]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mpora.py
6db3c67a5a471d9cd850ad3bd828a9e2478c00e3
[youtubedl] / youtube_dl / extractor / mpora.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import int_or_none
5
6
7 class MporaIE(InfoExtractor):
8 _VALID_URL = r'https?://(www\.)?mpora\.(?:com|de)/videos/(?P<id>[^?#/]+)'
9 IE_NAME = 'MPORA'
10
11 _TEST = {
12 'url': 'http://mpora.de/videos/AAdo8okx4wiz/embed?locale=de',
13 'md5': 'a7a228473eedd3be741397cf452932eb',
14 'info_dict': {
15 'id': 'AAdo8okx4wiz',
16 'ext': 'mp4',
17 'title': 'Katy Curd - Winter in the Forest',
18 'duration': 416,
19 'uploader': 'Peter Newman Media',
20 },
21 }
22
23 def _real_extract(self, url):
24 video_id = self._match_id(url)
25 webpage = self._download_webpage(url, video_id)
26
27 data_json = self._search_regex(
28 r"new FM\.Player\('[^']+',\s*(\{.*?)\).player;", webpage, 'json')
29 data = self._parse_json(data_json, video_id)
30
31 uploader = data['info_overlay'].get('username')
32 duration = data['video']['duration'] // 1000
33 thumbnail = data['video']['encodings']['sd']['poster']
34 title = data['info_overlay']['title']
35
36 formats = []
37 for encoding_id, edata in data['video']['encodings'].items():
38 for src in edata['sources']:
39 width_str = self._search_regex(
40 r'_([0-9]+)\.[a-zA-Z0-9]+$', src['src'],
41 False, default=None)
42 vcodec = src['type'].partition('/')[2]
43
44 formats.append({
45 'format_id': encoding_id + '-' + vcodec,
46 'url': src['src'],
47 'vcodec': vcodec,
48 'width': int_or_none(width_str),
49 })
50
51 self._sort_formats(formats)
52
53 return {
54 'id': video_id,
55 'title': title,
56 'formats': formats,
57 'uploader': uploader,
58 'duration': duration,
59 'thumbnail': thumbnail,
60 }