blob: 0929bd22ed8eeb0ffe9daedc8bd2a85d9379c2f6 (
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
|
# Note: Run this script from the root of the repo
import requests
import json
from urllib.parse import urlparse
from bs4 import BeautifulSoup
mightyList = {}
def get_host_name(link):
url = urlparse(link)
return url.netloc
# Invidious
r = requests.get('https://api.invidious.io/instances.json')
rJson = json.loads(r.text)
invidiousList = {}
invidiousList['normal'] = []
invidiousList['tor'] = []
for instance in rJson:
if instance[1]['type'] == 'https':
invidiousList['normal'].append(instance[1]['uri'])
elif instance[1]['type'] == 'tor':
invidiousList['tor'].append(instance[1]['uri'])
mightyList['invidious'] = invidiousList
print('fetched Invidious')
# Nitter
r = requests.get('https://github.com/zedeus/nitter/wiki/Instances')
soup = BeautifulSoup(r.text, 'html.parser')
markdownBody = soup.find(class_='markdown-body')
tables = markdownBody.find_all('table')
tables.pop(3)
tables.pop(3)
nitterList = {}
nitterList['normal'] = []
nitterList['tor'] = []
for table in tables:
tbody = table.find('tbody')
trs = tbody.find_all('tr')
for tr in trs:
td = tr.find('td')
a = td.find('a')
url = a.contents[0]
if url.endswith('.onion'):
url = 'http://' + url
nitterList['tor'].append(url)
else:
url = 'https://' + url
nitterList['normal'].append(url)
mightyList['nitter'] = nitterList
print('fetched Nitter')
# Bibliogram
r = requests.get('https://bibliogram.art/api/instances')
rJson = json.loads(r.text)
bibliogramList = {}
bibliogramList['normal'] = []
for item in rJson['data']:
bibliogramList['normal'].append(item['address'])
mightyList['bibliogram'] = bibliogramList
print('fetched Bibliogram')
# Teddit
r = requests.get(
'https://codeberg.org/teddit/teddit/raw/branch/main/instances.json')
rJson = json.loads(r.text)
tedditList = {}
tedditList['normal'] = []
tedditList['tor'] = []
for item in rJson:
url = item['url']
if url != '':
tedditList['normal'].append(url)
if 'tor' in item:
onion = item['tor']
if onion != '':
tedditList['tor'].append(onion)
mightyList['teddit'] = tedditList
print('fetched Teddit')
# Wikiless
r = requests.get('https://wikiless.org/instances.json')
rJson = json.loads(r.text)
wikilessList = {}
wikilessList['normal'] = []
wikilessList['tor'] = []
for item in rJson:
if item.endswith('.onion'):
wikilessList['tor'].append('http://' + item)
else:
wikilessList['normal'].append('https://' + item)
mightyList['wikiless'] = wikilessList
print('fetched Wikiless')
# Scribe
r = requests.get(
'https://git.sr.ht/~edwardloveall/scribe/blob/main/docs/instances.json')
rJson = json.loads(r.text)
scribeList = {}
scribeList['normal'] = []
for item in rJson:
scribeList['normal'].append(item)
mightyList['scribe'] = scribeList
print('fetched Scribe')
# SimplyTranslate
r = requests.get('https://simple-web.org/instances/simplytranslate')
simplyTranslateList = {}
simplyTranslateList['normal'] = []
for item in r.text.strip().split('\n'):
simplyTranslateList['normal'].append('https://' + item)
r = requests.get('https://simple-web.org/instances/simplytranslate_onion')
simplyTranslateList['tor'] = []
for item in r.text.strip().split('\n'):
simplyTranslateList['tor'].append('http://' + item)
mightyList['simplyTranslate'] = simplyTranslateList
print('fetched SimplyTranslate')
# LinvgaTranslate
r = requests.get(
'https://raw.githubusercontent.com/TheDavidDelta/lingva-translate/main/instances.json')
rJson = json.loads(r.text)
lingvaList = {}
lingvaList['normal'] = []
for item in rJson:
lingvaList['normal'].append(item)
mightyList['lingva'] = lingvaList
print('fetched LinvgaTranslate')
# SearX
r = requests.get('https://searx.space/data/instances.json')
rJson = json.loads(r.text)
searxList = {}
searxList['normal'] = []
searxList['tor'] = []
searxList['i2p'] = []
for item in rJson['instances'].keys():
item = item[:-1]
if item.endswith('.onion'):
searxList['tor'].append(item)
elif item.endswith('.i2p'):
searxList['i2p'].append(item)
else:
searxList['normal'].append(item)
mightyList['searx'] = searxList
print('fetched SearX')
# Whoogle
r = requests.get(
'https://raw.githubusercontent.com/benbusby/whoogle-search/main/misc/instances.txt')
tmpList = r.text.strip().split('\n')
whoogleList = {}
whoogleList['normal'] = []
for item in tmpList:
whoogleList['normal'].append(item)
mightyList['whoogle'] = whoogleList
print('fetched Whoogle')
# Rimgo
r = requests.get(
'https://codeberg.org/video-prize-ranch/rimgo/raw/branch/main/instances.json')
rJson = json.loads(r.text)
rimgoList = {}
rimgoList['normal'] = []
rimgoList['tor'] = []
for item in rJson:
if item.endswith('.onion'):
rimgoList['tor'].append('http://' + item)
else:
rimgoList['normal'].append('https://' + item)
mightyList['rimgo'] = rimgoList
print('fetched Rimgo')
# Writing to file
json_object = json.dumps(mightyList, ensure_ascii=False, indent=2)
with open('src/instances/data.json', 'w') as outfile:
outfile.write(json_object)
# print(json_object)
print('wrote instances/data.json')
|
