]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/videomega.py
debian/changelog: Highlight the fix of youtube videos.
[youtubedl] / youtube_dl / extractor / videomega.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..compat import (
6 compat_urllib_parse,
7 compat_urllib_request,
8 )
9 from ..utils import (
10 remove_start,
11 )
12
13
14 class VideoMegaIE(InfoExtractor):
15 _VALID_URL = r'''(?x)https?://
16 (?:www\.)?videomega\.tv/
17 (?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
18 '''
19 _TEST = {
20 'url': 'http://videomega.tv/?ref=QR0HCUHI1661IHUCH0RQ',
21 'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
22 'info_dict': {
23 'id': 'QR0HCUHI1661IHUCH0RQ',
24 'ext': 'mp4',
25 'title': 'Big Buck Bunny',
26 'thumbnail': 're:^https?://.*\.jpg$',
27 }
28 }
29
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32
33 iframe_url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
34 req = compat_urllib_request.Request(iframe_url)
35 req.add_header('Referer', url)
36 webpage = self._download_webpage(req, video_id)
37
38 escaped_data = self._search_regex(
39 r'unescape\("([^"]+)"\)', webpage, 'escaped data')
40 playlist = compat_urllib_parse.unquote(escaped_data)
41
42 thumbnail = self._search_regex(
43 r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False)
44 video_url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL')
45 title = remove_start(self._html_search_regex(
46 r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ')
47
48 formats = [{
49 'format_id': 'sd',
50 'url': video_url,
51 }]
52 self._sort_formats(formats)
53
54 return {
55 'id': video_id,
56 'title': title,
57 'formats': formats,
58 'thumbnail': thumbnail,
59 'http_referer': iframe_url,
60 }