aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/newgrounds.py
blob: 0e26f8399dd8ea8777c28d0bb61483e27f954965 (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
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    extract_attributes,
    int_or_none,
    parse_duration,
    parse_filesize,
    unified_timestamp,
)


class NewgroundsIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'https://www.newgrounds.com/audio/listen/549479',
        'md5': 'fe6033d297591288fa1c1f780386f07a',
        'info_dict': {
            'id': '549479',
            'ext': 'mp3',
            'title': 'B7 - BusMode',
            'uploader': 'Burn7',
            'timestamp': 1378878540,
            'upload_date': '20130911',
            'duration': 143,
        },
    }, {
        'url': 'https://www.newgrounds.com/portal/view/673111',
        'md5': '3394735822aab2478c31b1004fe5e5bc',
        'info_dict': {
            'id': '673111',
            'ext': 'mp4',
            'title': 'Dancin',
            'uploader': 'Squirrelman82',
            'timestamp': 1460256780,
            'upload_date': '20160410',
        },
    }, {
        # source format unavailable, additional mp4 formats
        'url': 'http://www.newgrounds.com/portal/view/689400',
        'info_dict': {
            'id': '689400',
            'ext': 'mp4',
            'title': 'ZTV News Episode 8',
            'uploader': 'BennettTheSage',
            'timestamp': 1487965140,
            'upload_date': '20170224',
        },
        'params': {
            'skip_download': True,
        },
    }]

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

        webpage = self._download_webpage(url, media_id)

        title = self._html_search_regex(
            r'<title>([^>]+)</title>', webpage, 'title')

        media_url = self._parse_json(self._search_regex(
            r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id)

        formats = [{
            'url': media_url,
            'format_id': 'source',
            'quality': 1,
        }]

        max_resolution = int_or_none(self._search_regex(
            r'max_resolution["\']\s*:\s*(\d+)', webpage, 'max resolution',
            default=None))
        if max_resolution:
            url_base = media_url.rpartition('.')[0]
            for resolution in (360, 720, 1080):
                if resolution > max_resolution:
                    break
                formats.append({
                    'url': '%s.%dp.mp4' % (url_base, resolution),
                    'format_id': '%dp' % resolution,
                    'height': resolution,
                })

        self._check_formats(formats, media_id)
        self._sort_formats(formats)

        uploader = self._search_regex(
            r'(?:Author|Writer)\s*<a[^>]+>([^<]+)', webpage, 'uploader',
            fatal=False)

        timestamp = unified_timestamp(self._search_regex(
            r'<dt>Uploaded</dt>\s*<dd>([^<]+)', webpage, 'timestamp',
            default=None))
        duration = parse_duration(self._search_regex(
            r'<dd>Song\s*</dd><dd>.+?</dd><dd>([^<]+)', webpage, 'duration',
            default=None))

        filesize_approx = parse_filesize(self._html_search_regex(
            r'<dd>Song\s*</dd><dd>(.+?)</dd>', webpage, 'filesize',
            default=None))
        if len(formats) == 1:
            formats[0]['filesize_approx'] = filesize_approx

        if '<dd>Song' in webpage:
            formats[0]['vcodec'] = 'none'

        return {
            'id': media_id,
            'title': title,
            'uploader': uploader,
            'timestamp': timestamp,
            'duration': duration,
            'formats': formats,
        }


class NewgroundsPlaylistIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:collection|[^/]+/search/[^/]+)/(?P<id>[^/?#&]+)'
    _TESTS = [{
        'url': 'https://www.newgrounds.com/collection/cats',
        'info_dict': {
            'id': 'cats',
            'title': 'Cats',
        },
        'playlist_mincount': 46,
    }, {
        'url': 'http://www.newgrounds.com/portal/search/author/ZONE-SAMA',
        'info_dict': {
            'id': 'ZONE-SAMA',
            'title': 'Portal Search: ZONE-SAMA',
        },
        'playlist_mincount': 47,
    }, {
        'url': 'http://www.newgrounds.com/audio/search/title/cats',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(url, playlist_id)

        title = self._search_regex(
            r'<title>([^>]+)</title>', webpage, 'title', default=None)

        # cut left menu
        webpage = self._search_regex(
            r'(?s)<div[^>]+\bclass=["\']column wide(.+)',
            webpage, 'wide column', default=webpage)

        entries = []
        for a, path, media_id in re.findall(
                r'(<a[^>]+\bhref=["\']/?((?:portal/view|audio/listen)/(\d+))[^>]+>)',
                webpage):
            a_class = extract_attributes(a).get('class')
            if a_class not in ('item-portalsubmission', 'item-audiosubmission'):
                continue
            entries.append(
                self.url_result(
                    'https://www.newgrounds.com/%s' % path,
                    ie=NewgroundsIE.ie_key(), video_id=media_id))

        return self.playlist_result(entries, playlist_id, title)