Merge pull request #5376 from PeteHemery/ffmpeg-postproc-utime-bug

[youtube-dl] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 36a1f65bfd6e1e07e123d22bbf5b2c87ad0c10f3..6c212efac4b0f5869f93e37a5c34b42dbe2ca88a 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -26,12 +26,15 @@ from ..utils import (
     unsmuggle_url,
     UnsupportedError,
     url_basename,
     unsmuggle_url,
     UnsupportedError,
     url_basename,

+    xpath_text,

 )
 from .brightcove import BrightcoveIE
 )
 from .brightcove import BrightcoveIE

+from .nbc import NBCSportsVPlayerIE

 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE

+from .udn import UDNEmbedIE

 
 
 class GenericIE(InfoExtractor):
 
 
 class GenericIE(InfoExtractor):


@@ -526,13 +529,24 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Viddler'],
         },
             },
             'add_ie': ['Viddler'],
         },

+        # Libsyn embed
+        {
+            'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+            'info_dict': {
+                'id': '3377616',
+                'ext': 'mp3',
+                'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+                'description': 'md5:601cb790edd05908957dae8aaa866465',
+                'upload_date': '20150220',
+            },
+        },

         # jwplayer YouTube
         {
             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
             'info_dict': {
                 'id': 'Mrj4DVp2zeA',
                 'ext': 'mp4',
         # jwplayer YouTube
         {
             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
             'info_dict': {
                 'id': 'Mrj4DVp2zeA',
                 'ext': 'mp4',

-                'upload_date': '20150204',
+                'upload_date': '20150212',

                 'uploader': 'The National Archives UK',
                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
                 'uploader_id': 'NationalArchives08',
                 'uploader': 'The National Archives UK',
                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
                 'uploader_id': 'NationalArchives08',


@@ -547,6 +561,107 @@ class GenericIE(InfoExtractor):
                 'id': 'aanslagen-kopenhagen',
                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
             }
                 'id': 'aanslagen-kopenhagen',
                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
             }

+        },
+        # Zapiks embed
+        {
+            'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
+            'info_dict': {
+                'id': '118046',
+                'ext': 'mp4',
+                'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
+            }
+        },
+        # Kaltura embed
+        {
+            'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
+            'info_dict': {
+                'id': '1_eergr3h1',
+                'ext': 'mp4',
+                'upload_date': '20150226',
+                'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
+                'timestamp': int,
+                'title': 'John Carlson Postgame 2/25/15',
+            },
+        },
+        # Eagle.Platform embed (generic URL)
+        {
+            'url': 'http://lenta.ru/news/2015/03/06/navalny/',
+            'info_dict': {
+                'id': '227304',
+                'ext': 'mp4',
+                'title': 'Навальный вышел на свободу',
+                'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 87,
+                'view_count': int,
+                'age_limit': 0,
+            },
+        },
+        # ClipYou (Eagle.Platform) embed (custom URL)
+        {
+            'url': 'http://muz-tv.ru/play/7129/',
+            'info_dict': {
+                'id': '12820',
+                'ext': 'mp4',
+                'title': "'O Sole Mio",
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 216,
+                'view_count': int,
+            },
+        },
+        # Pladform embed
+        {
+            'url': 'http://muz-tv.ru/kinozal/view/7400/',
+            'info_dict': {
+                'id': '100183293',
+                'ext': 'mp4',
+                'title': 'Тайны перевала Дятлова • Тайна перевала Дятлова 1 серия 2 часть',
+                'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 694,
+                'age_limit': 0,
+            },
+        },
+        # 5min embed
+        {
+            'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
+            'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
+            'info_dict': {
+                'id': '518726732',
+                'ext': 'mp4',
+                'title': 'Facebook Creates "On This Day" | Crunch Report',
+            },
+        },
+        # RSS feed with enclosure
+        {
+            'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
+            'info_dict': {
+                'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+                'ext': 'm4v',
+                'upload_date': '20150228',
+                'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+            }
+        },
+        # NBC Sports vplayer embed
+        {
+            'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
+            'info_dict': {
+                'id': 'ln7x1qSThw4k',
+                'ext': 'flv',
+                'title': "PFT Live: New leader in the 'new-look' defense",
+                'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
+            },
+        },
+        # UDN embed
+        {
+            'url': 'http://www.udn.com/news/story/7314/822787',
+            'md5': 'de06b4c90b042c128395a88f0384817e',
+            'info_dict': {
+                'id': '300040',
+                'ext': 'mp4',
+                'title': '生物老師男變女 全校挺"做自己"',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }

         }
     ]
 
         }
     ]
 


@@ -559,11 +674,24 @@ class GenericIE(InfoExtractor):
         playlist_desc_el = doc.find('./channel/description')
         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
 
         playlist_desc_el = doc.find('./channel/description')
         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
 

-        entries = [{
-            '_type': 'url',
-            'url': e.find('link').text,
-            'title': e.find('title').text,
-        } for e in doc.findall('./channel/item')]
+        entries = []
+        for it in doc.findall('./channel/item'):
+            next_url = xpath_text(it, 'link', fatal=False)
+            if not next_url:
+                enclosure_nodes = it.findall('./enclosure')
+                for e in enclosure_nodes:
+                    next_url = e.attrib.get('url')
+                    if next_url:
+                        break
+
+            if not next_url:
+                continue
+
+            entries.append({
+                '_type': 'url',
+                'url': next_url,
+                'title': it.find('title').text,
+            })

 
         return {
             '_type': 'playlist',
 
         return {
             '_type': 'playlist',


@@ -922,6 +1050,19 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 

+        # Look for NYTimes player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for Libsyn player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+

         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or


@@ -1098,6 +1239,54 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'Livestream')
 
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'Livestream')
 

+        # Look for Zapiks embed
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Zapiks')
+
+        # Look for Kaltura embeds
+        mobj = re.search(
+            r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
+        if mobj is not None:
+            return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
+
+        # Look for Eagle.Platform embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'EaglePlatform')
+
+        # Look for ClipYou (uses Eagle.Platform) embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
+        if mobj is not None:
+            return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
+
+        # Look for Pladform embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Pladform')
+
+        # Look for 5min embeds
+        mobj = re.search(
+            r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
+        if mobj is not None:
+            return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
+
+        # Look for NBC Sports VPlayer embeds
+        nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
+        if nbc_sports_url:
+            return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
+
+        # Look for UDN embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
+        if mobj is not None:
+            return self.url_result(
+                compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
+

         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True


@@ -1154,10 +1343,16 @@ class GenericIE(InfoExtractor):
             # HTML5 video
             found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
             # HTML5 video
             found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:

+            REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'

             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'

-                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,

                 webpage)
                 webpage)

+            if not found:
+                # Look also in Refresh HTTP header
+                refresh_header = head_response.headers.get('Refresh')
+                if refresh_header:
+                    found = re.search(REDIRECT_REGEX, refresh_header)

             if found:
                 new_url = found.group(1)
                 self.report_following_redirect(new_url)
             if found:
                 new_url = found.group(1)
                 self.report_following_redirect(new_url)


@@ -1193,7 +1388,9 @@ class GenericIE(InfoExtractor):
             return entries[0]
         else:
             for num, e in enumerate(entries, start=1):
             return entries[0]
         else:
             for num, e in enumerate(entries, start=1):

-                e['title'] = '%s (%d)' % (e['title'], num)
+                # 'url' results don't have a title
+                if e.get('title') is not None:
+                    e['title'] = '%s (%d)' % (e['title'], num)

             return {
                 '_type': 'playlist',
                 'entries': entries,
             return {
                 '_type': 'playlist',
                 'entries': entries,