X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..83c8b40add31fb501d587b64fb17a936ffd5dbc5:/youtube_dl/extractor/xhamster.py diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 4e8fbde..bd8e1af 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -4,51 +4,68 @@ import re from .common import InfoExtractor from ..utils import ( - ExtractorError, - unified_strdate, - str_to_int, + dict_get, + float_or_none, int_or_none, - parse_duration, + unified_strdate, ) class XHamsterIE(InfoExtractor): - """Information Extractor for xHamster""" - _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.+?)\.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_id': 'Ruseful2011', - 'duration': 893, - 'age_limit': 18, - } + _VALID_URL = r'(?Phttps?)://(?:.+?\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.*?)\.html(?:\?.*)?' + _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': 893.52, + '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_id': 'jojo747400', - 'duration': 200, - 'age_limit': 18, - } - } - ] - - def _real_extract(self,url): - def extract_video_url(webpage): - mp4 = re.search(r'', webpage) - if mp4 is None: - raise ExtractorError('Unable to extract media URL') - else: - return mp4.group(1) + }, { + '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': 200.48, + 'age_limit': 18, + }, + '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': 72.0, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + def extract_video_url(webpage, name): + return self._search_regex( + [r'''file\s*:\s*(?P["'])(?P.+?)(?P=q)''', + r'''["'])(?P.+?)(?P=q)\s+class=["']mp4Thumb''', + r''']+file=(?P["'])(?P.+?)(?P=q)[^>]*>'''], + webpage, name, group='mp4') def is_hd(webpage): return '
(?P.+?) - xHamster\.com', webpage, 'title') + title = self._html_search_regex( + [r']*>([^<]+)', + r']+itemprop=".*?caption.*?"[^>]+content="(.+?)"', + r']*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)'], + webpage, 'title') # Only a few videos have an description mobj = re.search(r'Description: ([^<]+)', webpage) description = mobj.group(1) if mobj else None - upload_date = self._html_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) - if upload_date: - upload_date = unified_strdate(upload_date) + 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_id = self._html_search_regex(r']+>(?P[^<]+)', - webpage, 'uploader id', default='anonymous') + uploader = self._html_search_regex( + r']+itemprop=["\']author[^>]+>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P.+?)', + webpage, 'uploader', default='anonymous') - thumbnail = self._html_search_regex(r'', webpage, 'thumbnail', fatal=False) + thumbnail = self._search_regex( + [r'''thumb\s*:\s*(?P["'])(?P.+?)(?P=q)''', + r''']+poster=(?P["'])(?P.+?)(?P=q)[^>]*>'''], + webpage, 'thumbnail', fatal=False, group='thumbnail') - duration = parse_duration(self._html_search_regex(r'Runtime: (\d+:\d+)
', - webpage, 'duration', fatal=False)) + duration = float_or_none(self._search_regex( + r'(["\'])duration\1\s*:\s*(["\'])(?P.+?)\2', + webpage, 'duration', fatal=False, group='duration')) - view_count = self._html_search_regex(r'Views: ([^<]+)', webpage, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) + 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\d+) Likes / (?P\d+) Dislikes'", webpage) (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None) @@ -93,7 +119,9 @@ class XHamsterIE(InfoExtractor): hd = is_hd(webpage) - video_url = extract_video_url(webpage) + format_id = 'hd' if hd else 'sd' + + video_url = extract_video_url(webpage, format_id) formats = [{ 'url': video_url, 'format_id': 'hd' if hd else 'sd', @@ -104,7 +132,7 @@ class XHamsterIE(InfoExtractor): mrss_url = self._search_regex(r'\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']+?src=(["\'])(?P(?: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')