release 2014.08.26

Don't rely on the XML being broken (if they fix it, our code wouldn't work anymore).
Instead, use the transform function we already have :)

This partially reverts commit c7bee2a725.

.gitignore

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

README.md

@@ -255,6 +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)
 
@@ -287,6 +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
 
@@ -429,6 +434,7 @@ If you want to add support for a new site, you can follow this quick list (assum
                 'id': '42',
                 'ext': 'mp4',
                 'title': 'Video title goes here',
+                'thumbnail': 're:^https?://.*\.jpg$',
                 # TODO more properties, either as:
                 # * A value
                 # * MD5 checksum; start the string with md5:

test/helper.py

@@ -102,7 +102,10 @@ 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),
+                'Expected a %r object, but got %r' % (compat_str, type(got)))
+            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)

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_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,
@@ -136,12 +137,18 @@ def generator(test_case):
                 self.assertEqual(res_dict['_type'], 'playlist')
                 expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
             if 'playlist_mincount' in test_case:
-                self.assertGreaterEqual(
+                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 at %d in playlist %s, but got %d.')
 
             for tc in test_cases:
                 tc_filename = get_tc_filename(tc)

test/test_playlists.py

@@ -62,6 +62,7 @@ from youtube_dl.extractor import (
     InstagramUserIE,
     CSpanIE,
     AolIE,
+    GameOnePlaylistIE,
 )
 
 
@@ -309,24 +310,6 @@ class TestPlaylists(unittest.TestCase):
         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)
@@ -407,5 +390,6 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['id'], 'rbhagwati2')
         assertGreaterEqual(self, len(result['entries']), 179)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -219,6 +219,7 @@ class TestUtil(unittest.TestCase):
         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(

youtube_dl/YoutubeDL.py

@@ -172,6 +172,7 @@ 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
@@ -424,7 +425,7 @@ 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'])
@@ -480,7 +481,10 @@ 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
@@ -633,6 +637,7 @@ 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

@@ -71,6 +71,9 @@ __authors__  = (
     'Sebastian Haas',
     'Alexander Kirk',
     'Erik Johnson',
+    'Keith Beckman',
+    'Ole Ernst',
+    'Aaron McDaniel (mcd1992)',
 )
 
 __license__ = 'Public Domain'
@@ -117,6 +120,7 @@ from .postprocessor import (
     FFmpegExtractAudioPP,
     FFmpegEmbedSubtitlePP,
     XAttrMetadataPP,
+    ExecAfterDownloadPP,
 )
 
 
@@ -316,6 +320,8 @@ 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',
@@ -546,7 +552,9 @@ 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)
@@ -750,6 +758,7 @@ 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,
@@ -826,6 +835,7 @@ 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:
@@ -849,6 +859,13 @@ 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)

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)
-        request = compat_urllib_request.Request(url, None, headers)
+        add_headers = info_dict.get('http_headers')
+        if add_headers:
+            headers.update(add_headers)
+        data = info_dict.get('http_post_data')
+        http_method = info_dict.get('http_method')
+        basic_request = compat_urllib_request.Request(url, data, headers)
+        request = compat_urllib_request.Request(url, data, headers)
+        if http_method is not None:
+            basic_request.get_method = lambda: http_method
+            request.get_method = lambda: http_method
 
         is_test = self.params.get('test', False)
 

youtube_dl/extractor/__init__.py

@@ -88,6 +88,7 @@ from .engadget import EngadgetIE
 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
@@ -115,7 +116,10 @@ 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
@@ -126,6 +130,7 @@ 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
@@ -183,6 +188,7 @@ 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
@@ -194,6 +200,7 @@ 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 (
@@ -243,6 +250,7 @@ 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
@@ -263,7 +271,7 @@ 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,
@@ -274,6 +282,7 @@ 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
@@ -306,6 +315,7 @@ 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
@@ -386,6 +396,7 @@ 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,

youtube_dl/extractor/arte.py

@@ -177,16 +177,26 @@ 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/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/common.py

@@ -84,6 +84,12 @@ 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)
@@ -434,6 +440,22 @@ class InfoExtractor(object):
         
         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):
@@ -598,11 +620,15 @@ 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')),
             })
@@ -610,6 +636,55 @@ 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:
+                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:
+                    video, audio = codecs.split(',')
+                    f['vcodec'] = video.partition('.')[0]
+                    f['acodec'] = audio.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):
     """

youtube_dl/extractor/ebaumsworld.py

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

youtube_dl/extractor/eighttracks.py

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

youtube_dl/extractor/empflix.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import fix_xml_ampersands
 
 
 class EmpflixIE(InfoExtractor):
@@ -36,7 +37,8 @@ class EmpflixIE(InfoExtractor):
             webpage, 'flashvars.config')
 
         cfg_xml = self._download_xml(
-            cfg_url, video_id, note='Downloading metadata')
+            cfg_url, video_id, note='Downloading metadata',
+            transform_source=fix_xml_ampersands)
 
         formats = [
             {
@@ -44,11 +46,13 @@ class EmpflixIE(InfoExtractor):
                 'format_id': item.find('res').text,
             } for item in cfg_xml.findall('./quality/item')
         ]
+        thumbnail = cfg_xml.find('./startThumb').text
 
         return {
             'id': video_id,
             'title': video_title,
             'description': video_description,
+            'thumbnail': thumbnail,
             'formats': formats,
             'age_limit': age_limit,
         }

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/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 +8,19 @@ 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,
 
     ExtractorError,
+    float_or_none,
     HEADRequest,
+    orderedSet,
     parse_xml,
     smuggle_url,
     unescapeHTML,
     unified_strdate,
+    unsmuggle_url,
     url_basename,
 )
 from .brightcove import BrightcoveIE
@@ -289,6 +290,68 @@ 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,
+        }
     ]
 
     def report_download_webpage(self, video_id):
@@ -301,58 +364,6 @@ 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 +383,43 @@ 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 +456,31 @@ 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:
-            response = self._send_head(url)
+        head_req = HEADRequest(url)
+        response = self._request_webpage(
+            head_req, video_id,
+            note=False, errnote='Could not send HEAD request to %s' % url,
+            fatal=False)
 
+        if response is not False:
             # Check for redirect
             new_url = response.geturl()
             if url != new_url:
                 self.report_following_redirect(new_url)
+                if force_videoid:
+                    new_url = smuggle_url(
+                        new_url, {'force_videoid': force_videoid})
                 return self.url_result(new_url)
 
             # Check for direct link to a video
@@ -439,10 +501,6 @@ 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 +518,11 @@ 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 +538,26 @@ 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 +593,7 @@ class GenericIE(InfoExtractor):
         matches = re.findall(r'''(?x)
             (?:
                 <iframe[^>]+?src=|
+                data-video-url=|
                 <embed[^>]+?src=|
                 embedSWF\(?:\s*
             )
@@ -522,19 +602,15 @@ class GenericIE(InfoExtractor):
                 (?:embed|v)/.+?)
             \1''', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
-                     for tuppl in matches]
-            return self.playlist_result(
-                urlrs, playlist_id=video_id, playlist_title=video_title)
+            return _playlist_from_matches(
+                matches, lambda m: unescapeHTML(m[1]), ie='Youtube')
 
         # Look for embedded Dailymotion player
         matches = re.findall(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(tuppl[1]))
-                     for tuppl in matches]
-            return self.playlist_result(
-                urlrs, playlist_id=video_id, playlist_title=video_title)
+            return _playlist_from_matches(
+                matches, lambda m: unescapeHTML(m[1]))
 
         # Look for embedded Wistia player
         match = re.search(
@@ -553,7 +629,7 @@ 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 +724,8 @@ class GenericIE(InfoExtractor):
         # Look for funnyordie embed
         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
-                     for eurl in matches]
-            return self.playlist_result(
-                urlrs, playlist_id=video_id, playlist_title=video_title)
+            return _playlist_from_matches(
+                matches, getter=unescapeHTML, ie='FunnyOrDie')
 
         # Look for embedded RUTV player
         rutv_url = RUTVIE._extract_url(webpage)
@@ -713,6 +787,13 @@ class GenericIE(InfoExtractor):
         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')
+
         # Start with something easy: JW Player in SWFObject
         found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if not found:
@@ -730,6 +811,14 @@ 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)
@@ -739,7 +828,12 @@ 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
+                    return '.' in vpath and not vpath.endswith('.swf')
+                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)
@@ -776,6 +870,7 @@ 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/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':
-            video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url')
-            return self.url_result(video_url, ie='IGN')
-        elif page_type != 'video':
+        if page_type != 'video':
             multiple_urls = re.findall(
                 '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
                 webpage)

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/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/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/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()
-        thumbnail = self._html_search_regex(
-            r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"',
-            webpage, 'thumbnail URL', fatal=False)
+            [r'<span title="([^"]+)">',
+             r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip()
+        thumbnails = [
+            {
+                '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/patreon.py

@@ -6,7 +6,6 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urlparse,
     js_to_json,
 )
 

youtube_dl/extractor/pbs.py

@@ -54,6 +54,18 @@ class PBSIE(InfoExtractor):
                 '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):
@@ -75,7 +87,7 @@ class PBSIE(InfoExtractor):
                 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',
-        u'file': u'1689755.flv',
-        u'md5': u'374dd6dcedd24234453b295209aa69b6',
-        u'info_dict': {
-            u"upload_date": u"20090708", 
-            u"title": u"Marilyn-Monroe-Bathing",
-            u"age_limit": 18
+        'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
+        'md5': '374dd6dcedd24234453b295209aa69b6',
+        'info_dict': {
+            'id': '1689755',
+            'ext': 'flv',
+            'upload_date': '20090708',
+            '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)
-        if upload_date: upload_date = unified_strdate(upload_date)
+        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False)
+        if upload_date:
+            upload_date = unified_strdate(upload_date)
         age_limit = self._rta_search(webpage)
 
-        info = {'id': video_id,
-                'url': video_url,
-                'uploader': None,
-                'upload_date': upload_date,
-                'title': video_title,
-                'ext': 'flv',
-                'format': 'flv',
-                'age_limit': age_limit}
-
-        return [info]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'upload_date': upload_date,
+            'title': video_title,
+            'ext': 'flv',
+            'format': 'flv',
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/rtlnl.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import parse_duration
 
 
 class RtlXlIE(InfoExtractor):
@@ -20,6 +21,7 @@ class RtlXlIE(InfoExtractor):
                 'onze mobiele apps.',
             'timestamp': 1408051800,
             'upload_date': '20140814',
+            'duration': 576.880,
         },
         'params': {
             # We download the first bytes of the first fragment, it can't be
@@ -35,7 +37,7 @@ class RtlXlIE(InfoExtractor):
         info = self._download_json(
             'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
             uuid)
-        meta = info['meta']
+
         material = info['material'][0]
         episode_info = info['episodes'][0]
 
@@ -45,8 +47,9 @@ class RtlXlIE(InfoExtractor):
 
         return {
             'id': uuid,
-            'title': '%s - %s' % (progname, subtitle), 
+            'title': '%s - %s' % (progname, subtitle),
             'formats': self._extract_f4m_formats(f4m_url, uuid),
             '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',
         },
-    }
-
-    def _decrypt_url(self, 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
+    }, {
+        'note': 'Live stream',
+        'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
+        'info_dict': {
+            'id': '1694255',
+            'ext': 'flv',
+            'title': 'TODO',
+        }
+    }]
 
     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/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/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/sportdeutschland.py

@@ -0,0 +1,77 @@
+# 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>[^?#/]+)(?:$|[?#])'
+    _TEST = {
+        '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': 1409043600,
+            'upload_date': '20140826',
+        },
+        'params': {
+            'skip_download': 'Live stream',
+        },
+    }
+
+    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']
+
+        smil_url = asset['video']
+        m3u8_url = smil_url.replace('.smil', '.m3u8')
+        formats = 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')])
+        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['live'],
+            'timestamp': parse_iso8601(asset.get('date')),
+        }
+

youtube_dl/extractor/vimeo.py

@@ -151,6 +151,19 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
                 'duration': 62,
             }
         },
+        {
+            'note': 'video player needs Referer',
+            'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053',
+            'md5': '6295fdab8f4bf6a002d058b2c6dce276',
+            'info_dict': {
+                'id': '91613211',
+                'ext': 'mp4',
+                'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn',
+                'uploader': 'DevWeek Events',
+                'duration': 2773,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }
+        }
     ]
 
     @classmethod
@@ -205,6 +218,8 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
         if data is not None:
             headers = headers.copy()
             headers.update(data)
+        if 'Referer' not in headers:
+            headers['Referer'] = url
 
         # Extract ID from URL
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/vodlocker.py

@@ -44,7 +44,7 @@ class VodlockerIE(InfoExtractor):
                 req, video_id, 'Downloading video page')
 
         title = self._search_regex(
-            r'id="file_title".*?>\s*(.*?)\s*<span', webpage, 'title')
+            r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
         thumbnail = self._search_regex(
             r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
         url = self._search_regex(

youtube_dl/extractor/wat.py

@@ -2,29 +2,43 @@
 from __future__ import unicode_literals
 
 import re
+import hashlib
 
 from .common import InfoExtractor
-from ..utils import (
-    unified_strdate,
-)
+from ..utils import unified_strdate
 
 
 class WatIE(InfoExtractor):
-    _VALID_URL = r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html'
+    _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html'
     IE_NAME = 'wat.tv'
-    _TEST = {
-        'url': 'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html',
-        'info_dict': {
-            'id': '10631273',
-            'ext': 'mp4',
-            'title': 'World War Z - Philadelphia VOST',
-            'description': 'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr',
+    _TESTS = [
+        {
+            'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
+            'md5': 'ce70e9223945ed26a8056d413ca55dc9',
+            'info_dict': {
+                'id': '11713067',
+                'display_id': 'soupe-figues-l-orange-aux-epices',
+                'ext': 'mp4',
+                'title': 'Soupe de figues à l\'orange et aux épices',
+                'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
+                'upload_date': '20140819',
+                'duration': 120,
+            },
         },
-        'params': {
-            # Sometimes wat serves the whole file with the --test option
-            'skip_download': True,
+        {
+            'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
+            'md5': 'fbc84e4378165278e743956d9c1bf16b',
+            'info_dict': {
+                'id': '11713075',
+                'display_id': 'gregory-lemarchal-voix-ange',
+                'ext': 'mp4',
+                'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
+                'description': 'md5:b7a849cf16a2b733d9cd10c52906dee3',
+                'upload_date': '20140816',
+                'duration': 2910,
+            },
         },
-    }
+    ]
 
     def download_video_info(self, real_id):
         # 'contentv4' is used in the website, but it also returns the related
@@ -36,13 +50,20 @@ class WatIE(InfoExtractor):
         def real_id_for_chapter(chapter):
             return chapter['tc_start'].split('-')[0]
         mobj = re.match(self._VALID_URL, url)
-        short_id = mobj.group('shortID')
-        webpage = self._download_webpage(url, short_id)
+        short_id = mobj.group('short_id')
+        display_id = mobj.group('display_id')
+        webpage = self._download_webpage(url, display_id or short_id)
         real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
 
         video_info = self.download_video_info(real_id)
+
+        geo_list = video_info.get('geoList')
+        country = geo_list[0] if geo_list else ''
+
         chapters = video_info['chapters']
         first_chapter = chapters[0]
+        files = video_info['files']
+        first_file = files[0]
 
         if real_id_for_chapter(first_chapter) != real_id:
             self.to_screen('Multipart video detected')
@@ -61,12 +82,47 @@ class WatIE(InfoExtractor):
             upload_date = unified_strdate(first_chapter['date_diffusion'])
         # Otherwise we can continue and extract just one part, we have to use
         # the short id for getting the video url
+
+        formats = [{
+            'url': 'http://wat.tv/get/android5/%s.mp4' % real_id,
+            'format_id': 'Mobile',
+        }]
+
+        fmts = [('SD', 'web')]
+        if first_file.get('hasHD'):
+            fmts.append(('HD', 'webhd'))
+
+        def compute_token(param):
+            timestamp = '%08x' % int(self._download_webpage(
+                'http://www.wat.tv/servertime', real_id,
+                'Downloading server time').split('|')[0])
+            magic = '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564'
+            return '%s/%s' % (hashlib.md5((magic + param + timestamp).encode('ascii')).hexdigest(), timestamp)
+
+        for fmt in fmts:
+            webid = '/%s/%s' % (fmt[1], real_id)
+            video_url = self._download_webpage(
+                'http://www.wat.tv/get%s?token=%s&getURL=1&country=%s' % (webid, compute_token(webid), country),
+                real_id,
+                'Downloding %s video URL' % fmt[0],
+                'Failed to download %s video URL' % fmt[0],
+                False)
+            if not video_url:
+                continue
+            formats.append({
+                'url': video_url,
+                'ext': 'mp4',
+                'format_id': fmt[0],
+            })
+
         return {
             'id': real_id,
-            'url': 'http://wat.tv/get/android5/%s.mp4' % real_id,
+            'display_id': display_id,
             'title': first_chapter['title'],
             'thumbnail': first_chapter['preview'],
             'description': first_chapter['description'],
             'view_count': video_info['views'],
             'upload_date': upload_date,
+            'duration': first_file['duration'],
+            'formats': formats,
         }

youtube_dl/extractor/wayofthemaster.py

@@ -0,0 +1,52 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class WayOfTheMasterIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.wayofthemaster\.com/([^/?#]*/)*(?P<id>[^/?#]+)\.s?html(?:$|[?#])'
+
+    _TEST = {
+        'url': 'http://www.wayofthemaster.com/hbks.shtml',
+        'md5': '5316b57487ada8480606a93cb3d18d24',
+        'info_dict': {
+            'id': 'hbks',
+            'ext': 'mp4',
+            'title': 'Intelligent Design vs. Evolution',
+        },
+    }
+
+    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._search_regex(
+            r'<img src="images/title_[^"]+".*?alt="([^"]+)"',
+            webpage, 'title', default=None)
+        if title is None:
+            title = self._html_search_regex(
+                r'<title>(.*?)</title>', webpage, 'page title')
+
+        url_base = self._search_regex(
+            r'<param\s+name="?movie"?\s+value=".*?/wotm_videoplayer_highlow[0-9]*\.swf\?vid=([^"]+)"',
+            webpage, 'URL base')
+        formats = [{
+            'format_id': 'low',
+            'quality': 1,
+            'url': url_base + '_low.mp4',
+        }, {
+            'format_id': 'high',
+            'quality': 2,
+            'url': url_base + '_high.mp4',
+        }]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }

youtube_dl/extractor/xhamster.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
-    _VALID_URL = r'http://(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
+    _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
     _TESTS = [
         {
             'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',

youtube_dl/extractor/youtube.py

@@ -37,6 +37,7 @@ from ..utils import (
 class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
+    _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor'
     _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
     _AGE_URL = 'https://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
     _NETRC_MACHINE = 'youtube'
@@ -50,12 +51,19 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             fatal=False))
 
     def _login(self):
+        """
+        Attempt to log in to YouTube.
+        True is returned if successful or skipped.
+        False is returned if login failed.
+
+        If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
+        """
         (username, password) = self._get_login_info()
         # No authentication to be performed
         if username is None:
             if self._LOGIN_REQUIRED:
                 raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
-            return False
+            return True
 
         login_page = self._download_webpage(
             self._LOGIN_URL, None,
@@ -73,6 +81,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                 u'Email': username,
                 u'GALX': galx,
                 u'Passwd': password,
+
                 u'PersistentCookie': u'yes',
                 u'_utf8': u'霱',
                 u'bgresponse': u'js_disabled',
@@ -88,6 +97,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                 u'uilel': u'3',
                 u'hl': u'en_US',
         }
+
         # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
         # chokes on unicode
         login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
@@ -99,6 +109,68 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             note=u'Logging in', errnote=u'unable to log in', fatal=False)
         if login_results is False:
             return False
+
+        if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
+            raise ExtractorError(u'Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
+
+        # Two-Factor
+        # TODO add SMS and phone call support - these require making a request and then prompting the user
+
+        if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None:
+            tfa_code = self._get_tfa_info()
+
+            if tfa_code is None:
+                self._downloader.report_warning(u'Two-factor authentication required. Provide it with --twofactor <code>')
+                self._downloader.report_warning(u'(Note that only TOTP (Google Authenticator App) codes work at this time.)')
+                return False
+
+            # Unlike the first login form, secTok and timeStmp are both required for the TFA form
+
+            match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U)
+            if match is None:
+                self._downloader.report_warning(u'Failed to get secTok - did the page structure change?')
+            secTok = match.group(1)
+            match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U)
+            if match is None:
+                self._downloader.report_warning(u'Failed to get timeStmp - did the page structure change?')
+            timeStmp = match.group(1)
+
+            tfa_form_strs = {
+                u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
+                u'smsToken': u'',
+                u'smsUserPin': tfa_code,
+                u'smsVerifyPin': u'Verify',
+
+                u'PersistentCookie': u'yes',
+                u'checkConnection': u'',
+                u'checkedDomains': u'youtube',
+                u'pstMsg': u'1',
+                u'secTok': secTok,
+                u'timeStmp': timeStmp,
+                u'service': u'youtube',
+                u'hl': u'en_US',
+            }
+            tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in tfa_form_strs.items())
+            tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii')
+
+            tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data)
+            tfa_results = self._download_webpage(
+                tfa_req, None,
+                note=u'Submitting TFA code', errnote=u'unable to submit tfa', fatal=False)
+
+            if tfa_results is False:
+                return False
+
+            if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None:
+                self._downloader.report_warning(u'Two-factor code expired. Please try again, or use a one-use backup code instead.')
+                return False
+            if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None:
+                self._downloader.report_warning(u'unable to log in - did the page structure change?')
+                return False
+            if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
+                self._downloader.report_warning(u'Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
+                return False
+
         if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
             self._downloader.report_warning(u'unable to log in: bad username or password')
             return False

youtube_dl/postprocessor/__init__.py

@@ -9,6 +9,7 @@ from .ffmpeg import (
     FFmpegEmbedSubtitlePP,
 )
 from .xattrpp import XAttrMetadataPP
+from .execafterdownload import ExecAfterDownloadPP
 
 __all__ = [
     'AtomicParsleyPP',
@@ -19,4 +20,5 @@ __all__ = [
     'FFmpegExtractAudioPP',
     'FFmpegEmbedSubtitlePP',
     'XAttrMetadataPP',
+    'ExecAfterDownloadPP',
 ]

youtube_dl/postprocessor/execafterdownload.py

@@ -0,0 +1,31 @@
+from __future__ import unicode_literals
+
+import subprocess
+
+from .common import PostProcessor
+from ..utils import (
+    shlex_quote,
+    PostProcessingError,
+)
+
+
+class ExecAfterDownloadPP(PostProcessor):
+    def __init__(self, downloader=None, verboseOutput=None, exec_cmd=None):
+        self.verboseOutput = verboseOutput
+        self.exec_cmd = exec_cmd
+
+    def run(self, information):
+        cmd = self.exec_cmd
+        if not '{}' in cmd:
+            cmd += ' {}'
+
+        cmd = cmd.replace('{}', shlex_quote(information['filepath']))
+
+        self._downloader.to_screen("[exec] Executing command: %s" % cmd)
+        retCode = subprocess.call(cmd, shell=True)
+        if retCode != 0:
+            raise PostProcessingError(
+                'Command returned error code %d' % retCode)
+
+        return None, information  # by default, keep file and do nothing
+

youtube_dl/utils.py

@@ -192,6 +192,13 @@ try:
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 
+try:
+    from shlex import quote as shlex_quote
+except ImportError:  # Python < 3.3
+    def shlex_quote(s):
+        return "'" + s.replace("'", "'\"'\"'") + "'"
+
+
 def compat_ord(c):
     if type(c) is int: return c
     else: return ord(c)
@@ -759,10 +766,9 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
         return ret
 
     def http_request(self, req):
-        for h,v in std_headers.items():
-            if h in req.headers:
-                del req.headers[h]
-            req.add_header(h, v)
+        for h, v in std_headers.items():
+            if h not in req.headers:
+                req.add_header(h, v)
         if 'Youtubedl-no-compression' in req.headers:
             if 'Accept-encoding' in req.headers:
                 del req.headers['Accept-encoding']
@@ -855,6 +861,7 @@ def unified_strdate(date_str):
         '%Y/%m/%d',
         '%d.%m.%Y',
         '%d/%m/%Y',
+        '%d/%m/%y',
         '%Y/%m/%d %H:%M:%S',
         '%Y-%m-%d %H:%M:%S',
         '%d.%m.%Y %H:%M',
@@ -1285,6 +1292,12 @@ def remove_start(s, start):
     return s
 
 
+def remove_end(s, end):
+    if s.endswith(end):
+        return s[:-len(end)]
+    return s
+
+
 def url_basename(url):
     path = compat_urlparse.urlparse(url).path
     return path.strip(u'/').split(u'/')[-1]
@@ -1324,7 +1337,7 @@ def parse_duration(s):
         return None
 
     m = re.match(
-        r'(?:(?:(?P<hours>[0-9]+)[:h])?(?P<mins>[0-9]+)[:m])?(?P<secs>[0-9]+)s?(?::[0-9]+)?$', s)
+        r'(?:(?:(?P<hours>[0-9]+)[:h])?(?P<mins>[0-9]+)[:m])?(?P<secs>[0-9]+)s?(?::[0-9]+)?(?P<ms>\.[0-9]+)?$', s)
     if not m:
         return None
     res = int(m.group('secs'))
@@ -1332,6 +1345,8 @@ def parse_duration(s):
         res += int(m.group('mins')) * 60
         if m.group('hours'):
             res += int(m.group('hours')) * 60 * 60
+    if m.group('ms'):
+        res += float(m.group('ms'))
     return res
 
 
@@ -1442,6 +1457,12 @@ def urlencode_postdata(*args, **kargs):
     return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii')
 
 
+try:
+    etree_iter = xml.etree.ElementTree.Element.iter
+except AttributeError:  # Python <=2.6
+    etree_iter = lambda n: n.findall('.//*')
+
+
 def parse_xml(s):
     class TreeBuilder(xml.etree.ElementTree.TreeBuilder):
         def doctype(self, name, pubid, system):
@@ -1449,7 +1470,14 @@ def parse_xml(s):
 
     parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder())
     kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {}
-    return xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
+    tree = xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
+    # Fix up XML parser in Python 2.x
+    if sys.version_info < (3, 0):
+        for n in etree_iter(tree):
+            if n.text is not None:
+                if not isinstance(n.text, compat_str):
+                    n.text = n.text.decode('utf-8')
+    return tree
 
 
 if sys.version_info < (3, 0) and sys.platform == 'win32':

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.08.22'
+__version__ = '2014.08.26'