]>
Commit | Line | Data |
---|---|---|
21fbf0f9 | 1 | import functools |
34541395 | 2 | import itertools |
df2a5633 | 3 | import math |
21fbf0f9 | 4 | import operator |
125cfd78 | 5 | import re |
6 | ||
7 | from .common import InfoExtractor | |
1cc79574 | 8 | from ..compat import ( |
34541395 | 9 | compat_HTTPError, |
79367a98 | 10 | compat_str, |
278d061a | 11 | compat_urllib_request, |
1cc79574 | 12 | ) |
278d061a | 13 | from .openload import PhantomJSwrapper |
1cc79574 | 14 | from ..utils import ( |
d0fb4bd1 | 15 | clean_html, |
b8526c78 | 16 | determine_ext, |
50789175 | 17 | ExtractorError, |
e0ddbd02 | 18 | format_field, |
ed8648a3 | 19 | int_or_none, |
cd85a1bb | 20 | merge_dicts, |
0164cd5d | 21 | NO_DEFAULT, |
8f9a477e | 22 | orderedSet, |
e1e35d1a | 23 | remove_quotes, |
0320ddc1 | 24 | str_to_int, |
2181983a | 25 | update_url_query, |
26 | urlencode_postdata, | |
4938c8d5 | 27 | url_or_none, |
125cfd78 | 28 | ) |
125cfd78 | 29 | |
9933b574 | 30 | |
71a1f617 | 31 | class PornHubBaseIE(InfoExtractor): |
2181983a | 32 | _NETRC_MACHINE = 'pornhub' |
4c968755 | 33 | _PORNHUB_HOST_RE = r'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd\.onion)' |
2181983a | 34 | |
71a1f617 S |
35 | def _download_webpage_handle(self, *args, **kwargs): |
36 | def dl(*args, **kwargs): | |
37 | return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs) | |
38 | ||
29f7c58a | 39 | ret = dl(*args, **kwargs) |
40 | ||
41 | if not ret: | |
42 | return ret | |
43 | ||
44 | webpage, urlh = ret | |
71a1f617 S |
45 | |
46 | if any(re.search(p, webpage) for p in ( | |
47 | r'<body\b[^>]+\bonload=["\']go\(\)', | |
48 | r'document\.cookie\s*=\s*["\']RNKEY=', | |
49 | r'document\.location\.reload\(true\)')): | |
50 | url_or_request = args[0] | |
51 | url = (url_or_request.get_full_url() | |
52 | if isinstance(url_or_request, compat_urllib_request.Request) | |
53 | else url_or_request) | |
54 | phantom = PhantomJSwrapper(self, required_version='2.0') | |
55 | phantom.get(url, html=webpage) | |
56 | webpage, urlh = dl(*args, **kwargs) | |
57 | ||
58 | return webpage, urlh | |
59 | ||
2181983a | 60 | def _real_initialize(self): |
61 | self._logged_in = False | |
62 | ||
63 | def _login(self, host): | |
64 | if self._logged_in: | |
65 | return | |
66 | ||
67 | site = host.split('.')[0] | |
68 | ||
69 | # Both sites pornhub and pornhubpremium have separate accounts | |
70 | # so there should be an option to provide credentials for both. | |
71 | # At the same time some videos are available under the same video id | |
72 | # on both sites so that we have to identify them as the same video. | |
73 | # For that purpose we have to keep both in the same extractor | |
74 | # but under different netrc machines. | |
75 | username, password = self._get_login_info(netrc_machine=site) | |
76 | if username is None: | |
77 | return | |
78 | ||
79 | login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '') | |
80 | login_page = self._download_webpage( | |
81 | login_url, None, 'Downloading %s login page' % site) | |
82 | ||
83 | def is_logged(webpage): | |
84 | return any(re.search(p, webpage) for p in ( | |
85 | r'class=["\']signOut', | |
86 | r'>Sign\s+[Oo]ut\s*<')) | |
87 | ||
88 | if is_logged(login_page): | |
89 | self._logged_in = True | |
90 | return | |
91 | ||
92 | login_form = self._hidden_inputs(login_page) | |
93 | ||
94 | login_form.update({ | |
95 | 'username': username, | |
96 | 'password': password, | |
97 | }) | |
98 | ||
99 | response = self._download_json( | |
100 | 'https://www.%s/front/authenticate' % host, None, | |
101 | 'Logging in to %s' % site, | |
102 | data=urlencode_postdata(login_form), | |
103 | headers={ | |
104 | 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', | |
105 | 'Referer': login_url, | |
106 | 'X-Requested-With': 'XMLHttpRequest', | |
107 | }) | |
108 | ||
109 | if response.get('success') == '1': | |
110 | self._logged_in = True | |
111 | return | |
112 | ||
113 | message = response.get('message') | |
114 | if message is not None: | |
115 | raise ExtractorError( | |
116 | 'Unable to login: %s' % message, expected=True) | |
117 | ||
118 | raise ExtractorError('Unable to log in') | |
119 | ||
71a1f617 S |
120 | |
121 | class PornHubIE(PornHubBaseIE): | |
bc4b2d75 S |
122 | IE_DESC = 'PornHub and Thumbzilla' |
123 | _VALID_URL = r'''(?x) | |
124 | https?:// | |
125 | (?: | |
ed807c18 | 126 | (?:[^/]+\.)? |
127 | %s | |
128 | /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| | |
bc4b2d75 S |
129 | (?:www\.)?thumbzilla\.com/video/ |
130 | ) | |
b52c9ef1 | 131 | (?P<id>[\da-z]+) |
ed807c18 | 132 | ''' % PornHubBaseIE._PORNHUB_HOST_RE |
360075e2 | 133 | _TESTS = [{ |
9933b574 | 134 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', |
cd85a1bb | 135 | 'md5': 'a6391306d050e4547f62b3f485dd9ba9', |
9933b574 | 136 | 'info_dict': { |
249efaf4 PH |
137 | 'id': '648719015', |
138 | 'ext': 'mp4', | |
611c1dd9 | 139 | 'title': 'Seductive Indian beauty strips down and fingers her pink pussy', |
ed8648a3 | 140 | 'uploader': 'Babes', |
3661ebf2 | 141 | 'upload_date': '20130628', |
cd85a1bb | 142 | 'timestamp': 1372447216, |
ed8648a3 S |
143 | 'duration': 361, |
144 | 'view_count': int, | |
145 | 'like_count': int, | |
146 | 'dislike_count': int, | |
147 | 'comment_count': int, | |
148 | 'age_limit': 18, | |
6bb05b32 YCH |
149 | 'tags': list, |
150 | 'categories': list, | |
d0fb4bd1 | 151 | 'cast': list, |
6c376029 S |
152 | }, |
153 | }, { | |
154 | # non-ASCII title | |
155 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002', | |
156 | 'info_dict': { | |
157 | 'id': '1331683002', | |
158 | 'ext': 'mp4', | |
159 | 'title': '重庆婷婷女王足交', | |
3661ebf2 | 160 | 'upload_date': '20150213', |
cd85a1bb | 161 | 'timestamp': 1423804862, |
6c376029 S |
162 | 'duration': 1753, |
163 | 'view_count': int, | |
164 | 'like_count': int, | |
165 | 'dislike_count': int, | |
166 | 'comment_count': int, | |
167 | 'age_limit': 18, | |
6bb05b32 YCH |
168 | 'tags': list, |
169 | 'categories': list, | |
6c376029 S |
170 | }, |
171 | 'params': { | |
172 | 'skip_download': True, | |
173 | }, | |
10db0d2f | 174 | 'skip': 'Video has been flagged for verification in accordance with our trust and safety policy', |
4938c8d5 GF |
175 | }, { |
176 | # subtitles | |
177 | 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7', | |
178 | 'info_dict': { | |
179 | 'id': 'ph5af5fef7c2aa7', | |
180 | 'ext': 'mp4', | |
181 | 'title': 'BFFS - Cute Teen Girls Share Cock On the Floor', | |
182 | 'uploader': 'BFFs', | |
183 | 'duration': 622, | |
184 | 'view_count': int, | |
185 | 'like_count': int, | |
186 | 'dislike_count': int, | |
187 | 'comment_count': int, | |
188 | 'age_limit': 18, | |
189 | 'tags': list, | |
190 | 'categories': list, | |
191 | 'subtitles': { | |
192 | 'en': [{ | |
193 | "ext": 'srt' | |
194 | }] | |
195 | }, | |
196 | }, | |
197 | 'params': { | |
198 | 'skip_download': True, | |
199 | }, | |
cd85a1bb | 200 | 'skip': 'This video has been disabled', |
360075e2 S |
201 | }, { |
202 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', | |
203 | 'only_matching': True, | |
272e4db5 | 204 | }, { |
eaaaaec0 | 205 | # removed at the request of cam4.com |
272e4db5 S |
206 | 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862', |
207 | 'only_matching': True, | |
eaaaaec0 S |
208 | }, { |
209 | # removed at the request of the copyright owner | |
210 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859', | |
211 | 'only_matching': True, | |
212 | }, { | |
213 | # removed by uploader | |
214 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111', | |
215 | 'only_matching': True, | |
195f0845 S |
216 | }, { |
217 | # private video | |
218 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7', | |
219 | 'only_matching': True, | |
bc4b2d75 S |
220 | }, { |
221 | 'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex', | |
222 | 'only_matching': True, | |
a99cc4ca S |
223 | }, { |
224 | 'url': 'http://www.pornhub.com/video/show?viewkey=648719015', | |
225 | 'only_matching': True, | |
f97c0991 S |
226 | }, { |
227 | 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', | |
228 | 'only_matching': True, | |
29f7c58a | 229 | }, { |
230 | 'url': 'https://www.pornhub.org/view_video.php?viewkey=203640933', | |
231 | 'only_matching': True, | |
fa9b8c66 TW |
232 | }, { |
233 | 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82', | |
234 | 'only_matching': True, | |
2181983a | 235 | }, { |
236 | # Some videos are available with the same id on both premium | |
237 | # and non-premium sites (e.g. this and the following test) | |
238 | 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5f75b0f4b18e3', | |
239 | 'only_matching': True, | |
240 | }, { | |
241 | 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3', | |
242 | 'only_matching': True, | |
ed807c18 | 243 | }, { |
244 | # geo restricted | |
245 | 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5a9813bfa7156', | |
246 | 'only_matching': True, | |
247 | }, { | |
4c968755 | 248 | 'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/view_video.php?viewkey=ph5a9813bfa7156', |
ed807c18 | 249 | 'only_matching': True, |
360075e2 | 250 | }] |
125cfd78 | 251 | |
b52c9ef1 S |
252 | @staticmethod |
253 | def _extract_urls(webpage): | |
254 | return re.findall( | |
2181983a | 255 | r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)', |
b52c9ef1 | 256 | webpage) |
65d161c4 | 257 | |
0320ddc1 | 258 | def _extract_count(self, pattern, webpage, name): |
b69fd25c | 259 | return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None)) |
0320ddc1 | 260 | |
125cfd78 | 261 | def _real_extract(self, url): |
5ad28e7f | 262 | mobj = self._match_valid_url(url) |
3430ff9b S |
263 | host = mobj.group('host') or 'pornhub.com' |
264 | video_id = mobj.group('id') | |
7399ca1f | 265 | |
2181983a | 266 | self._login(host) |
fa9b8c66 | 267 | |
3430ff9b | 268 | self._set_cookie(host, 'age_verified', '1') |
125cfd78 | 269 | |
9a372f14 | 270 | def dl_webpage(platform): |
3430ff9b | 271 | self._set_cookie(host, 'platform', platform) |
9a372f14 | 272 | return self._download_webpage( |
2c53c0eb | 273 | 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id), |
79367a98 | 274 | video_id, 'Downloading %s webpage' % platform) |
9a372f14 S |
275 | |
276 | webpage = dl_webpage('pc') | |
125cfd78 | 277 | |
50789175 | 278 | error_msg = self._html_search_regex( |
10db0d2f | 279 | (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>', |
280 | r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'), | |
3cb3b600 | 281 | webpage, 'error message', default=None, group='error') |
50789175 PH |
282 | if error_msg: |
283 | error_msg = re.sub(r'\s+', ' ', error_msg) | |
284 | raise ExtractorError( | |
285 | 'PornHub said: %s' % error_msg, | |
286 | expected=True, video_id=video_id) | |
287 | ||
ed807c18 | 288 | if any(re.search(p, webpage) for p in ( |
289 | r'class=["\']geoBlocked["\']', | |
290 | r'>\s*This content is unavailable in your country')): | |
291 | self.raise_geo_restricted() | |
292 | ||
6c376029 S |
293 | # video_title from flashvars contains whitespace instead of non-ASCII (see |
294 | # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying | |
295 | # on that anymore. | |
79367a98 | 296 | title = self._html_search_meta( |
46cc54ca S |
297 | 'twitter:title', webpage, default=None) or self._html_search_regex( |
298 | (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>', | |
299 | r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1', | |
300 | r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'), | |
6c376029 S |
301 | webpage, 'title', group='title') |
302 | ||
79367a98 S |
303 | video_urls = [] |
304 | video_urls_set = set() | |
4938c8d5 | 305 | subtitles = {} |
79367a98 | 306 | |
ed8648a3 S |
307 | flashvars = self._parse_json( |
308 | self._search_regex( | |
03442072 | 309 | r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), |
ed8648a3 S |
310 | video_id) |
311 | if flashvars: | |
4938c8d5 GF |
312 | subtitle_url = url_or_none(flashvars.get('closedCaptionsFile')) |
313 | if subtitle_url: | |
314 | subtitles.setdefault('en', []).append({ | |
315 | 'url': subtitle_url, | |
316 | 'ext': 'srt', | |
317 | }) | |
ed8648a3 S |
318 | thumbnail = flashvars.get('image_url') |
319 | duration = int_or_none(flashvars.get('video_duration')) | |
79367a98 S |
320 | media_definitions = flashvars.get('mediaDefinitions') |
321 | if isinstance(media_definitions, list): | |
322 | for definition in media_definitions: | |
323 | if not isinstance(definition, dict): | |
324 | continue | |
325 | video_url = definition.get('videoUrl') | |
326 | if not video_url or not isinstance(video_url, compat_str): | |
327 | continue | |
328 | if video_url in video_urls_set: | |
329 | continue | |
330 | video_urls_set.add(video_url) | |
331 | video_urls.append( | |
332 | (video_url, int_or_none(definition.get('quality')))) | |
ed8648a3 | 333 | else: |
79367a98 S |
334 | thumbnail, duration = [None] * 2 |
335 | ||
0164cd5d | 336 | def extract_js_vars(webpage, pattern, default=NO_DEFAULT): |
79367a98 | 337 | assignments = self._search_regex( |
0164cd5d | 338 | pattern, webpage, 'encoded url', default=default) |
f4134726 S |
339 | if not assignments: |
340 | return {} | |
341 | ||
342 | assignments = assignments.split(';') | |
79367a98 S |
343 | |
344 | js_vars = {} | |
345 | ||
346 | def parse_js_value(inp): | |
347 | inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp) | |
348 | if '+' in inp: | |
349 | inps = inp.split('+') | |
350 | return functools.reduce( | |
351 | operator.concat, map(parse_js_value, inps)) | |
352 | inp = inp.strip() | |
353 | if inp in js_vars: | |
354 | return js_vars[inp] | |
355 | return remove_quotes(inp) | |
356 | ||
357 | for assn in assignments: | |
358 | assn = assn.strip() | |
359 | if not assn: | |
360 | continue | |
361 | assn = re.sub(r'var\s+', '', assn) | |
362 | vname, value = assn.split('=', 1) | |
363 | js_vars[vname] = parse_js_value(value) | |
f4134726 | 364 | return js_vars |
79367a98 | 365 | |
f4134726 S |
366 | def add_video_url(video_url): |
367 | v_url = url_or_none(video_url) | |
368 | if not v_url: | |
369 | return | |
370 | if v_url in video_urls_set: | |
371 | return | |
372 | video_urls.append((v_url, None)) | |
373 | video_urls_set.add(v_url) | |
374 | ||
29f7c58a | 375 | def parse_quality_items(quality_items): |
376 | q_items = self._parse_json(quality_items, video_id, fatal=False) | |
377 | if not isinstance(q_items, list): | |
378 | return | |
379 | for item in q_items: | |
380 | if isinstance(item, dict): | |
381 | add_video_url(item.get('url')) | |
382 | ||
f4134726 | 383 | if not video_urls: |
29f7c58a | 384 | FORMAT_PREFIXES = ('media', 'quality', 'qualityItems') |
f4134726 S |
385 | js_vars = extract_js_vars( |
386 | webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES), | |
0164cd5d | 387 | default=None) |
f4134726 S |
388 | if js_vars: |
389 | for key, format_url in js_vars.items(): | |
29f7c58a | 390 | if key.startswith(FORMAT_PREFIXES[-1]): |
391 | parse_quality_items(format_url) | |
392 | elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]): | |
f4134726 | 393 | add_video_url(format_url) |
0164cd5d S |
394 | if not video_urls and re.search( |
395 | r'<[^>]+\bid=["\']lockedPlayer', webpage): | |
396 | raise ExtractorError( | |
397 | 'Video %s is locked' % video_id, expected=True) | |
f4134726 S |
398 | |
399 | if not video_urls: | |
400 | js_vars = extract_js_vars( | |
401 | dl_webpage('tv'), r'(var.+?mediastring.+?)</script>') | |
402 | add_video_url(js_vars['mediastring']) | |
79367a98 S |
403 | |
404 | for mobj in re.finditer( | |
405 | r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1', | |
406 | webpage): | |
407 | video_url = mobj.group('url') | |
408 | if video_url not in video_urls_set: | |
409 | video_urls.append((video_url, None)) | |
410 | video_urls_set.add(video_url) | |
411 | ||
3661ebf2 | 412 | upload_date = None |
79367a98 | 413 | formats = [] |
10db0d2f | 414 | |
415 | def add_format(format_url, height=None): | |
f7ad7160 | 416 | ext = determine_ext(format_url) |
417 | if ext == 'mpd': | |
418 | formats.extend(self._extract_mpd_formats( | |
419 | format_url, video_id, mpd_id='dash', fatal=False)) | |
420 | return | |
421 | if ext == 'm3u8': | |
422 | formats.extend(self._extract_m3u8_formats( | |
423 | format_url, video_id, 'mp4', entry_protocol='m3u8_native', | |
424 | m3u8_id='hls', fatal=False)) | |
425 | return | |
ed807c18 | 426 | if not height: |
427 | height = int_or_none(self._search_regex( | |
428 | r'(?P<height>\d+)[pP]?_\d+[kK]', format_url, 'height', | |
429 | default=None)) | |
10db0d2f | 430 | formats.append({ |
431 | 'url': format_url, | |
e0ddbd02 | 432 | 'format_id': format_field(height, template='%dp'), |
10db0d2f | 433 | 'height': height, |
10db0d2f | 434 | }) |
435 | ||
79367a98 | 436 | for video_url, height in video_urls: |
3661ebf2 S |
437 | if not upload_date: |
438 | upload_date = self._search_regex( | |
439 | r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None) | |
440 | if upload_date: | |
441 | upload_date = upload_date.replace('/', '') | |
10db0d2f | 442 | if '/video/get_media' in video_url: |
443 | medias = self._download_json(video_url, video_id, fatal=False) | |
444 | if isinstance(medias, list): | |
445 | for media in medias: | |
446 | if not isinstance(media, dict): | |
447 | continue | |
448 | video_url = url_or_none(media.get('videoUrl')) | |
449 | if not video_url: | |
450 | continue | |
451 | height = int_or_none(media.get('quality')) | |
452 | add_format(video_url, height) | |
453 | continue | |
454 | add_format(video_url) | |
ed807c18 | 455 | |
456 | # field_preference is unnecessary here, but kept for code-similarity with youtube-dl | |
457 | self._sort_formats( | |
458 | formats, field_preference=('height', 'width', 'fps', 'format_id')) | |
ed8648a3 | 459 | |
0320ddc1 | 460 | video_uploader = self._html_search_regex( |
2d4fe594 | 461 | r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', |
cd85a1bb | 462 | webpage, 'uploader', default=None) |
125cfd78 | 463 | |
29f7c58a | 464 | def extract_vote_count(kind, name): |
465 | return self._extract_count( | |
466 | (r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind, | |
467 | r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind), | |
468 | webpage, name) | |
469 | ||
7700207e | 470 | view_count = self._extract_count( |
540b9f51 | 471 | r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view') |
29f7c58a | 472 | like_count = extract_vote_count('Up', 'like') |
473 | dislike_count = extract_vote_count('Down', 'dislike') | |
0320ddc1 | 474 | comment_count = self._extract_count( |
7700207e | 475 | r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') |
0320ddc1 | 476 | |
5dda1ede | 477 | def extract_list(meta_key): |
d2d970d0 | 478 | div = self._search_regex( |
5dda1ede S |
479 | r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>' |
480 | % meta_key, webpage, meta_key, default=None) | |
d2d970d0 | 481 | if div: |
d0fb4bd1 | 482 | return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)] |
6bb05b32 | 483 | |
cd85a1bb S |
484 | info = self._search_json_ld(webpage, video_id, default={}) |
485 | # description provided in JSON-LD is irrelevant | |
486 | info['description'] = None | |
487 | ||
488 | return merge_dicts({ | |
125cfd78 | 489 | 'id': video_id, |
490 | 'uploader': video_uploader, | |
3661ebf2 | 491 | 'upload_date': upload_date, |
6c376029 | 492 | 'title': title, |
125cfd78 | 493 | 'thumbnail': thumbnail, |
ed8648a3 | 494 | 'duration': duration, |
0320ddc1 S |
495 | 'view_count': view_count, |
496 | 'like_count': like_count, | |
497 | 'dislike_count': dislike_count, | |
498 | 'comment_count': comment_count, | |
79367a98 | 499 | 'formats': formats, |
750e9833 | 500 | 'age_limit': 18, |
5dda1ede S |
501 | 'tags': extract_list('tags'), |
502 | 'categories': extract_list('categories'), | |
d0fb4bd1 | 503 | 'cast': extract_list('pornstars'), |
4938c8d5 | 504 | 'subtitles': subtitles, |
cd85a1bb | 505 | }, info) |
e66e1a00 S |
506 | |
507 | ||
71a1f617 | 508 | class PornHubPlaylistBaseIE(PornHubBaseIE): |
2181983a | 509 | def _extract_page(self, url): |
510 | return int_or_none(self._search_regex( | |
511 | r'\bpage=(\d+)', url, 'page', default=None)) | |
512 | ||
3430ff9b | 513 | def _extract_entries(self, webpage, host): |
475bcb22 S |
514 | # Only process container div with main playlist content skipping |
515 | # drop-down menu that uses similar pattern for videos (see | |
067aa17e | 516 | # https://github.com/ytdl-org/youtube-dl/issues/11594). |
475bcb22 S |
517 | container = self._search_regex( |
518 | r'(?s)(<div[^>]+class=["\']container.+)', webpage, | |
519 | 'container', default=webpage) | |
520 | ||
40e146aa | 521 | return [ |
3a23bae9 | 522 | self.url_result( |
3430ff9b | 523 | 'http://www.%s/%s' % (host, video_url), |
3a23bae9 S |
524 | PornHubIE.ie_key(), video_title=title) |
525 | for video_url, title in orderedSet(re.findall( | |
526 | r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"', | |
475bcb22 | 527 | container)) |
40e146aa | 528 | ] |
e66e1a00 | 529 | |
40e146aa | 530 | |
21b08463 | 531 | class PornHubUserIE(PornHubPlaylistBaseIE): |
ed807c18 | 532 | _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE |
40e146aa | 533 | _TESTS = [{ |
21b08463 S |
534 | 'url': 'https://www.pornhub.com/model/zoe_ph', |
535 | 'playlist_mincount': 118, | |
536 | }, { | |
537 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious', | |
40e146aa | 538 | 'info_dict': { |
21b08463 | 539 | 'id': 'liz-vicious', |
40e146aa | 540 | }, |
21b08463 S |
541 | 'playlist_mincount': 118, |
542 | }, { | |
543 | 'url': 'https://www.pornhub.com/users/russianveet69', | |
9634de17 | 544 | 'only_matching': True, |
21b08463 S |
545 | }, { |
546 | 'url': 'https://www.pornhub.com/channels/povd', | |
9634de17 S |
547 | 'only_matching': True, |
548 | }, { | |
549 | 'url': 'https://www.pornhub.com/model/zoe_ph?abc=1', | |
550 | 'only_matching': True, | |
2181983a | 551 | }, { |
552 | # Unavailable via /videos page, but available with direct pagination | |
553 | # on pornstar page (see [1]), requires premium | |
554 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27853 | |
555 | 'url': 'https://www.pornhubpremium.com/pornstar/sienna-west', | |
556 | 'only_matching': True, | |
557 | }, { | |
558 | # Same as before, multi page | |
559 | 'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau', | |
560 | 'only_matching': True, | |
ed807c18 | 561 | }, { |
4c968755 | 562 | 'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph', |
ed807c18 | 563 | 'only_matching': True, |
21b08463 S |
564 | }] |
565 | ||
21b08463 | 566 | def _real_extract(self, url): |
5ad28e7f | 567 | mobj = self._match_valid_url(url) |
21b08463 | 568 | user_id = mobj.group('id') |
2181983a | 569 | videos_url = '%s/videos' % mobj.group('url') |
570 | page = self._extract_page(url) | |
571 | if page: | |
572 | videos_url = update_url_query(videos_url, {'page': page}) | |
21b08463 | 573 | return self.url_result( |
2181983a | 574 | videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id) |
21b08463 S |
575 | |
576 | ||
577 | class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): | |
4bf568d3 S |
578 | @staticmethod |
579 | def _has_more(webpage): | |
580 | return re.search( | |
581 | r'''(?x) | |
582 | <li[^>]+\bclass=["\']page_next| | |
583 | <link[^>]+\brel=["\']next| | |
584 | <button[^>]+\bid=["\']moreDataBtn | |
585 | ''', webpage) is not None | |
586 | ||
2181983a | 587 | def _entries(self, url, host, item_id): |
588 | page = self._extract_page(url) | |
21b08463 | 589 | |
2181983a | 590 | VIDEOS = '/videos' |
591 | ||
592 | def download_page(base_url, num, fallback=False): | |
593 | note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '') | |
594 | return self._download_webpage( | |
595 | base_url, item_id, note, query={'page': num}) | |
1f7a563a | 596 | |
2181983a | 597 | def is_404(e): |
598 | return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404 | |
599 | ||
600 | base_url = url | |
601 | has_page = page is not None | |
602 | first_page = page if has_page else 1 | |
603 | for page_num in (first_page, ) if has_page else itertools.count(first_page): | |
21b08463 | 604 | try: |
2181983a | 605 | try: |
606 | webpage = download_page(base_url, page_num) | |
607 | except ExtractorError as e: | |
608 | # Some sources may not be available via /videos page, | |
609 | # trying to fallback to main page pagination (see [1]) | |
610 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27853 | |
611 | if is_404(e) and page_num == first_page and VIDEOS in base_url: | |
612 | base_url = base_url.replace(VIDEOS, '') | |
613 | webpage = download_page(base_url, page_num, fallback=True) | |
614 | else: | |
615 | raise | |
21b08463 | 616 | except ExtractorError as e: |
2181983a | 617 | if is_404(e) and page_num != first_page: |
21b08463 S |
618 | break |
619 | raise | |
620 | page_entries = self._extract_entries(webpage, host) | |
621 | if not page_entries: | |
622 | break | |
2181983a | 623 | for e in page_entries: |
624 | yield e | |
21b08463 S |
625 | if not self._has_more(webpage): |
626 | break | |
627 | ||
2181983a | 628 | def _real_extract(self, url): |
5ad28e7f | 629 | mobj = self._match_valid_url(url) |
2181983a | 630 | host = mobj.group('host') |
631 | item_id = mobj.group('id') | |
632 | ||
633 | self._login(host) | |
634 | ||
635 | return self.playlist_result(self._entries(url, host, item_id), item_id) | |
21b08463 S |
636 | |
637 | ||
9634de17 | 638 | class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): |
df2a5633 | 639 | _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE |
21b08463 | 640 | _TESTS = [{ |
1f7a563a | 641 | 'url': 'https://www.pornhub.com/model/zoe_ph/videos', |
21b08463 | 642 | 'only_matching': True, |
34541395 S |
643 | }, { |
644 | 'url': 'http://www.pornhub.com/users/rushandlia/videos', | |
645 | 'only_matching': True, | |
21b08463 S |
646 | }, { |
647 | 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos', | |
648 | 'info_dict': { | |
9634de17 | 649 | 'id': 'pornstar/jenny-blighe/videos', |
21b08463 S |
650 | }, |
651 | 'playlist_mincount': 149, | |
1f7a563a S |
652 | }, { |
653 | 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3', | |
654 | 'info_dict': { | |
9634de17 | 655 | 'id': 'pornstar/jenny-blighe/videos', |
1f7a563a S |
656 | }, |
657 | 'playlist_mincount': 40, | |
f66df20c PV |
658 | }, { |
659 | # default sorting as Top Rated Videos | |
660 | 'url': 'https://www.pornhub.com/channels/povd/videos', | |
661 | 'info_dict': { | |
9634de17 | 662 | 'id': 'channels/povd/videos', |
f66df20c PV |
663 | }, |
664 | 'playlist_mincount': 293, | |
665 | }, { | |
666 | # Top Rated Videos | |
667 | 'url': 'https://www.pornhub.com/channels/povd/videos?o=ra', | |
668 | 'only_matching': True, | |
669 | }, { | |
670 | # Most Recent Videos | |
671 | 'url': 'https://www.pornhub.com/channels/povd/videos?o=da', | |
672 | 'only_matching': True, | |
673 | }, { | |
674 | # Most Viewed Videos | |
675 | 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi', | |
676 | 'only_matching': True, | |
92ded33a S |
677 | }, { |
678 | 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', | |
679 | 'only_matching': True, | |
21b08463 S |
680 | }, { |
681 | # Most Viewed Videos | |
682 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv', | |
683 | 'only_matching': True, | |
684 | }, { | |
685 | # Top Rated Videos | |
686 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr', | |
687 | 'only_matching': True, | |
688 | }, { | |
689 | # Longest Videos | |
690 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg', | |
691 | 'only_matching': True, | |
692 | }, { | |
693 | # Newest Videos | |
694 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm', | |
695 | 'only_matching': True, | |
21b08463 S |
696 | }, { |
697 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid', | |
698 | 'only_matching': True, | |
699 | }, { | |
700 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly', | |
701 | 'only_matching': True, | |
9634de17 S |
702 | }, { |
703 | 'url': 'https://www.pornhub.com/video', | |
704 | 'only_matching': True, | |
705 | }, { | |
706 | 'url': 'https://www.pornhub.com/video?page=3', | |
707 | 'only_matching': True, | |
708 | }, { | |
709 | 'url': 'https://www.pornhub.com/video/search?search=123', | |
710 | 'only_matching': True, | |
711 | }, { | |
712 | 'url': 'https://www.pornhub.com/categories/teen', | |
713 | 'only_matching': True, | |
714 | }, { | |
715 | 'url': 'https://www.pornhub.com/categories/teen?page=3', | |
716 | 'only_matching': True, | |
717 | }, { | |
718 | 'url': 'https://www.pornhub.com/hd', | |
719 | 'only_matching': True, | |
720 | }, { | |
721 | 'url': 'https://www.pornhub.com/hd?page=3', | |
722 | 'only_matching': True, | |
723 | }, { | |
724 | 'url': 'https://www.pornhub.com/described-video', | |
725 | 'only_matching': True, | |
726 | }, { | |
727 | 'url': 'https://www.pornhub.com/described-video?page=2', | |
728 | 'only_matching': True, | |
729 | }, { | |
730 | 'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn', | |
731 | 'only_matching': True, | |
ed807c18 | 732 | }, { |
4c968755 | 733 | 'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph/videos', |
ed807c18 | 734 | 'only_matching': True, |
40e146aa S |
735 | }] |
736 | ||
21b08463 S |
737 | @classmethod |
738 | def suitable(cls, url): | |
739 | return (False | |
9634de17 S |
740 | if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url) |
741 | else super(PornHubPagedVideoListIE, cls).suitable(url)) | |
21b08463 | 742 | |
34541395 | 743 | |
21b08463 | 744 | class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): |
ed807c18 | 745 | _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE |
21b08463 S |
746 | _TESTS = [{ |
747 | 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', | |
748 | 'info_dict': { | |
749 | 'id': 'jenny-blighe', | |
750 | }, | |
751 | 'playlist_mincount': 129, | |
752 | }, { | |
753 | 'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload', | |
754 | 'only_matching': True, | |
ed807c18 | 755 | }, { |
4c968755 | 756 | 'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/pornstar/jenny-blighe/videos/upload', |
ed807c18 | 757 | 'only_matching': True, |
21b08463 | 758 | }] |
df2a5633 | 759 | |
760 | ||
761 | class PornHubPlaylistIE(PornHubPlaylistBaseIE): | |
762 | _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE | |
763 | _TESTS = [{ | |
764 | 'url': 'https://www.pornhub.com/playlist/44121572', | |
765 | 'info_dict': { | |
766 | 'id': '44121572', | |
767 | }, | |
768 | 'playlist_count': 77, | |
769 | }, { | |
770 | 'url': 'https://www.pornhub.com/playlist/4667351', | |
771 | 'only_matching': True, | |
772 | }, { | |
773 | 'url': 'https://de.pornhub.com/playlist/4667351', | |
774 | 'only_matching': True, | |
775 | }, { | |
776 | 'url': 'https://de.pornhub.com/playlist/4667351?page=2', | |
777 | 'only_matching': True, | |
778 | }] | |
779 | ||
780 | def _entries(self, url, host, item_id): | |
781 | webpage = self._download_webpage(url, item_id, 'Downloading page 1') | |
782 | playlist_id = self._search_regex(r'var\s+playlistId\s*=\s*"([^"]+)"', webpage, 'playlist_id') | |
783 | video_count = int_or_none( | |
784 | self._search_regex(r'var\s+itemsCount\s*=\s*([0-9]+)\s*\|\|', webpage, 'video_count')) | |
785 | token = self._search_regex(r'var\s+token\s*=\s*"([^"]+)"', webpage, 'token') | |
786 | page_count = math.ceil((video_count - 36) / 40.) + 1 | |
787 | page_entries = self._extract_entries(webpage, host) | |
788 | ||
789 | def download_page(page_num): | |
790 | note = 'Downloading page {}'.format(page_num) | |
791 | page_url = 'https://www.{}/playlist/viewChunked'.format(host) | |
792 | return self._download_webpage(page_url, item_id, note, query={ | |
793 | 'id': playlist_id, | |
794 | 'page': page_num, | |
795 | 'token': token, | |
796 | }) | |
797 | ||
798 | for page_num in range(1, page_count + 1): | |
799 | if page_num > 1: | |
800 | webpage = download_page(page_num) | |
801 | page_entries = self._extract_entries(webpage, host) | |
802 | if not page_entries: | |
803 | break | |
804 | for e in page_entries: | |
805 | yield e | |
806 | ||
807 | def _real_extract(self, url): | |
5ad28e7f | 808 | mobj = self._match_valid_url(url) |
df2a5633 | 809 | host = mobj.group('host') |
810 | item_id = mobj.group('id') | |
811 | ||
812 | self._login(host) | |
813 | ||
814 | return self.playlist_result(self._entries(mobj.group('url'), host, item_id), item_id) |