aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/keek.py
blob: 24f5c7cb71e727bd0ed3df7e7b873c63ff6e0a9f (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
from __future__ import unicode_literals

import re

from .common import InfoExtractor


class KeekIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?keek\.com/keek/(?P<id>\w+)'
    IE_NAME = 'keek'
    _TEST = {
        'url': 'https://www.keek.com/keek/NODfbab',
        'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
        'info_dict': {
            'id': 'NODfbab',
            'ext': 'mp4',
            'title': 'test chars: "\'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de . - Video - Videos on Keek',
            'description': 'test chars: "\'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .',
            'uploader': 'ytdl',
            'uploader_id': 'eGT5bab',
        },
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)
        uploader = uploader_id = None
        matches = re.search(r'data-username="(?P<uploader>[^"]+)"[^>]*data-user-id="(?P<uploader_id>[^"]+)"', webpage)
        if matches:
            uploader, uploader_id = matches.groups()

        return {
            'id': video_id,
            'url': self._og_search_video_url(webpage),
            'ext': 'mp4',
            'title': self._og_search_title(webpage),
            'description': self._og_search_description(webpage),
            'thumbnail': self._og_search_thumbnail(webpage),
            'uploader': uploader,
            'uploader_id': uploader_id,
        }