about summary refs log tree commit diff
path: root/youtube_dl/extractor/hitbox.py
blob: 1d905dc81d925f89a5c8f7a4a23c1e62238d01b5 (plain) (blame)
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
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    clean_html,
    parse_iso8601,
    float_or_none,
    int_or_none,
    compat_str,
    determine_ext,
)


class HitboxIE(InfoExtractor):
    IE_NAME = 'hitbox'
    _VALID_URL = r'https?://(?:www\.)?(?:hitbox|smashcast)\.tv/(?:[^/]+/)*videos?/(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://www.hitbox.tv/video/203213',
        'info_dict': {
            'id': '203213',
            'title': 'hitbox @ gamescom, Sub Button Hype extended, Giveaway - hitbox News Update with Oxy',
            'alt_title': 'hitboxlive - Aug 9th #6',
            'description': '',
            'ext': 'mp4',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 215.1666,
            'resolution': 'HD 720p',
            'uploader': 'hitboxlive',
            'view_count': int,
            'timestamp': 1407576133,
            'upload_date': '20140809',
            'categories': ['Live Show'],
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }, {
        'url': 'https://www.smashcast.tv/hitboxlive/videos/203213',
        'only_matching': True,
    }]

    def _extract_metadata(self, url, video_id):
        thumb_base = 'https://edge.sf.hitbox.tv'
        metadata = self._download_json(
            '%s/%s' % (url, video_id), video_id, 'Downloading metadata JSON')

        date = 'media_live_since'
        media_type = 'livestream'
        if metadata.get('media_type') == 'video':
            media_type = 'video'
            date = 'media_date_added'

        video_meta = metadata.get(media_type, [])[0]
        title = video_meta.get('media_status')
        alt_title = video_meta.get('media_title')
        description = clean_html(
            video_meta.get('media_description') or
            video_meta.get('media_description_md'))
        duration = float_or_none(video_meta.get('media_duration'))
        uploader = video_meta.get('media_user_name')
        views = int_or_none(video_meta.get('media_views'))
        timestamp = parse_iso8601(video_meta.get(date), ' ')
        categories = [video_meta.get('category_name')]
        thumbs = [{
            'url': thumb_base + video_meta.get('media_thumbnail'),
            'width': 320,
            'height': 180
        }, {
            'url': thumb_base + video_meta.get('media_thumbnail_large'),
            'width': 768,
            'height': 432
        }]

        return {
            'id': video_id,
            'title': title,
            'alt_title': alt_title,
            'description': description,
            'ext': 'mp4',
            'thumbnails': thumbs,
            'duration': duration,
            'uploader': uploader,
            'view_count': views,
            'timestamp': timestamp,
            'categories': categories,
        }

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

        player_config = self._download_json(
            'https://www.smashcast.tv/api/player/config/video/%s' % video_id,
            video_id, 'Downloading video JSON')

        formats = []
        for video in player_config['clip']['bitrates']:
            label = video.get('label')
            if label == 'Auto':
                continue
            video_url = video.get('url')
            if not video_url:
                continue
            bitrate = int_or_none(video.get('bitrate'))
            if determine_ext(video_url) == 'm3u8':
                if not video_url.startswith('http'):
                    continue
                formats.append({
                    'url': video_url,
                    'ext': 'mp4',
                    'tbr': bitrate,
                    'format_note': label,
                    'protocol': 'm3u8_native',
                })
            else:
                formats.append({
                    'url': video_url,
                    'tbr': bitrate,
                    'format_note': label,
                })
        self._sort_formats(formats)

        metadata = self._extract_metadata(
            'https://www.smashcast.tv/api/media/video', video_id)
        metadata['formats'] = formats

        return metadata


class HitboxLiveIE(HitboxIE):
    IE_NAME = 'hitbox:live'
    _VALID_URL = r'https?://(?:www\.)?(?:hitbox|smashcast)\.tv/(?P<id>[^/?#&]+)'
    _TESTS = [{
        'url': 'http://www.hitbox.tv/dimak',
        'info_dict': {
            'id': 'dimak',
            'ext': 'mp4',
            'description': 'md5:c9f80fa4410bc588d7faa40003fc7d0e',
            'timestamp': int,
            'upload_date': compat_str,
            'title': compat_str,
            'uploader': 'Dimak',
        },
        'params': {
            # live
            'skip_download': True,
        },
    }, {
        'url': 'https://www.smashcast.tv/dimak',
        'only_matching': True,
    }]

    @classmethod
    def suitable(cls, url):
        return False if HitboxIE.suitable(url) else super(HitboxLiveIE, cls).suitable(url)

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

        player_config = self._download_json(
            'https://www.smashcast.tv/api/player/config/live/%s' % video_id,
            video_id)

        formats = []
        cdns = player_config.get('cdns')
        servers = []
        for cdn in cdns:
            # Subscribe URLs are not playable
            if cdn.get('rtmpSubscribe') is True:
                continue
            base_url = cdn.get('netConnectionUrl')
            host = re.search(r'.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1)
            if base_url not in servers:
                servers.append(base_url)
                for stream in cdn.get('bitrates'):
                    label = stream.get('label')
                    if label == 'Auto':
                        continue
                    stream_url = stream.get('url')
                    if not stream_url:
                        continue
                    bitrate = int_or_none(stream.get('bitrate'))
                    if stream.get('provider') == 'hls' or determine_ext(stream_url) == 'm3u8':
                        if not stream_url.startswith('http'):
                            continue
                        formats.append({
                            'url': stream_url,
                            'ext': 'mp4',
                            'tbr': bitrate,
                            'format_note': label,
                            'rtmp_live': True,
                        })
                    else:
                        formats.append({
                            'url': '%s/%s' % (base_url, stream_url),
                            'ext': 'mp4',
                            'tbr': bitrate,
                            'rtmp_live': True,
                            'format_note': host,
                            'page_url': url,
                            'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf',
                        })
        self._sort_formats(formats)

        metadata = self._extract_metadata(
            'https://www.smashcast.tv/api/media/live', video_id)
        metadata['formats'] = formats
        metadata['is_live'] = True
        metadata['title'] = self._live_title(metadata.get('title'))

        return metadata