[youku] compare bytes and str for compatible; use compat_urllib_parse for making...

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 4946cc1325b0ffdecca0767e7532ddcb4741a028..9a7b0d25d790054e39729bab63e42b1ea7a89dff 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -32,11 +32,13 @@ from .brightcove import BrightcoveIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE

+from .sportbox import SportBoxEmbedIE

 from .smotri import SmotriIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
 from .bliptv import BlipTVIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
 from .bliptv import BlipTVIE

+from .svt import SVTIE

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


@@ -223,6 +225,37 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
                 'skip_download': True,
             },
         },

+        # SportBox embed
+        {
+            'url': 'http://www.vestifinance.ru/articles/25753',
+            'info_dict': {
+                'id': '25753',
+                'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'id': '370908',
+                    'title': 'Госзаказ. День 3',
+                    'ext': 'mp4',
+                }
+            }, {
+                'info_dict': {
+                    'id': '370905',
+                    'title': 'Госзаказ. День 2',
+                    'ext': 'mp4',
+                }
+            }, {
+                'info_dict': {
+                    'id': '370902',
+                    'title': 'Госзаказ. День 1',
+                    'ext': 'mp4',
+                }
+            }],
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },

         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',


@@ -645,6 +678,17 @@ class GenericIE(InfoExtractor):
                 'title': 'Facebook Creates "On This Day" | Crunch Report',
             },
         },
                 'title': 'Facebook Creates "On This Day" | Crunch Report',
             },
         },

+        # SVT embed
+        {
+            'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
+            'info_dict': {
+                'id': '2900353',
+                'ext': 'flv',
+                'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
+                'duration': 27,
+                'age_limit': 0,
+            },
+        },

         # RSS feed with enclosure
         {
             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
         # RSS feed with enclosure
         {
             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',


@@ -1078,6 +1122,11 @@ class GenericIE(InfoExtractor):
         if bliptv_url:
             return self.url_result(bliptv_url, 'BlipTV')
 
         if bliptv_url:
             return self.url_result(bliptv_url, 'BlipTV')
 

+        # Look for SVT player
+        svt_url = SVTIE._extract_url(webpage)
+        if svt_url:
+            return self.url_result(svt_url, 'SVT')
+

         # Look for embedded condenast player
         matches = re.findall(
             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
         # Look for embedded condenast player
         matches = re.findall(
             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',


@@ -1212,6 +1261,11 @@ class GenericIE(InfoExtractor):
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 

+        # Look for embedded SportBox player
+        sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
+        if sportbox_urls:
+            return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
+

         # Look for embedded TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
         # Look for embedded TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)


@@ -1289,6 +1343,10 @@ class GenericIE(InfoExtractor):
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
             webpage)
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
             webpage)

+        if not mobj:
+            mobj = re.search(
+                r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
+                webpage)

         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
 
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
 


@@ -1367,7 +1425,7 @@ class GenericIE(InfoExtractor):
         # Look for Senate ISVP iframe
         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
         if senate_isvp_url:
         # Look for Senate ISVP iframe
         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
         if senate_isvp_url:

-            return self.url_result(surl, 'SenateISVP')
+            return self.url_result(senate_isvp_url, 'SenateISVP')

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


@@ -1436,7 +1494,7 @@ class GenericIE(InfoExtractor):
                 if refresh_header:
                     found = re.search(REDIRECT_REGEX, refresh_header)
             if found:
                 if refresh_header:
                     found = re.search(REDIRECT_REGEX, refresh_header)
             if found:

-                new_url = found.group(1)
+                new_url = compat_urlparse.urljoin(url, found.group(1))

                 self.report_following_redirect(new_url)
                 return {
                     '_type': 'url',
                 self.report_following_redirect(new_url)
                 return {
                     '_type': 'url',