mirror of
https://github.com/Mic92/nixos-wiki-infra.git
synced 2024-11-24 17:23:34 +01:00
linkcheck: download xmldump conservatively
Signed-off-by: phanirithvij <phanirithvij2000@gmail.com>
This commit is contained in:
parent
31e229cefc
commit
7128152b64
@ -8,7 +8,8 @@ workdir="$SCRIPT_DIR/workdir"
|
|||||||
mkdir -p "$workdir"
|
mkdir -p "$workdir"
|
||||||
pushd "$workdir" || exit
|
pushd "$workdir" || exit
|
||||||
|
|
||||||
curl "https://wiki.nixos.org/wikidump.xml.zst" | zstd -d >wikidump.xml
|
curl -o wikidump.xml.zst "https://wiki.nixos.org/wikidump.xml.zst" -z wikidump.xml.zst
|
||||||
|
<wikidump.xml.zst zstd -d >wikidump.xml
|
||||||
|
|
||||||
# filter unimportant pages like User:* Talk:*
|
# filter unimportant pages like User:* Talk:*
|
||||||
python3 ../main.py filter wikidump.xml wikidump-filtered.xml
|
python3 ../main.py filter wikidump.xml wikidump-filtered.xml
|
||||||
@ -17,7 +18,7 @@ python3 ../main.py filter wikidump.xml wikidump-filtered.xml
|
|||||||
python3 ../main.py badlinks ../allowed.links exclude-args
|
python3 ../main.py badlinks ../allowed.links exclude-args
|
||||||
|
|
||||||
extrargs=(
|
extrargs=(
|
||||||
# exlude sending requests to the wiki
|
# exclude sending requests to the wiki
|
||||||
"--exclude" "wiki.nixos.org/wiki"
|
"--exclude" "wiki.nixos.org/wiki"
|
||||||
# default is too high
|
# default is too high
|
||||||
"--max-concurrency" "16"
|
"--max-concurrency" "16"
|
||||||
|
Loading…
Reference in New Issue
Block a user