X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fvbox7.py;h=a1e0851b7424e4c73cd34b72c02f16bc1905b6ce;hb=dcdb292fddc82ae11f4c0b647815a45c88a6b6d5;hp=455b6d9da62f221cf0854655f707d5963546840f;hpb=9e1a5b845586a0a5431fb72467142046d8571e6f;p=youtube-dl diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index 455b6d9da..a1e0851b7 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -1,20 +1,23 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse, - compat_urllib_request, - - ExtractorError, -) +from ..utils import urlencode_postdata class Vbox7IE(InfoExtractor): - _VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P[^/]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?vbox7\.com/(?:play:|emb/external\.php\?.*?\bvid=)(?P[\da-fA-F]+)' + _TESTS = [{ + 'url': 'http://vbox7.com/play:0946fff23c', + 'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf', + 'info_dict': { + 'id': '0946fff23c', + 'ext': 'mp4', + 'title': 'Борисов: Притеснен съм за бъдещето на България', + }, + }, { 'url': 'http://vbox7.com/play:249bb972c2', 'md5': '99f65c0c9ef9b682b97313e052734c3f', 'info_dict': { @@ -22,34 +25,50 @@ class Vbox7IE(InfoExtractor): 'ext': 'mp4', 'title': 'Смях! Чудо - чист за секунди - Скрита камера', }, - } + 'skip': 'georestricted', + }, { + 'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1', + 'only_matching': True, + }] + + @staticmethod + def _extract_url(webpage): + mobj = re.search( + ']+src=(?P["\'])(?P(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)', + webpage) + if mobj: + return mobj.group('url') def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - redirect_page, urlh = self._download_webpage_handle(url, video_id) - new_location = self._search_regex(r'window\.location = \'(.*)\';', - redirect_page, 'redirect location') - redirect_url = urlh.geturl() + new_location - webpage = self._download_webpage(redirect_url, video_id, - 'Downloading redirect page') - - title = self._html_search_regex(r'(.*)', - webpage, 'title').split('/')[0].strip() - - info_url = "http://vbox7.com/play/magare.do" - data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id}) - info_request = compat_urllib_request.Request(info_url, data) - info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage') - if info_response is None: - raise ExtractorError('Unable to extract the media url') - (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'http://vbox7.com/play:%s' % video_id, video_id) + + title = self._html_search_regex( + r'(.+?)', webpage, 'title').split('/')[0].strip() + + video_url = self._search_regex( + r'src\s*:\s*(["\'])(?P.+?.mp4.*?)\1', + webpage, 'video url', default=None, group='url') + + thumbnail_url = self._og_search_thumbnail(webpage) + + if not video_url: + info_response = self._download_webpage( + 'http://vbox7.com/play/magare.do', video_id, + 'Downloading info webpage', + data=urlencode_postdata({'as3': '1', 'vid': video_id}), + headers={'Content-Type': 'application/x-www-form-urlencoded'}) + final_url, thumbnail_url = map( + lambda x: x.split('=')[1], info_response.split('&')) + + if '/na.mp4' in video_url: + self.raise_geo_restricted() return { 'id': video_id, - 'url': final_url, + 'url': self._proto_relative_url(video_url, 'http:'), 'title': title, 'thumbnail': thumbnail_url, }