X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/c512650955de0b16d37e7fa7fb29ea0985e415bb..e24ec2f4d08121be7bca938fb603fa29f680d46a:/youtube_dl/extractor/xnxx.py diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py index 7a73b24..ac1ccc4 100644 --- a/youtube_dl/extractor/xnxx.py +++ b/youtube_dl/extractor/xnxx.py @@ -1,49 +1,84 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( - compat_urllib_parse, + determine_ext, + int_or_none, + NO_DEFAULT, + str_to_int, ) class XNXXIE(InfoExtractor): - _VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P[0-9]+)/(.*)' - _TEST = { - 'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_', - 'md5': '0831677e2b4761795f68d417e0b7b445', + _VALID_URL = r'https?://(?:video|www)\.xnxx\.com/video-?(?P[0-9a-z]+)/' + _TESTS = [{ + 'url': 'http://www.xnxx.com/video-55awb78/skyrim_test_video', + 'md5': '7583e96c15c0f21e9da3453d9920fbba', 'info_dict': { - 'id': '1135332', - 'ext': 'flv', - 'title': 'lida » Naked Funny Actress (5)', + 'id': '55awb78', + 'ext': 'mp4', + 'title': 'Skyrim Test Video', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 469, + 'view_count': int, 'age_limit': 18, - } - } + }, + }, { + 'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_', + 'only_matching': True, + }, { + 'url': 'http://www.xnxx.com/video-55awb78/', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - # Get webpage content webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'flv_url=(.*?)&', - webpage, 'video URL') - video_url = compat_urllib_parse.unquote(video_url) + def get(meta, default=NO_DEFAULT, fatal=True): + return self._search_regex( + r'set%s\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1' % meta, + webpage, meta, default=default, fatal=fatal, group='value') + + title = self._og_search_title( + webpage, default=None) or get('VideoTitle') - video_title = self._html_search_regex(r'(.*?)\s+-\s+XNXX.COM', - webpage, 'title') + formats = [] + for mobj in re.finditer( + r'setVideo(?:Url(?P<id>Low|High)|HLS)\s*\(\s*(?P<q>["\'])(?P<url>(?:https?:)?//.+?)(?P=q)', webpage): + format_url = mobj.group('url') + if determine_ext(format_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', entry_protocol='m3u8_native', + preference=1, m3u8_id='hls', fatal=False)) + else: + format_id = mobj.group('id') + if format_id: + format_id = format_id.lower() + formats.append({ + 'url': format_url, + 'format_id': format_id, + 'quality': -1 if format_id == 'low' else 0, + }) + self._sort_formats(formats) - video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&', - webpage, 'thumbnail', fatal=False) + thumbnail = self._og_search_thumbnail(webpage, default=None) or get( + 'ThumbUrl', fatal=False) or get('ThumbUrl169', fatal=False) + duration = int_or_none(self._og_search_property('duration', webpage)) + view_count = str_to_int(self._search_regex( + r'id=["\']nb-views-number[^>]+>([\d,.]+)', webpage, 'view count', + default=None)) return { 'id': video_id, - 'url': video_url, - 'title': video_title, - 'ext': 'flv', - 'thumbnail': video_thumbnail, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, 'age_limit': 18, + 'formats': formats, }