mirror of
https://github.com/blackjack4494/yt-dlc.git
synced 2024-12-23 16:26:40 +00:00
[videomega] Fix extraction and update test (Fixes #5235)
This commit is contained in:
parent
2ed849eccf
commit
eecc0685c9
1 changed files with 14 additions and 31 deletions
|
@ -4,28 +4,21 @@ 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,
|
||||
)
|
||||
from ..compat import compat_urllib_request
|
||||
|
||||
|
||||
class VideoMegaIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://
|
||||
(?:www\.)?videomega\.tv/
|
||||
(?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
|
||||
(?:iframe\.php|cdn\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
|
||||
'''
|
||||
_TEST = {
|
||||
'url': 'http://videomega.tv/?ref=QR0HCUHI1661IHUCH0RQ',
|
||||
'url': 'http://videomega.tv/?ref=4GNA688SU99US886ANG4',
|
||||
'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
|
||||
'info_dict': {
|
||||
'id': 'QR0HCUHI1661IHUCH0RQ',
|
||||
'id': '4GNA688SU99US886ANG4',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny',
|
||||
'title': 'BigBuckBunny_320x180',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
}
|
||||
}
|
||||
|
@ -33,34 +26,24 @@ class VideoMegaIE(InfoExtractor):
|
|||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
iframe_url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
|
||||
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)
|
||||
|
||||
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'<title>(.*?)</title>', 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'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ')
|
||||
|
||||
formats = [{
|
||||
'format_id': 'sd',
|
||||
'url': video_url,
|
||||
}]
|
||||
self._sort_formats(formats)
|
||||
r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
|
||||
video_url = self._search_regex(
|
||||
r'<source[^>]+?src="([^"]+)"', webpage, 'video URL')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'url': video_url,
|
||||
'thumbnail': thumbnail,
|
||||
'http_headers': {
|
||||
'Referer': iframe_url,
|
||||
|
|
Loading…
Reference in a new issue