]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/epidemicsound.py
[ie/matchtv] Fix extractor (#10190)
[yt-dlp.git] / yt_dlp / extractor / epidemicsound.py
1 from .common import InfoExtractor
2 from ..utils import (
3 float_or_none,
4 int_or_none,
5 orderedSet,
6 parse_iso8601,
7 parse_qs,
8 parse_resolution,
9 str_or_none,
10 traverse_obj,
11 url_or_none,
12 )
13
14
15 class EpidemicSoundIE(InfoExtractor):
16 _VALID_URL = r'https?://(?:www\.)?epidemicsound\.com/track/(?P<id>[0-9a-zA-Z]+)'
17 _TESTS = [{
18 'url': 'https://www.epidemicsound.com/track/yFfQVRpSPz/',
19 'md5': 'd98ff2ddb49e8acab9716541cbc9dfac',
20 'info_dict': {
21 'id': '45014',
22 'display_id': 'yFfQVRpSPz',
23 'ext': 'mp3',
24 'title': 'Door Knock Door 1',
25 'alt_title': 'Door Knock Door 1',
26 'tags': ['foley', 'door', 'knock', 'glass', 'window', 'glass door knock'],
27 'categories': ['Misc. Door'],
28 'duration': 1,
29 'thumbnail': 'https://cdn.epidemicsound.com/curation-assets/commercial-release-cover-images/default-sfx/3000x3000.jpg',
30 'timestamp': 1415320353,
31 'upload_date': '20141107',
32 },
33 }, {
34 'url': 'https://www.epidemicsound.com/track/mj8GTTwsZd/',
35 'md5': 'c82b745890f9baf18dc2f8d568ee3830',
36 'info_dict': {
37 'id': '148700',
38 'display_id': 'mj8GTTwsZd',
39 'ext': 'mp3',
40 'title': 'Noplace',
41 'tags': ['liquid drum n bass', 'energetic'],
42 'categories': ['drum and bass'],
43 'duration': 237,
44 'timestamp': 1694426482,
45 'thumbnail': 'https://cdn.epidemicsound.com/curation-assets/commercial-release-cover-images/11138/3000x3000.jpg',
46 'upload_date': '20230911',
47 'release_timestamp': 1700535606,
48 'release_date': '20231121',
49 },
50 }]
51
52 @staticmethod
53 def _epidemic_parse_thumbnail(url: str):
54 if not url_or_none(url):
55 return None
56
57 return {
58 'url': url,
59 **(traverse_obj(url, ({parse_qs}, {
60 'width': ('width', 0, {int_or_none}),
61 'height': ('height', 0, {int_or_none}),
62 })) or parse_resolution(url)),
63 }
64
65 @staticmethod
66 def _epidemic_fmt_or_none(f):
67 if not f.get('format'):
68 f['format'] = f.get('format_id')
69 elif not f.get('format_id'):
70 f['format_id'] = f['format']
71 if not f['url'] or not f['format']:
72 return None
73 if f.get('format_note'):
74 f['format_note'] = f'track ID {f["format_note"]}'
75 if f['format'] != 'full':
76 f['preference'] = -2
77 return f
78
79 def _real_extract(self, url):
80 video_id = self._match_id(url)
81 json_data = self._download_json(f'https://www.epidemicsound.com/json/track/{video_id}', video_id)
82
83 thumbnails = traverse_obj(json_data, [('imageUrl', 'cover')])
84 thumb_base_url = traverse_obj(json_data, ('coverArt', 'baseUrl', {url_or_none}))
85 if thumb_base_url:
86 thumbnails.extend(traverse_obj(json_data, (
87 'coverArt', 'sizes', ..., {thumb_base_url.__add__})))
88
89 return traverse_obj(json_data, {
90 'id': ('id', {str_or_none}),
91 'display_id': ('publicSlug', {str}),
92 'title': ('title', {str}),
93 'alt_title': ('oldTitle', {str}),
94 'duration': ('length', {float_or_none}),
95 'timestamp': ('added', {parse_iso8601}),
96 'release_timestamp': ('releaseDate', {parse_iso8601}),
97 'categories': ('genres', ..., 'tag', {str}),
98 'tags': ('metadataTags', ..., {str}),
99 'age_limit': ('isExplicit', {lambda b: 18 if b else None}),
100 'thumbnails': ({lambda _: thumbnails}, {orderedSet}, ..., {self._epidemic_parse_thumbnail}),
101 'formats': ('stems', {dict.items}, ..., {
102 'format': (0, {str_or_none}),
103 'format_note': (1, 's3TrackId', {str_or_none}),
104 'format_id': (1, 'stemType', {str}),
105 'url': (1, 'lqMp3Url', {url_or_none}),
106 }, {self._epidemic_fmt_or_none}),
107 })