opencultureconsulting
/
noah
mirror of https://github.com/opencultureconsulting/noah.git
2
0
Fork 0
Code Issues Projects Releases Wiki Activity

fix #27 Münster: Linkcheck soll weitere Informationen ausgeben

This commit is contained in:
Felix Lohmeier 2021-03-02 14:59:24 +01:00
parent 1f1298c6f0
commit 3b154c21cb
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
Taskfile.yml
View File

@ -168,14 +168,15 @@ tasks:
cmds: cmds:
- test -n "{{.PROJECT}}" - test -n "{{.PROJECT}}"
# Links extrahieren # Links extrahieren
- xmllint --xpath '//@*[local-name(.) = "href"]' split/*.xml | cut -d '"' -f2 | sort | uniq > links.txt - grep -o 'href="[^"]*"' split/*.xml | sed 's/:href=/\t/' | tr -d '"' | sort -k 2 --unique > links.txt
# http status code aller Links ermitteln # http status code ermitteln
- awk '{ print "url = " $0 "\noutput = /dev/null"; }' links.txt > curl.cfg - awk '{ print "url = " $2 "\noutput = /dev/null"; }' links.txt > curl.cfg
- curl --silent --head --location --write-out "%{http_code} %{url_effective}\n" --config curl.cfg > linkcheck.log - curl --silent --head --location --write-out "%{http_code}\t%{url_effective}\n" --config curl.cfg > curl.log
# Tabelle mit status code, effektiver URL, Dateiname und start URL erstellen
- paste curl.log links.txt > linkcheck.log
- rm -rf curl.cfg curl.log links.txt
# Logdatei auf status code != 2XX prüfen # Logdatei auf status code != 2XX prüfen
- if grep '^[^2]' linkcheck.log; then echo 1>&2 "Logdatei $PWD/linkcheck.log enthält problematische status codes!" && exit 1; fi - if grep '^[^2]' linkcheck.log; then echo 1>&2 "Logdatei $PWD/linkcheck.log enthält problematische status codes!" && exit 1; fi
# Aufräumen bei Erfolg
- rm -rf curl.cfg links.txt
sources: sources:
- split/*.xml - split/*.xml
generates: generates: