X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=2ff002643c9e4404b3427f4f309c187186ccc37a;hb=4e8cc1e973da2656c46c5df84d4e85c5d78836ac;hp=fbbc79a574ca03f1e483738a726f2fde0bf6b21d;hpb=f076b63821100af17379ed8b470e508846bb8432;p=youtube-dl

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index fbbc79a57..2ff002643 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -26,8 +26,10 @@ from ..utils import (
     unsmuggle_url,
     UnsupportedError,
     url_basename,
+    xpath_text,
 )
 from .brightcove import BrightcoveIE
+from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
@@ -473,6 +475,7 @@ class GenericIE(InfoExtractor):
         {
             'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
             'info_dict': {
+                'id': '1986',
                 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
             },
             'playlist_mincount': 2,
@@ -524,6 +527,129 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20150126',
             },
             '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',
+                'upload_date': '20150212',
+                'uploader': 'The National Archives UK',
+                'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
+                'uploader_id': 'NationalArchives08',
+                'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
+            },
+        },
+        # rtl.nl embed
+        {
+            'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
+            'playlist_mincount': 5,
+            'info_dict': {
+                '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',
+            },
         }
     ]
 
@@ -536,11 +662,24 @@ class GenericIE(InfoExtractor):
         playlist_desc_el = doc.find('./channel/description')
         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
 
-        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',
@@ -769,6 +908,13 @@ class GenericIE(InfoExtractor):
                 'entries': entries,
             }
 
+        # Look for embedded rtl.nl player
+        matches = re.findall(
+            r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
+            webpage)
+        if matches:
+            return _playlist_from_matches(matches, ie='RtlNl')
+
         # Look for embedded (iframe) Vimeo player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
@@ -776,7 +922,6 @@ class GenericIE(InfoExtractor):
             player_url = unescapeHTML(mobj.group('url'))
             surl = smuggle_url(player_url, {'Referer': url})
             return self.url_result(surl)
-
         # Look for embedded (swf embed) Vimeo player
         mobj = re.search(
             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
@@ -893,6 +1038,19 @@ class GenericIE(InfoExtractor):
         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
@@ -1034,7 +1192,12 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded sbs.com.au player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1',
+            r'''(?x)
+            (?:
+                <meta\s+property="og:video"\s+content=|
+                <iframe[^>]+?src=
+            )
+            (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
             webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'SBS')
@@ -1064,7 +1227,50 @@ class GenericIE(InfoExtractor):
         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')
+
         def check_video(vurl):
+            if YoutubeIE.suitable(vurl):
+                return True
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
@@ -1082,7 +1288,8 @@ class GenericIE(InfoExtractor):
                     JWPlayerOptions|
                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
                 )
-                .*?file\s*:\s*["\'](.*?)["\']''', webpage))
+                .*?
+                ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
         if not found:
             # Broaden the search a little bit
             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
@@ -1117,10 +1324,16 @@ class GenericIE(InfoExtractor):
             # 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")'
-                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
                 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)
@@ -1156,7 +1369,9 @@ class GenericIE(InfoExtractor):
             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,