ceskatelevize: Closed captions support
[youtube-dl] / youtube_dl / extractor / played.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5 import os.path
6
7 from .common import InfoExtractor
8 from ..compat import (
9     compat_urllib_parse,
10     compat_urllib_request,
11 )
12 from ..utils import (
13     ExtractorError,
14 )
15
16
17 class PlayedIE(InfoExtractor):
18     IE_NAME = 'played.to'
19     _VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
20
21     _TEST = {
22         'url': 'http://played.to/j2f2sfiiukgt',
23         'md5': 'c2bd75a368e82980e7257bf500c00637',
24         'info_dict': {
25             'id': 'j2f2sfiiukgt',
26             'ext': 'flv',
27             'title': 'youtube-dl_test_video.mp4',
28         },
29     }
30
31     def _real_extract(self, url):
32         video_id = self._match_id(url)
33         orig_webpage = self._download_webpage(url, video_id)
34
35         m_error = re.search(
36             r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
37         if m_error:
38             raise ExtractorError(m_error.group('msg'), expected=True)
39
40         fields = re.findall(
41             r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
42         data = dict(fields)
43
44         self._sleep(2, video_id)
45
46         post = compat_urllib_parse.urlencode(data)
47         headers = {
48             b'Content-Type': b'application/x-www-form-urlencoded',
49         }
50         req = compat_urllib_request.Request(url, post, headers)
51         webpage = self._download_webpage(
52             req, video_id, note='Downloading video page ...')
53
54         title = os.path.splitext(data['fname'])[0]
55
56         video_url = self._search_regex(
57             r'file: "?(.+?)",', webpage, 'video URL')
58
59         return {
60             'id': video_id,
61             'title': title,
62             'url': video_url,
63         }