2 from __future__ import unicode_literals
8 from .common import InfoExtractor
11 compat_urllib_parse_unquote,
12 compat_urllib_parse_unquote_plus,
13 compat_urllib_parse_urlparse,
28 class PornHubIE(InfoExtractor):
29 IE_DESC = 'PornHub and Thumbzilla'
33 (?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
34 (?:www\.)?thumbzilla\.com/video/
39 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
40 'md5': '1e19b41231a02eba417839222ac9d58e',
44 'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
57 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
62 'uploader': 'cj397186295',
73 'skip_download': True,
76 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
77 'only_matching': True,
79 # removed at the request of cam4.com
80 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
81 'only_matching': True,
83 # removed at the request of the copyright owner
84 'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
85 'only_matching': True,
88 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
89 'only_matching': True,
92 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
93 'only_matching': True,
95 'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
96 'only_matching': True,
100 def _extract_urls(webpage):
102 r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
105 def _extract_count(self, pattern, webpage, name):
106 return str_to_int(self._search_regex(
107 pattern, webpage, '%s count' % name, fatal=False))
109 def _real_extract(self, url):
110 video_id = self._match_id(url)
112 req = sanitized_Request(
113 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)
114 req.add_header('Cookie', 'age_verified=1')
115 webpage = self._download_webpage(req, video_id)
117 error_msg = self._html_search_regex(
118 r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
119 webpage, 'error message', default=None, group='error')
121 error_msg = re.sub(r'\s+', ' ', error_msg)
122 raise ExtractorError(
123 'PornHub said: %s' % error_msg,
124 expected=True, video_id=video_id)
126 # video_title from flashvars contains whitespace instead of non-ASCII (see
127 # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
129 title = self._html_search_meta(
130 'twitter:title', webpage, default=None) or self._search_regex(
131 (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
132 r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
133 r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
134 webpage, 'title', group='title')
136 flashvars = self._parse_json(
138 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
141 thumbnail = flashvars.get('image_url')
142 duration = int_or_none(flashvars.get('video_duration'))
144 title, thumbnail, duration = [None] * 3
146 video_uploader = self._html_search_regex(
147 r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
148 webpage, 'uploader', fatal=False)
150 view_count = self._extract_count(
151 r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
152 like_count = self._extract_count(
153 r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
154 dislike_count = self._extract_count(
155 r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
156 comment_count = self._extract_count(
157 r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
160 for quote, video_url in re.findall(
161 r'player_quality_[0-9]{3,4}p\s*=\s*(["\'])(.+?)\1;', webpage):
162 video_urls.append(compat_urllib_parse_unquote(re.sub(
163 r'{0}\s*\+\s*{0}'.format(quote), '', video_url)))
165 if webpage.find('"encrypted":true') != -1:
166 password = compat_urllib_parse_unquote_plus(
167 self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
168 video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
171 for video_url in video_urls:
172 path = compat_urllib_parse_urlparse(video_url).path
173 extension = os.path.splitext(path)[1][1:]
174 format = path.split('/')[5].split('_')[:2]
175 format = '-'.join(format)
177 m = re.match(r'^(?P<height>[0-9]+)[pP]-(?P<tbr>[0-9]+)[kK]$', format)
182 height = int(m.group('height'))
183 tbr = int(m.group('tbr'))
193 self._sort_formats(formats)
195 page_params = self._parse_json(self._search_regex(
196 r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
197 webpage, 'page parameters', group='data', default='{}'),
198 video_id, transform_source=js_to_json, fatal=False)
199 tags = categories = None
201 tags = page_params.get('tags', '').split(',')
202 categories = page_params.get('categories', '').split(',')
206 'uploader': video_uploader,
208 'thumbnail': thumbnail,
209 'duration': duration,
210 'view_count': view_count,
211 'like_count': like_count,
212 'dislike_count': dislike_count,
213 'comment_count': comment_count,
217 'categories': categories,
221 class PornHubPlaylistBaseIE(InfoExtractor):
222 def _extract_entries(self, webpage):
225 'http://www.pornhub.com/%s' % video_url,
226 PornHubIE.ie_key(), video_title=title)
227 for video_url, title in orderedSet(re.findall(
228 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
232 def _real_extract(self, url):
233 playlist_id = self._match_id(url)
235 webpage = self._download_webpage(url, playlist_id)
237 # Only process container div with main playlist content skipping
238 # drop-down menu that uses similar pattern for videos (see
239 # https://github.com/rg3/youtube-dl/issues/11594).
240 container = self._search_regex(
241 r'(?s)(<div[^>]+class=["\']container.+)', webpage,
242 'container', default=webpage)
244 entries = self._extract_entries(container)
246 playlist = self._parse_json(
248 r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
251 return self.playlist_result(
252 entries, playlist_id, playlist.get('title'), playlist.get('description'))
255 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
256 _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
258 'url': 'http://www.pornhub.com/playlist/4667351',
261 'title': 'Nataly Hot',
263 'playlist_mincount': 2,
267 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
268 _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
270 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
274 'playlist_mincount': 171,
276 'url': 'http://www.pornhub.com/users/rushandlia/videos',
277 'only_matching': True,
280 def _real_extract(self, url):
281 user_id = self._match_id(url)
284 for page_num in itertools.count(1):
286 webpage = self._download_webpage(
287 url, user_id, 'Downloading page %d' % page_num,
288 query={'page': page_num})
289 except ExtractorError as e:
290 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
292 page_entries = self._extract_entries(webpage)
295 entries.extend(page_entries)
297 return self.playlist_result(entries, user_id)