blob: 69dcea480365a98aae6f504b97b2c7dc71279962 (
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
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
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
|
on:
workflow_dispatch:
schedule:
- cron: '0 0 * * *'
jobs:
update-instances:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Install dependencies
run: sudo apt-get install -y jq dnsutils
- uses: webfactory/ssh-agent@v0.5.3
with:
ssh-private-key: |
${{ secrets.PRIMARY_REPO_KEY }}
- name: Fetch instances
run: |
function apply_update() {
mv services-tmp.json services-full.json
rm -f *-tmp.json
# Ensure no trailing slashes for any instance
sed -i 's/\/"/"/g' services-full.json
}
function remove_cf_instances() {
rm -f out.json
file="services-full.json"
while read -r line; do
if [[ "$line" == "\"https://"* ]]; then
domain=$(echo "$line" | sed -e "s/^\"https:\/\///" -e "s/\",//" -e "s/\"//")
ns=$(dig ns "$domain" || true)
if [[ "$ns" == *"cloudflare"* ]]; then
echo "\"$domain\" using cloudflare, skipping..."
elif [ ${#ns} -eq 0 ]; then
echo "Unable to verify records for \"$domain\", skipping..."
else
echo "$line" >> out.json
fi
else
echo "$line" >> out.json
fi
done <$file
# Remove any trailing commas from new instance lists
sed -e ':begin' -e '$!N' -e 's/,\n]/\n]/g' -e 'tbegin' -e 'P' -e 'D' out.json
cat out.json | jq --indent 2 . > services.json
rm -f out.json
}
# ==============================================================
# Git config
# ==============================================================
git config --global user.name github-actions
git config --global user.email 41898282+github-actions[bot]@users.noreply.github.com
git remote set-url origin git@github.com:benbusby/farside.git
git checkout main
# ==============================================================
# Bibliogram update
# ==============================================================
curl -s https://bibliogram.art/api/instances | \
jq '[
.data |
.[] |
select(.onion_site | not) |
.address
] | sort' > bibliogram-tmp.json
jq --slurpfile bibliogram bibliogram-tmp.json \
'( .[] | select(.type == "bibliogram") )
.instances |= $bibliogram[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# searx update
# ==============================================================
curl -s https://searx.space/data/instances.json | \
jq '[
.instances |
to_entries[] |
select(.value.network_type == "normal") |
select(.value.version | . != null) |
select(.value.version | startswith("1.0.0")) |
select(.value.network.asn_privacy == 0) |
select(.value.http.error == null) |
select(.value.tls.grade == "A+" or .value.tls.grade == "A") |
select(.value.http.grade == "A+" or .value.http.grade == "A") |
select(.value.html.grade == "V" or .value.html.grade == "F") |
select(.key | contains(".i2p") | not) |
.key
] | sort' > searx-tmp.json
cat searx-tmp.json | jq .
jq --slurpfile searx searx-tmp.json \
'( .[] | select(.type == "searx") )
.instances |= $searx[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# SearXNG update
# ==============================================================
curl -s https://searx.space/data/instances.json | \
jq '[
.instances |
to_entries[] |
select(.value.network_type == "normal") |
select(.value.generator | . != null) |
select(.value.generator | contains("searxng")) |
select(.value.version | . != null) |
select(.value.network.asn_privacy == 0) |
select(.value.http.error == null) |
select(.value.tls.grade == "A+" or .value.tls.grade == "A") |
select(.value.http.grade == "A+" or .value.http.grade == "A") |
select(.value.html.grade == "V" or .value.html.grade == "F") |
select(.key | contains(".i2p") | not) |
.key
] | sort' > searxng-tmp.json
cat searxng-tmp.json | jq .
jq --slurpfile searxng searxng-tmp.json \
'( .[] | select(.type == "searxng") )
.instances |= $searxng[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# SimplyTranslate update
# ==============================================================
curl -s https://simple-web.org/instances/simplytranslate > st-out
sed -i -e 's/^/https:\/\//' st-out
jq -ncR '[inputs]' <<< "$(cat st-out | sort)" > st-tmp.json
jq --slurpfile simplytranslate st-tmp.json \
'( .[] | select(.type == "simplytranslate") )
.instances |= $simplytranslate[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# Whoogle update
# ==============================================================
curl -s https://raw.githubusercontent.com/benbusby/whoogle-search/main/misc/instances.txt > whoogle-out
jq -ncR '[inputs]' <<< "$(cat whoogle-out | sort)" > whoogle-tmp.json
jq --slurpfile whoogle whoogle-tmp.json \
'( .[] | select(.type == "whoogle") )
.instances |= $whoogle[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# Invidious update
# ==============================================================
curl -s https://api.invidious.io/instances.json | \
jq '[
.[] |
select(.[1].type | contains("https")) ] |
[.[][1].uri] |
sort' > invidious-tmp.json
jq --slurpfile invidious invidious-tmp.json \
'( .[] | select(.type == "invidious") )
.instances |= $invidious[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# Scribe update
# ==============================================================
curl -s https://git.sr.ht/~edwardloveall/scribe/blob/main/docs/instances.json > scribe-tmp.json
jq --slurpfile scribe scribe-tmp.json \
'( .[] | select(.type == "scribe") )
.instances |= $scribe[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# teddit update
# ==============================================================
curl -s https://codeberg.org/teddit/teddit/raw/branch/main/instances.json | \
jq '[
.[] |
select(.url | contains("https")) |
.url ] |
sort' > teddit-tmp.json
jq --slurpfile teddit teddit-tmp.json \
'( .[] | select(.type == "teddit") )
.instances |= $teddit[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# Wikiless update
# ==============================================================
curl -s https://codeberg.org/orenom/Wikiless/raw/branch/main/instances.json | \
jq '[
.[] |
select((.url | contains(".onion") | not) and (.url | contains("https"))).url ] |
sort' > wikiless-tmp.json
jq --slurpfile wikiless wikiless-tmp.json \
'( .[] | select(.type == "wikiless") )
.instances |= $wikiless[0]' services-full.json > services-tmp.json
apply_update
# ==============================================================
# TODO: Update instances for other services
# ==============================================================
# ==============================================================
# Remove cloudflare instances
# ==============================================================
remove_cf_instances
# ==============================================================
# Push changes
# ==============================================================
git add services.json services-full.json
git commit -m '[CI] Auto update instances' || exit 0
git push
|
