X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/509eeaaa67b2f901752c50fc6edf41954dbe3085..474aa0db26d02763aedd55afc30b4897534576e8:/youtube_dl/extractor/slutload.py diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py index e6e7d08..661f9e5 100644 --- a/youtube_dl/extractor/slutload.py +++ b/youtube_dl/extractor/slutload.py @@ -1,44 +1,65 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor class SlutloadIE(InfoExtractor): - _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P[^/]+)/?$' - _TEST = { + _VALID_URL = r'https?://(?:\w+\.)?slutload\.com/(?:video/[^/]+|embed_player|watch)/(?P[^/]+)' + _TESTS = [{ 'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/', - 'md5': '0cf531ae8006b530bd9df947a6a0df77', + 'md5': '868309628ba00fd488cf516a113fd717', 'info_dict': { 'id': 'TD73btpBqSxc', 'ext': 'mp4', - "title": "virginie baisee en cam", - "age_limit": 18, - 'thumbnail': 're:https?://.*?\.jpg' - } - } + 'title': 'virginie baisee en cam', + 'age_limit': 18, + 'thumbnail': r're:https?://.*?\.jpg' + }, + }, { + # mobile site + 'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/', + 'only_matching': True, + }, { + 'url': 'http://www.slutload.com/embed_player/TD73btpBqSxc/', + 'only_matching': True, + }, { + 'url': 'http://www.slutload.com/watch/TD73btpBqSxc/Virginie-Baisee-En-Cam.html', + '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) - webpage = self._download_webpage(url, video_id) + embed_page = self._download_webpage( + 'http://www.slutload.com/embed_player/%s' % video_id, video_id, + 'Downloading embed page', fatal=False) - video_title = self._html_search_regex(r'

([^<]+)', - webpage, 'title').strip() + if embed_page: + def extract(what): + return self._html_search_regex( + r'data-video-%s=(["\'])(?P(?:(?!\1).)+)\1' % what, + embed_page, 'video %s' % what, default=None, group='url') - video_url = self._html_search_regex( - r'(?s)
([^<]+)', embed_page, 'title', default=video_id) + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': extract('preview'), + 'age_limit': 18 + } - return { + webpage = self._download_webpage( + 'http://www.slutload.com/video/_/%s/' % video_id, video_id) + title = self._html_search_regex( + r'

([^<]+)', webpage, 'title').strip() + info = self._parse_html5_media_entries(url, webpage, video_id)[0] + info.update({ 'id': video_id, - 'url': video_url, - 'title': video_title, - 'thumbnail': thumbnail, - 'age_limit': 18 - } + 'title': title, + 'age_limit': 18, + }) + return info