aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/cbsnews.py
blob: f0de73aebccf3fd1bea305f9fba086b34a228d17 (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
121
122
123
124
125
126
127
128
129
# encoding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from .theplatform import ThePlatformIE
from ..utils import parse_duration


class CBSNewsIE(ThePlatformIE):
    IE_DESC = 'CBS News'
    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:news|videos)/(?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': 'mp4',
                'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
                'thumbnail': 're:^https?://.*\.jpg$',
                'duration': 205,
                'subtitles': {
                    'en': [{
                        'ext': 'ttml',
                    }],
                },
            },
            'params': {
                # m3u8 download
                'skip_download': True,
            },
        },
    ]

    def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
        closed_caption_e = smil.find(self._xpath_ns('.//param[@name=\'ClosedCaptionURL\']', namespace))
        return {
            'en': [{
                'ext': 'ttml',
                'url': closed_caption_e.attrib['value'],
            }]
        } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []

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

        webpage = self._download_webpage(url, video_id)

        video_info = self._parse_json(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'), video_id)

        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')

        subtitles = {}
        formats = []
        for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
            pid = item.get('media' + format_id)
            if not pid:
                continue
            release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?format=SMIL&mbr=true' % pid
            tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
            formats.extend(tp_formats)
            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
        self._sort_formats(formats)

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


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

    _TEST = {
        'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
        'info_dict': {
            'id': 'clinton-sanders-prepare-to-face-off-in-nh',
            'ext': 'flv',
            'title': 'Clinton, Sanders Prepare To Face Off In NH',
            'duration': 334,
        },
    }

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

        webpage = self._download_webpage(url, video_id)

        video_info = self._parse_json(self._html_search_regex(
            r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']

        hdcore_sign = 'hdcore=3.3.1'
        f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
        if f4m_formats:
            for entry in f4m_formats:
                # URLs without the extra param induce an 404 error
                entry.update({'extra_param_to_segment_url': hdcore_sign})

        return {
            'id': video_id,
            'title': video_info['headline'],
            'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
            'duration': parse_duration(video_info.get('segmentDur')),
            'formats': f4m_formats,
        }