release 2014.04.04.4

Otherwise on python 2.x we get `UnicodeDecodeError` because it may contain non ascii characters.

MANIFEST.in

@@ -3,5 +3,4 @@ include test/*.py
 include test/*.json
 include youtube-dl.bash-completion
 include youtube-dl.1
-recursive-include docs *
-prune docs/_build
+recursive-include docs Makefile conf.py *.rst

README.md

@@ -371,7 +371,67 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). 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). Don't forget to run the tests with `python test/test_download.py TestDownload.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
+If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
+
+1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
+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`:
+
+        # coding: utf-8
+        from __future__ import unicode_literals
+
+        import re
+
+        from .common import InfoExtractor
+        
+        
+        class YourExtractorIE(InfoExtractor):
+            _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
+            _TEST = {
+                'url': 'http://yourextractor.com/watch/42',
+                'md5': 'TODO: md5 sum of the first 10KiB of the video file',
+                'info_dict': {
+                    'id': '42',
+                    'ext': 'mp4',
+                    'title': 'Video title goes here',
+                    # TODO more properties, either as:
+                    # * A value
+                    # * MD5 checksum; start the string with md5:
+                    # * A regular expression; start the string with re:
+                    # * Any Python type (for example int or float)
+                }
+            }
+
+            def _real_extract(self, url):
+                mobj = re.match(self._VALID_URL, url)
+                video_id = mobj.group('id')
+
+                # TODO more code goes here, for example ...
+                webpage = self._download_webpage(url, video_id)
+                title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
+
+                return {
+                    'id': video_id,
+                    'title': title,
+                    # TODO more properties (see youtube_dl/extractor/common.py)
+                }
+
+
+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.
+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:
+
+        $ git add youtube_dl/extractor/__init__.py
+        $ git add youtube_dl/extractor/yourextractor.py
+        $ git commit -m '[yourextractor] Add new extractor'
+        $ git push origin yourextractor
+
+10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
+
+In any case, thank you very much for your contributions!
 
 # BUGS
 

test/test_YoutubeDL.py

@@ -26,16 +26,27 @@ class YDL(FakeYDL):
         self.msgs.append(msg)
 
 
+def _make_result(formats, **kwargs):
+    res = {
+        'formats': formats,
+        'id': 'testid',
+        'title': 'testttitle',
+        'extractor': 'testex',
+    }
+    res.update(**kwargs)
+    return res
+
+
 class TestFormatSelection(unittest.TestCase):
     def test_prefer_free_formats(self):
         # Same resolution => download webm
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 460},
-            {'ext': 'mp4',  'height': 460},
+            {'ext': 'webm', 'height': 460, 'url': 'x'},
+            {'ext': 'mp4', 'height': 460, 'url': 'y'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
         yie = YoutubeIE(ydl)
         yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
@@ -46,8 +57,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 720},
-            {'ext': 'mp4', 'height': 1080},
+            {'ext': 'webm', 'height': 720, 'url': 'a'},
+            {'ext': 'mp4', 'height': 1080, 'url': 'b'},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -60,9 +71,9 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'webm', 'height': 720},
-            {'ext': 'mp4', 'height': 720},
-            {'ext': 'flv', 'height': 720},
+            {'ext': 'webm', 'height': 720, 'url': '_'},
+            {'ext': 'mp4', 'height': 720, 'url': '_'},
+            {'ext': 'flv', 'height': 720, 'url': '_'},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -74,8 +85,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'flv', 'height': 720},
-            {'ext': 'webm', 'height': 720},
+            {'ext': 'flv', 'height': 720, 'url': '_'},
+            {'ext': 'webm', 'height': 720, 'url': '_'},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -91,8 +102,7 @@ class TestFormatSelection(unittest.TestCase):
             {'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
             {'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
         ]
-        info_dict = {
-            'formats': formats, 'extractor': 'test', 'id': 'testvid'}
+        info_dict = _make_result(formats)
 
         ydl = YDL()
         ydl.process_ie_result(info_dict)
@@ -120,12 +130,12 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection(self):
         formats = [
-            {'format_id': '35', 'ext': 'mp4', 'preference': 1},
-            {'format_id': '45', 'ext': 'webm', 'preference': 2},
-            {'format_id': '47', 'ext': 'webm', 'preference': 3},
-            {'format_id': '2', 'ext': 'flv', 'preference': 4},
+            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'},
+            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'},
+            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'},
+            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
 
         ydl = YDL({'format': '20/47'})
         ydl.process_ie_result(info_dict.copy())
@@ -154,12 +164,12 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_audio(self):
         formats = [
-            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none'},
-            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none'},
-            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4},
+            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
 
         ydl = YDL({'format': 'bestaudio'})
         ydl.process_ie_result(info_dict.copy())
@@ -172,10 +182,10 @@ class TestFormatSelection(unittest.TestCase):
         self.assertEqual(downloaded['format_id'], 'audio-low')
 
         formats = [
-            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1},
-            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2},
+            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'},
+            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
 
         ydl = YDL({'format': 'bestaudio/worstaudio/best'})
         ydl.process_ie_result(info_dict.copy())
@@ -184,11 +194,11 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_video(self):
         formats = [
-            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none'},
-            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3},
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
 
         ydl = YDL({'format': 'bestvideo'})
         ydl.process_ie_result(info_dict.copy())
@@ -217,10 +227,12 @@ class TestFormatSelection(unittest.TestCase):
         for f1id, f2id in zip(order, order[1:]):
             f1 = YoutubeIE._formats[f1id].copy()
             f1['format_id'] = f1id
+            f1['url'] = 'url:' + f1id
             f2 = YoutubeIE._formats[f2id].copy()
             f2['format_id'] = f2id
+            f2['url'] = 'url:' + f2id
 
-            info_dict = {'formats': [f1, f2], 'extractor': 'youtube'}
+            info_dict = _make_result([f1, f2], extractor='youtube')
             ydl = YDL()
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])
@@ -228,7 +240,7 @@ class TestFormatSelection(unittest.TestCase):
             downloaded = ydl.downloaded_info_dicts[0]
             self.assertEqual(downloaded['format_id'], f1id)
 
-            info_dict = {'formats': [f2, f1], 'extractor': 'youtube'}
+            info_dict = _make_result([f2, f1], extractor='youtube')
             ydl = YDL()
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])

test/test_all_urls.py

@@ -153,6 +153,9 @@ class TestAllURLsMatching(unittest.TestCase):
         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'])
 
 if __name__ == '__main__':
     unittest.main()

test/test_playlists.py

@@ -42,6 +42,7 @@ from youtube_dl.extractor import (
     ToypicsUserIE,
     XTubeUserIE,
     InstagramUserIE,
+    CSpanIE,
 )
 
 
@@ -314,6 +315,19 @@ class TestPlaylists(unittest.TestCase):
         }
         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')
+        self.assertEqual(len(result['entries']), 9)
+        whole_duration = sum(e['duration'] for e in result['entries'])
+        self.assertEqual(whole_duration, 14855)
+
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -702,6 +702,11 @@ class YoutubeDL(object):
     def process_video_result(self, info_dict, download=True):
         assert info_dict.get('_type', 'video') == 'video'
 
+        if 'id' not in info_dict:
+            raise ExtractorError('Missing "id" field in extractor result')
+        if 'title' not in info_dict:
+            raise ExtractorError('Missing "title" field in extractor result')
+
         if 'playlist' not in info_dict:
             # It isn't part of a playlist
             info_dict['playlist'] = None
@@ -733,6 +738,9 @@ class YoutubeDL(object):
 
         # We check that all the formats have the format and format_id fields
         for i, format in enumerate(formats):
+            if 'url' not in format:
+                raise ExtractorError('Missing "url" key in result (index %d)' % i)
+
             if format.get('format_id') is None:
                 format['format_id'] = compat_str(i)
             if format.get('format') is None:
@@ -743,7 +751,7 @@ class YoutubeDL(object):
                 )
             # Automatically determine file extension if missing
             if 'ext' not in format:
-                format['ext'] = determine_ext(format['url'])
+                format['ext'] = determine_ext(format['url']).lower()
 
         format_limit = self.params.get('format_limit', None)
         if format_limit:
@@ -868,7 +876,7 @@ class YoutubeDL(object):
 
         try:
             dn = os.path.dirname(encodeFilename(filename))
-            if dn != '' and not os.path.exists(dn):
+            if dn and not os.path.exists(dn):
                 os.makedirs(dn)
         except (OSError, IOError) as err:
             self.report_error('unable to create directory ' + compat_str(err))

youtube_dl/__init__.py

@@ -242,7 +242,7 @@ def parseOpts(overrideArguments=None):
         help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
     general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
     general.add_option(
-        '--prefer-insecure', action='store_true', dest='prefer_insecure',
+        '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure',
         help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
     general.add_option(
         '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',

youtube_dl/downloader/common.py

@@ -4,9 +4,10 @@ import sys
 import time
 
 from ..utils import (
+    compat_str,
     encodeFilename,
-    timeconvert,
     format_bytes,
+    timeconvert,
 )
 
 
@@ -173,7 +174,7 @@ class FileDownloader(object):
                 return
             os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
         except (IOError, OSError) as err:
-            self.report_error(u'unable to rename file: %s' % str(err))
+            self.report_error(u'unable to rename file: %s' % compat_str(err))
 
     def try_utime(self, filename, last_modified_hdr):
         """Try to set the last-modified time of the given file."""

youtube_dl/downloader/f4m.py

@@ -297,6 +297,7 @@ class F4mFD(FileDownloader):
                         break
             frags_filenames.append(frag_filename)
 
+        dest_stream.close()
         self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
 
         self.try_rename(tmpfilename, filename)

youtube_dl/extractor/__init__.py

@@ -40,6 +40,7 @@ from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
 from .cmt import CMTIE
+from .cnet import CNETIE
 from .cnn import (
     CNNIE,
     CNNBlogsIE,
@@ -83,6 +84,7 @@ from .fktv import (
 )
 from .flickr import FlickrIE
 from .fourtube import FourTubeIE
+from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -152,10 +154,13 @@ from .mixcloud import MixcloudIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
 from .mooshare import MooshareIE
+from .morningstar import MorningstarIE
+from .motorsport import MotorsportIE
 from .mtv import (
     MTVIE,
     MTVIggyIE,
 )
+from .musicplayon import MusicPlayOnIE
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE
 from .myspass import MySpassIE

youtube_dl/extractor/breakcom.py

@@ -27,9 +27,10 @@ class BreakIE(InfoExtractor):
             webpage, 'info json', flags=re.DOTALL)
         info = json.loads(info_json)
         video_url = info['videoUri']
-        m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
-        if m_youtube is not None:
-            return self.url_result(m_youtube.group(1), 'Youtube')
+        youtube_id = info.get('youtubeId')
+        if youtube_id:
+            return self.url_result(youtube_id, 'Youtube')
+
         final_url = video_url + '?' + info['AuthToken']
         return {
             'id': video_id,

youtube_dl/extractor/brightcove.py

@@ -87,7 +87,7 @@ class BrightcoveIE(InfoExtractor):
         object_str = object_str.replace('<--', '<!--')
         object_str = fix_xml_ampersands(object_str)
 
-        object_doc = xml.etree.ElementTree.fromstring(object_str)
+        object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
         if fv_el is not None:

youtube_dl/extractor/c56.py

@@ -2,39 +2,46 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 
 
 class C56IE(InfoExtractor):
-    _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
+    _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
     IE_NAME = '56.com'
     _TEST = {
         'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
-        'file': '93440716.flv',
         'md5': 'e59995ac63d0457783ea05f93f12a866',
         'info_dict': {
+            'id': '93440716',
+            'ext': 'flv',
             'title': '网事知多少 第32期：车怒',
+            'duration': 283.813,
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
         text_id = mobj.group('textid')
-        info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
-                                           text_id, 'Downloading video info')
-        info = json.loads(info_page)['info']
-        formats = [{
-            'format_id': f['type'],
-            'filesize': int(f['filesize']),
-            'url': f['url']
-        } for f in info['rfiles']]
+
+        page = self._download_json(
+            'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
+
+        info = page['info']
+
+        formats = [
+            {
+                'format_id': f['type'],
+                'filesize': int(f['filesize']),
+                'url': f['url']
+            } for f in info['rfiles']
+        ]
         self._sort_formats(formats)
 
         return {
             'id': info['vid'],
             'title': info['Subject'],
+            'duration': int(info['duration']) / 1000.0,
             'formats': formats,
             'thumbnail': info.get('bimg') or info.get('img'),
         }

youtube_dl/extractor/cnet.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class CNETIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
+    _TEST = {
+        'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
+        'md5': '041233212a0d06b179c87cbcca1577b8',
+        'info_dict': {
+            'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
+            'ext': 'mp4',
+            'title': 'Hands-on with Microsoft Windows 8.1 Update',
+            'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
+            'thumbnail': 're:^http://.*/flmswindows8.jpg$',
+            'uploader_id': 'sarah.mitroff@cbsinteractive.com',
+            'uploader': 'Sarah Mitroff',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+        data_json = self._html_search_regex(
+            r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'",
+            webpage, 'data json')
+        data = json.loads(data_json)
+        vdata = data['video']
+        if not vdata:
+            vdata = data['videos'][0]
+        if not vdata:
+            raise ExtractorError('Cannot find video data')
+
+        video_id = vdata['id']
+        title = vdata['headline']
+        description = vdata.get('dek')
+        thumbnail = vdata.get('image', {}).get('path')
+        author = vdata.get('author')
+        if author:
+            uploader = '%s %s' % (author['firstName'], author['lastName'])
+            uploader_id = author.get('email')
+        else:
+            uploader = None
+            uploader_id = None
+
+        formats = [{
+            'format_id': '%s-%s-%s' % (
+                f['type'], f['format'],
+                int_or_none(f.get('bitrate'), 1000, default='')),
+            'url': f['uri'],
+            'tbr': int_or_none(f.get('bitrate'), 1000),
+        } for f in vdata['files']['data']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/comedycentral.py

@@ -41,9 +41,9 @@ class ComedyCentralShowsIE(InfoExtractor):
     _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
                       |https?://(:www\.)?
                           (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
-                         (full-episodes/(?P<episode>.*)|
+                         (full-episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
                           (?P<clip>
-                              (?:videos/[^/]+/(?P<videotitle>[^/?#]+))
+                              (?:(?:guests/[^/]+|videos)/[^/]+/(?P<videotitle>[^/?#]+))
                               |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
                               |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
                           )|
@@ -59,7 +59,7 @@ class ComedyCentralShowsIE(InfoExtractor):
             'upload_date': '20121213',
             'description': 'Kristen Stewart learns to let loose in "On the Road."',
             'uploader': 'thedailyshow',
-            'title': 'thedailyshow-kristen-stewart part 1',
+            'title': 'thedailyshow kristen-stewart part 1',
         }
     }
 
@@ -165,7 +165,7 @@ class ComedyCentralShowsIE(InfoExtractor):
             content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
             duration = float_or_none(content.attrib.get('duration'))
             mediagen_url = content.attrib['url']
-            guid = itemEl.find('.//guid').text.rpartition(':')[-1]
+            guid = itemEl.find('./guid').text.rpartition(':')[-1]
 
             cdoc = self._download_xml(
                 mediagen_url, epTitle,

youtube_dl/extractor/common.py

@@ -252,6 +252,17 @@ class InfoExtractor(object):
                 outf.write(webpage_bytes)
 
         content = webpage_bytes.decode(encoding, 'replace')
+
+        if (u'<title>Access to this site is blocked</title>' in content and
+                u'Websense' in content[:512]):
+            msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
+            blocked_iframe = self._html_search_regex(
+                r'<iframe src="([^"]+)"', content,
+                u'Websense information URL', default=None)
+            if blocked_iframe:
+                msg += u' Visit %s for more details' % blocked_iframe
+            raise ExtractorError(msg, expected=True)
+
         return (content, urlh)
 
     def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):

youtube_dl/extractor/cspan.py

@@ -4,6 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    int_or_none,
     unescapeHTML,
     find_xpath_attr,
 )
@@ -54,18 +55,29 @@ class CSpanIE(InfoExtractor):
         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
         data = self._download_json(info_url, video_id)
 
-        url = unescapeHTML(data['video']['files'][0]['path']['#text'])
-
-        doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+        doc = self._download_xml(
+            'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
             video_id)
 
-        def find_string(s):
-            return find_xpath_attr(doc, './/string', 'name', s).text
+        title = find_xpath_attr(doc, './/string', 'name', 'title').text
+        thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
+
+        files = data['video']['files']
+
+        entries = [{
+            'id': '%s_%d' % (video_id, partnum + 1),
+            'title': (
+                title if len(files) == 1 else
+                '%s part %d' % (title, partnum + 1)),
+            'url': unescapeHTML(f['path']['#text']),
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': int_or_none(f.get('length', {}).get('#text')),
+        } for partnum, f in enumerate(files)]
 
         return {
+            '_type': 'playlist',
+            'entries': entries,
+            'title': title,
             'id': video_id,
-            'title': find_string('title'),
-            'url': url,
-            'description': description,
-            'thumbnail': find_string('poster'),
         }

youtube_dl/extractor/dailymotion.py

@@ -180,7 +180,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
     IE_NAME = u'dailymotion:playlist'
     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
-    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
+    _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
 
     def _extract_entries(self, id):
@@ -190,10 +190,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
             webpage = self._download_webpage(request,
                                              id, u'Downloading page %s' % pagenum)
 
-            playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage)
-            video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
+            video_ids.extend(re.findall(r'data-id="(.+?)"', webpage))
 
-            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+            if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 break
         return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
                    for video_id in orderedSet(video_ids)]
@@ -212,8 +211,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = u'dailymotion:user'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
-    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
 
     def _real_extract(self, url):

youtube_dl/extractor/franceculture.py

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

youtube_dl/extractor/generic.py

@@ -82,6 +82,17 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Brightcove'],
         },
+        {
+            'url': 'http://www.championat.com/video/football/v/87/87499.html',
+            'md5': 'fb973ecf6e4a78a67453647444222983',
+            'info_dict': {
+                'id': '3414141473001',
+                'ext': 'mp4',
+                'title': 'Видео. Удаление Дзагоева (ЦСКА)',
+                'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
+                'uploader': 'Championat',
+            },
+        },
         # Direct link to a video
         {
             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
@@ -103,20 +114,6 @@ class GenericIE(InfoExtractor):
                 'title': '2cc213299525360.mov',  # that's what we get
             },
         },
-        # second style of embedded ooyala videos
-        {
-            'url': 'http://www.smh.com.au/tv/business/show/financial-review-sunday/behind-the-scenes-financial-review-sunday--4350201.html',
-            'info_dict': {
-                'id': '13djJjYjptA1XpPx8r9kuzPyj3UZH0Uk',
-                'ext': 'mp4',
-                'title': 'Behind-the-scenes: Financial Review Sunday ',
-                'description': 'Step inside Channel Nine studios for an exclusive tour of its upcoming financial business show.',
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-        },
         # google redirect
         {
             'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',

youtube_dl/extractor/keezmovies.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import re
 
@@ -11,22 +13,22 @@ from ..aes import (
     aes_decrypt_text
 )
 
+
 class KeezMoviesIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)'
     _TEST = {
-        u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
-        u'file': u'1214711.mp4',
-        u'md5': u'6e297b7e789329923fcf83abb67c9289',
-        u'info_dict': {
-            u"title": u"Petite Asian Lady Mai Playing In Bathtub",
-            u"age_limit": 18,
+        'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
+        'file': '1214711.mp4',
+        'md5': '6e297b7e789329923fcf83abb67c9289',
+        'info_dict': {
+            'title': 'Petite Asian Lady Mai Playing In Bathtub',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
@@ -38,10 +40,10 @@ class KeezMoviesIE(InfoExtractor):
             embedded_url = mobj.group(1)
             return self.url_result(embedded_url)
 
-        video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, u'title')
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
-        if webpage.find('encrypted=true')!=-1:
-            password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, u'password')
+        video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title')
+        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, 'video_url'))
+        if 'encrypted=true' in webpage:
+            password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, 'password')
             video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]

youtube_dl/extractor/morningstar.py

@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import hashlib
+import json
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_parse_qs,
+    compat_str,
+    int_or_none,
+)
+
+
+class MorningstarIE(InfoExtractor):
+    IE_DESC = 'morningstar.com'
+    _VALID_URL = r'https?://(?:www\.)?morningstar\.com/cover/videocenter\.aspx\?id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869',
+        'md5': '6c0acface7a787aadc8391e4bbf7b0f5',
+        'info_dict': {
+            'id': '615869',
+            'ext': 'mp4',
+            'title': 'Get Ahead of the Curve on 2013 Taxes',
+            'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.",
+            'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.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)
+        title = self._html_search_regex(
+            r'<h1 id="titleLink">(.*?)</h1>', webpage, 'title')
+        video_url = self._html_search_regex(
+            r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"',
+            webpage, 'video URL')
+        thumbnail = self._html_search_regex(
+            r'<input type="hidden" id="hidSnapshot" value="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+        description = self._html_search_regex(
+            r'<div id="mstarDeck".*?>(.*?)</div>',
+            webpage, 'description', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'description': description,
+        }

youtube_dl/extractor/motorsport.py

@@ -0,0 +1,63 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import hashlib
+import json
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_parse_qs,
+    compat_str,
+    int_or_none,
+)
+
+
+class MotorsportIE(InfoExtractor):
+    IE_DESC = 'motorsport.com'
+    _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])'
+    _TEST = {
+        'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
+        'md5': '5592cb7c5005d9b2c163df5ac3dc04e4',
+        'info_dict': {
+            'id': '7063',
+            'ext': 'mp4',
+            'title': 'Red Bull Racing: 2014 Rules Explained',
+            'duration': 207,
+            'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.',
+            'uploader': 'rainiere',
+            'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$'
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+        flashvars_code = self._html_search_regex(
+            r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
+        flashvars = compat_parse_qs(flashvars_code)
+        params = json.loads(flashvars['parameters'][0])
+
+        e = compat_str(int(time.time()) + 24 * 60 * 60)
+        base_video_url = params['location'] + '?e=' + e
+        s = 'h3hg713fh32'
+        h = hashlib.md5(s + base_video_url).hexdigest()
+        video_url = base_video_url + '&h=' + h
+
+        uploader = self._html_search_regex(
+            r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage,
+            'uploader', fatal=False)
+
+        return {
+            'id': params['video_id'],
+            'display_id': display_id,
+            'title': params['title'],
+            'url': video_url,
+            'description': params.get('description'),
+            'thumbnail': params.get('main_thumb'),
+            'duration': int_or_none(params.get('duration')),
+            'uploader': uploader,
+        }

youtube_dl/extractor/musicplayon.py

@@ -0,0 +1,75 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class MusicPlayOnIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=100&play)=(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://en.musicplayon.com/play?v=433377',
+        'info_dict': {
+            'id': '433377',
+            'ext': 'mp4',
+            'title': 'Rick Ross - Interview On Chelsea Lately (2014)',
+            'description': 'Rick Ross Interview On Chelsea Lately',
+            'duration': 342,
+            'uploader': 'ultrafish',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(page)
+        description = self._og_search_description(page)
+        thumbnail = self._og_search_thumbnail(page)
+        duration = self._html_search_meta('video:duration', page, 'duration', fatal=False)
+        view_count = self._og_search_property('count', page, fatal=False)
+        uploader = self._html_search_regex(
+            r'<div>by&nbsp;<a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False)
+
+        formats = [
+            {
+                'url': 'http://media0-eu-nl.musicplayon.com/stream-mobile?id=%s&type=.mp4' % video_id,
+                'ext': 'mp4',
+            }
+        ]
+
+        manifest = self._download_webpage(
+            'http://en.musicplayon.com/manifest.m3u8?v=%s' % video_id, video_id, 'Downloading manifest')
+
+        for entry in manifest.split('#')[1:]:
+            if entry.startswith('EXT-X-STREAM-INF:'):
+                meta, url, _ = entry.split('\n')
+                params = dict(param.split('=') for param in meta.split(',')[1:])
+                formats.append({
+                    'url': url,
+                    'ext': 'mp4',
+                    'tbr': int(params['BANDWIDTH']),
+                    'width': int(params['RESOLUTION'].split('x')[1]),
+                    'height': int(params['RESOLUTION'].split('x')[-1]),
+                    'format_note': params['NAME'].replace('"', '').strip(),
+                })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'duration': int_or_none(duration),
+            'view_count': int_or_none(view_count),
+            'formats': formats,
+        }

youtube_dl/extractor/pornhd.py

@@ -1,44 +1,81 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse
+from ..utils import int_or_none
 
 
 class PornHdIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+    _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
-        'file': '1962.flv',
-        'md5': '35272469887dca97abd30abecc6cdf75',
+        'md5': '956b8ca569f7f4d8ec563e2c41598441',
         'info_dict': {
-            "title": "sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
-            "age_limit": 18,
+            'id': '1962',
+            'ext': 'mp4',
+            'title': 'Sierra loves doing laundry',
+            'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('video_id')
-        video_title = mobj.group('video_title')
+        video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
 
-        next_url = self._html_search_regex(
-            r'&hd=(http.+?)&', webpage, 'video URL')
-        next_url = compat_urllib_parse.unquote(next_url)
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' porn HD Video | PornHD.com '
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
 
-        video_url = self._download_webpage(
-            next_url, video_id, note='Retrieving video URL',
-            errnote='Could not retrieve video URL')
-        age_limit = 18
+        description = self._html_search_regex(
+            r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
+        view_count = int_or_none(self._html_search_regex(
+            r'(\d+) views 	</span>', webpage, 'view count', fatal=False))
+
+        formats = [
+            {
+                'url': url,
+                'ext': format.lower(),
+                'format_id': '%s-%s' % (format.lower(), quality.lower()),
+                'quality': 1 if quality.lower() == 'high' else 0,
+            } for format, quality, url in re.findall(
+                r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
+        ]
+
+        mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
+        if mobj:
+            flashvars = json.loads(mobj.group('flashvars'))
+            formats.extend([
+                {
+                    'url': flashvars['hashlink'].replace('?noProxy=1', ''),
+                    'ext': 'flv',
+                    'format_id': 'flv-low',
+                    'quality': 0,
+                },
+                {
+                    'url': flashvars['hd'].replace('?noProxy=1', ''),
+                    'ext': 'flv',
+                    'format_id': 'flv-high',
+                    'quality': 1,
+                }
+            ])
+            thumbnail = flashvars['urlWallpaper']
+        else:
+            thumbnail = self._og_search_thumbnail(webpage)
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'flv',
-            'title': video_title,
-            'age_limit': age_limit,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': 18,
         }

youtube_dl/extractor/rts.py

@@ -9,46 +9,133 @@ from ..utils import (
     parse_duration,
     parse_iso8601,
     unescapeHTML,
+    compat_str,
 )
 
 
 class RTSIE(InfoExtractor):
     IE_DESC = 'RTS.ch'
-    _VALID_URL = r'^https?://(?:www\.)?rts\.ch/archives/tv/[^/]+/(?P<id>[0-9]+)-.*?\.html'
+    _VALID_URL = r'^https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-.*?\.html'
 
-    _TEST = {
-        'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
-        'md5': '753b877968ad8afaeddccc374d4256a5',
-        'info_dict': {
-            'id': '3449373',
-            'ext': 'mp4',
-            'duration': 1488,
-            'title': 'Les Enfants Terribles',
-            'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
-            'uploader': 'Divers',
-            'upload_date': '19680921',
-            'timestamp': -40280400,
-            'thumbnail': 're:^https?://.*\.image'
+    _TESTS = [
+        {
+            'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
+            'md5': '753b877968ad8afaeddccc374d4256a5',
+            'info_dict': {
+                'id': '3449373',
+                'ext': 'mp4',
+                'duration': 1488,
+                'title': 'Les Enfants Terribles',
+                'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
+                'uploader': 'Divers',
+                'upload_date': '19680921',
+                'timestamp': -40280400,
+                'thumbnail': 're:^https?://.*\.image'
+            },
         },
-    }
+        {
+            'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
+            'md5': 'c197f0b2421995c63a64cc73d800f42e',
+            'info_dict': {
+                'id': '5738317',
+                'ext': 'mp4',
+                'duration': 55,
+                'title': 'Bande de lancement de Passe-moi les jumelles',
+                'description': '',
+                'uploader': 'Passe-moi les jumelles',
+                'upload_date': '20140404',
+                'timestamp': 1396635300,
+                'thumbnail': 're:^https?://.*\.image'
+            },
+        },
+        {
+            'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
+            'md5': 'b4326fecd3eb64a458ba73c73e91299d',
+            'info_dict': {
+                'id': '5745975',
+                'ext': 'mp4',
+                'duration': 48,
+                'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
+                'description': 'Hockey - Playoff',
+                'uploader': 'Hockey',
+                'upload_date': '20140403',
+                'timestamp': 1396556882,
+                'thumbnail': 're:^https?://.*\.image'
+            },
+            'skip': 'Blocked outside Switzerland',
+        },
+        {
+            'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
+            'md5': '9bb06503773c07ce83d3cbd793cebb91',
+            'info_dict': {
+                'id': '5745356',
+                'ext': 'mp4',
+                'duration': 33,
+                'title': 'Londres cachée par un épais smog',
+                'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
+                'uploader': 'Le Journal en continu',
+                'upload_date': '20140403',
+                'timestamp': 1396537322,
+                'thumbnail': 're:^https?://.*\.image'
+            },
+        },
+        {
+            'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
+            'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
+            'info_dict': {
+                'id': '5706148',
+                'ext': 'mp3',
+                'duration': 123,
+                'title': '"Urban Hippie", de Damien Krisl',
+                'description': 'Des Hippies super glam.',
+                'upload_date': '20140403',
+                'timestamp': 1396551600,
+            },
+        },
+    ]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
         video_id = m.group('id')
 
-        all_info = self._download_json(
-            'http://www.rts.ch/a/%s.html?f=json/article' % video_id, video_id)
-        info = all_info['video']['JSONinfo']
+        def download_json(video_id):
+            return self._download_json(
+                'http://www.rts.ch/a/%s.html?f=json/article' % video_id, video_id)
+
+        all_info = download_json(video_id)
+
+        # video_id extracted out of URL is not always a real id
+        if 'video' not in all_info and 'audio' not in all_info:
+            page = self._download_webpage(url, video_id)
+            video_id = self._html_search_regex(r'<(?:video|audio) data-id="(\d+)"', page, 'video id')
+            all_info = download_json(video_id)
+
+        info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 
         upload_timestamp = parse_iso8601(info.get('broadcast_date'))
-        duration = parse_duration(info.get('duration'))
+        duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
+        if isinstance(duration, compat_str):
+            duration = parse_duration(duration)
+        view_count = info.get('plays')
         thumbnail = unescapeHTML(info.get('preview_image_url'))
+
+        def extract_bitrate(url):
+            return int_or_none(self._search_regex(
+                r'-([0-9]+)k\.', url, 'bitrate', default=None))
+
         formats = [{
             'format_id': fid,
             'url': furl,
-            'tbr': int_or_none(self._search_regex(
-                r'-([0-9]+)k\.', furl, 'bitrate', default=None)),
+            'tbr': extract_bitrate(furl),
         } for fid, furl in info['streams'].items()]
+
+        if 'media' in info:
+            formats.extend([{
+                'format_id': '%s-%sk' % (media['ext'], media['rate']),
+                'url': 'http://download-video.rts.ch/%s' % media['url'],
+                'tbr': media['rate'] or extract_bitrate(media['url']),
+            } for media in info['media'] if media.get('rate')])
+
         self._sort_formats(formats)
 
         return {
@@ -57,6 +144,7 @@ class RTSIE(InfoExtractor):
             'title': info['title'],
             'description': info.get('intro'),
             'duration': duration,
+            'view_count': view_count,
             'uploader': info.get('programName'),
             'timestamp': upload_timestamp,
             'thumbnail': thumbnail,

youtube_dl/extractor/rutube.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
-import json
 import itertools
 
 from .common import InfoExtractor
@@ -39,17 +38,15 @@ class RutubeIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        
-        api_response = self._download_webpage(
+
+        video = self._download_json(
             'http://rutube.ru/api/video/%s/?format=json' % video_id,
             video_id, 'Downloading video JSON')
-        video = json.loads(api_response)
-        
-        api_response = self._download_webpage(
+
+        trackinfo = self._download_json(
             'http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id,
             video_id, 'Downloading trackinfo JSON')
-        trackinfo = json.loads(api_response)
-        
+
         # Some videos don't have the author field
         author = trackinfo.get('author') or {}
         m3u8_url = trackinfo['video_balancer'].get('m3u8')
@@ -82,10 +79,9 @@ class RutubeChannelIE(InfoExtractor):
     def _extract_videos(self, channel_id, channel_title=None):
         entries = []
         for pagenum in itertools.count(1):
-            api_response = self._download_webpage(
+            page = self._download_json(
                 self._PAGE_TEMPLATE % (channel_id, pagenum),
                 channel_id, 'Downloading page %s' % pagenum)
-            page = json.loads(api_response)
             results = page['results']
             if not results:
                 break
@@ -111,10 +107,9 @@ class RutubeMovieIE(RutubeChannelIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         movie_id = mobj.group('id')
-        api_response = self._download_webpage(
+        movie = self._download_json(
             self._MOVIE_TEMPLATE % movie_id, movie_id,
             'Downloading movie JSON')
-        movie = json.loads(api_response)
         movie_name = movie['name']
         return self._extract_videos(movie_id, movie_name)
 

youtube_dl/extractor/vk.py

@@ -16,7 +16,7 @@ from ..utils import (
 
 class VKIE(InfoExtractor):
     IE_NAME = 'vk.com'
-    _VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
+    _VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
     _NETRC_MACHINE = 'vk'
 
     _TESTS = [

youtube_dl/extractor/wimp.py

@@ -3,11 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 
 
 class WimpIE(InfoExtractor):
     _VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.wimp.com/maruexhausted/',
         'md5': 'f1acced123ecb28d9bb79f2479f2b6a1',
         'info_dict': {
@@ -16,7 +17,20 @@ class WimpIE(InfoExtractor):
             'title': 'Maru is exhausted.',
             'description': 'md5:57e099e857c0a4ea312542b684a869b8',
         }
-    }
+    }, {
+        # youtube video
+        'url': 'http://www.wimp.com/clowncar/',
+        'info_dict': {
+            'id': 'cG4CEr2aiSg',
+            'ext': 'mp4',
+            'title': 'Basset hound clown car...incredible!',
+            'description': 'md5:8d228485e0719898c017203f900b3a35',
+            'uploader': 'Gretchen Hoey',
+            'uploader_id': 'gretchenandjeff1',
+            'upload_date': '20140303',
+        },
+        'add_ie': ['Youtube'],
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -24,6 +38,13 @@ class WimpIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         video_url = self._search_regex(
             r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL')
+        if YoutubeIE.suitable(video_url):
+            self.to_screen('Found YouTube video')
+            return {
+                '_type': 'url',
+                'url': video_url,
+                'ie_key': YoutubeIE.ie_key(),
+            }
 
         return {
             'id': video_id,
@@ -31,4 +52,4 @@ class WimpIE(InfoExtractor):
             'title': self._og_search_title(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
-        }
+        }

youtube_dl/extractor/yahoo.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import itertools
-import json
 import re
 
 from .common import InfoExtractor, SearchInfoExtractor
@@ -19,18 +18,20 @@ class YahooIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
-            'file': '214727115.mp4',
             'md5': '4962b075c08be8690a922ee026d05e69',
             'info_dict': {
+                'id': '214727115',
+                'ext': 'mp4',
                 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
                 'description': 'Julian and Travis watch Julian Smith',
             },
         },
         {
             'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
-            'file': '103000935.mp4',
             'md5': 'd6e6fc6e1313c608f316ddad7b82b306',
             'info_dict': {
+                'id': '103000935',
+                'ext': 'mp4',
                 'title': 'Codefellas - The Cougar Lies with Spanish Moss',
                 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
             },
@@ -60,10 +61,9 @@ class YahooIE(InfoExtractor):
             'env': 'prod',
             'format': 'json',
         })
-        query_result_json = self._download_webpage(
+        query_result = self._download_json(
             'http://video.query.yahoo.com/v1/public/yql?' + data,
             video_id, 'Downloading video info')
-        query_result = json.loads(query_result_json)
         info = query_result['query']['results']['mediaObj'][0]
         meta = info['meta']
 
@@ -86,7 +86,6 @@ class YahooIE(InfoExtractor):
             else:
                 format_url = compat_urlparse.urljoin(host, path)
                 format_info['url'] = format_url
-                
             formats.append(format_info)
 
         self._sort_formats(formats)
@@ -134,27 +133,25 @@ class YahooSearchIE(SearchInfoExtractor):
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""
-
-        res = {
-            '_type': 'playlist',
-            'id': query,
-            'entries': []
-        }
-        for pagenum in itertools.count(0): 
+        entries = []
+        for pagenum in itertools.count(0):
             result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
-            webpage = self._download_webpage(result_url, query,
-                                             note='Downloading results page '+str(pagenum+1))
-            info = json.loads(webpage)
+            info = self._download_json(result_url, query,
+                note='Downloading results page '+str(pagenum+1))
             m = info['m']
             results = info['results']
 
             for (i, r) in enumerate(results):
-                if (pagenum * 30) +i >= n:
+                if (pagenum * 30) + i >= n:
                     break
                 mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
                 e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
-                res['entries'].append(e)
-            if (pagenum * 30 +i >= n) or (m['last'] >= (m['total'] -1)):
+                entries.append(e)
+            if (pagenum * 30 + i >= n) or (m['last'] >= (m['total'] - 1)):
                 break
 
-        return res
+        return {
+            '_type': 'playlist',
+            'id': query,
+            'entries': entries,
+        }

youtube_dl/extractor/youtube.py

@@ -1453,7 +1453,8 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
             more_widget_html = more['load_more_widget_html']
 
         playlist_title = self._html_search_regex(
-                r'<h1 class="pl-header-title">\s*(.*?)\s*</h1>', page, u'title')
+            r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
+            page, u'title')
 
         url_results = self._ids_to_results(ids)
         return self.playlist_result(url_results, playlist_id, playlist_title)
@@ -1738,11 +1739,10 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
         feed_entries = []
         paging = 0
         for i in itertools.count(1):
-            info = self._download_webpage(self._FEED_TEMPLATE % paging,
+            info = self._download_json(self._FEED_TEMPLATE % paging,
                                           u'%s feed' % self._FEED_NAME,
                                           u'Downloading page %s' % i)
-            info = json.loads(info)
-            feed_html = info['feed_html']
+            feed_html = info.get('feed_html') or info.get('content_html')
             m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
             ids = orderedSet(m.group(1) for m in m_ids)
             feed_entries.extend(
@@ -1754,7 +1754,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
         return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
 
 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
-    IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword(requires authentication)'
+    IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
     _FEED_NAME = 'subscriptions'
     _PLAYLIST_TITLE = u'Youtube Subscriptions'

youtube_dl/utils.py

@@ -1176,12 +1176,12 @@ class HEADRequest(compat_urllib_request.Request):
         return "HEAD"
 
 
-def int_or_none(v, scale=1):
-    return v if v is None else (int(v) // scale)
+def int_or_none(v, scale=1, default=None):
+    return default if v is None else (int(v) // scale)
 
 
-def float_or_none(v, scale=1):
-    return v if v is None else (float(v) / scale)
+def float_or_none(v, scale=1, default=None):
+    return default if v is None else (float(v) / scale)
 
 
 def parse_duration(s):
@@ -1264,8 +1264,8 @@ class PagedList(object):
 
 def uppercase_escape(s):
     return re.sub(
-        r'\\U([0-9a-fA-F]{8})',
-        lambda m: compat_chr(int(m.group(1), base=16)), s)
+        r'\\U[0-9a-fA-F]{8}',
+        lambda m: m.group(0).decode('unicode-escape'), s)
 
 try:
     struct.pack(u'!I', 0)

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.04.01.2'
+__version__ = '2014.04.04.4'