youtube-dl

commit b52c9ef1655042688a4822d241af398592b951f9
parent e28ed498e64545f02f2d3dbccf97ecf0e47aa82a
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun,  6 Nov 2016 21:52:00 +0700

[extractor/generic] Improve support for pornhub embeds (closes #11100)

Diffstat:
M
youtube_dl/extractor/generic.py
 | 
10
+++++-----
M
youtube_dl/extractor/pornhub.py
 | 
13
++++++-------

2 files changed, 11 insertions(+), 12 deletions(-)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -1983,11 +1983,6 @@ class GenericIE(InfoExtractor):
         if sportbox_urls:
             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
 
-        # Look for embedded PornHub player
-        pornhub_url = PornHubIE._extract_url(webpage)
-        if pornhub_url:
-            return self.url_result(pornhub_url, 'PornHub')
-
         # Look for embedded XHamster player
         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
         if xhamster_urls:
@@ -1998,6 +1993,11 @@ class GenericIE(InfoExtractor):
         if tnaflix_urls:
             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
 
+        # Look for embedded PornHub player
+        pornhub_urls = PornHubIE._extract_urls(webpage)
+        if pornhub_urls:
+            return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
+
         # Look for embedded DrTuber player
         drtuber_urls = DrTuberIE._extract_urls(webpage)
         if drtuber_urls:
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
@@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor):
                             (?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
-                        (?P<id>[0-9a-z]+)
+                        (?P<id>[\da-z]+)
                     '''
     _TESTS = [{
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
@@ -96,12 +96,11 @@ class PornHubIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @classmethod
-    def _extract_url(cls, webpage):
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
-        if mobj:
-            return mobj.group('url')
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
+            webpage)
 
     def _extract_count(self, pattern, webpage, name):
         return str_to_int(self._search_regex(