=(?P<id>\d+)'
+    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?:[?&])id=(?P<id>[0-9]+)'
 
     _TEST = {
-        u'url': u'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
+        'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
-        u'file': u'453614.mp4',
+        'info_dict': {
-        u'info_dict': {
+            'id': '453614',
-            u'title': u'Quick clip: Weise 4-3 goal vs Flames',
+            'ext': 'mp4',
-            u'description': u'Dale Weise scores his first of the season to put the Canucks up 4-3.',
+            'title': 'Quick clip: Weise 4-3 goal vs Flames',
-            u'duration': 18,
+            'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
-            u'upload_date': u'20131006',
+            'duration': 18,
+            'upload_date': '20131006',
         },
     }
 
@@ -61,23 +64,23 @@ class NHLIE(NHLBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
-        info_json = self._download_webpage(json_url, video_id,
+        data = self._download_json(
-            u'Downloading info json')
+            json_url, video_id, transform_source=self._fix_json)
-        info_json = self._fix_json(info_json)
+        return self._extract_video(data[0])
-        info = json.loads(info_json)[0]
-        return self._extract_video(info)
 
 
 class NHLVideocenterIE(NHLBaseInfoExtractor):
-    IE_NAME = u'nhl.com:videocenter'
+    IE_NAME = 'nhl.com:videocenter'
-    IE_DESC = u'NHL videocenter category'
+    IE_DESC = 'NHL videocenter category'
-    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[^&]+))?'
+    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
-
+    _TEST = {
-    @classmethod
+        'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
-    def suitable(cls, url):
+        'info_dict': {
-        if NHLIE.suitable(url):
+            'id': '999',
-            return False
+            'title': 'Highlights',
-        return super(NHLVideocenterIE, cls).suitable(url)
+        },
+        'playlist_count': 12,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -86,10 +89,10 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         cat_id = self._search_regex(
             [r'var defaultCatId = "(.+?)";',
              r'{statusIndex:0,index:0,.*?id:(.*?),'],
-            webpage, u'category id')
+            webpage, 'category id')
         playlist_title = self._html_search_regex(
             r'tab0"[^>]*?>(.*?)</td>',
-            webpage, u'playlist title', flags=re.DOTALL).lower().capitalize()
+            webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()
 
         data = compat_urllib_parse.urlencode({
             'cid': cat_id,
@@ -104,7 +107,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         response = self._fix_json(response)
         if not response.strip():
             self._downloader.report_warning(u'Got an empty reponse, trying '
-                                            u'adding the "newvideos" parameter')
+                                            'adding the "newvideos" parameter')
             response = self._download_webpage(request_url + '&newvideos=true',
                 playlist_title)
             response = self._fix_json(response)
@@ -114,5 +117,5 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
             '_type': 'playlist',
             'title': playlist_title,
             'id': cat_id,
-            'entries': [self._extract_video(i) for i in videos],
+            'entries': [self._extract_video(v) for v in videos],
         }

youtube_dl/extractor/nosvideo.py

@@ -0,0 +1,65 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+    xpath_with_ns,
+)
+
+_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
+_find = lambda el, p: el.find(_x(p)).text.strip()
+
+
+class NosVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
+                 '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
+    _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
+    _TEST = {
+        'url': 'http://nosvideo.com/?v=drlp6s40kg54',
+        'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c',
+        'info_dict': {
+            'id': 'drlp6s40kg54',
+            'ext': 'mp4',
+            'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        fields = {
+            'id': video_id,
+            'op': 'download1',
+            'method_free': 'Continue to Video',
+        }
+        post = compat_urllib_parse.urlencode(fields)
+        req = compat_urllib_request.Request(url, post)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+        webpage = self._download_webpage(req, video_id,
+                                         'Downloading download page')
+        xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
+        playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
+        playlist = self._download_xml(playlist_url, video_id)
+
+        track = playlist.find(_x('.//xspf:track'))
+        title = _find(track, './xspf:title')
+        url = _find(track, './xspf:file')
+        thumbnail = _find(track, './xspf:image')
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/nowness.py

@@ -1,3 +1,4 @@
+# encoding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -8,19 +9,34 @@ from ..utils import ExtractorError
 
 
 class NownessIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])'
+    _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])'
 
-    _TEST = {
+    _TESTS = [
-        'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation',
+        {
-        'md5': '068bc0202558c2e391924cb8cc470676',
+            'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation',
-        'info_dict': {
+            'md5': '068bc0202558c2e391924cb8cc470676',
-            'id': '2520295746001',
+            'info_dict': {
-            'ext': 'mp4',
+                'id': '2520295746001',
-            'description': 'Candor: The Art of Gesticulation',
+                'ext': 'mp4',
-            'uploader': 'Nowness',
+                'title': 'Candor: The Art of Gesticulation',
-            'title': 'Candor: The Art of Gesticulation',
+                'description': 'Candor: The Art of Gesticulation',
-        }
+                'thumbnail': 're:^https?://.*\.jpg',
-    }
+                'uploader': 'Nowness',
+            }
+        },
+        {
+            'url': 'http://cn.nowness.com/day/2014/8/7/4069/kasper-bj-rke-ft-jaakko-eino-kalevi--tnr',
+            'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
+            'info_dict': {
+                'id': '3716354522001',
+                'ext': 'mp4',
+                'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
+                'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'uploader': 'Nowness',
+            }
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/npo.py

@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     unified_strdate,
+    qualities,
 )
 
 
@@ -17,7 +18,7 @@ class NPOIE(InfoExtractor):
         'md5': '4b3f9c429157ec4775f2c9cb7b911016',
         'info_dict': {
             'id': 'VPWON_1220719',
-            'ext': 'mp4',
+            'ext': 'm4v',
             'title': 'Nieuwsuur',
             'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
             'upload_date': '20140622',
@@ -39,24 +40,32 @@ class NPOIE(InfoExtractor):
             video_id,
             note='Downloading token'
         )
-        token = self._search_regex(r'npoplayer.token = "(.+?)"', token_page, 'token')
+        token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token')
-        streams_info = self._download_json(
-            'http://ida.omroep.nl/odi/?prid=%s&puboptions=h264_std&adaptive=yes&token=%s' % (video_id, token),
-            video_id
-        )
 
-        stream_info = self._download_json(
+        formats = []
-            streams_info['streams'][0] + '&type=json',
+        quality = qualities(['adaptive', 'h264_sb', 'h264_bb', 'h264_std'])
-            video_id,
+        for format_id in metadata['pubopties']:
-            'Downloading stream info'
+            streams_info = self._download_json(
-        )
+                'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token),
+                video_id, 'Downloading %s streams info' % format_id)
+            stream_info = self._download_json(
+                streams_info['streams'][0] + '&type=json',
+                video_id, 'Downloading %s stream info' % format_id)
+            if format_id == 'adaptive':
+                formats.extend(self._extract_m3u8_formats(stream_info['url'], video_id))
+            else:
+                formats.append({
+                    'url': stream_info['url'],
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                })
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': metadata['titel'],
-            'ext': 'mp4',
-            'url': stream_info['url'],
             'description': metadata['info'],
             'thumbnail': metadata['images'][-1]['url'],
             'upload_date': unified_strdate(metadata['gidsdatum']),
+            'formats': formats,
         }

youtube_dl/extractor/nuvid.py

@@ -38,7 +38,7 @@ class NuvidIE(InfoExtractor):
             webpage = self._download_webpage(
                 request, video_id, 'Downloading %s page' % format_id)
             video_url = self._html_search_regex(
-                r'<a href="([^"]+)"\s*>Continue to watch video', webpage, '%s video URL' % format_id, fatal=False)
+                r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False)
             if not video_url:
                 continue
             formats.append({
@@ -49,19 +49,24 @@ class NuvidIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
         title = self._html_search_regex(
-            r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'title').strip()
+            [r'<span title="([^"]+)">',
-        thumbnail = self._html_search_regex(
+             r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip()
-            r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"',
+        thumbnails = [
-            webpage, 'thumbnail URL', fatal=False)
+            {
+                'url': thumb_url,
+            } for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage)
+        ]
+        thumbnail = thumbnails[0]['url'] if thumbnails else None
         duration = parse_duration(self._html_search_regex(
-            r'Length:\s*<span>(\d{2}:\d{2})</span>',webpage, 'duration', fatal=False))
+            r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False))
         upload_date = unified_strdate(self._html_search_regex(
-            r'Added:\s*<span>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload date', fatal=False))
+            r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False))
 
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': 'http://m.nuvid.com%s' % thumbnail,
+            'thumbnails': thumbnails,
+            'thumbnail': thumbnail,
             'duration': duration,
             'upload_date': upload_date,
             'age_limit': 18,

youtube_dl/extractor/oe1.py

@@ -1,40 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import calendar
-import datetime
-import re
-
-from .common import InfoExtractor
-
-# audios on oe1.orf.at are only available for 7 days, so we can't
-# add tests.
-
-
-class OE1IE(InfoExtractor):
-    IE_DESC = 'oe1.orf.at'
-    _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        show_id = mobj.group('id')
-
-        data = self._download_json(
-            'http://oe1.orf.at/programm/%s/konsole' % show_id,
-            show_id
-        )
-
-        timestamp = datetime.datetime.strptime('%s %s' % (
-            data['item']['day_label'],
-            data['item']['time']
-        ), '%d.%m.%Y %H:%M')
-        unix_timestamp = calendar.timegm(timestamp.utctimetuple())
-
-        return {
-            'id': show_id,
-            'title': data['item']['title'],
-            'url': data['item']['url_stream'],
-            'ext': 'mp3',
-            'description': data['item'].get('info'),
-            'timestamp': unix_timestamp
-        }

youtube_dl/extractor/ooyala.py

@@ -3,23 +3,38 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import unescapeHTML
+from ..utils import (
+    unescapeHTML,
+    ExtractorError,
+)
 
 
 class OoyalaIE(InfoExtractor):
     _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)'
 
-    _TEST = {
+    _TESTS = [
-        # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
+        {
-        'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
+            # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
-        'md5': '3f5cceb3a7bf461d6c29dc466cf8033c',
+            'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
-        'info_dict': {
+            'md5': '3f5cceb3a7bf461d6c29dc466cf8033c',
-            'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
+            'info_dict': {
-            'ext': 'mp4',
+                'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
-            'title': 'Explaining Data Recovery from Hard Drives and SSDs',
+                'ext': 'mp4',
-            'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+                'title': 'Explaining Data Recovery from Hard Drives and SSDs',
+                'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+            },
+        }, {
+            # Only available for ipad
+            'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
+            'md5': '4b9754921fddb68106e48c142e2a01e6',
+            'info_dict': {
+                'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
+                'ext': 'mp4',
+                'title': 'Simulation Overview - Levels of Simulation',
+                'description': '',
+            },
         },
-    }
+    ]
 
     @staticmethod
     def _url_for_embed_code(embed_code):
@@ -47,13 +62,30 @@ class OoyalaIE(InfoExtractor):
         player = self._download_webpage(player_url, embedCode)
         mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
                                         player, 'mobile player url')
-        mobile_player = self._download_webpage(mobile_url, embedCode)
+        # Looks like some videos are only available for particular devices
-        videos_info = self._search_regex(
+        # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
-            r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
+        # is only available for ipad)
-            mobile_player, 'info').replace('\\"','"')
+        # Working around with fetching URLs for all the devices found starting with 'unknown'
-        videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"','"')
+        # until we succeed or eventually fail for each device.
+        devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
+        devices.remove('unknown')
+        devices.insert(0, 'unknown')
+        for device in devices:
+            mobile_player = self._download_webpage(
+                '%s&device=%s' % (mobile_url, device), embedCode,
+                'Downloading mobile player JS for %s device' % device)
+            videos_info = self._search_regex(
+                r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
+                mobile_player, 'info', fatal=False, default=None)
+            if videos_info:
+                break
+        if not videos_info:
+            raise ExtractorError('Unable to extract info')
+        videos_info = videos_info.replace('\\"', '"')
+        videos_more_info = self._search_regex(
+            r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
         videos_info = json.loads(videos_info)
-        videos_more_info =json.loads(videos_more_info)
+        videos_more_info = json.loads(videos_more_info)
 
         if videos_more_info.get('lineup'):
             videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]

youtube_dl/extractor/orf.py

@@ -3,6 +3,8 @@ from __future__ import unicode_literals
 
 import json
 import re
+import calendar
+import datetime
 
 from .common import InfoExtractor
 from ..utils import (
@@ -12,7 +14,9 @@ from ..utils import (
 )
 
 
-class ORFIE(InfoExtractor):
+class ORFTVthekIE(InfoExtractor):
+    IE_NAME = 'orf:tvthek'
+    IE_DESC = 'ORF TVthek'
     _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)'
 
     _TEST = {
@@ -105,3 +109,73 @@ class ORFIE(InfoExtractor):
             'entries': entries,
             'id': playlist_id,
         }
+
+
+# Audios on ORF radio are only available for 7 days, so we can't add tests.
+
+
+class ORFOE1IE(InfoExtractor):
+    IE_NAME = 'orf:oe1'
+    IE_DESC = 'Radio Österreich 1'
+    _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        show_id = mobj.group('id')
+
+        data = self._download_json(
+            'http://oe1.orf.at/programm/%s/konsole' % show_id,
+            show_id
+        )
+
+        timestamp = datetime.datetime.strptime('%s %s' % (
+            data['item']['day_label'],
+            data['item']['time']
+        ), '%d.%m.%Y %H:%M')
+        unix_timestamp = calendar.timegm(timestamp.utctimetuple())
+
+        return {
+            'id': show_id,
+            'title': data['item']['title'],
+            'url': data['item']['url_stream'],
+            'ext': 'mp3',
+            'description': data['item'].get('info'),
+            'timestamp': unix_timestamp
+        }
+
+
+class ORFFM4IE(InfoExtractor):
+    IE_DESC = 'orf:fm4'
+    IE_DESC = 'radio FM4'
+    _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        show_date = mobj.group('date')
+        show_id = mobj.group('show')
+
+        data = self._download_json(
+            'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id),
+            show_id
+        )
+
+        def extract_entry_dict(info, title, subtitle):
+            return {
+                'id': info['loopStreamId'].replace('.mp3', ''),
+                'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'],
+                'title': title,
+                'description': subtitle,
+                'duration': (info['end'] - info['start']) / 1000,
+                'timestamp': info['start'] / 1000,
+                'ext': 'mp3'
+            }
+
+        entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
+
+        return {
+            '_type': 'playlist',
+            'id': show_id,
+            'title': data['title'],
+            'description': data['subtitle'],
+            'entries': entries
+        }

youtube_dl/extractor/patreon.py

@@ -0,0 +1,100 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+)
+
+
+class PatreonIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(.+)'
+    _TESTS = [
+        {
+            'url': 'http://www.patreon.com/creation?hid=743933',
+            'md5': 'e25505eec1053a6e6813b8ed369875cc',
+            'info_dict': {
+                'id': '743933',
+                'ext': 'mp3',
+                'title': 'Episode 166: David Smalley of Dogma Debate',
+                'uploader': 'Cognitive Dissonance Podcast',
+                'thumbnail': 're:^https?://.*$',
+            },
+        },
+        {
+            'url': 'http://www.patreon.com/creation?hid=754133',
+            'md5': '3eb09345bf44bf60451b8b0b81759d0a',
+            'info_dict': {
+                'id': '754133',
+                'ext': 'mp3',
+                'title': 'CD 167 Extra',
+                'uploader': 'Cognitive Dissonance Podcast',
+                'thumbnail': 're:^https?://.*$',
+            },
+        },
+    ]
+
+    # Currently Patreon exposes download URL via hidden CSS, so login is not
+    # needed. Keeping this commented for when this inevitably changes.
+    '''
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'redirectUrl': 'http://www.patreon.com/',
+            'email': username,
+            'password': password,
+        }
+
+        request = compat_urllib_request.Request(
+            'https://www.patreon.com/processLogin',
+            compat_urllib_parse.urlencode(login_form).encode('utf-8')
+        )
+        login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
+
+        if re.search(r'onLoginFailed', login_page):
+            raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
+
+    def _real_initialize(self):
+        self._login()
+    '''
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._og_search_title(webpage).strip()
+
+        attach_fn = self._html_search_regex(
+            r'<div class="attach"><a target="_blank" href="([^"]+)">',
+            webpage, 'attachment URL', default=None)
+        if attach_fn is not None:
+            video_url = 'http://www.patreon.com' + attach_fn
+            thumbnail = self._og_search_thumbnail(webpage)
+            uploader = self._html_search_regex(
+                r'<strong>(.*?)</strong> is creating', webpage, 'uploader')
+        else:
+            playlist_js = self._search_regex(
+                r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])',
+                webpage, 'playlist JSON')
+            playlist_json = js_to_json(playlist_js)
+            playlist = json.loads(playlist_json)
+            data = playlist[0]
+            video_url = self._proto_relative_url(data['mp3'])
+            thumbnail = self._proto_relative_url(data.get('cover'))
+            uploader = data.get('artist')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp3',
+            'title': title,
+            'uploader': uploader,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/pbs.py

@@ -20,17 +20,53 @@ class PBSIE(InfoExtractor):
         )
     '''
 
-    _TEST = {
+    _TESTS = [
-        'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
+        {
-        'md5': 'ce1888486f0908d555a8093cac9a7362',
+            'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
-        'info_dict': {
+            'md5': 'ce1888486f0908d555a8093cac9a7362',
-            'id': '2365006249',
+            'info_dict': {
-            'ext': 'mp4',
+                'id': '2365006249',
-            'title': 'A More Perfect Union',
+                'ext': 'mp4',
-            'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
+                'title': 'A More Perfect Union',
-            'duration': 3190,
+                'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
+                'duration': 3190,
+            },
         },
-    }
+        {
+            'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
+            'md5': '143c98aa54a346738a3d78f54c925321',
+            'info_dict': {
+                'id': '2365297690',
+                'ext': 'mp4',
+                'title': 'Losing Iraq',
+                'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
+                'duration': 5050,
+            },
+        },
+        {
+            'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
+            'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
+            'info_dict': {
+                'id': '2201174722',
+                'ext': 'mp4',
+                'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist',
+                'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
+                'duration': 801,
+            },
+        },
+        {
+            'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/',
+            'md5': 'c62859342be2a0358d6c9eb306595978',
+            'info_dict': {
+                'id': '2365297708',
+                'ext': 'mp4',
+                'description': 'md5:68d87ef760660eb564455eb30ca464fe',
+                'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
+                'duration': 6559,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }
+        }
+    ]
 
     def _extract_ids(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -40,15 +76,18 @@ class PBSIE(InfoExtractor):
         if presumptive_id:
             webpage = self._download_webpage(url, display_id)
 
-            # frontline video embed
+            MEDIA_ID_REGEXES = [
+                r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
+                r'class="coveplayerid">([^<]+)<',                       # coveplayer
+            ]
+
             media_id = self._search_regex(
-                r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",
+                MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
-                webpage, 'frontline video ID', fatal=False, default=None)
             if media_id:
                 return media_id, presumptive_id
 
             url = self._search_regex(
-                r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+                r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
                 webpage, 'player URL')
             mobj = re.match(self._VALID_URL, url)
 

youtube_dl/extractor/playfm.py

@@ -0,0 +1,82 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+)
+
+
+class PlayFMIE(InfoExtractor):
+    IE_NAME = 'play.fm'
+    _VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])'
+
+    _TEST = {
+        'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220',
+        'md5': 'c505f8307825a245d0c7ad1850001f22',
+        'info_dict': {
+            'id': '137220',
+            'ext': 'mp3',
+            'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
+            'uploader': 'Sven Tasnadi',
+            'uploader_id': 'sventasnadi',
+            'duration': 5627.428,
+            'upload_date': '20140712',
+            'view_count': int,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        upload_date = mobj.group('upload_date')
+
+        rec_data = compat_urllib_parse.urlencode({'rec_id': video_id})
+        req = compat_urllib_request.Request(
+            'http://www.play.fm/flexRead/recording', data=rec_data)
+        req.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        rec_doc = self._download_xml(req, video_id)
+
+        error_node = rec_doc.find('./error')
+        if error_node is not None:
+            raise ExtractorError('An error occured: %s (code %s)' % (
+                error_node.text, rec_doc.find('./status').text))
+
+        recording = rec_doc.find('./recording')
+        title = recording.find('./title').text
+        view_count = int_or_none(recording.find('./stats/playcount').text)
+        duration = float_or_none(recording.find('./duration').text, scale=1000)
+        thumbnail = recording.find('./image').text
+
+        artist = recording.find('./artists/artist')
+        uploader = artist.find('./name').text
+        uploader_id = artist.find('./slug').text
+
+        video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % (
+            'http:', recording.find('./url').text,
+            recording.find('./_class').text, recording.find('./file_id').text,
+            rec_doc.find('./uuid').text, video_id,
+            rec_doc.find('./jingle/file_id').text,
+            'http%3A%2F%2Fwww.play.fm%2Fplayer',
+        )
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp3',
+            'filesize': int_or_none(recording.find('./size').text),
+            'title': title,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'duration': duration,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+        }

youtube_dl/extractor/pornotube.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,15 +11,16 @@ from ..utils import (
 
 
 class PornotubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+    _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
     _TEST = {
-        u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
+        'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
-        u'file': u'1689755.flv',
+        'md5': '374dd6dcedd24234453b295209aa69b6',
-        u'md5': u'374dd6dcedd24234453b295209aa69b6',
+        'info_dict': {
-        u'info_dict': {
+            'id': '1689755',
-            u"upload_date": u"20090708", 
+            'ext': 'flv',
-            u"title": u"Marilyn-Monroe-Bathing",
+            'upload_date': '20090708',
-            u"age_limit": 18
+            'title': 'Marilyn-Monroe-Bathing',
+            'age_limit': 18
         }
     }
 
@@ -32,22 +35,22 @@ class PornotubeIE(InfoExtractor):
 
         # Get the video URL
         VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
-        video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
+        video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url')
         video_url = compat_urllib_parse.unquote(video_url)
 
         #Get the uploaded date
         VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
-        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
+        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False)
-        if upload_date: upload_date = unified_strdate(upload_date)
+        if upload_date:
+            upload_date = unified_strdate(upload_date)
         age_limit = self._rta_search(webpage)
 
-        info = {'id': video_id,
+        return {
-                'url': video_url,
+            'id': video_id,
-                'uploader': None,
+            'url': video_url,
-                'upload_date': upload_date,
+            'upload_date': upload_date,
-                'title': video_title,
+            'title': video_title,
-                'ext': 'flv',
+            'ext': 'flv',
-                'format': 'flv',
+            'format': 'flv',
-                'age_limit': age_limit}
+            'age_limit': age_limit,
-
+        }
-        return [info]

youtube_dl/extractor/promptfile.py

@@ -0,0 +1,67 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+
+
+class PromptFileIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
+    _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]'
+    _TEST = {
+        'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
+        'md5': 'd1451b6302da7215485837aaea882c4c',
+        'info_dict': {
+            'id': 'D21B4746E9-F01462F0FF',
+            'ext': 'mp4',
+            'title': 'Birds.mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
+        fields = dict(re.findall(r'''(?x)type="hidden"\s+
+            name="(.+?)"\s+
+            value="(.*?)"
+            ''', webpage))
+        post = compat_urllib_parse.urlencode(fields)
+        req = compat_urllib_request.Request(url, post)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+        webpage = self._download_webpage(
+            req, video_id, 'Downloading video page')
+
+        url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL')
+        title = self._html_search_regex(
+            r'<span.+title="([^"]+)">', webpage, 'title')
+        thumbnail = self._html_search_regex(
+            r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
+            webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+            'ext': determine_ext(title),
+        }]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/reverbnation.py

@@ -1,23 +1,23 @@
 from __future__ import unicode_literals
 
 import re
-import time
 
 from .common import InfoExtractor
-from ..utils import strip_jsonp
+from ..utils import str_or_none
 
 
 class ReverbNationIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
     _TESTS = [{
         'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
-        'file': '16965047.mp3',
         'md5': '3da12ebca28c67c111a7f8b262d3f7a7',
         'info_dict': {
+            "id": "16965047",
+            "ext": "mp3",
             "title": "MONA LISA",
             "uploader": "ALKILADOS",
-            "uploader_id": 216429,
+            "uploader_id": "216429",
-            "thumbnail": "//gp1.wac.edgecastcdn.net/802892/production_public/Photo/13761700/image/1366002176_AVATAR_MONA_LISA.jpg"
+            "thumbnail": "re:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$"
         },
     }]
 
@@ -26,10 +26,8 @@ class ReverbNationIE(InfoExtractor):
         song_id = mobj.group('id')
 
         api_res = self._download_json(
-            'https://api.reverbnation.com/song/%s?callback=api_response_5&_=%d'
+            'https://api.reverbnation.com/song/%s' % song_id,
-                % (song_id, int(time.time() * 1000)),
             song_id,
-            transform_source=strip_jsonp,
             note='Downloading information of song %s' % song_id
         )
 
@@ -38,8 +36,9 @@ class ReverbNationIE(InfoExtractor):
             'title': api_res.get('name'),
             'url': api_res.get('url'),
             'uploader': api_res.get('artist', {}).get('name'),
-            'uploader_id': api_res.get('artist', {}).get('id'),
+            'uploader_id': str_or_none(api_res.get('artist', {}).get('id')),
-            'thumbnail': api_res.get('image', api_res.get('thumbnail')),
+            'thumbnail': self._proto_relative_url(
+                api_res.get('image', api_res.get('thumbnail'))),
             'ext': 'mp3',
             'vcodec': 'none',
         }

youtube_dl/extractor/rtlnl.py

@@ -0,0 +1,67 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class RtlXlIE(InfoExtractor):
+    IE_NAME = 'rtlxl.nl'
+    _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)'
+
+    _TEST = {
+        'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677',
+        'md5': 'cc16baa36a6c169391f0764fa6b16654',
+        'info_dict': {
+            'id': '6e4203a6-0a5e-3596-8424-c599a59e0677',
+            'ext': 'mp4',
+            'title': 'RTL Nieuws - Laat',
+            'description': 'md5:6b61f66510c8889923b11f2778c72dc5',
+            'timestamp': 1408051800,
+            'upload_date': '20140814',
+            'duration': 576.880,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        uuid = mobj.group('uuid')
+
+        info = self._download_json(
+            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
+            uuid)
+
+        material = info['material'][0]
+        episode_info = info['episodes'][0]
+
+        progname = info['abstracts'][0]['name']
+        subtitle = material['title'] or info['episodes'][0]['name']
+
+        videopath = material['videopath']
+        f4m_url = 'http://manifest.us.rtl.nl' + videopath
+
+        formats = self._extract_f4m_formats(f4m_url, uuid)
+
+        video_urlpart = videopath.split('/flash/')[1][:-4]
+        PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
+
+        formats.extend([
+            {
+                'url': PG_URL_TEMPLATE % ('a2m', video_urlpart),
+                'format_id': 'pg-sd',
+            },
+            {
+                'url': PG_URL_TEMPLATE % ('a3m', video_urlpart),
+                'format_id': 'pg-hd',
+            }
+        ])
+
+        return {
+            'id': uuid,
+            'title': '%s - %s' % (progname, subtitle),
+            'formats': formats,
+            'timestamp': material['original_date'],
+            'description': episode_info['synopsis'],
+            'duration': parse_duration(material.get('duration')),
+        }

youtube_dl/extractor/rtve.py

@@ -1,21 +1,66 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
 import base64
+import re
+import time
 
 from .common import InfoExtractor
 from ..utils import (
     struct_unpack,
+    remove_end,
 )
 
 
+def _decrypt_url(png):
+    encrypted_data = base64.b64decode(png)
+    text_index = encrypted_data.find(b'tEXt')
+    text_chunk = encrypted_data[text_index - 4:]
+    length = struct_unpack('!I', text_chunk[:4])[0]
+    # Use bytearray to get integers when iterating in both python 2.x and 3.x
+    data = bytearray(text_chunk[8:8 + length])
+    data = [chr(b) for b in data if b != 0]
+    hash_index = data.index('#')
+    alphabet_data = data[:hash_index]
+    url_data = data[hash_index + 1:]
+
+    alphabet = []
+    e = 0
+    d = 0
+    for l in alphabet_data:
+        if d == 0:
+            alphabet.append(l)
+            d = e = (e + 1) % 4
+        else:
+            d -= 1
+    url = ''
+    f = 0
+    e = 3
+    b = 1
+    for letter in url_data:
+        if f == 0:
+            l = int(letter) * 10
+            f = 1
+        else:
+            if e == 0:
+                l += int(letter)
+                url += alphabet[l]
+                e = (b + 3) % 4
+                f = 0
+                b += 1
+            else:
+                e -= 1
+
+    return url
+
+
+
 class RTVEALaCartaIE(InfoExtractor):
     IE_NAME = 'rtve.es:alacarta'
     IE_DESC = 'RTVE a la carta'
     _VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
         'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
         'info_dict': {
@@ -23,48 +68,15 @@ class RTVEALaCartaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
         },
-    }
+    }, {
-
+        'note': 'Live stream',
-    def _decrypt_url(self, png):
+        'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
-        encrypted_data = base64.b64decode(png)
+        'info_dict': {
-        text_index = encrypted_data.find(b'tEXt')
+            'id': '1694255',
-        text_chunk = encrypted_data[text_index-4:]
+            'ext': 'flv',
-        length = struct_unpack('!I', text_chunk[:4])[0]
+            'title': 'TODO',
-        # Use bytearray to get integers when iterating in both python 2.x and 3.x
+        }
-        data = bytearray(text_chunk[8:8+length])
+    }]
-        data = [chr(b) for b in data if b != 0]
-        hash_index = data.index('#')
-        alphabet_data = data[:hash_index]
-        url_data = data[hash_index+1:]
-
-        alphabet = []
-        e = 0
-        d = 0
-        for l in alphabet_data:
-            if d == 0:
-                alphabet.append(l)
-                d = e = (e + 1) % 4
-            else:
-                d -= 1
-        url = ''
-        f = 0
-        e = 3
-        b = 1
-        for letter in url_data:
-            if f == 0:
-                l = int(letter)*10
-                f = 1
-            else:
-                if e == 0:
-                    l += int(letter)
-                    url += alphabet[l]
-                    e = (b + 3) % 4
-                    f = 0
-                    b += 1
-                else:
-                    e -= 1
-
-        return url
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -74,11 +86,57 @@ class RTVEALaCartaIE(InfoExtractor):
             video_id)['page']['items'][0]
         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
         png = self._download_webpage(png_url, video_id, 'Downloading url information')
-        video_url = self._decrypt_url(png)
+        video_url = _decrypt_url(png)
 
         return {
             'id': video_id,
             'title': info['title'],
             'url': video_url,
-            'thumbnail': info['image'],
+            'thumbnail': info.get('image'),
+            'page_url': url,
+        }
+
+
+class RTVELiveIE(InfoExtractor):
+    IE_NAME = 'rtve.es:live'
+    IE_DESC = 'RTVE.es live streams'
+    _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)'
+
+    _TESTS = [{
+        'url': 'http://www.rtve.es/noticias/directo-la-1/',
+        'info_dict': {
+            'id': 'directo-la-1',
+            'ext': 'flv',
+            'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
+        },
+        'params': {
+            'skip_download': 'live stream',
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        start_time = time.gmtime()
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        player_url = self._search_regex(
+            r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL')
+        title = remove_end(self._og_search_title(webpage), ' en directo')
+        title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
+
+        vidplayer_id = self._search_regex(
+            r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
+        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
+        png = self._download_webpage(png_url, video_id, 'Downloading url information')
+        video_url = _decrypt_url(png)
+
+        return {
+            'id': video_id,
+            'ext': 'flv',
+            'title': title,
+            'url': video_url,
+            'app': 'rtve-live-live?ovpfv=2.1.2',
+            'player_url': player_url,
+            'rtmp_live': True,
         }

youtube_dl/extractor/rutube.py

@@ -74,6 +74,13 @@ class RutubeChannelIE(InfoExtractor):
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'
     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://rutube.ru/tags/video/1800/',
+        'info_dict': {
+            'id': '1800',
+        },
+        'playlist_mincount': 68,
+    }]
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 
@@ -101,6 +108,7 @@ class RutubeMovieIE(RutubeChannelIE):
     IE_NAME = 'rutube:movie'
     IE_DESC = 'Rutube movies'
     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
+    _TESTS = []
 
     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
@@ -119,5 +127,12 @@ class RutubePersonIE(RutubeChannelIE):
     IE_NAME = 'rutube:person'
     IE_DESC = 'Rutube person videos'
     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://rutube.ru/video/person/313878/',
+        'info_dict': {
+            'id': '313878',
+        },
+        'playlist_mincount': 37,
+    }]
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'

youtube_dl/extractor/sbs.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import json
+import re
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    remove_end,
+)
+
+
+class SBSIE(InfoExtractor):
+    IE_DESC = 'sbs.com.au'
+    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/single/(?P<id>[0-9]+)/'
+
+    _TESTS = [{
+        # Original URL is handled by the generic IE which finds the iframe:
+        # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation
+        'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
+        'md5': '3150cf278965eeabb5b4cea1c963fe0a',
+        'info_dict': {
+            'id': '320403011771',
+            'ext': 'flv',
+            'title': 'Dingo Conservation',
+            'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+        'add_ies': ['generic'],
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        release_urls_json = js_to_json(self._search_regex(
+            r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n',
+            webpage, ''))
+        release_urls = json.loads(release_urls_json)
+        theplatform_url = (
+            release_urls.get('progressive') or release_urls.get('standard'))
+
+        title = remove_end(self._og_search_title(webpage), ' (The Feed)')
+        description = self._html_search_meta('description', webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': theplatform_url,
+
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/shared.py

@@ -17,11 +17,11 @@ class SharedIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://shared.sx/0060718775',
-        'md5': '53e1c58fc3e777ae1dfe9e57ba2f9c72',
+        'md5': '106fefed92a8a2adb8c98e6a0652f49b',
         'info_dict': {
             'id': '0060718775',
             'ext': 'mp4',
-            'title': 'Big Buck Bunny Trailer',
+            'title': 'Bmp4',
         },
     }
 

youtube_dl/extractor/smotri.py

@@ -267,6 +267,14 @@ class SmotriCommunityIE(InfoExtractor):
     IE_DESC = 'Smotri.com community videos'
     IE_NAME = 'smotri:community'
     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
+    _TEST = {
+        'url': 'http://smotri.com/community/video/kommuna',
+        'info_dict': {
+            'id': 'kommuna',
+            'title': 'КПРФ',
+        },
+        'playlist_mincount': 4,
+    }
     
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -289,6 +297,14 @@ class SmotriUserIE(InfoExtractor):
     IE_DESC = 'Smotri.com user videos'
     IE_NAME = 'smotri:user'
     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
+    _TESTS = [{
+        'url': 'http://smotri.com/user/inspector',
+        'info_dict': {
+            'id': 'inspector',
+            'title': 'Inspector',
+        },
+        'playlist_mincount': 9,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/sockshare.py

@@ -61,7 +61,10 @@ class SockshareIE(InfoExtractor):
             r'<a href="([^"]*)".+class="download_file_link"',
             webpage, 'file url')
         video_url = "http://www.sockshare.com" + video_url
-        title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title')
+        title = self._html_search_regex((
+            r'<h1>(.+)<strong>',
+            r'var name = "([^"]+)";'),
+            webpage, 'title', default=None)
         thumbnail = self._html_search_regex(
             r'<img\s+src="([^"]*)".+?name="bg"',
             webpage, 'thumbnail')

youtube_dl/extractor/soundcloud.py

@@ -28,7 +28,8 @@ class SoundcloudIE(InfoExtractor):
     _VALID_URL = r'''(?x)^(?:https?://)?
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?P<uploader>[\w\d-]+)/
-                            (?!sets/)(?P<title>[\w\d-]+)/?
+                            (?!sets/|likes/?(?:$|[?#]))
+                            (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
                        |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
@@ -221,13 +222,16 @@ class SoundcloudIE(InfoExtractor):
 class SoundcloudSetIE(SoundcloudIE):
     _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
     IE_NAME = 'soundcloud:set'
-    # it's in tests/test_playlists.py
+    _TESTS = [{
-    _TESTS = []
+        'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep',
+        'info_dict': {
+            'title': 'The Royal Concept EP',
+        },
+        'playlist_mincount': 6,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
 
         # extract uploader (which is in the url)
         uploader = mobj.group(1)
@@ -246,20 +250,32 @@ class SoundcloudSetIE(SoundcloudIE):
                 self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message']))
             return
 
-        self.report_extraction(full_title)
+        return {
-        return {'_type': 'playlist',
+            '_type': 'playlist',
-                'entries': [self._extract_info_dict(track) for track in info['tracks']],
+            'entries': [self._extract_info_dict(track) for track in info['tracks']],
-                'id': info['id'],
+            'id': info['id'],
-                'title': info['title'],
+            'title': info['title'],
-                }
+        }
 
 
 class SoundcloudUserIE(SoundcloudIE):
     _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$'
     IE_NAME = 'soundcloud:user'
-
+    _TESTS = [{
-    # it's in tests/test_playlists.py
+        'url': 'https://soundcloud.com/the-concept-band',
-    _TESTS = []
+        'info_dict': {
+            'id': '9615865',
+            'title': 'The Royal Concept',
+        },
+        'playlist_mincount': 12
+    }, {
+        'url': 'https://soundcloud.com/the-concept-band/likes',
+        'info_dict': {
+            'id': '9615865',
+            'title': 'The Royal Concept',
+        },
+        'playlist_mincount': 1,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -301,9 +317,18 @@ class SoundcloudUserIE(SoundcloudIE):
 class SoundcloudPlaylistIE(SoundcloudIE):
     _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)'
     IE_NAME = 'soundcloud:playlist'
+    _TESTS = [
 
-     # it's in tests/test_playlists.py
+        {
-    _TESTS = []
+            'url': 'http://api.soundcloud.com/playlists/4110309',
+            'info_dict': {
+                'id': '4110309',
+                'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]',
+                'description': 're:.*?TILT Brass - Bowery Poetry Club',
+            },
+            'playlist_count': 6,
+        }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/sportdeutschland.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    parse_iso8601,
+)
+
+
+class SportDeutschlandIE(InfoExtractor):
+    _VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])'
+    _TESTS = [{
+        'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen',
+        'info_dict': {
+            'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen',
+            'ext': 'mp4',
+            'title': 'LIVE: Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen',
+            'categories': ['Badminton'],
+            'view_count': int,
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 're:^Die Badminton-WM 2014 aus Kopenhagen LIVE',
+            'timestamp': int,
+            'upload_date': 're:^201408[23][0-9]$',
+        },
+        'params': {
+            'skip_download': 'Live stream',
+        },
+    }, {
+        'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
+        'info_dict': {
+            'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
+            'ext': 'mp4',
+            'upload_date': '20140825',
+            'description': 'md5:60a20536b57cee7d9a4ec005e8687504',
+            'timestamp': 1408976060,
+            'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'view_count': int,
+            'categories': ['Li-Ning Badminton WM 2014'],
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        sport_id = mobj.group('sport')
+
+        api_url = 'http://splink.tv/api/permalinks/%s/%s' % (
+            sport_id, video_id)
+        req = compat_urllib_request.Request(api_url, headers={
+            'Accept': 'application/vnd.vidibus.v2.html+json',
+            'Referer': url,
+        })
+        data = self._download_json(req, video_id)
+
+        categories = list(data.get('section', {}).get('tags', {}).values())
+        asset = data['asset']
+
+        formats = []
+        smil_url = asset['video']
+        if '.smil' in smil_url:
+            m3u8_url = smil_url.replace('.smil', '.m3u8')
+            formats.extend(
+                self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4'))
+
+            smil_doc = self._download_xml(
+                smil_url, video_id, note='Downloading SMIL metadata')
+            base_url = smil_doc.find('./head/meta').attrib['base']
+            formats.extend([{
+                'format_id': 'rmtp',
+                'url': base_url,
+                'play_path': n.attrib['src'],
+                'ext': 'flv',
+                'preference': -100,
+                'format_note': 'Seems to fail at example stream',
+            } for n in smil_doc.findall('./body/video')])
+        else:
+            formats.append({'url': smil_url})
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': asset['title'],
+            'thumbnail': asset.get('image'),
+            'description': asset.get('teaser'),
+            'categories': categories,
+            'view_count': asset.get('views'),
+            'rtmp_live': asset.get('live'),
+            'timestamp': parse_iso8601(asset.get('date')),
+        }
+

youtube_dl/extractor/sunporno.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+    qualities,
+    determine_ext,
+)
+
+
+class SunPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.sunporno.com/videos/807778/',
+        'md5': '6457d3c165fd6de062b99ef6c2ff4c86',
+        'info_dict': {
+            'id': '807778',
+            'ext': 'flv',
+            'title': 'md5:0a400058e8105d39e35c35e7c5184164',
+            'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 302,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
+        description = self._html_search_meta('description', webpage, 'description')
+        thumbnail = self._html_search_regex(
+            r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
+
+        duration = parse_duration(self._search_regex(
+            r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False))
+
+        view_count = int_or_none(self._html_search_regex(
+            r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False))
+        comment_count = int_or_none(self._html_search_regex(
+            r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False))
+
+        formats = []
+        quality = qualities(['mp4', 'flv'])
+        for video_url in re.findall(r'<source src="([^"]+)"', webpage):
+            video_ext = determine_ext(video_url)
+            formats.append({
+                'url': video_url,
+                'format_id': video_ext,
+                'quality': quality(video_ext),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'formats': formats,
+            'age_limit': 18,
+        }