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