X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=d224aa8e18471787bc00a515836b39fd558bac1f;hb=9e1a5b845586a0a5431fb72467142046d8571e6f;hp=51dbbc8db13fb680822eac81b526e7397d18b6d2;hpb=23be51d8ce132dbb967f460e1225fdaaa43dff39;p=youtube-dl

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 51dbbc8db..d224aa8e1 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -7,11 +7,12 @@ import re
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urlparse,
     compat_xml_parse_error,
-
+)
+from ..utils import (
     determine_ext,
     ExtractorError,
     float_or_none,
@@ -99,6 +100,22 @@ class GenericIE(InfoExtractor):
                 'uploader': 'Championat',
             },
         },
+        {
+            # https://github.com/rg3/youtube-dl/issues/3541
+            'add_ie': ['Brightcove'],
+            'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
+            'info_dict': {
+                'id': '3866516442001',
+                'ext': 'mp4',
+                'title': 'Leer mij vrouwen kennen: Aflevering 1',
+                'description': 'Leer mij vrouwen kennen: Aflevering 1',
+                'uploader': 'SBS Broadcasting',
+            },
+            'skip': 'Restricted to Netherlands',
+            'params': {
+                'skip_download': True,  # m3u8 download
+            },
+        },
         # Direct link to a video
         {
             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
@@ -325,7 +342,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'age_limit': 18,
                 'uploader': 'www.handjobhub.com',
-                'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
+                'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
             }
         },
         # RSS feed
@@ -389,7 +406,44 @@ class GenericIE(InfoExtractor):
                 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
                 'duration': 1715.0,
                 'uploader': 'thoughtworks.wistia.com',
-            },   
+            },
+        },
+        # Direct download with broken HEAD
+        {
+            'url': 'http://ai-radio.org:8000/radio.opus',
+            'info_dict': {
+                'id': 'radio',
+                'ext': 'opus',
+                'title': 'radio',
+            },
+            'params': {
+                'skip_download': True,  # infinite live stream
+            },
+            'expected_warnings': [
+                r'501.*Not Implemented'
+            ],
+        },
+        # Soundcloud embed
+        {
+            'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
+            'info_dict': {
+                'id': '174391317',
+                'ext': 'mp3',
+                'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
+                'uploader': 'Sophos Security',
+                'title': 'Chet Chat 171 - Oct 29, 2014',
+                'upload_date': '20141029',
+            }
+        },
+        # Livestream embed
+        {
+            'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
+            'info_dict': {
+                'id': '67864563',
+                'ext': 'flv',
+                'upload_date': '20141112',
+                'title': 'Rosetta #CometLanding webcast HL 10',
+            }
         },
     ]
 
@@ -532,6 +586,7 @@ class GenericIE(InfoExtractor):
             return {
                 'id': video_id,
                 'title': os.path.splitext(url_basename(url))[0],
+                'direct': True,
                 'formats': [{
                     'format_id': m.group('format_id'),
                     'url': url,
@@ -544,7 +599,7 @@ class GenericIE(InfoExtractor):
             self._downloader.report_warning('Falling back on generic information extractor.')
 
         if full_response:
-            webpage = _webpage_read_content(url, video_id)
+            webpage = self._webpage_read_content(full_response, url, video_id)
         else:
             webpage = self._download_webpage(url, video_id)
         self.report_extraction(video_id)
@@ -678,7 +733,7 @@ class GenericIE(InfoExtractor):
                 'title': video_title,
                 'id': video_id,
             }
-            
+
         match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
         if match:
             return {
@@ -693,7 +748,7 @@ class GenericIE(InfoExtractor):
         # Look for embedded blip.tv player
         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')
+            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)
         if mobj:
             return self.url_result(mobj.group(1), 'BlipTV')
@@ -729,7 +784,7 @@ class GenericIE(InfoExtractor):
 
         # 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))
+                re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
             return OoyalaIE._build_url_result(mobj.group('ec'))
 
@@ -823,7 +878,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embeded soundcloud player
         mobj = re.search(
-            r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
+            r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
             webpage)
         if mobj is not None:
             url = unescapeHTML(mobj.group('url'))
@@ -860,7 +915,7 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'SBS')
 
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
             webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
@@ -871,6 +926,12 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
 
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Livestream')
+
         def check_video(vurl):
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
@@ -918,7 +979,7 @@ class GenericIE(InfoExtractor):
                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
         if not found:
             # HTML5 video
-            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage)
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
@@ -964,4 +1025,3 @@ class GenericIE(InfoExtractor):
                 '_type': 'playlist',
                 'entries': entries,
             }
-