[videomega] Fix extraction (Closes #4703)

This commit is contained in:
Naglis Jonaitis 2015-01-15 19:57:36 +02:00
parent c8dfe360eb
commit a45c0a5d67
1 changed files with 13 additions and 8 deletions

View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request,
) )
from ..utils import ( from ..utils import (
remove_start, remove_start,
@ -16,20 +17,23 @@ class VideoMegaIE(InfoExtractor):
(?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+) (?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
''' '''
_TEST = { _TEST = {
'url': 'http://videomega.tv/?ref=GKeGPVedBe', 'url': 'http://videomega.tv/?ref=QR0HCUHI1661IHUCH0RQ',
'md5': '240fb5bcf9199961f48eb17839b084d6', 'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
'info_dict': { 'info_dict': {
'id': 'GKeGPVedBe', 'id': 'QR0HCUHI1661IHUCH0RQ',
'ext': 'mp4', 'ext': 'mp4',
'title': 'XXL - All Sports United', 'title': 'Big Buck Bunny',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
webpage = self._download_webpage(url, video_id) iframe_url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
req = compat_urllib_request.Request(iframe_url)
req.add_header('Referer', url)
webpage = self._download_webpage(req, video_id)
escaped_data = self._search_regex( escaped_data = self._search_regex(
r'unescape\("([^"]+)"\)', webpage, 'escaped data') r'unescape\("([^"]+)"\)', webpage, 'escaped data')
@ -37,13 +41,13 @@ class VideoMegaIE(InfoExtractor):
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False) r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False)
url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL') video_url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL')
title = remove_start(self._html_search_regex( title = remove_start(self._html_search_regex(
r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ') r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ')
formats = [{ formats = [{
'format_id': 'sd', 'format_id': 'sd',
'url': url, 'url': video_url,
}] }]
self._sort_formats(formats) self._sort_formats(formats)
@ -52,4 +56,5 @@ class VideoMegaIE(InfoExtractor):
'title': title, 'title': title,
'formats': formats, 'formats': formats,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'http_referer': iframe_url,
} }