aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vier.py
blob: fe54ae47564695bb958feb42895ad7e7f91638a2 (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
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor


class VierIE(InfoExtractor):
    IE_NAME = 'vier'
    _VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
    _TESTS = [{
        'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
        'info_dict': {
            'id': '16129',
            'display_id': 'het-wordt-warm-de-moestuin',
            'ext': 'mp4',
            'title': 'Het wordt warm in De Moestuin',
            'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }, {
        'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
        'only_matching': True,
    }, {
        'url': 'http://www.vier.be/video/v3/embed/16129',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        embed_id = mobj.group('embed_id')
        display_id = mobj.group('display_id') or embed_id

        webpage = self._download_webpage(url, display_id)

        video_id = self._search_regex(
            r'"nid"\s*:\s*"(\d+)"', webpage, 'video id')
        application = self._search_regex(
            r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod')
        filename = self._search_regex(
            r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename')

        playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename)
        formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4')

        title = self._og_search_title(webpage, default=display_id)
        description = self._og_search_description(webpage, default=None)
        thumbnail = self._og_search_thumbnail(webpage, default=None)

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


class VierVideosIE(InfoExtractor):
    IE_NAME = 'vier:videos'
    _VALID_URL = r'https?://(?:www\.)?vier\.be/(?P<program>[^/]+)/videos(?:\?page=(?P<page>\d+))?$'
    _TESTS = [{
        'url': 'http://www.vier.be/demoestuin/videos',
        'info_dict': {
            'id': 'demoestuin',
        },
        'playlist_mincount': 153,
    }, {
        'url': 'http://www.vier.be/demoestuin/videos?page=6',
        'info_dict': {
            'id': 'demoestuin-page6',
        },
        'playlist_mincount': 20,
    }, {
        'url': 'http://www.vier.be/demoestuin/videos?page=7',
        'info_dict': {
            'id': 'demoestuin-page7',
        },
        'playlist_mincount': 13,
    }]

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

        webpage = self._download_webpage(url, program)

        page_id = mobj.group('page')
        if page_id:
            page_id = int(page_id)
            start_page = page_id
            last_page = start_page + 1
            playlist_id = '%s-page%d' % (program, page_id)
        else:
            start_page = 0
            last_page = int(self._search_regex(
                r'videos\?page=(\d+)">laatste</a>',
                webpage, 'last page', default=0)) + 1
            playlist_id = program

        entries = []
        for current_page_id in range(start_page, last_page):
            current_page = self._download_webpage(
                'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
                program,
                'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage
            page_entries = [
                self.url_result('http://www.vier.be' + video_url, 'Vier')
                for video_url in re.findall(
                    r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
            entries.extend(page_entries)

        return self.playlist_result(entries, playlist_id)