]>
Commit | Line | Data |
---|---|---|
1 | import functools | |
2 | import itertools | |
3 | import math | |
4 | import operator | |
5 | import re | |
6 | import urllib.request | |
7 | ||
8 | from .common import InfoExtractor | |
9 | from .openload import PhantomJSwrapper | |
10 | from ..compat import compat_HTTPError, compat_str | |
11 | from ..utils import ( | |
12 | NO_DEFAULT, | |
13 | ExtractorError, | |
14 | clean_html, | |
15 | determine_ext, | |
16 | format_field, | |
17 | int_or_none, | |
18 | merge_dicts, | |
19 | orderedSet, | |
20 | remove_quotes, | |
21 | remove_start, | |
22 | str_to_int, | |
23 | update_url_query, | |
24 | url_or_none, | |
25 | urlencode_postdata, | |
26 | ) | |
27 | ||
28 | ||
29 | class PornHubBaseIE(InfoExtractor): | |
30 | _NETRC_MACHINE = 'pornhub' | |
31 | _PORNHUB_HOST_RE = r'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd\.onion)' | |
32 | ||
33 | def _download_webpage_handle(self, *args, **kwargs): | |
34 | def dl(*args, **kwargs): | |
35 | return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs) | |
36 | ||
37 | ret = dl(*args, **kwargs) | |
38 | ||
39 | if not ret: | |
40 | return ret | |
41 | ||
42 | webpage, urlh = ret | |
43 | ||
44 | if any(re.search(p, webpage) for p in ( | |
45 | r'<body\b[^>]+\bonload=["\']go\(\)', | |
46 | r'document\.cookie\s*=\s*["\']RNKEY=', | |
47 | r'document\.location\.reload\(true\)')): | |
48 | url_or_request = args[0] | |
49 | url = (url_or_request.get_full_url() | |
50 | if isinstance(url_or_request, urllib.request.Request) | |
51 | else url_or_request) | |
52 | phantom = PhantomJSwrapper(self, required_version='2.0') | |
53 | phantom.get(url, html=webpage) | |
54 | webpage, urlh = dl(*args, **kwargs) | |
55 | ||
56 | return webpage, urlh | |
57 | ||
58 | def _real_initialize(self): | |
59 | self._logged_in = False | |
60 | ||
61 | def _login(self, host): | |
62 | if self._logged_in: | |
63 | return | |
64 | ||
65 | site = host.split('.')[0] | |
66 | ||
67 | # Both sites pornhub and pornhubpremium have separate accounts | |
68 | # so there should be an option to provide credentials for both. | |
69 | # At the same time some videos are available under the same video id | |
70 | # on both sites so that we have to identify them as the same video. | |
71 | # For that purpose we have to keep both in the same extractor | |
72 | # but under different netrc machines. | |
73 | username, password = self._get_login_info(netrc_machine=site) | |
74 | if username is None: | |
75 | return | |
76 | ||
77 | login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '') | |
78 | login_page = self._download_webpage( | |
79 | login_url, None, 'Downloading %s login page' % site) | |
80 | ||
81 | def is_logged(webpage): | |
82 | return any(re.search(p, webpage) for p in ( | |
83 | r'class=["\']signOut', | |
84 | r'>Sign\s+[Oo]ut\s*<')) | |
85 | ||
86 | if is_logged(login_page): | |
87 | self._logged_in = True | |
88 | return | |
89 | ||
90 | login_form = self._hidden_inputs(login_page) | |
91 | ||
92 | login_form.update({ | |
93 | 'username': username, | |
94 | 'password': password, | |
95 | }) | |
96 | ||
97 | response = self._download_json( | |
98 | 'https://www.%s/front/authenticate' % host, None, | |
99 | 'Logging in to %s' % site, | |
100 | data=urlencode_postdata(login_form), | |
101 | headers={ | |
102 | 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', | |
103 | 'Referer': login_url, | |
104 | 'X-Requested-With': 'XMLHttpRequest', | |
105 | }) | |
106 | ||
107 | if response.get('success') == '1': | |
108 | self._logged_in = True | |
109 | return | |
110 | ||
111 | message = response.get('message') | |
112 | if message is not None: | |
113 | raise ExtractorError( | |
114 | 'Unable to login: %s' % message, expected=True) | |
115 | ||
116 | raise ExtractorError('Unable to log in') | |
117 | ||
118 | ||
119 | class PornHubIE(PornHubBaseIE): | |
120 | IE_DESC = 'PornHub and Thumbzilla' | |
121 | _VALID_URL = r'''(?x) | |
122 | https?:// | |
123 | (?: | |
124 | (?:[^/]+\.)? | |
125 | %s | |
126 | /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| | |
127 | (?:www\.)?thumbzilla\.com/video/ | |
128 | ) | |
129 | (?P<id>[\da-z]+) | |
130 | ''' % PornHubBaseIE._PORNHUB_HOST_RE | |
131 | _TESTS = [{ | |
132 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', | |
133 | 'md5': 'a6391306d050e4547f62b3f485dd9ba9', | |
134 | 'info_dict': { | |
135 | 'id': '648719015', | |
136 | 'ext': 'mp4', | |
137 | 'title': 'Seductive Indian beauty strips down and fingers her pink pussy', | |
138 | 'uploader': 'Babes', | |
139 | 'upload_date': '20130628', | |
140 | 'timestamp': 1372447216, | |
141 | 'duration': 361, | |
142 | 'view_count': int, | |
143 | 'like_count': int, | |
144 | 'dislike_count': int, | |
145 | 'comment_count': int, | |
146 | 'age_limit': 18, | |
147 | 'tags': list, | |
148 | 'categories': list, | |
149 | 'cast': list, | |
150 | }, | |
151 | }, { | |
152 | # non-ASCII title | |
153 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002', | |
154 | 'info_dict': { | |
155 | 'id': '1331683002', | |
156 | 'ext': 'mp4', | |
157 | 'title': '重庆婷婷女王足交', | |
158 | 'upload_date': '20150213', | |
159 | 'timestamp': 1423804862, | |
160 | 'duration': 1753, | |
161 | 'view_count': int, | |
162 | 'like_count': int, | |
163 | 'dislike_count': int, | |
164 | 'comment_count': int, | |
165 | 'age_limit': 18, | |
166 | 'tags': list, | |
167 | 'categories': list, | |
168 | }, | |
169 | 'params': { | |
170 | 'skip_download': True, | |
171 | }, | |
172 | 'skip': 'Video has been flagged for verification in accordance with our trust and safety policy', | |
173 | }, { | |
174 | # subtitles | |
175 | 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7', | |
176 | 'info_dict': { | |
177 | 'id': 'ph5af5fef7c2aa7', | |
178 | 'ext': 'mp4', | |
179 | 'title': 'BFFS - Cute Teen Girls Share Cock On the Floor', | |
180 | 'uploader': 'BFFs', | |
181 | 'duration': 622, | |
182 | 'view_count': int, | |
183 | 'like_count': int, | |
184 | 'dislike_count': int, | |
185 | 'comment_count': int, | |
186 | 'age_limit': 18, | |
187 | 'tags': list, | |
188 | 'categories': list, | |
189 | 'subtitles': { | |
190 | 'en': [{ | |
191 | "ext": 'srt' | |
192 | }] | |
193 | }, | |
194 | }, | |
195 | 'params': { | |
196 | 'skip_download': True, | |
197 | }, | |
198 | 'skip': 'This video has been disabled', | |
199 | }, { | |
200 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph601dc30bae19a', | |
201 | 'info_dict': { | |
202 | 'id': 'ph601dc30bae19a', | |
203 | 'uploader': 'Projekt Melody', | |
204 | 'uploader_id': 'projekt-melody', | |
205 | 'upload_date': '20210205', | |
206 | 'title': '"Welcome to My Pussy Mansion" - CB Stream (02/03/21)', | |
207 | 'thumbnail': r're:https?://.+', | |
208 | }, | |
209 | }, { | |
210 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', | |
211 | 'only_matching': True, | |
212 | }, { | |
213 | # removed at the request of cam4.com | |
214 | 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862', | |
215 | 'only_matching': True, | |
216 | }, { | |
217 | # removed at the request of the copyright owner | |
218 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859', | |
219 | 'only_matching': True, | |
220 | }, { | |
221 | # removed by uploader | |
222 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111', | |
223 | 'only_matching': True, | |
224 | }, { | |
225 | # private video | |
226 | 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7', | |
227 | 'only_matching': True, | |
228 | }, { | |
229 | 'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex', | |
230 | 'only_matching': True, | |
231 | }, { | |
232 | 'url': 'http://www.pornhub.com/video/show?viewkey=648719015', | |
233 | 'only_matching': True, | |
234 | }, { | |
235 | 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', | |
236 | 'only_matching': True, | |
237 | }, { | |
238 | 'url': 'https://www.pornhub.org/view_video.php?viewkey=203640933', | |
239 | 'only_matching': True, | |
240 | }, { | |
241 | 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82', | |
242 | 'only_matching': True, | |
243 | }, { | |
244 | # Some videos are available with the same id on both premium | |
245 | # and non-premium sites (e.g. this and the following test) | |
246 | 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5f75b0f4b18e3', | |
247 | 'only_matching': True, | |
248 | }, { | |
249 | 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3', | |
250 | 'only_matching': True, | |
251 | }, { | |
252 | # geo restricted | |
253 | 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5a9813bfa7156', | |
254 | 'only_matching': True, | |
255 | }, { | |
256 | 'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/view_video.php?viewkey=ph5a9813bfa7156', | |
257 | 'only_matching': True, | |
258 | }] | |
259 | ||
260 | @staticmethod | |
261 | def _extract_urls(webpage): | |
262 | return re.findall( | |
263 | r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)', | |
264 | webpage) | |
265 | ||
266 | def _extract_count(self, pattern, webpage, name): | |
267 | return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None)) | |
268 | ||
269 | def _real_extract(self, url): | |
270 | mobj = self._match_valid_url(url) | |
271 | host = mobj.group('host') or 'pornhub.com' | |
272 | video_id = mobj.group('id') | |
273 | ||
274 | self._login(host) | |
275 | ||
276 | self._set_cookie(host, 'age_verified', '1') | |
277 | ||
278 | def dl_webpage(platform): | |
279 | self._set_cookie(host, 'platform', platform) | |
280 | return self._download_webpage( | |
281 | 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id), | |
282 | video_id, 'Downloading %s webpage' % platform) | |
283 | ||
284 | webpage = dl_webpage('pc') | |
285 | ||
286 | error_msg = self._html_search_regex( | |
287 | (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>', | |
288 | r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'), | |
289 | webpage, 'error message', default=None, group='error') | |
290 | if error_msg: | |
291 | error_msg = re.sub(r'\s+', ' ', error_msg) | |
292 | raise ExtractorError( | |
293 | 'PornHub said: %s' % error_msg, | |
294 | expected=True, video_id=video_id) | |
295 | ||
296 | if any(re.search(p, webpage) for p in ( | |
297 | r'class=["\']geoBlocked["\']', | |
298 | r'>\s*This content is unavailable in your country')): | |
299 | self.raise_geo_restricted() | |
300 | ||
301 | # video_title from flashvars contains whitespace instead of non-ASCII (see | |
302 | # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying | |
303 | # on that anymore. | |
304 | title = self._html_search_meta( | |
305 | 'twitter:title', webpage, default=None) or self._html_search_regex( | |
306 | (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>', | |
307 | r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1', | |
308 | r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'), | |
309 | webpage, 'title', group='title') | |
310 | ||
311 | video_urls = [] | |
312 | video_urls_set = set() | |
313 | subtitles = {} | |
314 | ||
315 | flashvars = self._parse_json( | |
316 | self._search_regex( | |
317 | r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), | |
318 | video_id) | |
319 | if flashvars: | |
320 | subtitle_url = url_or_none(flashvars.get('closedCaptionsFile')) | |
321 | if subtitle_url: | |
322 | subtitles.setdefault('en', []).append({ | |
323 | 'url': subtitle_url, | |
324 | 'ext': 'srt', | |
325 | }) | |
326 | thumbnail = flashvars.get('image_url') | |
327 | duration = int_or_none(flashvars.get('video_duration')) | |
328 | media_definitions = flashvars.get('mediaDefinitions') | |
329 | if isinstance(media_definitions, list): | |
330 | for definition in media_definitions: | |
331 | if not isinstance(definition, dict): | |
332 | continue | |
333 | video_url = definition.get('videoUrl') | |
334 | if not video_url or not isinstance(video_url, compat_str): | |
335 | continue | |
336 | if video_url in video_urls_set: | |
337 | continue | |
338 | video_urls_set.add(video_url) | |
339 | video_urls.append( | |
340 | (video_url, int_or_none(definition.get('quality')))) | |
341 | else: | |
342 | thumbnail, duration = [None] * 2 | |
343 | ||
344 | def extract_js_vars(webpage, pattern, default=NO_DEFAULT): | |
345 | assignments = self._search_regex( | |
346 | pattern, webpage, 'encoded url', default=default) | |
347 | if not assignments: | |
348 | return {} | |
349 | ||
350 | assignments = assignments.split(';') | |
351 | ||
352 | js_vars = {} | |
353 | ||
354 | def parse_js_value(inp): | |
355 | inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp) | |
356 | if '+' in inp: | |
357 | inps = inp.split('+') | |
358 | return functools.reduce( | |
359 | operator.concat, map(parse_js_value, inps)) | |
360 | inp = inp.strip() | |
361 | if inp in js_vars: | |
362 | return js_vars[inp] | |
363 | return remove_quotes(inp) | |
364 | ||
365 | for assn in assignments: | |
366 | assn = assn.strip() | |
367 | if not assn: | |
368 | continue | |
369 | assn = re.sub(r'var\s+', '', assn) | |
370 | vname, value = assn.split('=', 1) | |
371 | js_vars[vname] = parse_js_value(value) | |
372 | return js_vars | |
373 | ||
374 | def add_video_url(video_url): | |
375 | v_url = url_or_none(video_url) | |
376 | if not v_url: | |
377 | return | |
378 | if v_url in video_urls_set: | |
379 | return | |
380 | video_urls.append((v_url, None)) | |
381 | video_urls_set.add(v_url) | |
382 | ||
383 | def parse_quality_items(quality_items): | |
384 | q_items = self._parse_json(quality_items, video_id, fatal=False) | |
385 | if not isinstance(q_items, list): | |
386 | return | |
387 | for item in q_items: | |
388 | if isinstance(item, dict): | |
389 | add_video_url(item.get('url')) | |
390 | ||
391 | if not video_urls: | |
392 | FORMAT_PREFIXES = ('media', 'quality', 'qualityItems') | |
393 | js_vars = extract_js_vars( | |
394 | webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES), | |
395 | default=None) | |
396 | if js_vars: | |
397 | for key, format_url in js_vars.items(): | |
398 | if key.startswith(FORMAT_PREFIXES[-1]): | |
399 | parse_quality_items(format_url) | |
400 | elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]): | |
401 | add_video_url(format_url) | |
402 | if not video_urls and re.search( | |
403 | r'<[^>]+\bid=["\']lockedPlayer', webpage): | |
404 | raise ExtractorError( | |
405 | 'Video %s is locked' % video_id, expected=True) | |
406 | ||
407 | if not video_urls: | |
408 | js_vars = extract_js_vars( | |
409 | dl_webpage('tv'), r'(var.+?mediastring.+?)</script>') | |
410 | add_video_url(js_vars['mediastring']) | |
411 | ||
412 | for mobj in re.finditer( | |
413 | r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1', | |
414 | webpage): | |
415 | video_url = mobj.group('url') | |
416 | if video_url not in video_urls_set: | |
417 | video_urls.append((video_url, None)) | |
418 | video_urls_set.add(video_url) | |
419 | ||
420 | upload_date = None | |
421 | formats = [] | |
422 | ||
423 | def add_format(format_url, height=None): | |
424 | ext = determine_ext(format_url) | |
425 | if ext == 'mpd': | |
426 | formats.extend(self._extract_mpd_formats( | |
427 | format_url, video_id, mpd_id='dash', fatal=False)) | |
428 | return | |
429 | if ext == 'm3u8': | |
430 | formats.extend(self._extract_m3u8_formats( | |
431 | format_url, video_id, 'mp4', entry_protocol='m3u8_native', | |
432 | m3u8_id='hls', fatal=False)) | |
433 | return | |
434 | if not height: | |
435 | height = int_or_none(self._search_regex( | |
436 | r'(?P<height>\d+)[pP]?_\d+[kK]', format_url, 'height', | |
437 | default=None)) | |
438 | formats.append({ | |
439 | 'url': format_url, | |
440 | 'format_id': format_field(height, None, '%dp'), | |
441 | 'height': height, | |
442 | }) | |
443 | ||
444 | for video_url, height in video_urls: | |
445 | if not upload_date: | |
446 | upload_date = self._search_regex( | |
447 | r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None) | |
448 | if upload_date: | |
449 | upload_date = upload_date.replace('/', '') | |
450 | if '/video/get_media' in video_url: | |
451 | medias = self._download_json(video_url, video_id, fatal=False) | |
452 | if isinstance(medias, list): | |
453 | for media in medias: | |
454 | if not isinstance(media, dict): | |
455 | continue | |
456 | video_url = url_or_none(media.get('videoUrl')) | |
457 | if not video_url: | |
458 | continue | |
459 | height = int_or_none(media.get('quality')) | |
460 | add_format(video_url, height) | |
461 | continue | |
462 | add_format(video_url) | |
463 | ||
464 | # field_preference is unnecessary here, but kept for code-similarity with youtube-dl | |
465 | self._sort_formats( | |
466 | formats, field_preference=('height', 'width', 'fps', 'format_id')) | |
467 | ||
468 | model_profile = self._search_json( | |
469 | r'var\s+MODEL_PROFILE\s*=', webpage, 'model profile', video_id, fatal=False) | |
470 | video_uploader = self._html_search_regex( | |
471 | r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', | |
472 | webpage, 'uploader', default=None) or model_profile.get('username') | |
473 | ||
474 | def extract_vote_count(kind, name): | |
475 | return self._extract_count( | |
476 | (r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind, | |
477 | r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind), | |
478 | webpage, name) | |
479 | ||
480 | view_count = self._extract_count( | |
481 | r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view') | |
482 | like_count = extract_vote_count('Up', 'like') | |
483 | dislike_count = extract_vote_count('Down', 'dislike') | |
484 | comment_count = self._extract_count( | |
485 | r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') | |
486 | ||
487 | def extract_list(meta_key): | |
488 | div = self._search_regex( | |
489 | r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>' | |
490 | % meta_key, webpage, meta_key, default=None) | |
491 | if div: | |
492 | return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)] | |
493 | ||
494 | info = self._search_json_ld(webpage, video_id, default={}) | |
495 | # description provided in JSON-LD is irrelevant | |
496 | info['description'] = None | |
497 | ||
498 | return merge_dicts({ | |
499 | 'id': video_id, | |
500 | 'uploader': video_uploader, | |
501 | 'uploader_id': remove_start(model_profile.get('modelProfileLink'), '/model/'), | |
502 | 'upload_date': upload_date, | |
503 | 'title': title, | |
504 | 'thumbnail': thumbnail, | |
505 | 'duration': duration, | |
506 | 'view_count': view_count, | |
507 | 'like_count': like_count, | |
508 | 'dislike_count': dislike_count, | |
509 | 'comment_count': comment_count, | |
510 | 'formats': formats, | |
511 | 'age_limit': 18, | |
512 | 'tags': extract_list('tags'), | |
513 | 'categories': extract_list('categories'), | |
514 | 'cast': extract_list('pornstars'), | |
515 | 'subtitles': subtitles, | |
516 | }, info) | |
517 | ||
518 | ||
519 | class PornHubPlaylistBaseIE(PornHubBaseIE): | |
520 | def _extract_page(self, url): | |
521 | return int_or_none(self._search_regex( | |
522 | r'\bpage=(\d+)', url, 'page', default=None)) | |
523 | ||
524 | def _extract_entries(self, webpage, host): | |
525 | # Only process container div with main playlist content skipping | |
526 | # drop-down menu that uses similar pattern for videos (see | |
527 | # https://github.com/ytdl-org/youtube-dl/issues/11594). | |
528 | container = self._search_regex( | |
529 | r'(?s)(<div[^>]+class=["\']container.+)', webpage, | |
530 | 'container', default=webpage) | |
531 | ||
532 | return [ | |
533 | self.url_result( | |
534 | 'http://www.%s/%s' % (host, video_url), | |
535 | PornHubIE.ie_key(), video_title=title) | |
536 | for video_url, title in orderedSet(re.findall( | |
537 | r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"', | |
538 | container)) | |
539 | ] | |
540 | ||
541 | ||
542 | class PornHubUserIE(PornHubPlaylistBaseIE): | |
543 | _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE | |
544 | _TESTS = [{ | |
545 | 'url': 'https://www.pornhub.com/model/zoe_ph', | |
546 | 'playlist_mincount': 118, | |
547 | }, { | |
548 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious', | |
549 | 'info_dict': { | |
550 | 'id': 'liz-vicious', | |
551 | }, | |
552 | 'playlist_mincount': 118, | |
553 | }, { | |
554 | 'url': 'https://www.pornhub.com/users/russianveet69', | |
555 | 'only_matching': True, | |
556 | }, { | |
557 | 'url': 'https://www.pornhub.com/channels/povd', | |
558 | 'only_matching': True, | |
559 | }, { | |
560 | 'url': 'https://www.pornhub.com/model/zoe_ph?abc=1', | |
561 | 'only_matching': True, | |
562 | }, { | |
563 | # Unavailable via /videos page, but available with direct pagination | |
564 | # on pornstar page (see [1]), requires premium | |
565 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27853 | |
566 | 'url': 'https://www.pornhubpremium.com/pornstar/sienna-west', | |
567 | 'only_matching': True, | |
568 | }, { | |
569 | # Same as before, multi page | |
570 | 'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau', | |
571 | 'only_matching': True, | |
572 | }, { | |
573 | 'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph', | |
574 | 'only_matching': True, | |
575 | }] | |
576 | ||
577 | def _real_extract(self, url): | |
578 | mobj = self._match_valid_url(url) | |
579 | user_id = mobj.group('id') | |
580 | videos_url = '%s/videos' % mobj.group('url') | |
581 | page = self._extract_page(url) | |
582 | if page: | |
583 | videos_url = update_url_query(videos_url, {'page': page}) | |
584 | return self.url_result( | |
585 | videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id) | |
586 | ||
587 | ||
588 | class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): | |
589 | @staticmethod | |
590 | def _has_more(webpage): | |
591 | return re.search( | |
592 | r'''(?x) | |
593 | <li[^>]+\bclass=["\']page_next| | |
594 | <link[^>]+\brel=["\']next| | |
595 | <button[^>]+\bid=["\']moreDataBtn | |
596 | ''', webpage) is not None | |
597 | ||
598 | def _entries(self, url, host, item_id): | |
599 | page = self._extract_page(url) | |
600 | ||
601 | VIDEOS = '/videos' | |
602 | ||
603 | def download_page(base_url, num, fallback=False): | |
604 | note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '') | |
605 | return self._download_webpage( | |
606 | base_url, item_id, note, query={'page': num}) | |
607 | ||
608 | def is_404(e): | |
609 | return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404 | |
610 | ||
611 | base_url = url | |
612 | has_page = page is not None | |
613 | first_page = page if has_page else 1 | |
614 | for page_num in (first_page, ) if has_page else itertools.count(first_page): | |
615 | try: | |
616 | try: | |
617 | webpage = download_page(base_url, page_num) | |
618 | except ExtractorError as e: | |
619 | # Some sources may not be available via /videos page, | |
620 | # trying to fallback to main page pagination (see [1]) | |
621 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27853 | |
622 | if is_404(e) and page_num == first_page and VIDEOS in base_url: | |
623 | base_url = base_url.replace(VIDEOS, '') | |
624 | webpage = download_page(base_url, page_num, fallback=True) | |
625 | else: | |
626 | raise | |
627 | except ExtractorError as e: | |
628 | if is_404(e) and page_num != first_page: | |
629 | break | |
630 | raise | |
631 | page_entries = self._extract_entries(webpage, host) | |
632 | if not page_entries: | |
633 | break | |
634 | for e in page_entries: | |
635 | yield e | |
636 | if not self._has_more(webpage): | |
637 | break | |
638 | ||
639 | def _real_extract(self, url): | |
640 | mobj = self._match_valid_url(url) | |
641 | host = mobj.group('host') | |
642 | item_id = mobj.group('id') | |
643 | ||
644 | self._login(host) | |
645 | ||
646 | return self.playlist_result(self._entries(url, host, item_id), item_id) | |
647 | ||
648 | ||
649 | class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): | |
650 | _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE | |
651 | _TESTS = [{ | |
652 | 'url': 'https://www.pornhub.com/model/zoe_ph/videos', | |
653 | 'only_matching': True, | |
654 | }, { | |
655 | 'url': 'http://www.pornhub.com/users/rushandlia/videos', | |
656 | 'only_matching': True, | |
657 | }, { | |
658 | 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos', | |
659 | 'info_dict': { | |
660 | 'id': 'pornstar/jenny-blighe/videos', | |
661 | }, | |
662 | 'playlist_mincount': 149, | |
663 | }, { | |
664 | 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3', | |
665 | 'info_dict': { | |
666 | 'id': 'pornstar/jenny-blighe/videos', | |
667 | }, | |
668 | 'playlist_mincount': 40, | |
669 | }, { | |
670 | # default sorting as Top Rated Videos | |
671 | 'url': 'https://www.pornhub.com/channels/povd/videos', | |
672 | 'info_dict': { | |
673 | 'id': 'channels/povd/videos', | |
674 | }, | |
675 | 'playlist_mincount': 293, | |
676 | }, { | |
677 | # Top Rated Videos | |
678 | 'url': 'https://www.pornhub.com/channels/povd/videos?o=ra', | |
679 | 'only_matching': True, | |
680 | }, { | |
681 | # Most Recent Videos | |
682 | 'url': 'https://www.pornhub.com/channels/povd/videos?o=da', | |
683 | 'only_matching': True, | |
684 | }, { | |
685 | # Most Viewed Videos | |
686 | 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi', | |
687 | 'only_matching': True, | |
688 | }, { | |
689 | 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', | |
690 | 'only_matching': True, | |
691 | }, { | |
692 | # Most Viewed Videos | |
693 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv', | |
694 | 'only_matching': True, | |
695 | }, { | |
696 | # Top Rated Videos | |
697 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr', | |
698 | 'only_matching': True, | |
699 | }, { | |
700 | # Longest Videos | |
701 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg', | |
702 | 'only_matching': True, | |
703 | }, { | |
704 | # Newest Videos | |
705 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm', | |
706 | 'only_matching': True, | |
707 | }, { | |
708 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid', | |
709 | 'only_matching': True, | |
710 | }, { | |
711 | 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly', | |
712 | 'only_matching': True, | |
713 | }, { | |
714 | 'url': 'https://www.pornhub.com/video', | |
715 | 'only_matching': True, | |
716 | }, { | |
717 | 'url': 'https://www.pornhub.com/video?page=3', | |
718 | 'only_matching': True, | |
719 | }, { | |
720 | 'url': 'https://www.pornhub.com/video/search?search=123', | |
721 | 'only_matching': True, | |
722 | }, { | |
723 | 'url': 'https://www.pornhub.com/categories/teen', | |
724 | 'only_matching': True, | |
725 | }, { | |
726 | 'url': 'https://www.pornhub.com/categories/teen?page=3', | |
727 | 'only_matching': True, | |
728 | }, { | |
729 | 'url': 'https://www.pornhub.com/hd', | |
730 | 'only_matching': True, | |
731 | }, { | |
732 | 'url': 'https://www.pornhub.com/hd?page=3', | |
733 | 'only_matching': True, | |
734 | }, { | |
735 | 'url': 'https://www.pornhub.com/described-video', | |
736 | 'only_matching': True, | |
737 | }, { | |
738 | 'url': 'https://www.pornhub.com/described-video?page=2', | |
739 | 'only_matching': True, | |
740 | }, { | |
741 | 'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn', | |
742 | 'only_matching': True, | |
743 | }, { | |
744 | 'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph/videos', | |
745 | 'only_matching': True, | |
746 | }] | |
747 | ||
748 | @classmethod | |
749 | def suitable(cls, url): | |
750 | return (False | |
751 | if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url) | |
752 | else super(PornHubPagedVideoListIE, cls).suitable(url)) | |
753 | ||
754 | ||
755 | class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): | |
756 | _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE | |
757 | _TESTS = [{ | |
758 | 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', | |
759 | 'info_dict': { | |
760 | 'id': 'jenny-blighe', | |
761 | }, | |
762 | 'playlist_mincount': 129, | |
763 | }, { | |
764 | 'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload', | |
765 | 'only_matching': True, | |
766 | }, { | |
767 | 'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/pornstar/jenny-blighe/videos/upload', | |
768 | 'only_matching': True, | |
769 | }] | |
770 | ||
771 | ||
772 | class PornHubPlaylistIE(PornHubPlaylistBaseIE): | |
773 | _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE | |
774 | _TESTS = [{ | |
775 | 'url': 'https://www.pornhub.com/playlist/44121572', | |
776 | 'info_dict': { | |
777 | 'id': '44121572', | |
778 | }, | |
779 | 'playlist_count': 77, | |
780 | }, { | |
781 | 'url': 'https://www.pornhub.com/playlist/4667351', | |
782 | 'only_matching': True, | |
783 | }, { | |
784 | 'url': 'https://de.pornhub.com/playlist/4667351', | |
785 | 'only_matching': True, | |
786 | }, { | |
787 | 'url': 'https://de.pornhub.com/playlist/4667351?page=2', | |
788 | 'only_matching': True, | |
789 | }] | |
790 | ||
791 | def _entries(self, url, host, item_id): | |
792 | webpage = self._download_webpage(url, item_id, 'Downloading page 1') | |
793 | playlist_id = self._search_regex(r'var\s+playlistId\s*=\s*"([^"]+)"', webpage, 'playlist_id') | |
794 | video_count = int_or_none( | |
795 | self._search_regex(r'var\s+itemsCount\s*=\s*([0-9]+)\s*\|\|', webpage, 'video_count')) | |
796 | token = self._search_regex(r'var\s+token\s*=\s*"([^"]+)"', webpage, 'token') | |
797 | page_count = math.ceil((video_count - 36) / 40.) + 1 | |
798 | page_entries = self._extract_entries(webpage, host) | |
799 | ||
800 | def download_page(page_num): | |
801 | note = 'Downloading page {}'.format(page_num) | |
802 | page_url = 'https://www.{}/playlist/viewChunked'.format(host) | |
803 | return self._download_webpage(page_url, item_id, note, query={ | |
804 | 'id': playlist_id, | |
805 | 'page': page_num, | |
806 | 'token': token, | |
807 | }) | |
808 | ||
809 | for page_num in range(1, page_count + 1): | |
810 | if page_num > 1: | |
811 | webpage = download_page(page_num) | |
812 | page_entries = self._extract_entries(webpage, host) | |
813 | if not page_entries: | |
814 | break | |
815 | for e in page_entries: | |
816 | yield e | |
817 | ||
818 | def _real_extract(self, url): | |
819 | mobj = self._match_valid_url(url) | |
820 | host = mobj.group('host') | |
821 | item_id = mobj.group('id') | |
822 | ||
823 | self._login(host) | |
824 | ||
825 | return self.playlist_result(self._entries(mobj.group('url'), host, item_id), item_id) |