from .common import InfoExtractor
from ..utils import (
- float_or_none,
+ clean_html,
+ dict_get,
+ ExtractorError,
int_or_none,
- str_to_int,
+ parse_duration,
unified_strdate,
)
class XHamsterIE(InfoExtractor):
- _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
- _TESTS = [
- {
- 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
- 'info_dict': {
- 'id': '1509445',
- 'ext': 'mp4',
- 'title': 'FemaleAgent Shy beauty takes the bait',
- 'upload_date': '20121014',
- 'uploader': 'Ruseful2011',
- 'duration': 893,
- 'age_limit': 18,
- }
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:.+?\.)?xhamster\.com/
+ (?:
+ movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
+ videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
+ )
+ '''
+
+ _TESTS = [{
+ 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+ 'md5': '8281348b8d3c53d39fffb377d24eac4e',
+ 'info_dict': {
+ 'id': '1509445',
+ 'ext': 'mp4',
+ 'title': 'FemaleAgent Shy beauty takes the bait',
+ 'upload_date': '20121014',
+ 'uploader': 'Ruseful2011',
+ 'duration': 893,
+ 'age_limit': 18,
+ 'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
},
- {
- 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
- 'info_dict': {
- 'id': '2221348',
- 'ext': 'mp4',
- 'title': 'Britney Spears Sexy Booty',
- 'upload_date': '20130914',
- 'uploader': 'jojo747400',
- 'duration': 200,
- 'age_limit': 18,
- }
+ }, {
+ 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+ 'info_dict': {
+ 'id': '2221348',
+ 'ext': 'mp4',
+ 'title': 'Britney Spears Sexy Booty',
+ 'upload_date': '20130914',
+ 'uploader': 'jojo747400',
+ 'duration': 200,
+ 'age_limit': 18,
+ 'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
},
- {
- 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
- 'only_matching': True,
+ 'params': {
+ 'skip_download': True,
},
- ]
+ }, {
+ # empty seo
+ 'url': 'http://xhamster.com/movies/5667973/.html',
+ 'info_dict': {
+ 'id': '5667973',
+ 'ext': 'mp4',
+ 'title': '....',
+ 'upload_date': '20160208',
+ 'uploader': 'parejafree',
+ 'duration': 72,
+ 'age_limit': 18,
+ 'categories': ['Amateur', 'Blowjobs'],
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
+ 'only_matching': True,
+ }, {
+ # This video is visible for marcoalfa123456's friends only
+ 'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
+ 'only_matching': True,
+ }, {
+ # new URL schema
+ 'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
def extract_video_url(webpage, name):
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- seo = mobj.group('seo')
- proto = mobj.group('proto')
- mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
- webpage = self._download_webpage(mrss_url, video_id)
+ video_id = mobj.group('id') or mobj.group('id_2')
+ display_id = mobj.group('display_id') or mobj.group('display_id_2')
+
+ webpage = self._download_webpage(url, video_id)
+
+ error = self._html_search_regex(
+ r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
+ webpage, 'error', default=None)
+ if error:
+ raise ExtractorError(error, expected=True)
title = self._html_search_regex(
- [r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>',
- r'<h1[^>]*>([^<]+)</h1>',
- r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"'], webpage, 'title')
+ [r'<h1[^>]*>([^<]+)</h1>',
+ r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
+ r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
+ webpage, 'title')
# Only a few videos have an description
mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
webpage, 'upload date', fatal=False))
uploader = self._html_search_regex(
- r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
+ r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
webpage, 'uploader', default='anonymous')
thumbnail = self._search_regex(
r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
webpage, 'thumbnail', fatal=False, group='thumbnail')
- duration = float_or_none(self._search_regex(
- r'(["\'])duration\1\s*:\s*(["\'])(?P<duration>.+?)\2',
- webpage, 'duration', fatal=False, group='duration'))
+ duration = parse_duration(self._search_regex(
+ r'Runtime:\s*</span>\s*([\d:]+)', webpage,
+ 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
r'content=["\']User(?:View|Play)s:(\d+)',
webpage, 'view count', fatal=False))
- mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
+ mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
(like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
self._sort_formats(formats)
+ categories_html = self._search_regex(
+ r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
+ 'categories', default=None)
+ categories = [clean_html(category) for category in re.findall(
+ r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
+
return {
'id': video_id,
'title': title,
'dislike_count': int_or_none(dislike_count),
'comment_count': int_or_none(comment_count),
'age_limit': age_limit,
+ 'categories': categories,
'formats': formats,
}
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
- r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
- webpage, 'xhamster url')
+ r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
+ webpage, 'xhamster url', default=None)
+
+ if not video_url:
+ vars = self._parse_json(
+ self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
+ video_id)
+ video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
return self.url_result(video_url, 'XHamster')
projects / youtube-dl / blobdiff