aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/piksel.py
blob: 88b6859b01a7c51eebe9f129d759f68005c75ce6 (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    ExtractorError,
    dict_get,
    int_or_none,
    unescapeHTML,
    parse_iso8601,
)


class PikselIE(InfoExtractor):
    _VALID_URL = r'https?://player\.piksel\.com/v/(?:refid/[^/]+/prefid/)?(?P<id>[a-z0-9_]+)'
    _TESTS = [
        {
            'url': 'http://player.piksel.com/v/ums2867l',
            'md5': '34e34c8d89dc2559976a6079db531e85',
            'info_dict': {
                'id': 'ums2867l',
                'ext': 'mp4',
                'title': 'GX-005 with Caption',
                'timestamp': 1481335659,
                'upload_date': '20161210'
            }
        },
        {
            # Original source: http://www.uscourts.gov/cameras-courts/state-washington-vs-donald-j-trump-et-al
            'url': 'https://player.piksel.com/v/v80kqp41',
            'md5': '753ddcd8cc8e4fa2dda4b7be0e77744d',
            'info_dict': {
                'id': 'v80kqp41',
                'ext': 'mp4',
                'title': 'WAW- State of Washington vs. Donald J. Trump, et al',
                'description': 'State of Washington vs. Donald J. Trump, et al, Case Number 17-CV-00141-JLR, TRO Hearing, Civil Rights Case, 02/3/2017, 1:00 PM (PST), Seattle Federal Courthouse, Seattle, WA, Judge James L. Robart presiding.',
                'timestamp': 1486171129,
                'upload_date': '20170204'
            }
        },
        {
            # https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2019240/
            'url': 'http://player.piksel.com/v/refid/nhkworld/prefid/nw_vod_v_en_2019_240_20190823233000_02_1566873477',
            'only_matching': True,
        }
    ]

    @staticmethod
    def _extract_url(webpage):
        mobj = re.search(
            r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//player\.piksel\.com/v/[a-z0-9]+)',
            webpage)
        if mobj:
            return mobj.group('url')

    def _real_extract(self, url):
        display_id = self._match_id(url)
        webpage = self._download_webpage(url, display_id)
        video_id = self._search_regex(
            r'data-de-program-uuid=[\'"]([a-z0-9]+)',
            webpage, 'program uuid', default=display_id)
        app_token = self._search_regex([
            r'clientAPI\s*:\s*"([^"]+)"',
            r'data-de-api-key\s*=\s*"([^"]+)"'
        ], webpage, 'app token')
        response = self._download_json(
            'http://player.piksel.com/ws/ws_program/api/%s/mode/json/apiv/5' % app_token,
            video_id, query={
                'v': video_id
            })['response']
        failure = response.get('failure')
        if failure:
            raise ExtractorError(response['failure']['reason'], expected=True)
        video_data = response['WsProgramResponse']['program']['asset']
        title = video_data['title']

        formats = []

        m3u8_url = dict_get(video_data, [
            'm3u8iPadURL',
            'ipadM3u8Url',
            'm3u8AndroidURL',
            'm3u8iPhoneURL',
            'iphoneM3u8Url'])
        if m3u8_url:
            formats.extend(self._extract_m3u8_formats(
                m3u8_url, video_id, 'mp4', 'm3u8_native',
                m3u8_id='hls', fatal=False))

        asset_type = dict_get(video_data, ['assetType', 'asset_type'])
        for asset_file in video_data.get('assetFiles', []):
            # TODO: extract rtmp formats
            http_url = asset_file.get('http_url')
            if not http_url:
                continue
            tbr = None
            vbr = int_or_none(asset_file.get('videoBitrate'), 1024)
            abr = int_or_none(asset_file.get('audioBitrate'), 1024)
            if asset_type == 'video':
                tbr = vbr + abr
            elif asset_type == 'audio':
                tbr = abr

            format_id = ['http']
            if tbr:
                format_id.append(compat_str(tbr))

            formats.append({
                'format_id': '-'.join(format_id),
                'url': unescapeHTML(http_url),
                'vbr': vbr,
                'abr': abr,
                'width': int_or_none(asset_file.get('videoWidth')),
                'height': int_or_none(asset_file.get('videoHeight')),
                'filesize': int_or_none(asset_file.get('filesize')),
                'tbr': tbr,
            })
        self._sort_formats(formats)

        subtitles = {}
        for caption in video_data.get('captions', []):
            caption_url = caption.get('url')
            if caption_url:
                subtitles.setdefault(caption.get('locale', 'en'), []).append({
                    'url': caption_url})

        return {
            'id': video_id,
            'title': title,
            'description': video_data.get('description'),
            'thumbnail': video_data.get('thumbnailUrl'),
            'timestamp': parse_iso8601(video_data.get('dateadd')),
            'formats': formats,
            'subtitles': subtitles,
        }