X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvidzi.py;h=3c78fb3d5a071a6f49dec7467e620c0b8a01ded9;hb=0f56bd2178d887adb2d5c61da44343d228eed504;hp=7d93dd301d059213b4ebb4d392ec965fefa23188;hpb=95ee84421e57982f208ec00c314abfabaa3418e8;p=youtube-dl diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index 7d93dd301..3c78fb3d5 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -1,30 +1,42 @@ -import re -from .common import InfoExtractor +# coding: utf-8 +from __future__ import unicode_literals -class VidziIE(InfoExtractor): +from .jwplatform import JWPlatformBaseIE +from ..utils import ( + decode_packed_codes, + js_to_json, +) + + +class VidziIE(JWPlatformBaseIE): _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P\w+)' _TEST = { - 'url': 'http://vidzi.tv/m1chxrwq7bx9', - 'md5': '5c4c4a8ca2281a199c8eefe8f411d630', + 'url': 'http://vidzi.tv/cghql9yq6emu.html', + 'md5': '4f16c71ca0c8c8635ab6932b5f3f1660', 'info_dict': { - 'id': 'm1chxrwq7bx9', + 'id': 'cghql9yq6emu', 'ext': 'mp4', - 'title': 'Watch Cadbury Dream Factory S01E04 HDTV x264 FiHTV mp4', + 'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭', + }, + 'params': { + # m3u8 download + 'skip_download': True, }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - webpage = self._download_webpage('http://vidzi.tv/' + video_id, video_id) - video_url = self._html_search_regex(r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, u'vidzi url') - title = self._html_search_regex(r'([^<]+)<\/Title>', webpage, u'vidzi title') - - return { - 'id': video_id, - 'title': title, - 'url': video_url, - 'ext': 'mp4', - } - \ No newline at end of file + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title') + + code = decode_packed_codes(webpage).replace('\\\'', '\'') + jwplayer_data = self._parse_json( + self._search_regex(r'setup\(([^)]+)\)', code, 'jwplayer data'), + video_id, transform_source=js_to_json) + + info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False) + info_dict['title'] = title + + return info_dict