summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/walla.py
blob: 442a9bcf9fc1dd6822611ce8e78c4798a798acce (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
import re

from .common import InfoExtractor
from ..utils import (
    int_or_none,
    xpath_text,
)


class WallaIE(InfoExtractor):
    _VALID_URL = r'https?://vod\.walla\.co\.il/[^/]+/(?P<id>\d+)/(?P<display_id>.+)'
    _TEST = {
        'url': 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one',
        'info_dict': {
            'id': '2642630',
            'display_id': 'one-direction-all-for-one',
            'ext': 'flv',
            'title': 'וואן דיירקשן: ההיסטריה',
            'description': 'md5:de9e2512a92442574cdb0913c49bc4d8',
            'thumbnail': r're:^https?://.*\.jpg',
            'duration': 3600,
        },
        'params': {
            # rtmp download
            'skip_download': True,
        },
    }

    _SUBTITLE_LANGS = {
        'עברית': 'heb',
    }

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

        video = self._download_xml(
            f'http://video2.walla.co.il/?w=null/null/{video_id}/@@/video/flv_pl',
            display_id)

        item = video.find('./items/item')

        title = xpath_text(item, './title', 'title')
        description = xpath_text(item, './synopsis', 'description')
        thumbnail = xpath_text(item, './preview_pic', 'thumbnail')
        duration = int_or_none(xpath_text(item, './duration', 'duration'))

        subtitles = {}
        for subtitle in item.findall('./subtitles/subtitle'):
            lang = xpath_text(subtitle, './title')
            subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{
                'ext': 'srt',
                'url': xpath_text(subtitle, './src'),
            }]

        formats = []
        for quality in item.findall('./qualities/quality'):
            format_id = xpath_text(quality, './title')
            fmt = {
                'url': 'rtmp://wafla.walla.co.il/vod',
                'play_path': xpath_text(quality, './src'),
                'player_url': 'http://isc.walla.co.il/w9/swf/video_swf/vod/WallaMediaPlayerAvod.swf',
                'page_url': url,
                'ext': 'flv',
                'format_id': xpath_text(quality, './title'),
            }
            m = re.search(r'^(?P<height>\d+)[Pp]', format_id)
            if m:
                fmt['height'] = int(m.group('height'))
            formats.append(fmt)

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