[videomega] Extend _VALID_URL and improve extraction (Closes #6260)

This commit is contained in:
Sergey M․ 2015-07-18 04:13:45 +06:00
parent fb10e1aa57
commit 4e1ad6e9a8
1 changed files with 10 additions and 13 deletions

View File

@ -8,17 +8,14 @@ from ..compat import compat_urllib_request
class VideoMegaIE(InfoExtractor): class VideoMegaIE(InfoExtractor):
_VALID_URL = r'''(?x)https?:// _VALID_URL = r'https?://(?:www\.)?videomega\.tv/(?:(?:view|iframe|cdn)\.php)?\?ref=(?P<id>[A-Za-z0-9]+)'
(?:www\.)?videomega\.tv/
(?:iframe\.php|cdn\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
'''
_TEST = { _TEST = {
'url': 'http://videomega.tv/?ref=4GNA688SU99US886ANG4', 'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA&width=1070&height=600',
'md5': 'bf5c2f95c4c917536e80936af7bc51e1', 'md5': 'cc1920a58add3f05c6a93285b84fb3aa',
'info_dict': { 'info_dict': {
'id': '4GNA688SU99US886ANG4', 'id': 'AOSQBJYKIDDIKYJBQSOA',
'ext': 'mp4', 'ext': 'mp4',
'title': 'BigBuckBunny_320x180', 'title': '1254207',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
} }
} }
@ -26,15 +23,15 @@ class VideoMegaIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id req = compat_urllib_request.Request(url)
req = compat_urllib_request.Request(iframe_url)
req.add_header('Referer', url) req.add_header('Referer', url)
req.add_header('Cookie', 'noadvtday=0')
webpage = self._download_webpage(req, video_id) webpage = self._download_webpage(req, video_id)
title = self._html_search_regex( title = self._html_search_regex(
r'<title>(.*?)</title>', webpage, 'title') r'<title>(.+?)</title>', webpage, 'title')
title = re.sub( title = re.sub(
r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s?|\s?-\svideomega\.tv$)', '', title) r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s*|\s*-\svideomega\.tv$)', '', title)
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False) r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
video_url = self._search_regex( video_url = self._search_regex(
@ -46,6 +43,6 @@ class VideoMegaIE(InfoExtractor):
'url': video_url, 'url': video_url,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'http_headers': { 'http_headers': {
'Referer': iframe_url, 'Referer': url,
}, },
} }