aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/gameone.py
blob: 3b3870878f4da1867229e9a44bc9a93f58ba0595 (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
# coding: utf-8
from __future__ import unicode_literals

import re
import xml.etree.ElementTree as ET

from .common import InfoExtractor
from ..utils import xpath_with_ns

NAMESPACE_MAP = {
    'media': 'http://search.yahoo.com/mrss/',
}

# URL prefix to download the mp4 files directly instead of streaming via rtmp
# Credits go to XBox-Maniac http://board.jdownloader.org/showpost.php?p=185835&postcount=31 
RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/'

class GameOneIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)'
    _TEST = {
        'url': 'http://www.gameone.de/tv/288',
        'md5': '136656b7fb4c9cb4a8e2d500651c499b',
        'info_dict': {
            'id': '288',
            'ext': 'mp4',
            'title': 'Game One - Folge 288',
            'duration': 1238,
            'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
            'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
            'age_limit': 16
        }
    }

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

        webpage = self._download_webpage(url, video_id)
        og_video = self._og_search_video_url(webpage, secure=False)
        description = self._html_search_meta('description', webpage)
        age_limit = int(self._search_regex(r'age=(\d+)', self._html_search_meta('age-de-meta-label', webpage), 'age_limit', '0'))
        mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss')

        mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss')
        title = mrss.find('.//item/title').text
        thumbnail = mrss.find('.//item/image').get('url')
        content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP))
        content_url = content.get('url')

        content = self._download_xml(content_url, video_id, 'Downloading media:content')
        rendition_items = content.findall('.//rendition')
        duration = int(rendition_items[0].get('duration'))
        formats = [
                {
                    'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text),
                    'width': int(r.get('width')),
                    'height': int(r.get('height')),
                    'tbr': int(r.get('bitrate')),
                }
            for r in rendition_items
        ]

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