release 2014.02.08

[Tube8] Extended valid urls schema

test/test_all_urls.py

@@ -37,6 +37,8 @@ class TestAllURLsMatching(unittest.TestCase):
         assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
         assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
         self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
+        # Top tracks
+        assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
 
     def test_youtube_matching(self):
         self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))

test/test_download.py

@@ -22,6 +22,7 @@ import socket
 
 import youtube_dl.YoutubeDL
 from youtube_dl.utils import (
+    compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_HTTPError,
@@ -110,7 +111,7 @@ def generator(test_case):
                     ydl.download([test_case['url']])
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
-                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
+                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
                         raise
 
                     if try_num == RETRIES:

test/test_playlists.py

@@ -34,6 +34,7 @@ from youtube_dl.extractor import (
     KhanAcademyIE,
     EveryonesMixtapeIE,
     RutubeChannelIE,
+    GoogleSearchIE,
     GenericIE,
 )
 
@@ -240,6 +241,14 @@ 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.assertTrue(len(result['entries']) == 15)
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -117,6 +117,13 @@ class TestYoutubeLists(unittest.TestCase):
         original_video = entries[0]
         self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
 
+    def test_youtube_toptracks(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
+        entries = result['entries']
+        self.assertEqual(len(entries), 100)
+
     def test_youtube_toplist(self):
         dl = FakeYDL()
         ie = YoutubeTopListIE(dl)

youtube_dl/__init__.py

@@ -41,6 +41,7 @@ __authors__  = (
     'Chris Gahan',
     'Saimadhav Heblikar',
     'Mike Col',
+    'Andreas Schmitz',
 )
 
 __license__ = 'Public Domain'

youtube_dl/downloader/rtmp.py

@@ -87,8 +87,10 @@ class RtmpFD(FileDownloader):
         url = info_dict['url']
         player_url = info_dict.get('player_url', None)
         page_url = info_dict.get('page_url', None)
+        app = info_dict.get('app', None)
         play_path = info_dict.get('play_path', None)
         tc_url = info_dict.get('tc_url', None)
+        flash_version = info_dict.get('flash_version', None)
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
 
@@ -111,12 +113,16 @@ class RtmpFD(FileDownloader):
             basic_args += ['--swfVfy', player_url]
         if page_url is not None:
             basic_args += ['--pageUrl', page_url]
+        if app is not None:
+            basic_args += ['--app', app]
         if play_path is not None:
             basic_args += ['--playpath', play_path]
         if tc_url is not None:
             basic_args += ['--tcUrl', url]
         if test:
             basic_args += ['--stop', '1']
+        if flash_version is not None:
+            basic_args += ['--flashVer', flash_version]
         if live:
             basic_args += ['--live']
         if conn:

youtube_dl/extractor/__init__.py

@@ -15,6 +15,7 @@ from .arte import (
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
+from .bbccouk import BBCCoUkIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
@@ -25,6 +26,7 @@ from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .cbs import CBSIE
 from .channel9 import Channel9IE
+from .chilloutzone import ChilloutzoneIE
 from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
@@ -54,12 +56,14 @@ from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
+from .elpais import ElPaisIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
+from .firstpost import FirstpostIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
@@ -118,6 +122,7 @@ from .lynda import (
     LyndaIE,
     LyndaCourseIE
 )
+from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
@@ -139,8 +144,10 @@ from .myvideo import MyVideoIE
 from .naver import NaverIE
 from .nba import NBAIE
 from .nbc import NBCNewsIE
+from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
+from .nfb import NFBIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE

youtube_dl/extractor/bbccouk.py

@@ -0,0 +1,116 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class BBCCoUkIE(InfoExtractor):
+    IE_NAME = 'bbc.co.uk'
+    IE_DESC = 'BBC - iPlayer Radio'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>[\da-z]{8})'
+
+    _TEST = {
+        'url': 'http://www.bbc.co.uk/programmes/p01q7wz1',
+        'info_dict': {
+            'id': 'p01q7wz4',
+            'ext': 'flv',
+            'title': 'Friction: Blu Mar Ten guest mix: Blu Mar Ten - Guest Mix',
+            'description': 'Blu Mar Ten deliver a Guest Mix for Friction.',
+            'duration': 1936,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        group_id = mobj.group('id')
+
+        playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
+            'Downloading playlist XML')
+
+        item = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}item')
+        if item is None:
+            no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+            if no_items is not None:
+                reason = no_items.get('reason')
+                if reason == 'preAvailability':
+                    msg = 'Episode %s is not yet available' % group_id
+                elif reason == 'postAvailability':
+                    msg = 'Episode %s is no longer available' % group_id
+                else:
+                    msg = 'Episode %s is not available: %s' % (group_id, reason)
+                raise ExtractorError(msg, expected=True)
+            raise ExtractorError('Failed to extract media for episode %s' % group_id, expected=True)
+
+        title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
+        description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+
+        radio_programme_id = item.get('identifier')
+        duration = int(item.get('duration'))
+
+        media_selection = self._download_xml(
+            'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'  % radio_programme_id,
+            radio_programme_id, 'Downloading media selection XML')
+
+        formats = []
+        for media in media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media'):
+            bitrate = int(media.get('bitrate'))
+            encoding = media.get('encoding')
+            service = media.get('service')
+            connection = media.find('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
+            protocol = connection.get('protocol')
+            priority = connection.get('priority')
+            supplier = connection.get('supplier')
+            if protocol == 'http':
+                href = connection.get('href')
+                # ASX playlist
+                if supplier == 'asx':
+                    asx = self._download_xml(href, radio_programme_id, 'Downloading %s ASX playlist' % service)
+                    for i, ref in enumerate(asx.findall('./Entry/ref')):
+                        formats.append({
+                            'url': ref.get('href'),
+                            'format_id': '%s_ref%s' % (service, i),
+                            'abr': bitrate,
+                            'acodec': encoding,
+                            'preference': priority,
+                        })
+                    continue
+                # Direct link
+                formats.append({
+                    'url': href,
+                    'format_id': service,
+                    'abr': bitrate,
+                    'acodec': encoding,
+                    'preference': priority,
+                })
+            elif protocol == 'rtmp':
+                application = connection.get('application', 'ondemand')
+                auth_string = connection.get('authString')
+                identifier = connection.get('identifier')
+                server = connection.get('server')
+                formats.append({
+                    'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
+                    'play_path': identifier,
+                    'app': '%s?%s' % (application, auth_string),
+                    'rtmp_live': False,
+                    'ext': 'flv',
+                    'format_id': service,
+                    'abr': bitrate,
+                    'acodec': encoding,
+                    'preference': priority,
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': radio_programme_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/channel9.py

@@ -15,14 +15,15 @@ class Channel9IE(InfoExtractor):
     '''
     IE_DESC = 'Channel 9'
     IE_NAME = 'channel9'
-    _VALID_URL = r'^https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
+    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
 
     _TESTS = [
         {
             'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
-            'file': 'Events_TechEd_Australia_2013_KOS002.mp4',
             'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
             'info_dict': {
+                'id': 'Events/TechEd/Australia/2013/KOS002',
+                'ext': 'mp4',
                 'title': 'Developer Kick-Off Session: Stuff We Love',
                 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
                 'duration': 4576,
@@ -35,9 +36,10 @@ class Channel9IE(InfoExtractor):
         },
         {
             'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
-            'file': 'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4',
             'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
             'info_dict': {
+                'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
+                'ext': 'mp4',
                 'title': 'Self-service BI with Power BI - nuclear testing',
                 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
                 'duration': 1540,

youtube_dl/extractor/chilloutzone.py

@@ -0,0 +1,97 @@
+from __future__ import unicode_literals
+
+import re
+import base64
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError
+)
+
+
+class ChilloutzoneIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
+        'md5': 'a76f3457e813ea0037e5244f509e66d1',
+        'info_dict': {
+            'id': 'enemene-meck-alle-katzen-weg',
+            'ext': 'mp4',
+            'title': 'Enemene Meck - Alle Katzen weg',
+            'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
+        },
+    }, {
+        'note': 'Video hosted at YouTube',
+        'url': 'http://www.chilloutzone.net/video/eine-sekunde-bevor.html',
+        'info_dict': {
+            'id': '1YVQaAgHyRU',
+            'ext': 'mp4',
+            'title': '16 Photos Taken 1 Second Before Disaster',
+            'description': 'md5:58a8fcf6a459fe0a08f54140f0ad1814',
+            'uploader': 'BuzzFeedVideo',
+            'uploader_id': 'BuzzFeedVideo',
+            'upload_date': '20131105',
+        },
+    }, {
+        'note': 'Video hosted at Vimeo',
+        'url': 'http://www.chilloutzone.net/video/icon-blending.html',
+        'md5': '2645c678b8dc4fefcc0e1b60db18dac1',
+        'info_dict': {
+            'id': '85523671',
+            'ext': 'mp4',
+            'title': 'The Sunday Times - Icons',
+            'description': 'md5:3e5e8e839f076a637c6b9406c8f25c4c',
+            'uploader': 'Us',
+            'uploader_id': 'usfilms',
+            'upload_date': '20140131'
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        base64_video_info = self._html_search_regex(
+            r'var cozVidData = "(.+?)";', webpage, 'video data')
+        decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
+        video_info_dict = json.loads(decoded_video_info)
+
+        # get video information from dict
+        video_url = video_info_dict['mediaUrl']
+        description = clean_html(video_info_dict.get('description'))
+        title = video_info_dict['title']
+        native_platform = video_info_dict['nativePlatform']
+        native_video_id = video_info_dict['nativeVideoId']
+        source_priority = video_info_dict['sourcePriority']
+
+        # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
+        if native_platform is None:
+            youtube_url = self._html_search_regex(
+                r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+                webpage, 'fallback video URL', default=None)
+            if youtube_url is not None:
+                return self.url_result(youtube_url, ie='Youtube')
+
+        # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
+        # the own CDN
+        if source_priority == 'native':
+            if native_platform == 'youtube':
+                return self.url_result(native_video_id, ie='Youtube')
+            if native_platform == 'vimeo':
+                return self.url_result(
+                    'http://vimeo.com/' + native_video_id, ie='Vimeo')
+
+        if not video_url:
+            raise ExtractorError('No video found')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/collegehumor.py

@@ -4,6 +4,7 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class CollegeHumorIE(InfoExtractor):
@@ -11,22 +12,25 @@ class CollegeHumorIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
-        'file': '6902724.mp4',
         'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
         'info_dict': {
+            'id': '6902724',
+            'ext': 'mp4',
             'title': 'Comic-Con Cosplay Catastrophe',
-            'description': 'Fans get creative this year at San Diego.  Too',
+            'description': 'Fans get creative this year',
             'age_limit': 13,
         },
     },
     {
         'url': 'http://www.collegehumor.com/video/3505939/font-conference',
-        'file': '3505939.mp4',
         'md5': '72fa701d8ef38664a4dbb9e2ab721816',
         'info_dict': {
+            'id': '3505939',
+            'ext': 'mp4',
             'title': 'Font Conference',
-            'description': 'This video wasn\'t long enough, so we made it double-spaced.',
+            'description': 'This video wasn\'t long enough,',
             'age_limit': 10,
+            'duration': 179,
         },
     },
     # embedded youtube video
@@ -82,6 +86,8 @@ class CollegeHumorIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
+        duration = int_or_none(vdata.get('duration'), 1000)
+
         return {
             'id': video_id,
             'title': vdata['title'],
@@ -89,4 +95,5 @@ class CollegeHumorIE(InfoExtractor):
             'thumbnail': vdata.get('thumbnail'),
             'formats': formats,
             'age_limit': age_limit,
+            'duration': duration,
         }

youtube_dl/extractor/elpais.py

@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class ElPaisIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])'
+    IE_DESC = 'El País'
+
+    _TEST = {
+        'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',
+        'md5': '98406f301f19562170ec071b83433d55',
+        'info_dict': {
+            'id': 'tiempo-nuevo-recetas-viejas',
+            'ext': 'mp4',
+            'title': 'Tiempo nuevo, recetas viejas',
+            'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.',
+            'upload_date': '20140206',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        prefix = self._html_search_regex(
+            r'var url_cache = "([^"]+)";', webpage, 'URL prefix')
+        video_suffix = self._search_regex(
+            r"URLMediaFile = url_cache \+ '([^']+)'", webpage, 'video URL')
+        video_url = prefix + video_suffix
+        thumbnail_suffix = self._search_regex(
+            r"URLMediaStill = url_cache \+ '([^']+)'", webpage, 'thumbnail URL',
+            fatal=False)
+        thumbnail = (
+            None if thumbnail_suffix is None
+            else prefix + thumbnail_suffix)
+        title = self._html_search_regex(
+            '<h2 class="entry-header entry-title.*?>(.*?)</h2>',
+            webpage, 'title')
+        date_str = self._search_regex(
+            r'<p class="date-header date-int updated"\s+title="([^"]+)">',
+            webpage, 'upload date', fatal=False)
+        upload_date = (None if date_str is None else unified_strdate(date_str))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/firstpost.py

@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class FirstpostIE(InfoExtractor):
+    IE_NAME = 'Firstpost.com'
+    _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
+
+    _TEST = {
+        'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
+        'md5': 'ee9114957692f01fb1263ed87039112a',
+        'info_dict': {
+            'id': '1025403',
+            'ext': 'mp4',
+            'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
+            'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._html_search_regex(
+            r'<div.*?name="div_video".*?flashvars="([^"]+)">',
+            webpage, 'video URL')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/googlesearch.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import itertools
 import re
 
@@ -8,32 +10,42 @@ from ..utils import (
 
 
 class GoogleSearchIE(SearchInfoExtractor):
-    IE_DESC = u'Google Video search'
-    _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
+    IE_DESC = 'Google Video search'
     _MAX_RESULTS = 1000
-    IE_NAME = u'video.google:search'
+    IE_NAME = 'video.google:search'
     _SEARCH_KEY = 'gvsearch'
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""
 
+        entries = []
         res = {
             '_type': 'playlist',
             'id': query,
-            'entries': []
+            'title': query,
         }
 
-        for pagenum in itertools.count(1):
-            result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10)
-            webpage = self._download_webpage(result_url, u'gvsearch:' + query,
-                                             note='Downloading result page ' + str(pagenum))
+        for pagenum in itertools.count():
+            result_url = (
+                'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en'
+                % (compat_urllib_parse.quote_plus(query), pagenum * 10))
 
-            for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage):
-                e = {
+            webpage = self._download_webpage(
+                result_url, 'gvsearch:' + query,
+                note='Downloading result page ' + str(pagenum + 1))
+
+            for hit_idx, mobj in enumerate(re.finditer(
+                    r'<h3 class="r"><a href="([^"]+)"', webpage)):
+
+                # Skip playlists
+                if not re.search(r'id="vidthumb%d"' % (hit_idx + 1), webpage):
+                    continue
+
+                entries.append({
                     '_type': 'url',
                     'url': mobj.group(1)
-                }
-                res['entries'].append(e)
+                })
 
-            if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
+            if (len(entries) >= n) or not re.search(r'class="pn" id="pnnext"', webpage):
+                res['entries'] = entries[:n]
                 return res

youtube_dl/extractor/ina.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class InaIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?ina\.fr/video/(?P<id>I?[A-F0-9]+)/.*'
+    _VALID_URL = r'http://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
     _TEST = {
         'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
         'md5': 'a667021bf2b41f8dc6049479d9bb38a3',

youtube_dl/extractor/ivi.py

@@ -14,15 +14,16 @@ from ..utils import (
 class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'
-    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
 
     _TESTS = [
         # Single movie
         {
             'url': 'http://www.ivi.ru/watch/53141',
-            'file': '53141.mp4',
             'md5': '6ff5be2254e796ed346251d117196cf4',
             'info_dict': {
+                'id': '53141',
+                'ext': 'mp4',
                 'title': 'Иван Васильевич меняет профессию',
                 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
                 'duration': 5498,
@@ -33,9 +34,10 @@ class IviIE(InfoExtractor):
         # Serial's serie
         {
             'url': 'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
-            'file': '74791.mp4',
             'md5': '3e6cc9a848c1d2ebcc6476444967baa9',
             'info_dict': {
+                'id': '74791',
+                'ext': 'mp4',
                 'title': 'Дежурный ангел - 1 серия',
                 'duration': 2490,
                 'thumbnail': 'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
@@ -124,7 +126,7 @@ class IviIE(InfoExtractor):
 class IviCompilationIE(InfoExtractor):
     IE_DESC = 'ivi.ru compilations'
     IE_NAME = 'ivi:compilation'
-    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
 
     def _extract_entries(self, html, compilation_id):
         return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')

youtube_dl/extractor/m6.py

@@ -0,0 +1,56 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class M6IE(InfoExtractor):
+    IE_NAME = 'm6'
+    _VALID_URL = r'http://(?:www\.)?m6\.fr/[^/]+/videos/(?P<id>\d+)-[^\.]+\.html'
+
+    _TEST = {
+        'url': 'http://www.m6.fr/emission-les_reines_du_shopping/videos/11323908-emeline_est_la_reine_du_shopping_sur_le_theme_ma_fete_d_8217_anniversaire.html',
+        'md5': '242994a87de2c316891428e0176bcb77',
+        'info_dict': {
+            'id': '11323908',
+            'ext': 'mp4',
+            'title': 'Emeline est la Reine du Shopping sur le thème « Ma fête d’anniversaire ! »',
+            'description': 'md5:1212ae8fb4b7baa4dc3886c5676007c2',
+            'duration': 100,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        rss = self._download_xml('http://ws.m6.fr/v1/video/info/m6/bonus/%s' % video_id, video_id,
+            'Downloading video RSS')
+
+        title = rss.find('./channel/item/title').text
+        description = rss.find('./channel/item/description').text
+        thumbnail = rss.find('./channel/item/visuel_clip_big').text
+        duration = int(rss.find('./channel/item/duration').text)
+        view_count = int(rss.find('./channel/item/nombre_vues').text)
+
+        formats = []
+        for format_id in ['lq', 'sd', 'hq', 'hd']:
+            video_url = rss.find('./channel/item/url_video_%s' % format_id)
+            if video_url is None:
+                continue
+            formats.append({
+                'url': video_url.text,
+                'format_id': format_id,
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/mooshare.py

@@ -61,7 +61,7 @@ class MooshareIE(InfoExtractor):
         }
 
         request = compat_urllib_request.Request(
-            'http://mooshare.biz/8dqtk4bjbp8g', compat_urllib_parse.urlencode(download_form))
+            'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 
         self.to_screen('%s: Waiting for timeout' % video_id)
@@ -111,4 +111,4 @@ class MooshareIE(InfoExtractor):
             'thumbnail': thumbnail,
             'duration': duration,
             'formats': formats,
-        }
+        }

youtube_dl/extractor/mtv.py

@@ -82,10 +82,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
             title_el = find_xpath_attr(
                 itemdoc, './/{http://search.yahoo.com/mrss/}category',
                 'scheme', 'urn:mtvn:video_title')
-        if title_el is None:
-            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
         if title_el is None:
             title_el = itemdoc.find('.//title')
+            if title_el.text is None:
+                title_el = None
+        if title_el is None:
+            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
+
         title = title_el.text
         if title is None:
             raise ExtractorError('Could not find video title')

youtube_dl/extractor/ndr.py

@@ -0,0 +1,89 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class NDRIE(InfoExtractor):
+    IE_NAME = 'ndr'
+    IE_DESC = 'NDR.de - Mediathek'
+    _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
+
+    _TESTS = [
+        # video
+        {
+            'url': 'http://www.ndr.de/fernsehen/sendungen/hallo_niedersachsen/media/hallonds19925.html',
+            'md5': '20eba151ff165f386643dad9c1da08f7',
+            'info_dict': {
+                'id': '19925',
+                'ext': 'mp4',
+                'title': 'Hallo Niedersachsen  ',
+                'description': 'Bei Hallo Niedersachsen um 19:30 Uhr erfahren Sie alles, was am Tag in Niedersachsen los war.',
+                'duration': 1722,
+            },
+        },
+        # audio
+        {
+            'url': 'http://www.ndr.de/903/audio191719.html',
+            'md5': '41ed601768534dd18a9ae34d84798129',
+            'info_dict': {
+                'id': '191719',
+                'ext': 'mp3',
+                'title': '"Es war schockierend"',
+                'description': 'md5:ed7ff8364793545021a6355b97e95f10',
+                'duration': 112,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id, 'Downloading page')
+
+        title = self._og_search_title(page)
+        description = self._og_search_description(page)
+
+        mobj = re.search(
+            r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
+            page)
+        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+        formats = []
+
+        mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+        if mp3_url:
+            formats.append({
+                'url': mp3_url.group('audio'),
+                'format_id': 'mp3',
+            })
+
+        thumbnail = None
+
+        video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+        if video_url:
+            thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
+                page, 'thumbnail', fatal=False)
+            if thumbnail:
+                thumbnail = 'http://www.ndr.de' + thumbnail
+            for format_id in ['lo', 'hi', 'hq']:
+                formats.append({
+                    'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
+                    'format_id': format_id,
+                })
+
+        if not formats:
+            raise ExtractorError('No media links available for %s' % video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/nfb.py

@@ -0,0 +1,93 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+
+class NFBIE(InfoExtractor):
+    IE_NAME = 'nfb'
+    IE_DESC = 'National Film Board of Canada'
+    _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
+
+    _TEST = {
+        'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
+        'info_dict': {
+            'id': 'qallunaat_why_white_people_are_funny',
+            'ext': 'mp4',
+            'title': 'Qallunaat! Why White People Are Funny ',
+            'description': 'md5:836d8aff55e087d04d9f6df554d4e038',
+            'duration': 3128,
+            'uploader': 'Mark Sandiford',
+            'uploader_id': 'mark-sandiford',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page')
+
+        uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"',
+            page, 'director id', fatal=False)
+        uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>',
+            page, 'director name', fatal=False)
+
+        request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id,
+            compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii'))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf')
+
+        config = self._download_xml(request, video_id, 'Downloading player config XML')
+
+        title = None
+        description = None
+        thumbnail = None
+        duration = None
+        formats = []
+
+        def extract_thumbnail(media):
+            thumbnails = {}
+            for asset in media.findall('assets/asset'):
+                thumbnails[asset.get('quality')] = asset.find('default/url').text
+            if not thumbnails:
+                return None
+            if 'high' in thumbnails:
+                return thumbnails['high']
+            return list(thumbnails.values())[0]
+
+        for media in config.findall('./player/stream/media'):
+            if media.get('type') == 'posterImage':
+                thumbnail = extract_thumbnail(media)
+            elif media.get('type') == 'video':
+                duration = int(media.get('duration'))
+                title = media.find('title').text
+                description = media.find('description').text
+                # It seems assets always go from lower to better quality, so no need to sort
+                formats = [{
+                    'url': x.find('default/streamerURI').text + '/',
+                    'play_path': x.find('default/url').text,
+                    'rtmp_live': False,
+                    'ext': 'mp4',
+                    'format_id': x.get('quality'),
+                } for x in media.findall('assets/asset')]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }

youtube_dl/extractor/pbs.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 

youtube_dl/extractor/thisav.py

@@ -1,22 +1,23 @@
 #coding: utf-8
+from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-)
+from ..utils import determine_ext
+
 
 class ThisAVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
     _TEST = {
-        u"url": u"http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html",
-        u"file": u"47734.flv",
-        u"md5": u"0480f1ef3932d901f0e0e719f188f19b",
-        u"info_dict": {
-            u"title": u"高樹マリア - Just fit",
-            u"uploader": u"dj7970",
-            u"uploader_id": u"dj7970"
+        'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
+        'md5': '0480f1ef3932d901f0e0e719f188f19b',
+        'info_dict': {
+            'id': '47734',
+            'ext': 'flv',
+            'title': '高樹マリア - Just fit',
+            'uploader': 'dj7970',
+            'uploader_id': 'dj7970'
         }
     }
 
@@ -25,19 +26,18 @@ class ThisAVIE(InfoExtractor):
 
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, u'title')
+        title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title')
         video_url = self._html_search_regex(
-            r"addVariable\('file','([^']+)'\);", webpage, u'video url')
+            r"addVariable\('file','([^']+)'\);", webpage, 'video url')
         uploader = self._html_search_regex(
             r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
-            webpage, u'uploader name', fatal=False)
+            webpage, 'uploader name', fatal=False)
         uploader_id = self._html_search_regex(
             r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
-            webpage, u'uploader id', fatal=False)
+            webpage, 'uploader id', fatal=False)
         ext = determine_ext(video_url)
         
         return {
-            '_type':       'video',
             'id':          video_id,
             'url':         video_url,
             'uploader':    uploader,

youtube_dl/extractor/toutv.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,25 +11,25 @@ from ..utils import (
 
 
 class TouTvIE(InfoExtractor):
-    IE_NAME = u'tou.tv'
+    IE_NAME = 'tou.tv'
     _VALID_URL = r'https?://www\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/(?P<episode>S[0-9]+E[0-9]+)))'
 
     _TEST = {
-        u'url': u'http://www.tou.tv/30-vies/S04E41',
-        u'file': u'30-vies_S04E41.mp4',
-        u'info_dict': {
-            u'title': u'30 vies Saison 4 / Épisode 41',
-            u'description': u'md5:da363002db82ccbe4dafeb9cab039b09',
-            u'age_limit': 8,
-            u'uploader': u'Groupe des Nouveaux Médias',
-            u'duration': 1296,
-            u'upload_date': u'20131118',
-            u'thumbnail': u'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
+        'url': 'http://www.tou.tv/30-vies/S04E41',
+        'file': '30-vies_S04E41.mp4',
+        'info_dict': {
+            'title': '30 vies Saison 4 / Épisode 41',
+            'description': 'md5:da363002db82ccbe4dafeb9cab039b09',
+            'age_limit': 8,
+            'uploader': 'Groupe des Nouveaux Médias',
+            'duration': 1296,
+            'upload_date': '20131118',
+            'thumbnail': 'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
         },
-        u'params': {
-            u'skip_download': True,  # Requires rtmpdump
+        'params': {
+            'skip_download': True,  # Requires rtmpdump
         },
-        u'skip': 'Only available in Canada'
+        'skip': 'Only available in Canada'
     }
 
     def _real_extract(self, url):
@@ -36,25 +38,25 @@ class TouTvIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         mediaId = self._search_regex(
-            r'"idMedia":\s*"([^"]+)"', webpage, u'media ID')
+            r'"idMedia":\s*"([^"]+)"', webpage, 'media ID')
 
-        streams_url = u'http://release.theplatform.com/content.select?pid=' + mediaId
+        streams_url = 'http://release.theplatform.com/content.select?pid=' + mediaId
         streams_doc = self._download_xml(
-            streams_url, video_id, note=u'Downloading stream list')
+            streams_url, video_id, note='Downloading stream list')
 
         video_url = next(n.text
                          for n in streams_doc.findall('.//choice/url')
-                         if u'//ad.doubleclick' not in n.text)
+                         if '//ad.doubleclick' not in n.text)
         if video_url.endswith('/Unavailable.flv'):
             raise ExtractorError(
-                u'Access to this video is blocked from outside of Canada',
+                'Access to this video is blocked from outside of Canada',
                 expected=True)
 
         duration_str = self._html_search_meta(
-            'video:duration', webpage, u'duration')
+            'video:duration', webpage, 'duration')
         duration = int(duration_str) if duration_str else None
         upload_date_str = self._html_search_meta(
-            'video:release_date', webpage, u'upload date')
+            'video:release_date', webpage, 'upload date')
         upload_date = unified_strdate(upload_date_str) if upload_date_str else None
 
         return {

youtube_dl/extractor/tube8.py

@@ -11,7 +11,7 @@ from ..aes import (
 )
 
 class Tube8IE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/[^/]+/[^/]+/(?P<videoid>[0-9]+)/?)'
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/.+?/(?P<videoid>\d+)/?)$'
     _TEST = {
         u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/',
         u'file': u'229795.mp4',

youtube_dl/extractor/youtube.py

@@ -1422,7 +1422,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
 class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
     IE_DESC = u'YouTube.com playlists'
-    _VALID_URL = r"""(?:
+    _VALID_URL = r"""(?x)(?:
                         (?:https?://)?
                         (?:\w+\.)?
                         youtube\.com/
@@ -1431,7 +1431,11 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
                            \? (?:.*?&)*? (?:p|a|list)=
                         |  p/
                         )
-                        ((?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,})
+                        (
+                            (?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}
+                            # Top tracks, they can also include dots 
+                            |(?:MC)[\w\.]*
+                        )
                         .*
                      |
                         ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
@@ -1441,11 +1445,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
     _VIDEO_RE = r'href="/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
     IE_NAME = u'youtube:playlist'
 
-    @classmethod
-    def suitable(cls, url):
-        """Receives a URL and returns True if suitable for this IE."""
-        return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
     def _real_initialize(self):
         self._login()
 
@@ -1469,7 +1468,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
 
     def _real_extract(self, url):
         # Extract playlist id
-        mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+        mobj = re.match(self._VALID_URL, url)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
         playlist_id = mobj.group(1) or mobj.group(2)

youtube_dl/utils.py

@@ -751,13 +751,14 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     https_request = http_request
     https_response = http_response
 
+
 def unified_strdate(date_str):
     """Return a string with the date in the format YYYYMMDD"""
     upload_date = None
     #Replace commas
     date_str = date_str.replace(',',' ')
     # %z (UTC offset) is only supported in python>=3.2
-    date_str = re.sub(r' (\+|-)[\d]*$', '', date_str)
+    date_str = re.sub(r' ?(\+|-)[0-9:]*$', '', date_str)
     format_expressions = [
         '%d %B %Y',
         '%B %d %Y',
@@ -771,11 +772,12 @@ def unified_strdate(date_str):
         '%Y-%m-%dT%H:%M:%S.%fZ',
         '%Y-%m-%dT%H:%M:%S.%f0Z',
         '%Y-%m-%dT%H:%M:%S',
+        '%Y-%m-%dT%H:%M',
     ]
     for expression in format_expressions:
         try:
             upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
-        except:
+        except ValueError:
             pass
     if upload_date is None:
         timetuple = email.utils.parsedate_tz(date_str)

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.02.04.1'
+__version__ = '2014.02.08'