Update to ytdl-2021.01.03

[yt-dlp.git] / youtube_dlc / extractor / pornhub.py

diff --git a/youtube_dlc/extractor/pornhub.py b/youtube_dlc/extractor/pornhub.py
index 529f3f7119fd4e93a8c82168d910ab4fc3d1720e..2fcbd186f84fb4a629c154f84339c6795bbfaf06 100644 (file)
--- a/youtube_dlc/extractor/pornhub.py
+++ b/youtube_dlc/extractor/pornhub.py
@@ -31,7 +31,12 @@ def _download_webpage_handle(self, *args, **kwargs):
         def dl(*args, **kwargs):
             return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
 
-        webpage, urlh = dl(*args, **kwargs)
+        ret = dl(*args, **kwargs)
+
+        if not ret:
+            return ret
+
+        webpage, urlh = ret
 
         if any(re.search(p, webpage) for p in (
                 r'<body\b[^>]+\bonload=["\']go\(\)',
@@ -53,7 +58,7 @@ class PornHubIE(PornHubBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+                            (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)
@@ -152,6 +157,9 @@ class PornHubIE(PornHubBaseIE):
     }, {
         'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
         'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.org/view_video.php?viewkey=203640933',
+        'only_matching': True,
     }, {
         'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
         'only_matching': True,
@@ -160,7 +168,7 @@ class PornHubIE(PornHubBaseIE):
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net|org)/embed/[\da-z]+)',
             webpage)
 
     def _extract_count(self, pattern, webpage, name):
@@ -280,14 +288,24 @@ def add_video_url(video_url):
             video_urls.append((v_url, None))
             video_urls_set.add(v_url)
 
+        def parse_quality_items(quality_items):
+            q_items = self._parse_json(quality_items, video_id, fatal=False)
+            if not isinstance(q_items, list):
+                return
+            for item in q_items:
+                if isinstance(item, dict):
+                    add_video_url(item.get('url'))
+
         if not video_urls:
-            FORMAT_PREFIXES = ('media', 'quality')
+            FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
             js_vars = extract_js_vars(
                 webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
                 default=None)
             if js_vars:
                 for key, format_url in js_vars.items():
-                    if any(key.startswith(p) for p in FORMAT_PREFIXES):
+                    if key.startswith(FORMAT_PREFIXES[-1]):
+                        parse_quality_items(format_url)
+                    elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
                         add_video_url(format_url)
             if not video_urls and re.search(
                     r'<[^>]+\bid=["\']lockedPlayer', webpage):
@@ -343,12 +361,16 @@ def add_video_url(video_url):
             r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
             webpage, 'uploader', default=None)
 
+        def extract_vote_count(kind, name):
+            return self._extract_count(
+                (r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind,
+                 r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind),
+                webpage, name)
+
         view_count = self._extract_count(
             r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
-        like_count = self._extract_count(
-            r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
-        dislike_count = self._extract_count(
-            r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
+        like_count = extract_vote_count('Up', 'like')
+        dislike_count = extract_vote_count('Down', 'dislike')
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
@@ -422,7 +444,7 @@ def _real_extract(self, url):
 
 
 class PornHubUserIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
+    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
     _TESTS = [{
         'url': 'https://www.pornhub.com/model/zoe_ph',
         'playlist_mincount': 118,
@@ -490,7 +512,7 @@ def _real_extract(self, url):
 
 
 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
     _TESTS = [{
         'url': 'https://www.pornhub.com/model/zoe_ph/videos',
         'only_matching': True,
@@ -605,7 +627,7 @@ def suitable(cls, url):
 
 
 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
-    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
+    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
     _TESTS = [{
         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
         'info_dict': {