aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nbc.py
blob: 3e3de9e2d8c7ffea00415bfd378df43ca1d33135 (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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
from __future__ import unicode_literals

import re
import json

from .common import InfoExtractor
from ..compat import (
    compat_str,
    compat_HTTPError,
)
from ..utils import (
    ExtractorError,
    find_xpath_attr,
)


class NBCIE(InfoExtractor):
    _VALID_URL = r'http://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'

    _TESTS = [
        {
            'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
            # md5 checksum is not stable
            'info_dict': {
                'id': 'bTmnLCvIbaaH',
                'ext': 'flv',
                'title': 'I Am a Firefighter',
                'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.',
            },
        },
        {
            'url': 'http://www.nbc.com/the-tonight-show/episodes/176',
            'info_dict': {
                'id': 'XwU9KZkp98TH',
                'ext': 'flv',
                'title': 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen',
                'description': 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.',
            },
            'skip': 'Only works from US',
        },
    ]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)
        theplatform_url = self._search_regex(
            '(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
            webpage, 'theplatform url').replace('_no_endcard', '')
        if theplatform_url.startswith('//'):
            theplatform_url = 'http:' + theplatform_url
        return self.url_result(theplatform_url)


class NBCNewsIE(InfoExtractor):
    _VALID_URL = r'''(?x)https?://www\.nbcnews\.com/
        ((video/.+?/(?P<id>\d+))|
        ((?P<program>feature|nightly-news)/[^/]+/(?P<title>.+)))
        '''

    _TESTS = [
        {
            'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
            'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
            'info_dict': {
                'id': '52753292',
                'ext': 'flv',
                'title': 'Crew emerges after four-month Mars food study',
                'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
            },
        },
        {
            'url': 'http://www.nbcnews.com/feature/edward-snowden-interview/how-twitter-reacted-snowden-interview-n117236',
            'md5': 'b2421750c9f260783721d898f4c42063',
            'info_dict': {
                'id': 'I1wpAI_zmhsQ',
                'ext': 'mp4',
                'title': 'How Twitter Reacted To The Snowden Interview',
                'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
            },
            'add_ie': ['ThePlatform'],
        },
        {
            'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
            'md5': 'fdbf39ab73a72df5896b6234ff98518a',
            'info_dict': {
                'id': 'Wjf9EDR3A_60',
                'ext': 'mp4',
                'title': 'FULL EPISODE: Family Business',
                'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
            },
        },
        {
            'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
            'md5': 'b5dda8cddd8650baa0dcb616dd2cf60d',
            'info_dict': {
                'id': 'sekXqyTVnmN3',
                'ext': 'mp4',
                'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
                'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
            },
        },
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        if video_id is not None:
            all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
            info = all_info.find('video')

            return {
                'id': video_id,
                'title': info.find('headline').text,
                'ext': 'flv',
                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
                'description': compat_str(info.find('caption').text),
                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
            }
        else:
            # "feature" and "nightly-news" pages use theplatform.com
            title = mobj.group('title')
            webpage = self._download_webpage(url, title)
            program = mobj.group('program')
            if program == 'feature':
                bootstrap_json = self._search_regex(
                    r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json',
                    flags=re.MULTILINE)
            else:
                # nightly-news
                bootstrap_json = self._search_regex(
                    r'var playlistData = ({.+});\s*$', webpage, 'playlist data',
                    flags=re.MULTILINE)
            bootstrap = json.loads(bootstrap_json)
            info = bootstrap['results'][0]['video']
            mpxid = info['mpxId']

            base_urls = [
                info['fallbackPlaylistUrl'],
                info['associatedPlaylistUrl'],
            ]

            for base_url in base_urls:
                if not base_url:
                    continue
                playlist_url = base_url + '?form=MPXNBCNewsAPI'

                try:
                    all_videos = self._download_json(playlist_url, title)
                except ExtractorError as ee:
                    if isinstance(ee.cause, compat_HTTPError):
                        continue
                    raise

                if not all_videos or 'videos' not in all_videos:
                    continue

                try:
                    info = next(v for v in all_videos['videos'] if v['mpxId'] == mpxid)
                    break
                except StopIteration:
                    continue

            if info is None:
                raise ExtractorError('Could not find video in playlists')

            return {
                '_type': 'url',
                # We get the best quality video
                'url': info['videoAssets'][-1]['publicUrl'],
                'ie_key': 'ThePlatform',
            }