X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmotherless.py;h=6fe3b6049b2917ed5d7b075d0ca2c7ae943c459f;hb=baa3e1845b26d9756642325bbb0d58e22025b2ec;hp=782651612400ffe1ece8bc6ba4b80f55e5ffce04;hpb=f3f1cd6b3bb47c843b01c950650228a623602745;p=youtube-dl diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 782651612..6fe3b6049 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -4,86 +4,109 @@ import datetime import re from .common import InfoExtractor -from ..utils import str_to_int +from ..utils import ( + ExtractorError, + str_to_int, + unified_strdate, +) class MotherlessIE(InfoExtractor): - """Information Extractor for Motherless""" - _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P[A-Z0-9]+)' - _TESTS = [ - { - 'url': 'http://motherless.com/AC3FFE1', - 'md5': '5527fef81d2e529215dad3c2d744a7d9', - 'info_dict': { - 'id': 'AC3FFE1', - 'ext': 'flv', - 'title': 'Fucked in the ass while playing PS3', - 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], - 'upload_date': '20100913', - 'uploader_id': 'famouslyfuckedup', - 'thumbnail': 'http://thumbs.motherlessmedia.com/thumbs/AC3FFE1.jpg', - 'age_limit': 18, - } + _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P[A-Z0-9]+)' + _TESTS = [{ + 'url': 'http://motherless.com/AC3FFE1', + 'md5': '310f62e325a9fafe64f68c0bccb6e75f', + 'info_dict': { + 'id': 'AC3FFE1', + 'ext': 'mp4', + 'title': 'Fucked in the ass while playing PS3', + 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], + 'upload_date': '20100913', + 'uploader_id': 'famouslyfuckedup', + 'thumbnail': r're:http://.*\.jpg', + 'age_limit': 18, + } + }, { + 'url': 'http://motherless.com/532291B', + 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131', + 'info_dict': { + 'id': '532291B', + 'ext': 'mp4', + 'title': 'Amazing girl playing the omegle game, PERFECT!', + 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', + 'game', 'hairy'], + 'upload_date': '20140622', + 'uploader_id': 'Sulivana7x', + 'thumbnail': r're:http://.*\.jpg', + 'age_limit': 18, }, - { - 'url': 'http://motherless.com/532291B', - 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131', - 'info_dict': { - 'id': '532291B', - 'ext': 'mp4', - 'title': 'Amazing girl playing the omegle game, PERFECT!', - 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'], - 'upload_date': '20140622', - 'uploader_id': 'Sulivana7x', - 'thumbnail': 'http://thumbs.motherlessmedia.com/thumbs/532291B.jpg', - 'age_limit': 18, - } + 'skip': '404', + }, { + 'url': 'http://motherless.com/g/cosplay/633979F', + 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0', + 'info_dict': { + 'id': '633979F', + 'ext': 'mp4', + 'title': 'Turtlette', + 'categories': ['superheroine heroine superher'], + 'upload_date': '20140827', + 'uploader_id': 'shade0230', + 'thumbnail': r're:http://.*\.jpg', + 'age_limit': 18, } - ] - - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + }, { + # no keywords + 'url': 'http://motherless.com/8B4BBC1', + 'only_matching': True, + }] + def _real_extract(self, url): + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'(?P<title>.+?) - MOTHERLESS.COM', webpage, 'title') - video_url = self._search_regex(r"__fileurl = '(?P[^']+)'", webpage, 'video_url') - thumbnail = self._og_search_thumbnail(webpage) - age_limit = self._rta_search(webpage) # Hint: it's 18 ;) - view_count = str_to_int(self._html_search_regex(r'Views(.+?)', webpage, - 'view_count', flags=re.DOTALL)) + if any(p in webpage for p in ( + '404 - MOTHERLESS.COM<', + ">The page you're looking for cannot be found.<")): + raise ExtractorError('Video %s does not exist' % video_id, expected=True) - like_count = str_to_int(self._html_search_regex(r'<strong>Favorited</strong>(.+?)</h2>', webpage, - 'like_count', flags=re.DOTALL)) - comment_count = webpage.count('class="media-comment-contents"') - uploader_id = self._html_search_regex(r'<div class="thumb-member-username">.*?<a [^>]*>(.+?)</a>', - webpage, 'uploader_id', flags=re.DOTALL) + if '>The content you are trying to view is for friends only.' in webpage: + raise ExtractorError('Video %s is for friends only' % video_id, expected=True) - categories = self._html_search_meta('keywords', webpage) - if categories is not None: - categories = [cat.strip() for cat in categories.split(',')] + title = self._html_search_regex( + r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') + video_url = self._html_search_regex( + r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL') + age_limit = self._rta_search(webpage) + view_count = str_to_int(self._html_search_regex( + r'<strong>Views</strong>\s+([^<]+)<', + webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'<strong>Favorited</strong>\s+([^<]+)<', + webpage, 'like count', fatal=False)) - upload_date = self._html_search_regex(r'<strong>Uploaded</strong>(.+?)</h2>', webpage, - 'upload_date', flags=re.DOTALL) - mobj = re.search(r'(\d+) days? ago', upload_date, re.I) - if mobj is not None: - upload_date = datetime.datetime.now() - datetime.timedelta(days=int(mobj.group(1))) + upload_date = self._html_search_regex( + r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date') + if 'Ago' in upload_date: + days = int(re.search(r'([0-9]+)', upload_date).group(1)) + upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') else: - mobj = re.search(r'(\w+) (\d+)\w* (\d+)', upload_date, re.I) - if mobj is not None: - upload_date = datetime.datetime.strptime('%s %s %s' % mobj.groups(), '%b %d %Y').date() - else: - upload_date = None - if upload_date is not None: - upload_date = upload_date.strftime('%Y%m%d') + upload_date = unified_strdate(upload_date) + + comment_count = webpage.count('class="media-comment-contents"') + uploader_id = self._html_search_regex( + r'"thumb-member-username">\s+<a href="/m/([^"]+)"', + webpage, 'uploader_id') + + categories = self._html_search_meta('keywords', webpage, default=None) + if categories: + categories = [cat.strip() for cat in categories.split(',')] return { 'id': video_id, 'title': title, 'upload_date': upload_date, 'uploader_id': uploader_id, - 'thumbnail': thumbnail, + 'thumbnail': self._og_search_thumbnail(webpage), 'categories': categories, 'view_count': view_count, 'like_count': like_count,