1 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_str
22 class XHamsterIE(InfoExtractor):
23 _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)'
28 movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
29 videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
33 'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
34 'md5': '98b4687efb1ffd331c4197854dc09e8f',
37 'display_id': 'femaleagent-shy-beauty-takes-the-bait',
39 'title': 'FemaleAgent Shy beauty takes the bait',
40 'timestamp': 1350194821,
41 'upload_date': '20121014',
42 'uploader': 'Ruseful2011',
47 'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
50 'display_id': 'britney-spears-sexy-booty',
52 'title': 'Britney Spears Sexy Booty',
53 'timestamp': 1379123460,
54 'upload_date': '20130914',
55 'uploader': 'jojo747400',
60 'skip_download': True,
63 # empty seo, unavailable via new URL schema
64 'url': 'http://xhamster.com/movies/5667973/.html',
69 'timestamp': 1454948101,
70 'upload_date': '20160208',
71 'uploader': 'parejafree',
76 'skip_download': True,
80 'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
81 'only_matching': True,
83 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
84 'only_matching': True,
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,
91 'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
92 'only_matching': True,
94 'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
95 'only_matching': True,
97 'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
98 'only_matching': True,
100 'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
101 'only_matching': True,
103 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
104 'only_matching': True,
106 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
107 'only_matching': True,
109 'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
110 'only_matching': True,
113 def _real_extract(self, url):
114 mobj = re.match(self._VALID_URL, url)
115 video_id = mobj.group('id') or mobj.group('id_2')
116 display_id = mobj.group('display_id') or mobj.group('display_id_2')
118 desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
119 webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
121 error = self._html_search_regex(
122 r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
123 webpage, 'error', default=None)
125 raise ExtractorError(error, expected=True)
127 age_limit = self._rta_search(webpage)
130 return int_or_none(self._search_regex(
131 r'^(\d+)[pP]', s, 'height', default=None))
133 initials = self._parse_json(
135 r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
137 video_id, fatal=False)
139 video = initials['videoModel']
140 title = video['title']
142 for format_id, formats_dict in video['sources'].items():
143 if not isinstance(formats_dict, dict):
145 for quality, format_item in formats_dict.items():
146 if format_id == 'download':
147 # Download link takes some time to be generated,
150 if not isinstance(format_item, dict):
152 format_url = format_item.get('link')
153 filesize = int_or_none(
154 format_item.get('size'), invscale=1000000)
156 format_url = format_item
158 format_url = url_or_none(format_url)
162 'format_id': '%s-%s' % (format_id, quality),
164 'ext': determine_ext(format_url, 'mp4'),
165 'height': get_height(quality),
166 'filesize': filesize,
168 'Referer': urlh.geturl(),
171 self._sort_formats(formats)
173 categories_list = video.get('categories')
174 if isinstance(categories_list, list):
176 for c in categories_list:
177 if not isinstance(c, dict):
179 c_name = c.get('name')
180 if isinstance(c_name, compat_str):
181 categories.append(c_name)
187 'display_id': display_id,
189 'description': video.get('description'),
190 'timestamp': int_or_none(video.get('created')),
192 video, lambda x: x['author']['name'], compat_str),
193 'thumbnail': video.get('thumbURL'),
194 'duration': int_or_none(video.get('duration')),
195 'view_count': int_or_none(video.get('views')),
196 'like_count': int_or_none(try_get(
197 video, lambda x: x['rating']['likes'], int)),
198 'dislike_count': int_or_none(try_get(
199 video, lambda x: x['rating']['dislikes'], int)),
200 'comment_count': int_or_none(video.get('views')),
201 'age_limit': age_limit,
202 'categories': categories,
206 # Old layout fallback
208 title = self._html_search_regex(
209 [r'<h1[^>]*>([^<]+)</h1>',
210 r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
211 r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
217 sources = self._parse_json(
219 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
221 video_id, fatal=False)
222 for format_id, format_url in sources.items():
223 format_url = url_or_none(format_url)
226 if format_url in format_urls:
228 format_urls.add(format_url)
230 'format_id': format_id,
232 'height': get_height(format_id),
235 video_url = self._search_regex(
236 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
237 r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
238 r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
239 webpage, 'video url', group='mp4', default=None)
240 if video_url and video_url not in format_urls:
245 self._sort_formats(formats)
247 # Only a few videos have an description
248 mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
249 description = mobj.group(1) if mobj else None
251 upload_date = unified_strdate(self._search_regex(
252 r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
253 webpage, 'upload date', fatal=False))
255 uploader = self._html_search_regex(
256 r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
257 webpage, 'uploader', default='anonymous')
259 thumbnail = self._search_regex(
260 [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
261 r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
262 webpage, 'thumbnail', fatal=False, group='thumbnail')
264 duration = parse_duration(self._search_regex(
265 [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
266 r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
267 'duration', fatal=False))
269 view_count = int_or_none(self._search_regex(
270 r'content=["\']User(?:View|Play)s:(\d+)',
271 webpage, 'view count', fatal=False))
273 mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
274 (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
276 mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
277 comment_count = mobj.group('commentcount') if mobj else 0
279 categories_html = self._search_regex(
280 r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
281 'categories', default=None)
282 categories = [clean_html(category) for category in re.findall(
283 r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
287 'display_id': display_id,
289 'description': description,
290 'upload_date': upload_date,
291 'uploader': uploader,
292 'thumbnail': thumbnail,
293 'duration': duration,
294 'view_count': view_count,
295 'like_count': int_or_none(like_count),
296 'dislike_count': int_or_none(dislike_count),
297 'comment_count': int_or_none(comment_count),
298 'age_limit': age_limit,
299 'categories': categories,
304 class XHamsterEmbedIE(InfoExtractor):
305 _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
307 'url': 'http://xhamster.com/xembed.php?video=3328539',
311 'title': 'Pen Masturbation',
312 'timestamp': 1406581861,
313 'upload_date': '20140728',
314 'uploader': 'ManyakisArt',
321 def _extract_urls(webpage):
322 return [url for _, url in re.findall(
323 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
326 def _real_extract(self, url):
327 video_id = self._match_id(url)
329 webpage = self._download_webpage(url, video_id)
331 video_url = self._search_regex(
332 r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
333 webpage, 'xhamster url', default=None)
336 vars = self._parse_json(
337 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
339 video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
341 return self.url_result(video_url, 'XHamster')
344 class XHamsterUserIE(InfoExtractor):
345 _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
347 # Paginated user profile
348 'url': 'https://xhamster.com/users/netvideogirls/videos',
350 'id': 'netvideogirls',
352 'playlist_mincount': 267,
354 # Non-paginated user profile
355 'url': 'https://xhamster.com/users/firatkaan/videos',
359 'playlist_mincount': 1,
362 def _entries(self, user_id):
363 next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
364 for pagenum in itertools.count(1):
365 page = self._download_webpage(
366 next_page_url, user_id, 'Downloading page %s' % pagenum)
367 for video_tag in re.findall(
368 r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
370 video = extract_attributes(video_tag)
371 video_url = url_or_none(video.get('href'))
372 if not video_url or not XHamsterIE.suitable(video_url):
374 video_id = XHamsterIE._match_id(video_url)
375 yield self.url_result(
376 video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
377 mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
380 next_page = extract_attributes(mobj.group(0))
381 next_page_url = url_or_none(next_page.get('href'))
382 if not next_page_url:
385 def _real_extract(self, url):
386 user_id = self._match_id(url)
387 return self.playlist_result(self._entries(user_id), user_id)