]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xhamster.py
Update README.md
[youtubedl] / youtube_dl / extractor / xhamster.py
1 from __future__ import unicode_literals
2
3 import itertools
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_str
8 from ..utils import (
9 clean_html,
10 determine_ext,
11 dict_get,
12 extract_attributes,
13 ExtractorError,
14 int_or_none,
15 parse_duration,
16 try_get,
17 unified_strdate,
18 url_or_none,
19 )
20
21
22 class XHamsterIE(InfoExtractor):
23 _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)'
24 _VALID_URL = r'''(?x)
25 https?://
26 (?:.+?\.)?%s/
27 (?:
28 movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
29 videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
30 )
31 ''' % _DOMAINS
32 _TESTS = [{
33 'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
34 'md5': '98b4687efb1ffd331c4197854dc09e8f',
35 'info_dict': {
36 'id': '1509445',
37 'display_id': 'femaleagent-shy-beauty-takes-the-bait',
38 'ext': 'mp4',
39 'title': 'FemaleAgent Shy beauty takes the bait',
40 'timestamp': 1350194821,
41 'upload_date': '20121014',
42 'uploader': 'Ruseful2011',
43 'duration': 893,
44 'age_limit': 18,
45 },
46 }, {
47 'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
48 'info_dict': {
49 'id': '2221348',
50 'display_id': 'britney-spears-sexy-booty',
51 'ext': 'mp4',
52 'title': 'Britney Spears Sexy Booty',
53 'timestamp': 1379123460,
54 'upload_date': '20130914',
55 'uploader': 'jojo747400',
56 'duration': 200,
57 'age_limit': 18,
58 },
59 'params': {
60 'skip_download': True,
61 },
62 }, {
63 # empty seo, unavailable via new URL schema
64 'url': 'http://xhamster.com/movies/5667973/.html',
65 'info_dict': {
66 'id': '5667973',
67 'ext': 'mp4',
68 'title': '....',
69 'timestamp': 1454948101,
70 'upload_date': '20160208',
71 'uploader': 'parejafree',
72 'duration': 72,
73 'age_limit': 18,
74 },
75 'params': {
76 'skip_download': True,
77 },
78 }, {
79 # mobile site
80 'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
81 'only_matching': True,
82 }, {
83 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
84 'only_matching': True,
85 }, {
86 # This video is visible for marcoalfa123456's friends only
87 'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
88 'only_matching': True,
89 }, {
90 # new URL schema
91 'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
92 'only_matching': True,
93 }, {
94 'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
95 'only_matching': True,
96 }, {
97 'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
98 'only_matching': True,
99 }, {
100 'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
101 'only_matching': True,
102 }, {
103 'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
104 'only_matching': True,
105 }, {
106 'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
107 'only_matching': True,
108 }, {
109 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
110 'only_matching': True,
111 }, {
112 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
113 'only_matching': True,
114 }, {
115 'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
116 'only_matching': True,
117 }]
118
119 def _real_extract(self, url):
120 mobj = re.match(self._VALID_URL, url)
121 video_id = mobj.group('id') or mobj.group('id_2')
122 display_id = mobj.group('display_id') or mobj.group('display_id_2')
123
124 desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
125 webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
126
127 error = self._html_search_regex(
128 r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
129 webpage, 'error', default=None)
130 if error:
131 raise ExtractorError(error, expected=True)
132
133 age_limit = self._rta_search(webpage)
134
135 def get_height(s):
136 return int_or_none(self._search_regex(
137 r'^(\d+)[pP]', s, 'height', default=None))
138
139 initials = self._parse_json(
140 self._search_regex(
141 (r'window\.initials\s*=\s*({.+?})\s*;\s*</script>',
142 r'window\.initials\s*=\s*({.+?})\s*;'), webpage, 'initials',
143 default='{}'),
144 video_id, fatal=False)
145 if initials:
146 video = initials['videoModel']
147 title = video['title']
148 formats = []
149 for format_id, formats_dict in video['sources'].items():
150 if not isinstance(formats_dict, dict):
151 continue
152 for quality, format_item in formats_dict.items():
153 if format_id == 'download':
154 # Download link takes some time to be generated,
155 # skipping for now
156 continue
157 if not isinstance(format_item, dict):
158 continue
159 format_url = format_item.get('link')
160 filesize = int_or_none(
161 format_item.get('size'), invscale=1000000)
162 else:
163 format_url = format_item
164 filesize = None
165 format_url = url_or_none(format_url)
166 if not format_url:
167 continue
168 formats.append({
169 'format_id': '%s-%s' % (format_id, quality),
170 'url': format_url,
171 'ext': determine_ext(format_url, 'mp4'),
172 'height': get_height(quality),
173 'filesize': filesize,
174 'http_headers': {
175 'Referer': urlh.geturl(),
176 },
177 })
178 self._sort_formats(formats)
179
180 categories_list = video.get('categories')
181 if isinstance(categories_list, list):
182 categories = []
183 for c in categories_list:
184 if not isinstance(c, dict):
185 continue
186 c_name = c.get('name')
187 if isinstance(c_name, compat_str):
188 categories.append(c_name)
189 else:
190 categories = None
191
192 return {
193 'id': video_id,
194 'display_id': display_id,
195 'title': title,
196 'description': video.get('description'),
197 'timestamp': int_or_none(video.get('created')),
198 'uploader': try_get(
199 video, lambda x: x['author']['name'], compat_str),
200 'thumbnail': video.get('thumbURL'),
201 'duration': int_or_none(video.get('duration')),
202 'view_count': int_or_none(video.get('views')),
203 'like_count': int_or_none(try_get(
204 video, lambda x: x['rating']['likes'], int)),
205 'dislike_count': int_or_none(try_get(
206 video, lambda x: x['rating']['dislikes'], int)),
207 'comment_count': int_or_none(video.get('views')),
208 'age_limit': age_limit,
209 'categories': categories,
210 'formats': formats,
211 }
212
213 # Old layout fallback
214
215 title = self._html_search_regex(
216 [r'<h1[^>]*>([^<]+)</h1>',
217 r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
218 r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
219 webpage, 'title')
220
221 formats = []
222 format_urls = set()
223
224 sources = self._parse_json(
225 self._search_regex(
226 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
227 default='{}'),
228 video_id, fatal=False)
229 for format_id, format_url in sources.items():
230 format_url = url_or_none(format_url)
231 if not format_url:
232 continue
233 if format_url in format_urls:
234 continue
235 format_urls.add(format_url)
236 formats.append({
237 'format_id': format_id,
238 'url': format_url,
239 'height': get_height(format_id),
240 })
241
242 video_url = self._search_regex(
243 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
244 r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
245 r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
246 webpage, 'video url', group='mp4', default=None)
247 if video_url and video_url not in format_urls:
248 formats.append({
249 'url': video_url,
250 })
251
252 self._sort_formats(formats)
253
254 # Only a few videos have an description
255 mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
256 description = mobj.group(1) if mobj else None
257
258 upload_date = unified_strdate(self._search_regex(
259 r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
260 webpage, 'upload date', fatal=False))
261
262 uploader = self._html_search_regex(
263 r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
264 webpage, 'uploader', default='anonymous')
265
266 thumbnail = self._search_regex(
267 [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
268 r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
269 webpage, 'thumbnail', fatal=False, group='thumbnail')
270
271 duration = parse_duration(self._search_regex(
272 [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
273 r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
274 'duration', fatal=False))
275
276 view_count = int_or_none(self._search_regex(
277 r'content=["\']User(?:View|Play)s:(\d+)',
278 webpage, 'view count', fatal=False))
279
280 mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
281 (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
282
283 mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
284 comment_count = mobj.group('commentcount') if mobj else 0
285
286 categories_html = self._search_regex(
287 r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
288 'categories', default=None)
289 categories = [clean_html(category) for category in re.findall(
290 r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
291
292 return {
293 'id': video_id,
294 'display_id': display_id,
295 'title': title,
296 'description': description,
297 'upload_date': upload_date,
298 'uploader': uploader,
299 'thumbnail': thumbnail,
300 'duration': duration,
301 'view_count': view_count,
302 'like_count': int_or_none(like_count),
303 'dislike_count': int_or_none(dislike_count),
304 'comment_count': int_or_none(comment_count),
305 'age_limit': age_limit,
306 'categories': categories,
307 'formats': formats,
308 }
309
310
311 class XHamsterEmbedIE(InfoExtractor):
312 _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
313 _TEST = {
314 'url': 'http://xhamster.com/xembed.php?video=3328539',
315 'info_dict': {
316 'id': '3328539',
317 'ext': 'mp4',
318 'title': 'Pen Masturbation',
319 'timestamp': 1406581861,
320 'upload_date': '20140728',
321 'uploader': 'ManyakisArt',
322 'duration': 5,
323 'age_limit': 18,
324 }
325 }
326
327 @staticmethod
328 def _extract_urls(webpage):
329 return [url for _, url in re.findall(
330 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
331 webpage)]
332
333 def _real_extract(self, url):
334 video_id = self._match_id(url)
335
336 webpage = self._download_webpage(url, video_id)
337
338 video_url = self._search_regex(
339 r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
340 webpage, 'xhamster url', default=None)
341
342 if not video_url:
343 vars = self._parse_json(
344 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
345 video_id)
346 video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
347
348 return self.url_result(video_url, 'XHamster')
349
350
351 class XHamsterUserIE(InfoExtractor):
352 _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
353 _TESTS = [{
354 # Paginated user profile
355 'url': 'https://xhamster.com/users/netvideogirls/videos',
356 'info_dict': {
357 'id': 'netvideogirls',
358 },
359 'playlist_mincount': 267,
360 }, {
361 # Non-paginated user profile
362 'url': 'https://xhamster.com/users/firatkaan/videos',
363 'info_dict': {
364 'id': 'firatkaan',
365 },
366 'playlist_mincount': 1,
367 }]
368
369 def _entries(self, user_id):
370 next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
371 for pagenum in itertools.count(1):
372 page = self._download_webpage(
373 next_page_url, user_id, 'Downloading page %s' % pagenum)
374 for video_tag in re.findall(
375 r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
376 page):
377 video = extract_attributes(video_tag)
378 video_url = url_or_none(video.get('href'))
379 if not video_url or not XHamsterIE.suitable(video_url):
380 continue
381 video_id = XHamsterIE._match_id(video_url)
382 yield self.url_result(
383 video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
384 mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
385 if not mobj:
386 break
387 next_page = extract_attributes(mobj.group(0))
388 next_page_url = url_or_none(next_page.get('href'))
389 if not next_page_url:
390 break
391
392 def _real_extract(self, url):
393 user_id = self._match_id(url)
394 return self.playlist_result(self._entries(user_id), user_id)