aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/twitcasting.py
blob: 05f8aa9ce5494c3162cb9c774227c933d45fdd50 (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
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor

import re


class TwitCastingIE(InfoExtractor):
    _VALID_URL = r'https?://(?:[^/]+\.)?twitcasting\.tv/(?P<uploader_id>[^/]+)/movie/(?P<id>\d+)'
    _TEST = {
        'url': 'https://twitcasting.tv/ivetesangalo/movie/2357609',
        'md5': '745243cad58c4681dc752490f7540d7f',
        'info_dict': {
            'id': '2357609',
            'ext': 'mp4',
            'title': 'Recorded Live #2357609',
            'uploader_id': 'ivetesangalo',
            'description': "Moi! I'm live on TwitCasting from my iPhone.",
            'thumbnail': r're:^https?://.*\.jpg$',
        },
        'params': {
            'skip_download': True,
        },
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        uploader_id = mobj.group('uploader_id')

        webpage = self._download_webpage(url, video_id)

        title = self._html_search_regex(
            r'(?s)<[^>]+id=["\']movietitle[^>]+>(.+?)</',
            webpage, 'title', default=None) or self._html_search_meta(
            'twitter:title', webpage, fatal=True)

        m3u8_url = self._search_regex(
            (r'data-movie-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
             r'(["\'])(?P<url>http.+?\.m3u8.*?)\1'),
            webpage, 'm3u8 url', group='url')

        formats = self._extract_m3u8_formats(
            m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
            m3u8_id='hls')

        thumbnail = self._og_search_thumbnail(webpage)
        description = self._og_search_description(
            webpage, default=None) or self._html_search_meta(
            'twitter:description', webpage)

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