summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/unistra.py
blob: edc1f8554449dddce6e4e6463badc390b3e4eb45 (plain)
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
import re

from .common import InfoExtractor
from ..utils import qualities


class UnistraIE(InfoExtractor):
    _VALID_URL = r'https?://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)'

    _TESTS = [
        {
            'url': 'http://utv.unistra.fr/video.php?id_video=154',
            'md5': '736f605cfdc96724d55bb543ab3ced24',
            'info_dict': {
                'id': '154',
                'ext': 'mp4',
                'title': 'M!ss Yella',
                'description': 'md5:104892c71bd48e55d70b902736b81bbf',
            },
        },
        {
            'url': 'http://utv.unistra.fr/index.php?id_video=437',
            'md5': '1ddddd6cccaae76f622ce29b8779636d',
            'info_dict': {
                'id': '437',
                'ext': 'mp4',
                'title': 'Prix Louise Weiss 2014',
                'description': 'md5:cc3a8735f079f4fb6b0b570fc10c135a',
            },
        },
    ]

    def _real_extract(self, url):
        mobj = self._match_valid_url(url)
        video_id = mobj.group('id')

        webpage = self._download_webpage(url, video_id)

        files = set(re.findall(r'file\s*:\s*"(/[^"]+)"', webpage))

        quality = qualities(['SD', 'HD'])
        formats = []
        for file_path in files:
            format_id = 'HD' if file_path.endswith('-HD.mp4') else 'SD'
            formats.append({
                'url': f'http://vod-flash.u-strasbg.fr:8080{file_path}',
                'format_id': format_id,
                'quality': quality(format_id),
            })

        title = self._html_search_regex(
            r'<title>UTV - (.*?)</', webpage, 'title')
        description = self._html_search_regex(
            r'<meta name="Description" content="(.*?)"', webpage, 'description', flags=re.DOTALL)
        thumbnail = self._search_regex(
            r'image: "(.*?)"', webpage, 'thumbnail')

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'formats': formats,
        }