Fix some regexes

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

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 953e38227e60e6fa08bac62b6ab56cb3f3be8b6e..54f5d7279eb10ec43042adc3100e95a87166efba 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -332,6 +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
@@ -1374,6 +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)
@@ -1645,7 +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')