Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/pornhub.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import itertools
   5 # import os
   6 import re
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_HTTPError,
  11     # compat_urllib_parse_unquote,
  12     # compat_urllib_parse_unquote_plus,
  13     # compat_urllib_parse_urlparse,
  14 )
  15 from ..utils import (
  16     ExtractorError,
  17     int_or_none,
  18     js_to_json,
  19     orderedSet,
  20     # sanitized_Request,
  21     str_to_int,
  22 )
  23 # from ..aes import (
  24 #     aes_decrypt_text
  25 # )
  26
  27
  28 class PornHubIE(InfoExtractor):
  29     IE_DESC = 'PornHub and Thumbzilla'
  30     _VALID_URL = r'''(?x)
  31                     https?://
  32                         (?:
  33                             (?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
  34                             (?:www\.)?thumbzilla\.com/video/
  35                         )
  36                         (?P<id>[\da-z]+)
  37                     '''
  38     _TESTS = [{
  39         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
  40         'md5': '1e19b41231a02eba417839222ac9d58e',
  41         'info_dict': {
  42             'id': '648719015',
  43             'ext': 'mp4',
  44             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
  45             'uploader': 'Babes',
  46             'duration': 361,
  47             'view_count': int,
  48             'like_count': int,
  49             'dislike_count': int,
  50             'comment_count': int,
  51             'age_limit': 18,
  52             'tags': list,
  53             'categories': list,
  54         },
  55     }, {
  56         # non-ASCII title
  57         'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
  58         'info_dict': {
  59             'id': '1331683002',
  60             'ext': 'mp4',
  61             'title': '重庆婷婷女王足交',
  62             'uploader': 'cj397186295',
  63             'duration': 1753,
  64             'view_count': int,
  65             'like_count': int,
  66             'dislike_count': int,
  67             'comment_count': int,
  68             'age_limit': 18,
  69             'tags': list,
  70             'categories': list,
  71         },
  72         'params': {
  73             'skip_download': True,
  74         },
  75     }, {
  76         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
  77         'only_matching': True,
  78     }, {
  79         # removed at the request of cam4.com
  80         'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
  81         'only_matching': True,
  82     }, {
  83         # removed at the request of the copyright owner
  84         'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
  85         'only_matching': True,
  86     }, {
  87         # removed by uploader
  88         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
  89         'only_matching': True,
  90     }, {
  91         # private video
  92         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
  93         'only_matching': True,
  94     }, {
  95         'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
  96         'only_matching': True,
  97     }]
  98
  99     @staticmethod
 100     def _extract_urls(webpage):
 101         return re.findall(
 102             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
 103             webpage)
 104
 105     def _extract_count(self, pattern, webpage, name):
 106         return str_to_int(self._search_regex(
 107             pattern, webpage, '%s count' % name, fatal=False))
 108
 109     def _real_extract(self, url):
 110         video_id = self._match_id(url)
 111
 112         def dl_webpage(platform):
 113             return self._download_webpage(
 114                 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
 115                 video_id, headers={
 116                     'Cookie': 'age_verified=1; platform=%s' % platform,
 117                 })
 118
 119         webpage = dl_webpage('pc')
 120
 121         error_msg = self._html_search_regex(
 122             r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
 123             webpage, 'error message', default=None, group='error')
 124         if error_msg:
 125             error_msg = re.sub(r'\s+', ' ', error_msg)
 126             raise ExtractorError(
 127                 'PornHub said: %s' % error_msg,
 128                 expected=True, video_id=video_id)
 129
 130         tv_webpage = dl_webpage('tv')
 131
 132         video_url = self._search_regex(
 133             r'<video[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//.+?)\1', tv_webpage,
 134             'video url', group='url')
 135
 136         title = self._search_regex(
 137             r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)
 138
 139         # video_title from flashvars contains whitespace instead of non-ASCII (see
 140         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
 141         # on that anymore.
 142         title = title or self._html_search_meta(
 143             'twitter:title', webpage, default=None) or self._search_regex(
 144             (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
 145              r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
 146              r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
 147             webpage, 'title', group='title')
 148
 149         flashvars = self._parse_json(
 150             self._search_regex(
 151                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
 152             video_id)
 153         if flashvars:
 154             thumbnail = flashvars.get('image_url')
 155             duration = int_or_none(flashvars.get('video_duration'))
 156         else:
 157             title, thumbnail, duration = [None] * 3
 158
 159         video_uploader = self._html_search_regex(
 160             r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
 161             webpage, 'uploader', fatal=False)
 162
 163         view_count = self._extract_count(
 164             r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
 165         like_count = self._extract_count(
 166             r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
 167         dislike_count = self._extract_count(
 168             r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
 169         comment_count = self._extract_count(
 170             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 171
 172         page_params = self._parse_json(self._search_regex(
 173             r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
 174             webpage, 'page parameters', group='data', default='{}'),
 175             video_id, transform_source=js_to_json, fatal=False)
 176         tags = categories = None
 177         if page_params:
 178             tags = page_params.get('tags', '').split(',')
 179             categories = page_params.get('categories', '').split(',')
 180
 181         return {
 182             'id': video_id,
 183             'url': video_url,
 184             'uploader': video_uploader,
 185             'title': title,
 186             'thumbnail': thumbnail,
 187             'duration': duration,
 188             'view_count': view_count,
 189             'like_count': like_count,
 190             'dislike_count': dislike_count,
 191             'comment_count': comment_count,
 192             # 'formats': formats,
 193             'age_limit': 18,
 194             'tags': tags,
 195             'categories': categories,
 196         }
 197
 198
 199 class PornHubPlaylistBaseIE(InfoExtractor):
 200     def _extract_entries(self, webpage):
 201         return [
 202             self.url_result(
 203                 'http://www.pornhub.com/%s' % video_url,
 204                 PornHubIE.ie_key(), video_title=title)
 205             for video_url, title in orderedSet(re.findall(
 206                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
 207                 webpage))
 208         ]
 209
 210     def _real_extract(self, url):
 211         playlist_id = self._match_id(url)
 212
 213         webpage = self._download_webpage(url, playlist_id)
 214
 215         # Only process container div with main playlist content skipping
 216         # drop-down menu that uses similar pattern for videos (see
 217         # https://github.com/rg3/youtube-dl/issues/11594).
 218         container = self._search_regex(
 219             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
 220             'container', default=webpage)
 221
 222         entries = self._extract_entries(container)
 223
 224         playlist = self._parse_json(
 225             self._search_regex(
 226                 r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
 227             playlist_id)
 228
 229         return self.playlist_result(
 230             entries, playlist_id, playlist.get('title'), playlist.get('description'))
 231
 232
 233 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 234     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
 235     _TESTS = [{
 236         'url': 'http://www.pornhub.com/playlist/4667351',
 237         'info_dict': {
 238             'id': '4667351',
 239             'title': 'Nataly Hot',
 240         },
 241         'playlist_mincount': 2,
 242     }]
 243
 244
 245 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
 246     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
 247     _TESTS = [{
 248         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
 249         'info_dict': {
 250             'id': 'zoe_ph',
 251         },
 252         'playlist_mincount': 171,
 253     }, {
 254         'url': 'http://www.pornhub.com/users/rushandlia/videos',
 255         'only_matching': True,
 256     }]
 257
 258     def _real_extract(self, url):
 259         user_id = self._match_id(url)
 260
 261         entries = []
 262         for page_num in itertools.count(1):
 263             try:
 264                 webpage = self._download_webpage(
 265                     url, user_id, 'Downloading page %d' % page_num,
 266                     query={'page': page_num})
 267             except ExtractorError as e:
 268                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
 269                     break
 270             page_entries = self._extract_entries(webpage)
 271             if not page_entries:
 272                 break
 273             entries.extend(page_entries)
 274
 275         return self.playlist_result(entries, user_id)