aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/servingsys.py
blob: 16dc3736b48bfb15a94b98713beef4757446b642 (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
from __future__ import unicode_literals

import re

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


class ServingSysIE(InfoExtractor):
    _VALID_URL = r'https?://(?:[^.]+\.)?serving-sys\.com/BurstingPipe/adServer\.bs\?.*?&pli=(?P<id>[0-9]+)'

    _TEST = {
        'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?',
        'playlist': [{
            'file': '29955898.flv',
            'md5': 'baed851342df6846eb8677a60a011a0f',
            'info_dict': {
                'title': 'AdAPPter_Hyundai_demo (1)',
                'duration': 74,
                'tbr': 1378,
                'width': 640,
                'height': 400,
            },
        }, {
            'file': '29907998.flv',
            'md5': '979b4da2655c4bc2d81aeb915a8c5014',
            'info_dict': {
                'title': 'AdAPPter_Hyundai_demo (2)',
                'duration': 34,
                'width': 854,
                'height': 480,
                'tbr': 516,
            },
        }],
        'params': {
            'playlistend': 2,
        },
        'skip': 'Blocked in the US [sic]',
    }

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

        vast_doc = self._download_xml(url, pl_id)
        title = vast_doc.find('.//AdTitle').text
        media = vast_doc.find('.//MediaFile').text
        info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL')

        doc = self._download_xml(info_url, pl_id, 'Downloading video info')
        entries = [{
            '_type': 'video',
            'id': a.attrib['id'],
            'title': '%s (%s)' % (title, a.attrib['assetID']),
            'url': a.attrib['URL'],
            'duration': int_or_none(a.attrib.get('length')),
            'tbr': int_or_none(a.attrib.get('bitrate')),
            'height': int_or_none(a.attrib.get('height')),
            'width': int_or_none(a.attrib.get('width')),
        } for a in doc.findall('.//AdditionalAssets/asset')]

        return {
            '_type': 'playlist',
            'id': pl_id,
            'title': title,
            'entries': entries,
        }