]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/plays.py
New upstream version 2020.06.16.1
[youtubedl] / youtube_dl / extractor / plays.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import int_or_none
8
9
10 class PlaysTVIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?plays\.tv/(?:video|embeds)/(?P<id>[0-9a-f]{18})'
12 _TESTS = [{
13 'url': 'https://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall',
14 'md5': 'dfeac1198506652b5257a62762cec7bc',
15 'info_dict': {
16 'id': '56af17f56c95335490',
17 'ext': 'mp4',
18 'title': 'Bjergsen - When you outplay the Azir wall',
19 'description': 'Posted by Bjergsen',
20 }
21 }, {
22 'url': 'https://plays.tv/embeds/56af17f56c95335490',
23 'only_matching': True,
24 }]
25
26 def _real_extract(self, url):
27 video_id = self._match_id(url)
28 webpage = self._download_webpage(
29 'https://plays.tv/video/%s' % video_id, video_id)
30
31 info = self._search_json_ld(webpage, video_id,)
32
33 mpd_url, sources = re.search(
34 r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>',
35 webpage).groups()
36 formats = self._extract_mpd_formats(
37 self._proto_relative_url(mpd_url), video_id, mpd_id='DASH')
38 for format_id, height, format_url in re.findall(r'<source\s+res="((\d+)h?)"\s+src="([^"]+)"', sources):
39 formats.append({
40 'url': self._proto_relative_url(format_url),
41 'format_id': 'http-' + format_id,
42 'height': int_or_none(height),
43 })
44 self._sort_formats(formats)
45
46 info.update({
47 'id': video_id,
48 'description': self._og_search_description(webpage),
49 'thumbnail': info.get('thumbnail') or self._og_search_thumbnail(webpage),
50 'formats': formats,
51 })
52
53 return info