aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/cbsnews.py
blob: 7b9dd67fd6f57275e68dddf29a35cad5b98d553b (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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
# encoding: utf-8
from __future__ import unicode_literals

import re
import json

from .common import InfoExtractor
from ..utils import remove_start


class CBSNewsIE(InfoExtractor):
    IE_DESC = 'CBS News'
    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)'

    _TESTS = [
        {
            'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
            'info_dict': {
                'id': 'tesla-and-spacex-elon-musks-industrial-empire',
                'ext': 'flv',
                'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire',
                'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg',
                'duration': 791,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            },
        },
        {
            'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
            'info_dict': {
                'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
                'ext': 'flv',
                'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
                'thumbnail': 're:^https?://.*\.jpg$',
                'duration': 205,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            },
        },
        {
            'url': 'http://www.cbsnews.com/videos/mountain-lions-of-l-a/',
            'info_dict': {
                'id': 'Mountain Lions of L.A.',
                'ext': 'flv',
                'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
                'thumbnail': 're:^http?://.*\.jpg$',
                'subtitles': 're:^http?://.*\.xml$',
                'duration': 787,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            },
        },
    ]

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

        webpage = self._download_webpage(url, video_id)

        video_info = json.loads(self._html_search_regex(
            r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
            webpage, 'video JSON info'))

        item = video_info['item'] if 'item' in video_info else video_info
        title = item.get('articleTitle') or item.get('hed')
        duration = item.get('duration')
        thumbnail = item.get('mediaImage') or item.get('thumbnail')

        formats = []
        for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
            uri = item.get('media' + format_id + 'URI')
            if not uri:
                continue
            uri = remove_start(uri, '{manifest:none}')
            fmt = {
                'url': uri,
                'format_id': format_id,
            }
            if uri.startswith('rtmp'):
                play_path = re.sub(
                    r'{slistFilePath}', '',
                    uri.split('<break>')[-1].split('{break}')[-1])
                play_path = re.sub(
                    r'{manifest:.+}.*$', '', play_path)
                fmt.update({
                    'app': 'ondemand?auth=cbs',
                    'play_path': 'mp4:' + play_path,
                    'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
                    'page_url': 'http://www.cbsnews.com',
                    'ext': 'flv',
                })
            elif uri.endswith('.m3u8'):
                fmt['ext'] = 'mp4'
            formats.append(fmt)

        if 'mpxRefId' in video_info:
            cap_url = 'http://www.cbsnews.com/videos/captions/%s.adb_xml' % video_info['mpxRefId']
            subtitles = {
                'en': [{
                    'url': cap_url,
                    'ext': 'xml'
                }], }
        else:
            subtitles = {}

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