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
|
import re
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
qualities,
)
class ClippitIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clippituser\.tv/c/(?P<id>[a-z]+)'
_TEST = {
'url': 'https://www.clippituser.tv/c/evmgm',
'md5': '963ae7a59a2ec4572ab8bf2f2d2c5f09',
'info_dict': {
'id': 'evmgm',
'ext': 'mp4',
'title': 'Bye bye Brutus. #BattleBots - Clippit',
'uploader': 'lizllove',
'uploader_url': 'https://www.clippituser.tv/p/lizllove',
'timestamp': 1472183818,
'upload_date': '20160826',
'description': 'BattleBots | ABC',
'thumbnail': r're:^https?://.*\.jpg$',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title.*>(.+?)</title>', webpage, 'title')
FORMATS = ('sd', 'hd')
quality = qualities(FORMATS)
formats = []
for format_id in FORMATS:
url = self._html_search_regex(rf'data-{format_id}-file="(.+?)"',
webpage, 'url', fatal=False)
if not url:
continue
match = re.search(r'/(?P<height>\d+)\.mp4', url)
formats.append({
'url': url,
'format_id': format_id,
'quality': quality(format_id),
'height': int(match.group('height')) if match else None,
})
uploader = self._html_search_regex(r'class="username".*>\s+(.+?)\n',
webpage, 'uploader', fatal=False)
uploader_url = ('https://www.clippituser.tv/p/' + uploader
if uploader else None)
timestamp = self._html_search_regex(r'datetime="(.+?)"',
webpage, 'date', fatal=False)
thumbnail = self._html_search_regex(r'data-image="(.+?)"',
webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'title': title,
'formats': formats,
'uploader': uploader,
'uploader_url': uploader_url,
'timestamp': parse_iso8601(timestamp),
'description': self._og_search_description(webpage),
'thumbnail': thumbnail,
}
|
