X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a6abd8dc822fb70852437ab5a77ced5f633739f8..b0b67c374528aca7bc76a9476d554a1d3ab96a9e:/youtube_dl/extractor/videomega.py diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py index 2730303..c02830d 100644 --- a/youtube_dl/extractor/videomega.py +++ b/youtube_dl/extractor/videomega.py @@ -4,63 +4,55 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) from ..utils import ( - ExtractorError, - remove_start, + decode_packed_codes, + sanitized_Request, ) class VideoMegaIE(InfoExtractor): - _VALID_URL = r'''(?x)https?:// - (?:www\.)?videomega\.tv/ - (?:iframe\.php)?\?ref=(?P[A-Za-z0-9]+) - ''' - _TEST = { - 'url': 'http://videomega.tv/?ref=QR0HCUHI1661IHUCH0RQ', - 'md5': 'bf5c2f95c4c917536e80936af7bc51e1', + _VALID_URL = r'(?:videomega:|https?://(?:www\.)?videomega\.tv/(?:(?:view|iframe|cdn)\.php)?\?ref=)(?P[A-Za-z0-9]+)' + _TESTS = [{ + 'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA', + 'md5': 'cc1920a58add3f05c6a93285b84fb3aa', 'info_dict': { - 'id': 'QR0HCUHI1661IHUCH0RQ', + 'id': 'AOSQBJYKIDDIKYJBQSOA', 'ext': 'mp4', - 'title': 'Big Buck Bunny', - 'thumbnail': 're:^https?://.*\.jpg$', + 'title': '1254207', + 'thumbnail': r're:^https?://.*\.jpg$', } - } + }, { + 'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA&width=1070&height=600', + 'only_matching': True, + }, { + 'url': 'http://videomega.tv/view.php?ref=090051111052065112106089103052052103089106112065052111051090', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - iframe_url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id) - req = compat_urllib_request.Request(iframe_url) + iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id + req = sanitized_Request(iframe_url) req.add_header('Referer', url) + req.add_header('Cookie', 'noadvtday=0') webpage = self._download_webpage(req, video_id) - try: - escaped_data = re.findall(r'unescape\("([^"]+)"\)', webpage)[-1] - except IndexError: - raise ExtractorError('Unable to extract escaped data') - - playlist = compat_urllib_parse.unquote(escaped_data) - + 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) - video_url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL') - title = remove_start(self._html_search_regex( - r'(.*?)', webpage, 'title'), 'VideoMega.tv - ') + r']+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False) - formats = [{ - 'format_id': 'sd', - 'url': video_url, - }] - self._sort_formats(formats) + real_codes = decode_packed_codes(webpage) + video_url = self._search_regex( + r'"src"\s*,\s*"([^"]+)"', real_codes, 'video URL') return { 'id': video_id, 'title': title, - 'formats': formats, + 'url': video_url, 'thumbnail': thumbnail, 'http_headers': { 'Referer': iframe_url,