]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/gofile.py
[ie/orf:on] Improve extraction (#9677)
[yt-dlp.git] / yt_dlp / extractor / gofile.py
1 import hashlib
2
3 from .common import InfoExtractor
4 from ..utils import (
5 ExtractorError,
6 try_get
7 )
8
9
10 class GofileIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?gofile\.io/d/(?P<id>[^/]+)'
12 _TESTS = [{
13 'url': 'https://gofile.io/d/AMZyDw',
14 'info_dict': {
15 'id': 'AMZyDw',
16 },
17 'playlist_mincount': 2,
18 'playlist': [{
19 'info_dict': {
20 'id': 'de571ac1-5edc-42e2-8ec2-bdac83ad4a31',
21 'filesize': 928116,
22 'ext': 'mp4',
23 'title': 'nuuh',
24 'release_timestamp': 1638338704,
25 'release_date': '20211201',
26 }
27 }]
28 }, {
29 'url': 'https://gofile.io/d/is8lKr',
30 'info_dict': {
31 'id': 'TMjXd9',
32 'ext': 'mp4',
33 },
34 'playlist_count': 0,
35 'skip': 'No video/audio found at provided URL.',
36 }, {
37 'url': 'https://gofile.io/d/TMjXd9',
38 'info_dict': {
39 'id': 'TMjXd9',
40 },
41 'playlist_count': 1,
42 }, {
43 'url': 'https://gofile.io/d/gqOtRf',
44 'info_dict': {
45 'id': 'gqOtRf',
46 },
47 'playlist_mincount': 1,
48 'params': {
49 'videopassword': 'password',
50 },
51 }]
52 _TOKEN = None
53
54 def _real_initialize(self):
55 token = self._get_cookies('https://gofile.io/').get('accountToken')
56 if token:
57 self._TOKEN = token.value
58 return
59
60 account_data = self._download_json(
61 'https://api.gofile.io/accounts', None, 'Getting a new guest account', data=b'{}')
62 self._TOKEN = account_data['data']['token']
63 self._set_cookie('.gofile.io', 'accountToken', self._TOKEN)
64
65 def _entries(self, file_id):
66 query_params = {'wt': '4fd6sg89d7s6'} # From https://gofile.io/dist/js/alljs.js
67 password = self.get_param('videopassword')
68 if password:
69 query_params['password'] = hashlib.sha256(password.encode('utf-8')).hexdigest()
70 files = self._download_json(
71 f'https://api.gofile.io/contents/{file_id}', file_id, 'Getting filelist',
72 query=query_params, headers={'Authorization': f'Bearer {self._TOKEN}'})
73
74 status = files['status']
75 if status == 'error-passwordRequired':
76 raise ExtractorError(
77 'This video is protected by a password, use the --video-password option', expected=True)
78 elif status != 'ok':
79 raise ExtractorError(f'{self.IE_NAME} said: status {status}', expected=True)
80
81 found_files = False
82 for file in (try_get(files, lambda x: x['data']['children'], dict) or {}).values():
83 file_type, file_format = file.get('mimetype').split('/', 1)
84 if file_type not in ('video', 'audio') and file_format != 'vnd.mts':
85 continue
86
87 found_files = True
88 file_url = file.get('link')
89 if file_url:
90 yield {
91 'id': file['id'],
92 'title': file['name'].rsplit('.', 1)[0],
93 'url': file_url,
94 'filesize': file.get('size'),
95 'release_timestamp': file.get('createTime')
96 }
97
98 if not found_files:
99 raise ExtractorError('No video/audio found at provided URL.', expected=True)
100
101 def _real_extract(self, url):
102 file_id = self._match_id(url)
103 return self.playlist_result(self._entries(file_id), playlist_id=file_id)