Prepare to upload.

[youtubedl] / youtube_dl / extractor / pornhub.py

diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 1dcc8df00b4c2eb2da3b2719a35d874eb290c4ed..6782848d90c289d02aeef76bb2d0925351d64121 100644 (file)
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -4,28 +4,22 @@ from __future__ import unicode_literals
 import functools
 import itertools
 import operator
 import functools
 import itertools
 import operator

-# import os

 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,

-    # compat_urllib_parse_unquote,
-    # compat_urllib_parse_unquote_plus,
-    # compat_urllib_parse_urlparse,
+    compat_str,

 )
 from ..utils import (
     ExtractorError,
     int_or_none,
     js_to_json,
     orderedSet,
 )
 from ..utils import (
     ExtractorError,
     int_or_none,
     js_to_json,
     orderedSet,

-    # sanitized_Request,

     remove_quotes,
     str_to_int,
     remove_quotes,
     str_to_int,

+    url_or_none,

 )
 )

-# from ..aes import (
-#     aes_decrypt_text
-# )

 
 
 class PornHubIE(InfoExtractor):
 
 
 class PornHubIE(InfoExtractor):


@@ -33,7 +27,7 @@ class PornHubIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
     _VALID_URL = r'''(?x)
                     https?://
                         (?:

-                            (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+                            (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|

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


@@ -62,7 +56,7 @@ class PornHubIE(InfoExtractor):
             'id': '1331683002',
             'ext': 'mp4',
             'title': '重庆婷婷女王足交',
             'id': '1331683002',
             'ext': 'mp4',
             'title': '重庆婷婷女王足交',

-            'uploader': 'cj397186295',
+            'uploader': 'Unknown',

             'duration': 1753,
             'view_count': int,
             'like_count': int,
             'duration': 1753,
             'view_count': int,
             'like_count': int,


@@ -75,6 +69,31 @@ class PornHubIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
         'params': {
             'skip_download': True,
         },

+    }, {
+        # subtitles
+        'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
+        'info_dict': {
+            'id': 'ph5af5fef7c2aa7',
+            'ext': 'mp4',
+            'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
+            'uploader': 'BFFs',
+            'duration': 622,
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'comment_count': int,
+            'age_limit': 18,
+            'tags': list,
+            'categories': list,
+            'subtitles': {
+                'en': [{
+                    "ext": 'srt'
+                }]
+            },
+        },
+        'params': {
+            'skip_download': True,
+        },

     }, {
         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
         'only_matching': True,
     }, {
         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
         'only_matching': True,


@@ -115,12 +134,13 @@ class PornHubIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

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

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

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

             return self._download_webpage(
                 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
             return self._download_webpage(
                 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,

-                video_id, headers={
-                    'Cookie': 'age_verified=1; platform=%s' % platform,
-                })
+                video_id, 'Downloading %s webpage' % platform)

 
         webpage = dl_webpage('pc')
 
 
         webpage = dl_webpage('pc')
 


@@ -133,60 +153,108 @@ class PornHubIE(InfoExtractor):
                 'PornHub said: %s' % error_msg,
                 expected=True, video_id=video_id)
 
                 'PornHub said: %s' % error_msg,
                 expected=True, video_id=video_id)
 

-        tv_webpage = dl_webpage('tv')
-
-        assignments = self._search_regex(
-            r'(var.+?mediastring.+?)</script>', tv_webpage,
-            'encoded url').split(';')
-
-        js_vars = {}
-
-        def parse_js_value(inp):
-            inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
-            if '+' in inp:
-                inps = inp.split('+')
-                return functools.reduce(
-                    operator.concat, map(parse_js_value, inps))
-            inp = inp.strip()
-            if inp in js_vars:
-                return js_vars[inp]
-            return remove_quotes(inp)
-
-        for assn in assignments:
-            assn = assn.strip()
-            if not assn:
-                continue
-            assn = re.sub(r'var\s+', '', assn)
-            vname, value = assn.split('=', 1)
-            js_vars[vname] = parse_js_value(value)
-
-        video_url = js_vars['mediastring']
-
-        title = self._search_regex(
-            r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)
-

         # video_title from flashvars contains whitespace instead of non-ASCII (see
         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
         # on that anymore.
         # video_title from flashvars contains whitespace instead of non-ASCII (see
         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
         # on that anymore.

-        title = title or self._html_search_meta(
+        title = self._html_search_meta(

             'twitter:title', webpage, default=None) or self._search_regex(
             (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
              r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
              r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
             webpage, 'title', group='title')
 
             'twitter:title', webpage, default=None) or self._search_regex(
             (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
              r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
              r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
             webpage, 'title', group='title')
 

+        video_urls = []
+        video_urls_set = set()
+        subtitles = {}
+

         flashvars = self._parse_json(
             self._search_regex(
                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
             video_id)
         if flashvars:
         flashvars = self._parse_json(
             self._search_regex(
                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
             video_id)
         if flashvars:

+            subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
+            if subtitle_url:
+                subtitles.setdefault('en', []).append({
+                    'url': subtitle_url,
+                    'ext': 'srt',
+                })

             thumbnail = flashvars.get('image_url')
             duration = int_or_none(flashvars.get('video_duration'))
             thumbnail = flashvars.get('image_url')
             duration = int_or_none(flashvars.get('video_duration'))

+            media_definitions = flashvars.get('mediaDefinitions')
+            if isinstance(media_definitions, list):
+                for definition in media_definitions:
+                    if not isinstance(definition, dict):
+                        continue
+                    video_url = definition.get('videoUrl')
+                    if not video_url or not isinstance(video_url, compat_str):
+                        continue
+                    if video_url in video_urls_set:
+                        continue
+                    video_urls_set.add(video_url)
+                    video_urls.append(
+                        (video_url, int_or_none(definition.get('quality'))))

         else:
         else:

-            title, thumbnail, duration = [None] * 3
+            thumbnail, duration = [None] * 2
+
+        if not video_urls:
+            tv_webpage = dl_webpage('tv')
+
+            assignments = self._search_regex(
+                r'(var.+?mediastring.+?)</script>', tv_webpage,
+                'encoded url').split(';')
+
+            js_vars = {}
+
+            def parse_js_value(inp):
+                inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
+                if '+' in inp:
+                    inps = inp.split('+')
+                    return functools.reduce(
+                        operator.concat, map(parse_js_value, inps))
+                inp = inp.strip()
+                if inp in js_vars:
+                    return js_vars[inp]
+                return remove_quotes(inp)
+
+            for assn in assignments:
+                assn = assn.strip()
+                if not assn:
+                    continue
+                assn = re.sub(r'var\s+', '', assn)
+                vname, value = assn.split('=', 1)
+                js_vars[vname] = parse_js_value(value)
+
+            video_url = js_vars['mediastring']
+            if video_url not in video_urls_set:
+                video_urls.append((video_url, None))
+                video_urls_set.add(video_url)
+
+        for mobj in re.finditer(
+                r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
+                webpage):
+            video_url = mobj.group('url')
+            if video_url not in video_urls_set:
+                video_urls.append((video_url, None))
+                video_urls_set.add(video_url)
+
+        formats = []
+        for video_url, height in video_urls:
+            tbr = None
+            mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
+            if mobj:
+                if not height:
+                    height = int(mobj.group('height'))
+                tbr = int(mobj.group('tbr'))
+            formats.append({
+                'url': video_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+                'tbr': tbr,
+            })
+        self._sort_formats(formats)

 
         video_uploader = self._html_search_regex(
 
         video_uploader = self._html_search_regex(

-            r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
+            r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',

             webpage, 'uploader', fatal=False)
 
         view_count = self._extract_count(
             webpage, 'uploader', fatal=False)
 
         view_count = self._extract_count(


@@ -209,7 +277,6 @@ class PornHubIE(InfoExtractor):
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'url': video_url,

             'uploader': video_uploader,
             'title': title,
             'thumbnail': thumbnail,
             'uploader': video_uploader,
             'title': title,
             'thumbnail': thumbnail,


@@ -218,22 +285,30 @@ class PornHubIE(InfoExtractor):
             'like_count': like_count,
             'dislike_count': dislike_count,
             'comment_count': comment_count,
             'like_count': like_count,
             'dislike_count': dislike_count,
             'comment_count': comment_count,

-            # 'formats': formats,
+            'formats': formats,

             'age_limit': 18,
             'tags': tags,
             'categories': categories,
             'age_limit': 18,
             'tags': tags,
             'categories': categories,

+            'subtitles': subtitles,

         }
 
 
 class PornHubPlaylistBaseIE(InfoExtractor):
     def _extract_entries(self, webpage):
         }
 
 
 class PornHubPlaylistBaseIE(InfoExtractor):
     def _extract_entries(self, webpage):

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

         return [
             self.url_result(
                 'http://www.pornhub.com/%s' % 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="([^"]+)"',
         return [
             self.url_result(
                 'http://www.pornhub.com/%s' % 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="([^"]+)"',

-                webpage))
+                container))

         ]
 
     def _real_extract(self, url):
         ]
 
     def _real_extract(self, url):


@@ -241,26 +316,22 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
         webpage = self._download_webpage(url, playlist_id)
 
 
         webpage = self._download_webpage(url, playlist_id)
 

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

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

-                r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
-            playlist_id)
+                r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
+                'playlist', default='{}'),
+            playlist_id, fatal=False)
+        title = playlist.get('title') or self._search_regex(
+            r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)

 
         return self.playlist_result(
 
         return self.playlist_result(

-            entries, playlist_id, playlist.get('title'), playlist.get('description'))
+            entries, playlist_id, title, playlist.get('description'))

 
 
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 
 
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):

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

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


@@ -268,11 +339,14 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE):
             'title': 'Nataly Hot',
         },
         'playlist_mincount': 2,
             'title': 'Nataly Hot',
         },
         'playlist_mincount': 2,

+    }, {
+        'url': 'https://de.pornhub.com/playlist/4667351',
+        'only_matching': True,

     }]
 
 
 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
     }]
 
 
 class PornHubUserVideosIE(PornHubPlaylistBaseIE):

-    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
+    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:(?: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': {


@@ -282,6 +356,34 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
     }, {
         'url': 'http://www.pornhub.com/users/rushandlia/videos',
         'only_matching': True,
     }, {
         'url': 'http://www.pornhub.com/users/rushandlia/videos',
         'only_matching': True,

+    }, {
+        # default sorting as Top Rated Videos
+        'url': 'https://www.pornhub.com/channels/povd/videos',
+        'info_dict': {
+            'id': 'povd',
+        },
+        'playlist_mincount': 293,
+    }, {
+        # Top Rated Videos
+        'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
+        'only_matching': True,
+    }, {
+        # Most Recent Videos
+        'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
+        'only_matching': True,
+    }, {
+        # Most Viewed Videos
+        'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):


@@ -296,6 +398,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
             except ExtractorError as e:
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
                     break
             except ExtractorError as e:
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
                     break

+                raise

             page_entries = self._extract_entries(webpage)
             if not page_entries:
                 break
             page_entries = self._extract_entries(webpage)
             if not page_entries:
                 break