2 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from ..compat import (
13 compat_urllib_request,
15 from .openload import PhantomJSwrapper
27 class PornHubBaseIE(InfoExtractor):
28 def _download_webpage_handle(self, *args, **kwargs):
29 def dl(*args, **kwargs):
30 return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
32 webpage, urlh = dl(*args, **kwargs)
34 if any(re.search(p, webpage) for p in (
35 r'<body\b[^>]+\bonload=["\']go\(\)',
36 r'document\.cookie\s*=\s*["\']RNKEY=',
37 r'document\.location\.reload\(true\)')):
38 url_or_request = args[0]
39 url = (url_or_request.get_full_url()
40 if isinstance(url_or_request, compat_urllib_request.Request)
42 phantom = PhantomJSwrapper(self, required_version='2.0')
43 phantom.get(url, html=webpage)
44 webpage, urlh = dl(*args, **kwargs)
49 class PornHubIE(PornHubBaseIE):
50 IE_DESC = 'PornHub and Thumbzilla'
54 (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
55 (?:www\.)?thumbzilla\.com/video/
60 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
61 'md5': '1e19b41231a02eba417839222ac9d58e',
65 'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
67 'upload_date': '20130628',
79 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
84 'uploader': 'Unknown',
85 'upload_date': '20150213',
96 'skip_download': True,
100 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
102 'id': 'ph5af5fef7c2aa7',
104 'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
109 'dislike_count': int,
110 'comment_count': int,
121 'skip_download': True,
124 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
125 'only_matching': True,
127 # removed at the request of cam4.com
128 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
129 'only_matching': True,
131 # removed at the request of the copyright owner
132 'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
133 'only_matching': True,
135 # removed by uploader
136 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
137 'only_matching': True,
140 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
141 'only_matching': True,
143 'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
144 'only_matching': True,
146 'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
147 'only_matching': True,
149 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
150 'only_matching': True,
154 def _extract_urls(webpage):
156 r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
159 def _extract_count(self, pattern, webpage, name):
160 return str_to_int(self._search_regex(
161 pattern, webpage, '%s count' % name, fatal=False))
163 def _real_extract(self, url):
164 mobj = re.match(self._VALID_URL, url)
165 host = mobj.group('host') or 'pornhub.com'
166 video_id = mobj.group('id')
168 self._set_cookie(host, 'age_verified', '1')
170 def dl_webpage(platform):
171 self._set_cookie(host, 'platform', platform)
172 return self._download_webpage(
173 'http://www.%s/view_video.php?viewkey=%s' % (host, video_id),
174 video_id, 'Downloading %s webpage' % platform)
176 webpage = dl_webpage('pc')
178 error_msg = self._html_search_regex(
179 r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
180 webpage, 'error message', default=None, group='error')
182 error_msg = re.sub(r'\s+', ' ', error_msg)
183 raise ExtractorError(
184 'PornHub said: %s' % error_msg,
185 expected=True, video_id=video_id)
187 # video_title from flashvars contains whitespace instead of non-ASCII (see
188 # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
190 title = self._html_search_meta(
191 'twitter:title', webpage, default=None) or self._search_regex(
192 (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
193 r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
194 r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
195 webpage, 'title', group='title')
198 video_urls_set = set()
201 flashvars = self._parse_json(
203 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
206 subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
208 subtitles.setdefault('en', []).append({
212 thumbnail = flashvars.get('image_url')
213 duration = int_or_none(flashvars.get('video_duration'))
214 media_definitions = flashvars.get('mediaDefinitions')
215 if isinstance(media_definitions, list):
216 for definition in media_definitions:
217 if not isinstance(definition, dict):
219 video_url = definition.get('videoUrl')
220 if not video_url or not isinstance(video_url, compat_str):
222 if video_url in video_urls_set:
224 video_urls_set.add(video_url)
226 (video_url, int_or_none(definition.get('quality'))))
228 thumbnail, duration = [None] * 2
231 tv_webpage = dl_webpage('tv')
233 assignments = self._search_regex(
234 r'(var.+?mediastring.+?)</script>', tv_webpage,
235 'encoded url').split(';')
239 def parse_js_value(inp):
240 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
242 inps = inp.split('+')
243 return functools.reduce(
244 operator.concat, map(parse_js_value, inps))
248 return remove_quotes(inp)
250 for assn in assignments:
254 assn = re.sub(r'var\s+', '', assn)
255 vname, value = assn.split('=', 1)
256 js_vars[vname] = parse_js_value(value)
258 video_url = js_vars['mediastring']
259 if video_url not in video_urls_set:
260 video_urls.append((video_url, None))
261 video_urls_set.add(video_url)
263 for mobj in re.finditer(
264 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
266 video_url = mobj.group('url')
267 if video_url not in video_urls_set:
268 video_urls.append((video_url, None))
269 video_urls_set.add(video_url)
273 for video_url, height in video_urls:
275 upload_date = self._search_regex(
276 r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
278 upload_date = upload_date.replace('/', '')
280 mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
283 height = int(mobj.group('height'))
284 tbr = int(mobj.group('tbr'))
287 'format_id': '%dp' % height if height else None,
291 self._sort_formats(formats)
293 video_uploader = self._html_search_regex(
294 r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
295 webpage, 'uploader', fatal=False)
297 view_count = self._extract_count(
298 r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
299 like_count = self._extract_count(
300 r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
301 dislike_count = self._extract_count(
302 r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
303 comment_count = self._extract_count(
304 r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
306 page_params = self._parse_json(self._search_regex(
307 r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
308 webpage, 'page parameters', group='data', default='{}'),
309 video_id, transform_source=js_to_json, fatal=False)
310 tags = categories = None
312 tags = page_params.get('tags', '').split(',')
313 categories = page_params.get('categories', '').split(',')
317 'uploader': video_uploader,
318 'upload_date': upload_date,
320 'thumbnail': thumbnail,
321 'duration': duration,
322 'view_count': view_count,
323 'like_count': like_count,
324 'dislike_count': dislike_count,
325 'comment_count': comment_count,
329 'categories': categories,
330 'subtitles': subtitles,
334 class PornHubPlaylistBaseIE(PornHubBaseIE):
335 def _extract_entries(self, webpage, host):
336 # Only process container div with main playlist content skipping
337 # drop-down menu that uses similar pattern for videos (see
338 # https://github.com/rg3/youtube-dl/issues/11594).
339 container = self._search_regex(
340 r'(?s)(<div[^>]+class=["\']container.+)', webpage,
341 'container', default=webpage)
345 'http://www.%s/%s' % (host, video_url),
346 PornHubIE.ie_key(), video_title=title)
347 for video_url, title in orderedSet(re.findall(
348 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
352 def _real_extract(self, url):
353 mobj = re.match(self._VALID_URL, url)
354 host = mobj.group('host')
355 playlist_id = mobj.group('id')
357 webpage = self._download_webpage(url, playlist_id)
359 entries = self._extract_entries(webpage, host)
361 playlist = self._parse_json(
363 r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
364 'playlist', default='{}'),
365 playlist_id, fatal=False)
366 title = playlist.get('title') or self._search_regex(
367 r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
369 return self.playlist_result(
370 entries, playlist_id, title, playlist.get('description'))
373 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
374 _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
376 'url': 'http://www.pornhub.com/playlist/4667351',
379 'title': 'Nataly Hot',
381 'playlist_mincount': 2,
383 'url': 'https://de.pornhub.com/playlist/4667351',
384 'only_matching': True,
388 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
389 _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
391 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
395 'playlist_mincount': 171,
397 'url': 'http://www.pornhub.com/users/rushandlia/videos',
398 'only_matching': True,
400 # default sorting as Top Rated Videos
401 'url': 'https://www.pornhub.com/channels/povd/videos',
405 'playlist_mincount': 293,
408 'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
409 'only_matching': True,
412 'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
413 'only_matching': True,
416 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
417 'only_matching': True,
419 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
420 'only_matching': True,
422 'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
423 'only_matching': True,
425 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
426 'only_matching': True,
429 def _real_extract(self, url):
430 mobj = re.match(self._VALID_URL, url)
431 host = mobj.group('host')
432 user_id = mobj.group('id')
435 for page_num in itertools.count(1):
437 webpage = self._download_webpage(
438 url, user_id, 'Downloading page %d' % page_num,
439 query={'page': page_num})
440 except ExtractorError as e:
441 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
444 page_entries = self._extract_entries(webpage, host)
447 entries.extend(page_entries)
449 return self.playlist_result(entries, user_id)