New upstream version 2016.12.01

[youtubedl] / youtube_dl / extractor / pornhub.py

diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 20976c101d97f53a58b3599ded30f7bfb1d4bcd5..40dbe6967fac2126b7bf6e6a1245768b3c039c8e 100644 (file)
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -15,6 +15,7 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
+    js_to_json,
     orderedSet,
     sanitized_Request,
     str_to_int,
@@ -32,7 +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',
@@ -48,6 +49,8 @@ class PornHubIE(InfoExtractor):
             'dislike_count': int,
             'comment_count': int,
             'age_limit': 18,
+            'tags': list,
+            'categories': list,
         },
     }, {
         # non-ASCII title
@@ -63,6 +66,8 @@ class PornHubIE(InfoExtractor):
             'dislike_count': int,
             'comment_count': int,
             'age_limit': 18,
+            'tags': list,
+            'categories': list,
         },
         'params': {
             'skip_download': True,
@@ -91,12 +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(
@@ -183,6 +187,15 @@ class PornHubIE(InfoExtractor):
             })
         self._sort_formats(formats)
 
+        page_params = self._parse_json(self._search_regex(
+            r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
+            webpage, 'page parameters', group='data', default='{}'),
+            video_id, transform_source=js_to_json, fatal=False)
+        tags = categories = None
+        if page_params:
+            tags = page_params.get('tags', '').split(',')
+            categories = page_params.get('categories', '').split(',')
+
         return {
             'id': video_id,
             'uploader': video_uploader,
@@ -195,6 +208,8 @@ class PornHubIE(InfoExtractor):
             'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,
+            'tags': tags,
+            'categories': categories,
         }