+from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
- compat_urllib_parse,
- unescapeHTML,
- determine_ext,
+ clean_html,
+ dict_get,
ExtractorError,
+ int_or_none,
+ parse_duration,
+ unified_strdate,
)
class XHamsterIE(InfoExtractor):
- """Information Extractor for xHamster"""
- _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
+ _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 = [{
- u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
- u'file': u'1509445.flv',
- u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
- u'info_dict': {
- u"upload_date": u"20121014",
- u"uploader_id": u"Ruseful2011",
- u"title": u"FemaleAgent Shy beauty takes the bait",
- u"age_limit": 18,
- }
- },
- {
- u'url': u'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
- u'file': u'2221348.flv',
- u'md5': u'e767b9475de189320f691f49c679c4c7',
- u'info_dict': {
- u"upload_date": u"20130914",
- u"uploader_id": u"jojo747400",
- u"title": u"Britney Spears Sexy Booty",
- u"age_limit": 18,
- }
+ 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+ 'md5': '8281348b8d3c53d39fffb377d24eac4e',
+ 'info_dict': {
+ 'id': '1509445',
+ 'display_id': 'femaleagent_shy_beauty_takes_the_bait',
+ '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',
+ 'display_id': 'britney_spears_sexy_booty',
+ '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'],
+ },
+ '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 _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
+ 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)
- video_id = mobj.group('id')
- seo = mobj.group('seo')
- mrss_url = 'http://xhamster.com/movies/%s/%s.html?hd' % (video_id, seo)
- webpage = self._download_webpage(mrss_url, video_id)
+ title = self._html_search_regex(
+ [r'<h1[^>]*>([^<]+)</h1>',
+ r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
+ r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
+ webpage, 'title')
- mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract media URL')
- if len(mobj.group('server')) == 0:
- video_url = compat_urllib_parse.unquote(mobj.group('file'))
- else:
- video_url = mobj.group('server')+'/key='+mobj.group('file')
+ formats = []
+ format_urls = set()
- video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
- webpage, u'title')
+ sources = self._parse_json(
+ self._search_regex(
+ r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
+ default='{}'),
+ video_id, fatal=False)
+ for format_id, format_url in sources.items():
+ if not isinstance(format_url, compat_str):
+ continue
+ if format_url in format_urls:
+ continue
+ format_urls.add(format_url)
+ formats.append({
+ 'format_id': format_id,
+ 'url': format_url,
+ 'height': int_or_none(self._search_regex(
+ r'^(\d+)[pP]', format_id, 'height', default=None))
+ })
+
+ video_url = self._search_regex(
+ [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
+ r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
+ r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
+ webpage, 'video url', group='mp4', default=None)
+ if video_url and video_url not in format_urls:
+ formats.append({
+ 'url': video_url,
+ })
+
+ self._sort_formats(formats)
# Only a few videos have an description
- mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
- if mobj:
- video_description = unescapeHTML(mobj.group('description'))
- else:
- video_description = None
+ mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
+ description = mobj.group(1) if mobj else None
+
+ upload_date = unified_strdate(self._search_regex(
+ r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
+ webpage, 'upload date', fatal=False))
+
+ uploader = self._html_search_regex(
+ r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
+ webpage, 'uploader', default='anonymous')
+
+ thumbnail = self._search_regex(
+ [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
+ r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
+ webpage, 'thumbnail', fatal=False, group='thumbnail')
+
+ duration = parse_duration(self._search_regex(
+ [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
+ r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
+ 'duration', fatal=False))
- mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
- if mobj:
- video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
- else:
- video_upload_date = None
- self._downloader.report_warning(u'Unable to extract upload date')
+ view_count = int_or_none(self._search_regex(
+ r'content=["\']User(?:View|Play)s:(\d+)',
+ webpage, 'view count', fatal=False))
- video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
- webpage, u'uploader id', default=u'anonymous')
+ 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)
- video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
- webpage, u'thumbnail', fatal=False)
+ mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
+ comment_count = mobj.group('commentcount') if mobj else 0
age_limit = self._rta_search(webpage)
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': determine_ext(video_url),
- 'title': video_title,
- 'description': video_description,
- 'upload_date': video_upload_date,
- 'uploader_id': video_uploader_id,
- 'thumbnail': video_thumbnail,
+ 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,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'upload_date': upload_date,
+ 'uploader': uploader,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'view_count': view_count,
+ 'like_count': int_or_none(like_count),
+ 'dislike_count': int_or_none(dislike_count),
+ 'comment_count': int_or_none(comment_count),
'age_limit': age_limit,
- }]
+ 'categories': categories,
+ 'formats': formats,
+ }
+
+
+class XHamsterEmbedIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://xhamster.com/xembed.php?video=3328539',
+ 'info_dict': {
+ 'id': '3328539',
+ 'ext': 'mp4',
+ 'title': 'Pen Masturbation',
+ 'upload_date': '20140728',
+ 'uploader_id': 'anonymous',
+ 'duration': 5,
+ 'age_limit': 18,
+ }
+ }
+
+ @staticmethod
+ def _extract_urls(webpage):
+ return [url for _, url in re.findall(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
+ webpage)]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ 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', 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')
Rapsys Git / youtubedl / blobdiff