Merge pull request #108 from ytdl-org/master

[pull] master from ytdl-org:master

youtube_dl/extractor/pornhub.py

@@ -403,6 +403,15 @@ class PornHubUserIE(PornHubPlaylistBaseIE):
 
 
 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
+    @staticmethod
+    def _has_more(webpage):
+        return re.search(
+            r'''(?x)
+                <li[^>]+\bclass=["\']page_next|
+                <link[^>]+\brel=["\']next|
+                <button[^>]+\bid=["\']moreDataBtn
+            ''', webpage) is not None
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         host = mobj.group('host')
@@ -411,13 +420,11 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
         page = int_or_none(self._search_regex(
             r'\bpage=(\d+)', url, 'page', default=None))
 
-        page_url = self._make_page_url(url)
-
         entries = []
         for page_num in (page, ) if page is not None else itertools.count(1):
             try:
                 webpage = self._download_webpage(
-                    page_url, item_id, 'Downloading page %d' % page_num,
+                    url, item_id, 'Downloading page %d' % page_num,
                     query={'page': page_num})
             except ExtractorError as e:
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
@@ -547,18 +554,6 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
                 if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
                 else super(PornHubPagedVideoListIE, cls).suitable(url))
 
-    def _make_page_url(self, url):
-        return url
-
-    @staticmethod
-    def _has_more(webpage):
-        return re.search(
-            r'''(?x)
-                <li[^>]+\bclass=["\']page_next|
-                <link[^>]+\brel=["\']next|
-                <button[^>]+\bid=["\']moreDataBtn
-            ''', webpage) is not None
-
 
 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
@@ -572,11 +567,3 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
         'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
         'only_matching': True,
     }]
-
-    def _make_page_url(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        return '%s/ajax' % mobj.group('url')
-
-    @staticmethod
-    def _has_more(webpage):
-        return True

youtube_dl/extractor/redtube.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    merge_dicts,
     str_to_int,
     unified_strdate,
     url_or_none,
@@ -45,11 +46,14 @@ class RedTubeIE(InfoExtractor):
         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
 
-        title = self._html_search_regex(
+        info = self._search_json_ld(webpage, video_id, default={})
-            (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
+
-             r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
+        if not info.get('title'):
-            webpage, 'title', group='title',
+            info['title'] = self._html_search_regex(
-            default=None) or self._og_search_title(webpage)
+                (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
+                 r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
+                webpage, 'title', group='title',
+                default=None) or self._og_search_title(webpage)
 
         formats = []
         sources = self._parse_json(
@@ -88,28 +92,28 @@ class RedTubeIE(InfoExtractor):
 
         thumbnail = self._og_search_thumbnail(webpage)
         upload_date = unified_strdate(self._search_regex(
-            r'<span[^>]+>ADDED ([^<]+)<',
+            r'<span[^>]+>(?:ADDED|Published on) ([^<]+)<',
-            webpage, 'upload date', fatal=False))
+            webpage, 'upload date', default=None))
         duration = int_or_none(self._og_search_property(
             'video:duration', webpage, default=None) or self._search_regex(
                 r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
         view_count = str_to_int(self._search_regex(
             (r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)',
-             r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)'),
+             r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)',
-            webpage, 'view count', fatal=False))
+             r'<span[^>]+\bclass=["\']video_view_count[^>]*>\s*([\d,.]+)'),
+            webpage, 'view count', default=None))
 
         # No self-labeling, but they describe themselves as
         # "Home of Videos Porno"
         age_limit = 18
 
-        return {
+        return merge_dicts(info, {
             'id': video_id,
             'ext': 'mp4',
-            'title': title,
             'thumbnail': thumbnail,
             'upload_date': upload_date,
             'duration': duration,
             'view_count': view_count,
             'age_limit': age_limit,
             'formats': formats,
-        }
+        })