1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-27 11:17:40 +00:00
youtube-dl/youtube_dl/extractor/videomega.py
2015-01-15 19:57:36 +02:00

60 lines
1.8 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
remove_start,
)
class VideoMegaIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://
(?:www\.)?videomega\.tv/
(?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
'''
_TEST = {
'url': 'http://videomega.tv/?ref=QR0HCUHI1661IHUCH0RQ',
'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
'info_dict': {
'id': 'QR0HCUHI1661IHUCH0RQ',
'ext': 'mp4',
'title': 'Big Buck Bunny',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
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)
req.add_header('Referer', url)
webpage = self._download_webpage(req, video_id)
escaped_data = self._search_regex(
r'unescape\("([^"]+)"\)', webpage, 'escaped data')
playlist = compat_urllib_parse.unquote(escaped_data)
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)
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'http_referer': iframe_url,
}