X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyoutube.py;h=6e2d57d6a1f1b5215ce8c3c758579b352e083a0f;hb=04af3aca049588b6b3d4d4b57ee47224fdeee90f;hp=3d0f5a5c90f3dedea235e570320abc916eaf70cc;hpb=c7121fa7b804d2b9e35dec05f8861e4ebba8afd2;p=youtube-dl

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 3d0f5a5c9..6e2d57d6a 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -16,6 +16,7 @@ from ..jsinterp import JSInterpreter
 from ..swfinterp import SWFInterpreter
 from ..compat import (
     compat_chr,
+    compat_kwargs,
     compat_parse_qs,
     compat_urllib_parse_unquote,
     compat_urllib_parse_unquote_plus,
@@ -245,6 +246,11 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
         return True
 
+    def _download_webpage(self, *args, **kwargs):
+        kwargs.setdefault('query', {})['disable_polymer'] = 'true'
+        return super(YoutubeBaseInfoExtractor, self)._download_webpage(
+            *args, **compat_kwargs(kwargs))
+
     def _real_initialize(self):
         if self._downloader is None:
             return
@@ -326,6 +332,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                          (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
                             (?:www\.)?deturl\.com/www\.youtube\.com/|
                             (?:www\.)?pwnyoutube\.com/|
+                            (?:www\.)?hooktube\.com/|
                             (?:www\.)?yourepeat\.com/|
                             tube\.majestyc\.net/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
@@ -1368,6 +1375,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             playback_url, video_id, 'Marking watched',
             'Unable to mark watched', fatal=False)
 
+    @staticmethod
+    def _extract_urls(webpage):
+        # Embedded YouTube player
+        entries = [
+            unescapeHTML(mobj.group('url'))
+            for mobj in re.finditer(r'''(?x)
+            (?:
+                <iframe[^>]+?src=|
+                data-video-url=|
+                <embed[^>]+?src=|
+                embedSWF\(?:\s*|
+                <object[^>]+data=|
+                new\s+SWFObject\(
+            )
+            (["\'])
+                (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
+                (?:embed|v|p)/.+?)
+            \1''', webpage)]
+
+        # lazyYT YouTube embed
+        entries.extend(list(map(
+            unescapeHTML,
+            re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
+
+        # Wordpress "YouTube Video Importer" plugin
+        matches = re.findall(r'''(?x)<div[^>]+
+            class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
+            data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
+        entries.extend(m[-1] for m in matches)
+
+        return entries
+
+    @staticmethod
+    def _extract_url(webpage):
+        urls = YoutubeIE._extract_urls(webpage)
+        return urls[0] if urls else None
+
     @classmethod
     def extract_id(cls, url):
         mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
@@ -1621,7 +1665,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
 
         if view_count is None:
-            view_count = extract_view_count(get_video_info)
+            view_count = extract_view_count(video_info)
 
         # Check for "rental" videos
         if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
@@ -1639,7 +1683,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         video_uploader_id = None
         video_uploader_url = None
         mobj = re.search(
-            r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
+            r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
             video_webpage)
         if mobj is not None:
             video_uploader_id = mobj.group('uploader_id')
@@ -1665,10 +1709,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if not upload_date:
             upload_date = self._search_regex(
                 [r'(?s)id="eow-date.*?>(.*?)</span>',
-                 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
+                 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
                 video_webpage, 'upload date', default=None)
-            if upload_date:
-                upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
         upload_date = unified_strdate(upload_date)
 
         video_license = self._html_search_regex(
@@ -1998,39 +2040,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         }
 
 
-class YoutubeSharedVideoIE(InfoExtractor):
-    _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})'
-    IE_NAME = 'youtube:shared'
-
-    _TEST = {
-        'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
-        'info_dict': {
-            'id': 'uPDB5I9wfp8',
-            'ext': 'webm',
-            'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
-            'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
-            'upload_date': '20160219',
-            'uploader': 'Pocoyo - Português (BR)',
-            'uploader_id': 'PocoyoBrazil',
-        },
-        'add_ie': ['Youtube'],
-        'params': {
-            # There are already too many Youtube downloads
-            'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        real_video_id = self._html_search_meta(
-            'videoId', webpage, 'YouTube video id', fatal=True)
-
-        return self.url_result(real_video_id, YoutubeIE.ie_key())
-
-
 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
     IE_DESC = 'YouTube.com playlists'
     _VALID_URL = r"""(?x)(?:
@@ -2054,7 +2063,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
                      |
                         (%(playlist_id)s)
                      )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
-    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
+    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
     _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
     IE_NAME = 'youtube:playlist'
     _TESTS = [{