X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvideomega.py;h=eb309a7cdf99b3ebc4bde755fe09d47505516f28;hb=2bb5b6d0a1671957c7a2e6d6433901b2a1b8f48f;hp=29c4e0101ec21eb59c22de9739a516b9f96c0e0f;hpb=34e14a9beb3abe76bcda1154030978979c6c1d1d;p=youtube-dl.git diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py index 29c4e0101..eb309a7cd 100644 --- a/youtube_dl/extractor/videomega.py +++ b/youtube_dl/extractor/videomega.py @@ -4,54 +4,48 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse, - remove_start, -) +from ..compat import compat_urllib_request class VideoMegaIE(InfoExtractor): _VALID_URL = r'''(?x)https?:// (?:www\.)?videomega\.tv/ - (?:iframe\.php)?\?ref=(?P[A-Za-z0-9]+) + (?:iframe\.php|cdn\.php)?\?ref=(?P[A-Za-z0-9]+) ''' _TEST = { - 'url': 'http://videomega.tv/?ref=GKeGPVedBe', - 'md5': '240fb5bcf9199961f48eb17839b084d6', + 'url': 'http://videomega.tv/?ref=4GNA688SU99US886ANG4', + 'md5': 'bf5c2f95c4c917536e80936af7bc51e1', 'info_dict': { - 'id': 'GKeGPVedBe', + 'id': '4GNA688SU99US886ANG4', 'ext': 'mp4', - 'title': 'XXL - All Sports United', + 'title': 'BigBuckBunny_320x180', 'thumbnail': 're:^https?://.*\.jpg$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id) - webpage = self._download_webpage(url, video_id) - - escaped_data = self._search_regex( - r'unescape\("([^"]+)"\)', webpage, 'escaped data') - playlist = compat_urllib_parse.unquote(escaped_data) + iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id + req = compat_urllib_request.Request(iframe_url) + req.add_header('Referer', url) + webpage = self._download_webpage(req, video_id) + title = self._html_search_regex( + r'(.*?)', webpage, 'title') + title = re.sub( + r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s?|\s?-\svideomega\.tv$)', '', title) thumbnail = self._search_regex( - r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False) - url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL') - title = remove_start(self._html_search_regex( - r'(.*?)', webpage, 'title'), 'VideoMega.tv - ') - - formats = [{ - 'format_id': 'sd', - 'url': url, - }] - self._sort_formats(formats) + r']+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False) + video_url = self._search_regex( + r']+?src="([^"]+)"', webpage, 'video URL') return { 'id': video_id, 'title': title, - 'formats': formats, + 'url': video_url, 'thumbnail': thumbnail, + 'http_headers': { + 'Referer': iframe_url, + }, }