aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/foxnews.py
blob: 917f76b1effb3a2fff9d4f4c17c1cca348280132 (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
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    parse_iso8601,
    int_or_none,
)


class FoxNewsIE(InfoExtractor):
    _VALID_URL = r'https?://video\.foxnews\.com/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
    _TESTS = [
        {
            'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
            'md5': '32aaded6ba3ef0d1c04e238d01031e5e',
            'info_dict': {
                'id': '3937480',
                'ext': 'flv',
                'title': 'Frozen in Time',
                'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler',
                'duration': 265,
                'timestamp': 1304411491,
                'upload_date': '20110503',
                'thumbnail': 're:^https?://.*\.jpg$',
            },
        },
        {
            'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips',
            'md5': '5846c64a1ea05ec78175421b8323e2df',
            'info_dict': {
                'id': '3922535568001',
                'ext': 'mp4',
                'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
                'description': "Congressman discusses the president's executive action",
                'duration': 292,
                'timestamp': 1417662047,
                'upload_date': '20141204',
                'thumbnail': 're:^https?://.*\.jpg$',
            },
        },
        {
            'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
            'only_matching': True,
        },
    ]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        video = self._download_json(
            'http://video.foxnews.com/v/feed/video/%s.js?template=fox' % video_id, video_id)

        item = video['channel']['item']
        title = item['title']
        description = item['description']
        timestamp = parse_iso8601(item['dc-date'])

        media_group = item['media-group']
        duration = None
        formats = []
        for media in media_group['media-content']:
            attributes = media['@attributes']
            video_url = attributes['url']
            if video_url.endswith('.f4m'):
                formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id))
            elif video_url.endswith('.m3u8'):
                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv'))
            elif not video_url.endswith('.smil'):
                duration = int_or_none(attributes.get('duration'))
                formats.append({
                    'url': video_url,
                    'format_id': media['media-category']['@attributes']['label'],
                    'preference': 1,
                    'vbr': int_or_none(attributes.get('bitrate')),
                    'filesize': int_or_none(attributes.get('fileSize'))
                })
        self._sort_formats(formats)

        media_thumbnail = media_group['media-thumbnail']['@attributes']
        thumbnails = [{
            'url': media_thumbnail['url'],
            'width': int_or_none(media_thumbnail.get('width')),
            'height': int_or_none(media_thumbnail.get('height')),
        }] if media_thumbnail else []

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'duration': duration,
            'timestamp': timestamp,
            'formats': formats,
            'thumbnails': thumbnails,
        }