]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/popcorntv.py
Fix extraction from youtube.
[youtubedl] / youtube_dl / extractor / popcorntv.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 extract_attributes,
8 int_or_none,
9 unified_timestamp,
10 )
11
12
13 class PopcornTVIE(InfoExtractor):
14 _VALID_URL = r'https?://[^/]+\.popcorntv\.it/guarda/(?P<display_id>[^/]+)/(?P<id>\d+)'
15 _TESTS = [{
16 'url': 'https://animemanga.popcorntv.it/guarda/food-wars-battaglie-culinarie-episodio-01/9183',
17 'md5': '47d65a48d147caf692ab8562fe630b45',
18 'info_dict': {
19 'id': '9183',
20 'display_id': 'food-wars-battaglie-culinarie-episodio-01',
21 'ext': 'mp4',
22 'title': 'Food Wars, Battaglie Culinarie | Episodio 01',
23 'description': 'md5:b8bea378faae4651d3b34c6e112463d0',
24 'thumbnail': r're:^https?://.*\.jpg$',
25 'timestamp': 1497610857,
26 'upload_date': '20170616',
27 'duration': 1440,
28 'view_count': int,
29 },
30 }, {
31 'url': 'https://cinema.popcorntv.it/guarda/smash-cut/10433',
32 'only_matching': True,
33 }]
34
35 def _real_extract(self, url):
36 mobj = re.match(self._VALID_URL, url)
37 display_id, video_id = mobj.group('display_id', 'id')
38
39 webpage = self._download_webpage(url, display_id)
40
41 m3u8_url = extract_attributes(
42 self._search_regex(
43 r'(<link[^>]+itemprop=["\'](?:content|embed)Url[^>]*>)',
44 webpage, 'content'
45 ))['href']
46
47 formats = self._extract_m3u8_formats(
48 m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native',
49 m3u8_id='hls')
50
51 title = self._search_regex(
52 r'<h1[^>]+itemprop=["\']name[^>]*>([^<]+)', webpage,
53 'title', default=None) or self._og_search_title(webpage)
54
55 description = self._html_search_regex(
56 r'(?s)<article[^>]+itemprop=["\']description[^>]*>(.+?)</article>',
57 webpage, 'description', fatal=False)
58 thumbnail = self._og_search_thumbnail(webpage)
59 timestamp = unified_timestamp(self._html_search_meta(
60 'uploadDate', webpage, 'timestamp'))
61 duration = int_or_none(self._html_search_meta(
62 'duration', webpage), invscale=60)
63 view_count = int_or_none(self._html_search_meta(
64 'interactionCount', webpage, 'view count'))
65
66 return {
67 'id': video_id,
68 'display_id': display_id,
69 'title': title,
70 'description': description,
71 'thumbnail': thumbnail,
72 'timestamp': timestamp,
73 'duration': duration,
74 'view_count': view_count,
75 'formats': formats,
76 }