aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/orf.py
blob: 41ef8e992ac8f898de90f775b72cbc133caec805 (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
# coding: utf-8

import re
import xml.etree.ElementTree
import json

from .common import InfoExtractor
from ..utils import (
    compat_urlparse,
    ExtractorError,
    find_xpath_attr,
)

class ORFIE(InfoExtractor):
    _VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'

    _TEST = {
        u'url': u'http://tvthek.orf.at/programs/1171769-Wetter-ZIB/episodes/6557323-Wetter',
        u'file': u'6566957.flv',
        u'info_dict': {
            u'title': u'Wetter',
            u'description': u'Christa Kummer, Marcus Wadsak und Kollegen  präsentieren abwechselnd ihre täglichen Wetterprognosen für Österreich.\r \r Mehr Wetter unter wetter.ORF.at',
        },
        u'params': {
            # It uses rtmp
            u'skip_download': True,
        }
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        playlist_id = mobj.group('id')
        webpage = self._download_webpage(url, playlist_id)

        flash_xml = self._search_regex('ORF.flashXML = \'(.+?)\'', webpage, u'flash xml')
        flash_xml = compat_urlparse.parse_qs('xml='+flash_xml)['xml'][0]
        flash_config = xml.etree.ElementTree.fromstring(flash_xml.encode('utf-8'))
        playlist_json = self._search_regex(r'playlist\': \'(\[.*?\])\'', webpage, u'playlist').replace(r'\"','"')
        playlist = json.loads(playlist_json)

        videos = []
        ns = '{http://tempuri.org/XMLSchema.xsd}'
        xpath = '%(ns)sPlaylist/%(ns)sItems/%(ns)sItem' % {'ns': ns}
        webpage_description = self._og_search_description(webpage)
        for (i, (item, info)) in enumerate(zip(flash_config.findall(xpath), playlist), 1):
            # Get best quality url
            rtmp_url = None
            for q in ['Q6A', 'Q4A', 'Q1A']:
                video_url = find_xpath_attr(item, '%sVideoUrl' % ns, 'quality', q)
                if video_url is not None:
                    rtmp_url = video_url.text
                    break
            if rtmp_url is None:
                raise ExtractorError(u'Couldn\'t get video url: %s' % info['id'])
            description = self._html_search_regex(
                r'id="playlist_entry_%s".*?<p>(.*?)</p>' % i, webpage,
                u'description', default=webpage_description, flags=re.DOTALL)
            videos.append({
                '_type': 'video',
                'id': info['id'],
                'title': info['title'],
                'url': rtmp_url,
                'ext': 'flv',
                'description': description,
                })

        return videos