Update changelog.

[youtubedl] / youtube_dl / extractor / pornhub.py

diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 19eaf389f829c2c9b0956e89615119dbab6f0593..cb59d526f9be7d7f4f033bed697bae363173ec98 100644 (file)
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -10,11 +10,13 @@ from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
     compat_str,
 from ..compat import (
     compat_HTTPError,
     compat_str,

+    compat_urllib_request,

 )
 )

+from .openload import PhantomJSwrapper

 from ..utils import (
 from ..utils import (

+    determine_ext,

     ExtractorError,
     int_or_none,
     ExtractorError,
     int_or_none,

-    js_to_json,

     orderedSet,
     remove_quotes,
     str_to_int,
     orderedSet,
     remove_quotes,
     str_to_int,


@@ -22,12 +24,34 @@ from ..utils import (
 )
 
 
 )
 
 

-class PornHubIE(InfoExtractor):
+class PornHubBaseIE(InfoExtractor):
+    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)
+
+        if any(re.search(p, webpage) for p in (
+                r'<body\b[^>]+\bonload=["\']go\(\)',
+                r'document\.cookie\s*=\s*["\']RNKEY=',
+                r'document\.location\.reload\(true\)')):
+            url_or_request = args[0]
+            url = (url_or_request.get_full_url()
+                   if isinstance(url_or_request, compat_urllib_request.Request)
+                   else url_or_request)
+            phantom = PhantomJSwrapper(self, required_version='2.0')
+            phantom.get(url, html=webpage)
+            webpage, urlh = dl(*args, **kwargs)
+
+        return webpage, urlh
+
+
+class PornHubIE(PornHubBaseIE):

     IE_DESC = 'PornHub and Thumbzilla'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
     IE_DESC = 'PornHub and Thumbzilla'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:

-                            (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+                            (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|

                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)
                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)


@@ -121,12 +145,15 @@ class PornHubIE(InfoExtractor):
     }, {
         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
         'only_matching': True,
     }, {
         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
         'only_matching': True,

+    }, {
+        'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
+        'only_matching': True,

     }]
 
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
     }]
 
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(

-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',

             webpage)
 
     def _extract_count(self, pattern, webpage, name):
             webpage)
 
     def _extract_count(self, pattern, webpage, name):


@@ -134,14 +161,16 @@ class PornHubIE(InfoExtractor):
             pattern, webpage, '%s count' % name, fatal=False))
 
     def _real_extract(self, url):
             pattern, webpage, '%s count' % name, fatal=False))
 
     def _real_extract(self, url):

-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host') or 'pornhub.com'
+        video_id = mobj.group('id')

 
 

-        self._set_cookie('pornhub.com', 'age_verified', '1')
+        self._set_cookie(host, 'age_verified', '1')

 
         def dl_webpage(platform):
 
         def dl_webpage(platform):

-            self._set_cookie('pornhub.com', 'platform', platform)
+            self._set_cookie(host, 'platform', platform)

             return self._download_webpage(
             return self._download_webpage(

-                'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
+                'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),

                 video_id, 'Downloading %s webpage' % platform)
 
         webpage = dl_webpage('pc')
                 video_id, 'Downloading %s webpage' % platform)
 
         webpage = dl_webpage('pc')


@@ -247,6 +276,10 @@ class PornHubIE(InfoExtractor):
                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
                 if upload_date:
                     upload_date = upload_date.replace('/', '')
                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
                 if upload_date:
                     upload_date = upload_date.replace('/', '')

+            if determine_ext(video_url) == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    video_url, video_id, mpd_id='dash', fatal=False))
+                continue

             tbr = None
             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
             if mobj:
             tbr = None
             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
             if mobj:


@@ -274,14 +307,12 @@ class PornHubIE(InfoExtractor):
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 

-        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(',')
+        def extract_list(meta_key):
+            div = self._search_regex(
+                r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
+                % meta_key, webpage, meta_key, default=None)
+            if div:
+                return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,


@@ -296,24 +327,24 @@ class PornHubIE(InfoExtractor):
             'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,
             'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,

-            'tags': tags,
-            'categories': categories,
+            'tags': extract_list('tags'),
+            'categories': extract_list('categories'),

             'subtitles': subtitles,
         }
 
 
             'subtitles': subtitles,
         }
 
 

-class PornHubPlaylistBaseIE(InfoExtractor):
-    def _extract_entries(self, webpage):
+class PornHubPlaylistBaseIE(PornHubBaseIE):
+    def _extract_entries(self, webpage, host):

         # Only process container div with main playlist content skipping
         # drop-down menu that uses similar pattern for videos (see
         # Only process container div with main playlist content skipping
         # drop-down menu that uses similar pattern for videos (see

-        # https://github.com/rg3/youtube-dl/issues/11594).
+        # https://github.com/ytdl-org/youtube-dl/issues/11594).

         container = self._search_regex(
             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
             'container', default=webpage)
 
         return [
             self.url_result(
         container = self._search_regex(
             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
             'container', default=webpage)
 
         return [
             self.url_result(

-                'http://www.pornhub.com/%s' % video_url,
+                'http://www.%s/%s' % (host, video_url),

                 PornHubIE.ie_key(), video_title=title)
             for video_url, title in orderedSet(re.findall(
                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
                 PornHubIE.ie_key(), video_title=title)
             for video_url, title in orderedSet(re.findall(
                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',


@@ -321,11 +352,13 @@ class PornHubPlaylistBaseIE(InfoExtractor):
         ]
 
     def _real_extract(self, url):
         ]
 
     def _real_extract(self, url):

-        playlist_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        playlist_id = mobj.group('id')

 
         webpage = self._download_webpage(url, playlist_id)
 
 
         webpage = self._download_webpage(url, playlist_id)
 

-        entries = self._extract_entries(webpage)
+        entries = self._extract_entries(webpage, host)

 
         playlist = self._parse_json(
             self._search_regex(
 
         playlist = self._parse_json(
             self._search_regex(


@@ -340,7 +373,7 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
 
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 
 
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):

-    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'

     _TESTS = [{
         'url': 'http://www.pornhub.com/playlist/4667351',
         'info_dict': {
     _TESTS = [{
         'url': 'http://www.pornhub.com/playlist/4667351',
         'info_dict': {


@@ -355,7 +388,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 
 
 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
 
 
 class PornHubUserVideosIE(PornHubPlaylistBaseIE):

-    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'

     _TESTS = [{
         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
         'info_dict': {
     _TESTS = [{
         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
         'info_dict': {


@@ -396,7 +429,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):

-        user_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        user_id = mobj.group('id')

 
         entries = []
         for page_num in itertools.count(1):
 
         entries = []
         for page_num in itertools.count(1):


@@ -408,7 +443,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
                     break
                 raise
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
                     break
                 raise

-            page_entries = self._extract_entries(webpage)
+            page_entries = self._extract_entries(webpage, host)

             if not page_entries:
                 break
             entries.extend(page_entries)
             if not page_entries:
                 break
             entries.extend(page_entries)