X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/1d3fd83f473663fce3e0a10303473a38d80cc3d0..f8df414a4abcde0ddd39325dac26ca071d2d15c6:/youtube_dl/extractor/xhamster.py diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 7b67037..be3624e 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -3,7 +3,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( + clean_html, dict_get, ExtractorError, int_or_none, @@ -13,29 +15,41 @@ from ..utils import ( class XHamsterIE(InfoExtractor): - _VALID_URL = r'(?Phttps?)://(?:.+?\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.*?)\.html(?:\?.*)?' + _VALID_URL = r'''(?x) + https?:// + (?:.+?\.)?xhamster\.com/ + (?: + movies/(?P\d+)/(?P[^/]*)\.html| + videos/(?P[^/]*)-(?P\d+) + ) + ''' + _TESTS = [{ '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, @@ -51,6 +65,7 @@ class XHamsterIE(InfoExtractor): 'uploader': 'parejafree', 'duration': 72, 'age_limit': 18, + 'categories': ['Amateur', 'Blowjobs'], }, 'params': { 'skip_download': True, @@ -62,26 +77,18 @@ class XHamsterIE(InfoExtractor): # 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): - 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 '
]+id=["\']videoClosed["\'][^>]*>(.+?)
', @@ -95,6 +102,39 @@ class XHamsterIE(InfoExtractor): r']*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)'], webpage, 'title') + formats = [] + format_urls = set() + + 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["'])(?P.+?)(?P=q)''', + r'''["'])(?P.+?)(?P=q)\s+class=["']mp4Thumb''', + r''']+file=(?P["'])(?P.+?)(?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(r'Description: ([^<]+)', webpage) description = mobj.group(1) if mobj else None @@ -104,7 +144,7 @@ class XHamsterIE(InfoExtractor): webpage, 'upload date', fatal=False)) uploader = self._html_search_regex( - r']+itemprop=["\']author[^>]+>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P.+?)', + r']+itemprop=["\']author[^>]+>]+>]+>([^<]+)', webpage, 'uploader', default='anonymous') thumbnail = self._search_regex( @@ -113,14 +153,15 @@ class XHamsterIE(InfoExtractor): webpage, 'thumbnail', fatal=False, group='thumbnail') duration = parse_duration(self._search_regex( - r'Runtime:\s*\s*([\d:]+)', webpage, + [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']', + r'Runtime:\s*\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\d+) Likes / (?P\d+) Dislikes'", webpage) + 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) mobj = re.search(r'Comments \((?P\d+)\)', webpage) @@ -128,32 +169,15 @@ class XHamsterIE(InfoExtractor): age_limit = self._rta_search(webpage) - hd = is_hd(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', - 'preference': 1, - }] - - if not hd: - mrss_url = self._search_regex(r'Categories:.+?)', webpage, + 'categories', default=None) + categories = [clean_html(category) for category in re.findall( + r']+>(.+?)', categories_html)] if categories_html else None return { 'id': video_id, + 'display_id': display_id, 'title': title, 'description': description, 'upload_date': upload_date, @@ -165,6 +189,7 @@ class XHamsterIE(InfoExtractor): 'dislike_count': int_or_none(dislike_count), 'comment_count': int_or_none(comment_count), 'age_limit': age_limit, + 'categories': categories, 'formats': formats, } @@ -196,7 +221,7 @@ class XHamsterEmbedIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = self._search_regex( - r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id, + r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id), webpage, 'xhamster url', default=None) if not video_url: