X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyoujizz.py;h=b86331e3cfa39ec8d3f287e829900b414892beee;hb=6b08cdf626afc71740e539a83ef570999df2c50b;hp=1265639e821bd873b74aeea08811f8c22e966ba1;hpb=66400c470c36a5cdceec531ebd2cfc52e02d6c53;p=youtube-dl diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index 1265639e8..b86331e3c 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,13 +9,14 @@ from ..utils import ( class YouJizzIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P[^.]+).html$' + _VALID_URL = r'^https?://(?:\w+\.)?youjizz\.com/videos/(?P[^.]+)\.html$' _TEST = { - u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', - u'file': u'2189178.flv', - u'md5': u'07e15fa469ba384c7693fd246905547c', - u'info_dict': { - u"title": u"Zeichentrick 1" + 'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', + 'file': '2189178.flv', + 'md5': '07e15fa469ba384c7693fd246905547c', + 'info_dict': { + "title": "Zeichentrick 1", + "age_limit": 18, } } @@ -25,14 +28,16 @@ class YouJizzIE(InfoExtractor): # Get webpage content webpage = self._download_webpage(url, video_id) + age_limit = self._rta_search(webpage) + # Get the video title video_title = self._html_search_regex(r'(?P<title>.*)', - webpage, u'title').strip() + webpage, 'title').strip() # Get the embed page result = re.search(r'https?://www.youjizz.com/videos/embed/(?P[0-9]+)', webpage) if result is None: - raise ExtractorError(u'ERROR: unable to extract embed page') + raise ExtractorError('ERROR: unable to extract embed page') embed_page_url = result.group(0).strip() video_id = result.group('videoid') @@ -44,22 +49,23 @@ class YouJizzIE(InfoExtractor): if m_playlist is not None: playlist_url = m_playlist.group('playlist') playlist_page = self._download_webpage(playlist_url, video_id, - u'Downloading playlist page') + 'Downloading playlist page') m_levels = list(re.finditer(r'[^"]+)"\)\);', - webpage, u'video URL') + webpage, 'video URL') - info = {'id': video_id, - 'url': video_url, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'player_url': embed_page_url} - - return [info] + return { + 'id': video_id, + 'url': video_url, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'player_url': embed_page_url, + 'age_limit': age_limit, + }