]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/krasview.py
6f3d2345b6f976ff9b380a04014f20df18483e6e
[youtubedl] / youtube_dl / extractor / krasview.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5 import re
6
7 from .common import InfoExtractor
8 from ..utils import (
9 int_or_none,
10 unescapeHTML,
11 )
12
13
14 class KrasViewIE(InfoExtractor):
15 IE_DESC = 'Красвью'
16 _VALID_URL = r'https?://krasview\.ru/video/(?P<id>\d+)'
17
18 _TEST = {
19 'url': 'http://krasview.ru/video/512228',
20 'md5': '3b91003cf85fc5db277870c8ebd98eae',
21 'info_dict': {
22 'id': '512228',
23 'ext': 'mp4',
24 'title': 'Снег, лёд, заносы',
25 'description': 'Снято в городе Нягань, в Ханты-Мансийском автономном округе.',
26 'duration': 27,
27 'thumbnail': 're:^https?://.*\.jpg',
28 },
29 }
30
31 def _real_extract(self, url):
32 mobj = re.match(self._VALID_URL, url)
33 video_id = mobj.group('id')
34
35 webpage = self._download_webpage(url, video_id)
36
37 flashvars = json.loads(self._search_regex(
38 r'flashvars\s*:\s*({.+?})\s*}\);', webpage, 'flashvars'))
39
40 video_url = flashvars['url']
41 title = unescapeHTML(flashvars['title'])
42 description = unescapeHTML(flashvars.get('subtitle') or self._og_search_description(webpage, default=None))
43 thumbnail = flashvars['image']
44 duration = int(flashvars['duration'])
45 filesize = int(flashvars['size'])
46 width = int_or_none(self._og_search_property('video:width', webpage, 'video width'))
47 height = int_or_none(self._og_search_property('video:height', webpage, 'video height'))
48
49 return {
50 'id': video_id,
51 'url': video_url,
52 'title': title,
53 'description': description,
54 'thumbnail': thumbnail,
55 'duration': duration,
56 'filesize': filesize,
57 'width': width,
58 'height': height,
59 }