2 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from ..compat import (
25 class PornHubIE(InfoExtractor):
26 IE_DESC = 'PornHub and Thumbzilla'
30 (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
31 (?:www\.)?thumbzilla\.com/video/
36 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
37 'md5': '1e19b41231a02eba417839222ac9d58e',
41 'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
54 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
59 'uploader': 'Unknown',
70 'skip_download': True,
74 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
76 'id': 'ph5af5fef7c2aa7',
78 'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
95 'skip_download': True,
98 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
99 'only_matching': True,
101 # removed at the request of cam4.com
102 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
103 'only_matching': True,
105 # removed at the request of the copyright owner
106 'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
107 'only_matching': True,
109 # removed by uploader
110 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
111 'only_matching': True,
114 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
115 'only_matching': True,
117 'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
118 'only_matching': True,
120 'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
121 'only_matching': True,
125 def _extract_urls(webpage):
127 r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
130 def _extract_count(self, pattern, webpage, name):
131 return str_to_int(self._search_regex(
132 pattern, webpage, '%s count' % name, fatal=False))
134 def _real_extract(self, url):
135 video_id = self._match_id(url)
137 self._set_cookie('pornhub.com', 'age_verified', '1')
139 def dl_webpage(platform):
140 self._set_cookie('pornhub.com', 'platform', platform)
141 return self._download_webpage(
142 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
143 video_id, 'Downloading %s webpage' % platform)
145 webpage = dl_webpage('pc')
147 error_msg = self._html_search_regex(
148 r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
149 webpage, 'error message', default=None, group='error')
151 error_msg = re.sub(r'\s+', ' ', error_msg)
152 raise ExtractorError(
153 'PornHub said: %s' % error_msg,
154 expected=True, video_id=video_id)
156 # video_title from flashvars contains whitespace instead of non-ASCII (see
157 # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
159 title = self._html_search_meta(
160 'twitter:title', webpage, default=None) or self._search_regex(
161 (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
162 r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
163 r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
164 webpage, 'title', group='title')
167 video_urls_set = set()
170 flashvars = self._parse_json(
172 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
175 subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
177 subtitles.setdefault('en', []).append({
181 thumbnail = flashvars.get('image_url')
182 duration = int_or_none(flashvars.get('video_duration'))
183 media_definitions = flashvars.get('mediaDefinitions')
184 if isinstance(media_definitions, list):
185 for definition in media_definitions:
186 if not isinstance(definition, dict):
188 video_url = definition.get('videoUrl')
189 if not video_url or not isinstance(video_url, compat_str):
191 if video_url in video_urls_set:
193 video_urls_set.add(video_url)
195 (video_url, int_or_none(definition.get('quality'))))
197 thumbnail, duration = [None] * 2
200 tv_webpage = dl_webpage('tv')
202 assignments = self._search_regex(
203 r'(var.+?mediastring.+?)</script>', tv_webpage,
204 'encoded url').split(';')
208 def parse_js_value(inp):
209 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
211 inps = inp.split('+')
212 return functools.reduce(
213 operator.concat, map(parse_js_value, inps))
217 return remove_quotes(inp)
219 for assn in assignments:
223 assn = re.sub(r'var\s+', '', assn)
224 vname, value = assn.split('=', 1)
225 js_vars[vname] = parse_js_value(value)
227 video_url = js_vars['mediastring']
228 if video_url not in video_urls_set:
229 video_urls.append((video_url, None))
230 video_urls_set.add(video_url)
232 for mobj in re.finditer(
233 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
235 video_url = mobj.group('url')
236 if video_url not in video_urls_set:
237 video_urls.append((video_url, None))
238 video_urls_set.add(video_url)
241 for video_url, height in video_urls:
243 mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
246 height = int(mobj.group('height'))
247 tbr = int(mobj.group('tbr'))
250 'format_id': '%dp' % height if height else None,
254 self._sort_formats(formats)
256 video_uploader = self._html_search_regex(
257 r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
258 webpage, 'uploader', fatal=False)
260 view_count = self._extract_count(
261 r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
262 like_count = self._extract_count(
263 r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
264 dislike_count = self._extract_count(
265 r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
266 comment_count = self._extract_count(
267 r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
269 page_params = self._parse_json(self._search_regex(
270 r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
271 webpage, 'page parameters', group='data', default='{}'),
272 video_id, transform_source=js_to_json, fatal=False)
273 tags = categories = None
275 tags = page_params.get('tags', '').split(',')
276 categories = page_params.get('categories', '').split(',')
280 'uploader': video_uploader,
282 'thumbnail': thumbnail,
283 'duration': duration,
284 'view_count': view_count,
285 'like_count': like_count,
286 'dislike_count': dislike_count,
287 'comment_count': comment_count,
291 'categories': categories,
292 'subtitles': subtitles,
296 class PornHubPlaylistBaseIE(InfoExtractor):
297 def _extract_entries(self, webpage):
298 # Only process container div with main playlist content skipping
299 # drop-down menu that uses similar pattern for videos (see
300 # https://github.com/rg3/youtube-dl/issues/11594).
301 container = self._search_regex(
302 r'(?s)(<div[^>]+class=["\']container.+)', webpage,
303 'container', default=webpage)
307 'http://www.pornhub.com/%s' % video_url,
308 PornHubIE.ie_key(), video_title=title)
309 for video_url, title in orderedSet(re.findall(
310 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
314 def _real_extract(self, url):
315 playlist_id = self._match_id(url)
317 webpage = self._download_webpage(url, playlist_id)
319 entries = self._extract_entries(webpage)
321 playlist = self._parse_json(
323 r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
324 'playlist', default='{}'),
325 playlist_id, fatal=False)
326 title = playlist.get('title') or self._search_regex(
327 r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
329 return self.playlist_result(
330 entries, playlist_id, title, playlist.get('description'))
333 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
334 _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)'
336 'url': 'http://www.pornhub.com/playlist/4667351',
339 'title': 'Nataly Hot',
341 'playlist_mincount': 2,
343 'url': 'https://de.pornhub.com/playlist/4667351',
344 'only_matching': True,
348 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
349 _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
351 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
355 'playlist_mincount': 171,
357 'url': 'http://www.pornhub.com/users/rushandlia/videos',
358 'only_matching': True,
360 # default sorting as Top Rated Videos
361 'url': 'https://www.pornhub.com/channels/povd/videos',
365 'playlist_mincount': 293,
368 'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
369 'only_matching': True,
372 'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
373 'only_matching': True,
376 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
377 'only_matching': True,
379 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
380 'only_matching': True,
382 'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
383 'only_matching': True,
385 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
386 'only_matching': True,
389 def _real_extract(self, url):
390 user_id = self._match_id(url)
393 for page_num in itertools.count(1):
395 webpage = self._download_webpage(
396 url, user_id, 'Downloading page %d' % page_num,
397 query={'page': page_num})
398 except ExtractorError as e:
399 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
402 page_entries = self._extract_entries(webpage)
405 entries.extend(page_entries)
407 return self.playlist_result(entries, user_id)