Automate updates for list of searx instances (#3)
* Create nightly update workflow for instances A nightly GitHub Actions CI workflow has been added to fetch new instances of supported services within Farside. Currently only Searx is supported, but obviously others could be added if there are similarly easy ways to fetch and filter instances programmatically. services.json has also been updated with the initial results of the workflow script. * Set headers for every HTTPoison request This serves as a workaround for bot blocking via filtron. * Expand filtering of searx instances New filter enforces: - No Cloudflare - Good TLS config - Good HTTP header config - Vanilla instances or forks - Instances with 100% search success
This commit is contained in:
Ben Busby
GitHub
parent
ff97d258f0
commit
8e3455a790
68
.github/workflows/update-instances.yml
vendored
Normal file
68
.github/workflows/update-instances.yml
vendored
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
on:
|
||||
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
|
||||
- name: Fetch instances
|
||||
run: |
|
||||
function apply_update() {
|
||||
mv services-tmp.json services.json
|
||||
rm -f *-tmp.json
|
||||
|
||||
# Ensure no trailing slashes for any instance
|
||||
sed -i '' 's/\/"/"/g' services.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
|
||||
|
||||
# ==============================================================
|
||||
# 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") |
|
||||
.key
|
||||
] | sort' > searx-tmp.json
|
||||
|
||||
jq --slurpfile searx searx-tmp.json \
|
||||
'( .[] | select(.type == "searx") )
|
||||
.instances |= $searx[0]' services.json > services-tmp.json
|
||||
|
||||
apply_update
|
||||
|
||||
# ==============================================================
|
||||
# TODO: Update instances for other services
|
||||
# ==============================================================
|
||||
|
||||
# ==============================================================
|
||||
# Push changes
|
||||
# ==============================================================
|
||||
if [[ $(git diff-index --quiet HEAD) ]]; then
|
||||
echo "No updates"
|
||||
else
|
||||
git add services.json
|
||||
git commit -m '[CI] Auto update instances'
|
||||
git push
|
||||
fi
|
||||
|
|
@ -8,4 +8,10 @@ config :farside,
|
|||
fallback_suffix: "-fallback",
|
||||
previous_suffix: "-previous",
|
||||
services_json: "services.json",
|
||||
index: "index.eex"
|
||||
index: "index.eex",
|
||||
headers: [
|
||||
{"User-Agent", "Mozilla/5.0 (Linux x86_64; rv:94.0) Gecko/20100101 Firefox/94.0"},
|
||||
{"Accept", "text/html"},
|
||||
{"Accept-Language", "en-US,en;q=0.5"},
|
||||
{"Accept-Encoding", "gzip, deflate, br"}
|
||||
]
|
||||
|
|
|
|||
|
|
@ -3,6 +3,7 @@ defmodule Farside.Instances do
|
|||
@update_file Application.fetch_env!(:farside, :update_file)
|
||||
@services_json Application.fetch_env!(:farside, :services_json)
|
||||
@service_prefix Application.fetch_env!(:farside, :service_prefix)
|
||||
@headers Application.fetch_env!(:farside, :headers)
|
||||
|
||||
def sync() do
|
||||
File.rename(@update_file, "#{@update_file}-prev")
|
||||
|
|
@ -21,7 +22,7 @@ defmodule Farside.Instances do
|
|||
System.get_env("FARSIDE_TEST") ->
|
||||
:good
|
||||
true ->
|
||||
case HTTPoison.get(url) do
|
||||
case HTTPoison.get(url, @headers) do
|
||||
{:ok, %HTTPoison.Response{status_code: 200}} ->
|
||||
# TODO: Add validation of results, not just status code
|
||||
:good
|
||||
|
|
|
|||
|
|
@ -134,36 +134,35 @@
|
|||
"test_url": "/search?q=github",
|
||||
"fallback": "https://searx.be",
|
||||
"instances": [
|
||||
"https://paulgo.io",
|
||||
"https://search.asynchronousexchange.com",
|
||||
"https://anon.sx",
|
||||
"https://searx.be",
|
||||
"https://searx.gnous.eu",
|
||||
"https://xeek.com",
|
||||
"https://searx.bar",
|
||||
"https://sx.fedi.tech",
|
||||
"https://searx.tiekoetter.com",
|
||||
"https://search.disroot.org",
|
||||
"https://northboot.xyz",
|
||||
"https://searx.fmac.xyz",
|
||||
"https://metasearch.nl",
|
||||
"https://searx.nevrlands.de",
|
||||
"https://search.mdosch.de",
|
||||
"https://searx.rasp.fr",
|
||||
"https://searx.zackptg5.com",
|
||||
"https://paulgo.io",
|
||||
"https://procurx.pt",
|
||||
"https://searx2.zackptg5.com",
|
||||
"https://searx.pwoss.org",
|
||||
"https://search.076.ne.jp/searx",
|
||||
"https://darmarit.org/searx",
|
||||
"https://suche.uferwerk.org",
|
||||
"https://searx.nakhan.ne",
|
||||
"https://suche.dasnetzundich.de",
|
||||
"https://search.antonkling.se",
|
||||
"https://jsearch.pw",
|
||||
"https://searx.hummel-web.at",
|
||||
"https://s.zhaocloud.net",
|
||||
"https://search.asynchronousexchange.com",
|
||||
"https://search.bluelock.org",
|
||||
"https://search.mdosch.de",
|
||||
"https://searx.ru"
|
||||
"https://searx.bar",
|
||||
"https://searx.be",
|
||||
"https://searx.divided-by-zero.eu",
|
||||
"https://searx.fmac.xyz",
|
||||
"https://searx.hummel-web.at",
|
||||
"https://searx.nevrlands.de",
|
||||
"https://searx.prvcy.eu",
|
||||
"https://searx.rasp.fr",
|
||||
"https://searx.ru",
|
||||
"https://searx.silkky.cloud",
|
||||
"https://searx.sp-codes.de",
|
||||
"https://searx.stuehieyr.com",
|
||||
"https://searx.theanonymouse.xyz",
|
||||
"https://searx.tiekoetter.com",
|
||||
"https://searx.tux.land",
|
||||
"https://searx.tuxcloud.net",
|
||||
"https://searx.webheberg.info",
|
||||
"https://searx.xyz",
|
||||
"https://searx2.zackptg5.com",
|
||||
"https://swag.pw",
|
||||
"https://sx.fedi.tech"
|
||||
]
|
||||
}
|
||||
]
|
||||
|
|
|
|||
Loading…
Reference in a new issue