19855efacc
Some checks failed
Tests / Go Tests (push) Has been cancelled
Tests / Python Tests (push) Has been cancelled
Tests / Integration Tests (push) Has been cancelled
Tests / Go Lint (push) Has been cancelled
Tests / Python Lint (push) Has been cancelled
Tests / Security Scan (push) Has been cancelled
Tests / All Checks Passed (push) Has been cancelled
Security Scanning / Secret Scanning (push) Has been cancelled
Security Scanning / Dependency Vulnerability Scan (push) Has been cancelled
Security Scanning / Go Security Scan (push) Has been cancelled
Security Scanning / Python Security Scan (push) Has been cancelled
Security Scanning / Node.js Security Scan (push) Has been cancelled
Security Scanning / Docker Image Security (push) Has been cancelled
Security Scanning / Security Summary (push) Has been cancelled
CI/CD Pipeline / Go Tests (push) Has been cancelled
CI/CD Pipeline / Python Tests (push) Has been cancelled
CI/CD Pipeline / Website Tests (push) Has been cancelled
CI/CD Pipeline / Linting (push) Has been cancelled
CI/CD Pipeline / Security Scan (push) Has been cancelled
CI/CD Pipeline / Docker Build & Push (push) Has been cancelled
CI/CD Pipeline / Integration Tests (push) Has been cancelled
CI/CD Pipeline / Deploy to Staging (push) Has been cancelled
CI/CD Pipeline / Deploy to Production (push) Has been cancelled
CI/CD Pipeline / CI Summary (push) Has been cancelled
ci/woodpecker/manual/build-ci-image Pipeline was successful
ci/woodpecker/manual/main Pipeline failed
All services: admin-v2, studio-v2, website, ai-compliance-sdk, consent-service, klausur-service, voice-service, and infrastructure. Large PDFs and compiled binaries excluded via .gitignore.
118 lines
2.8 KiB
YAML
118 lines
2.8 KiB
YAML
# Trust Score Regeln für Education Search
|
|
# Score-Berechnung: Summe aller matchenden Regeln, dann clamp(0, 1)
|
|
|
|
domain_boosts:
|
|
# Bundesebene (höchste Vertrauensstufe)
|
|
- match: "*.kmk.org"
|
|
add: 0.50
|
|
reason: "KMK - Kultusministerkonferenz"
|
|
- match: "*.bildungsserver.de"
|
|
add: 0.50
|
|
reason: "Deutscher Bildungsserver"
|
|
- match: "*.bpb.de"
|
|
add: 0.45
|
|
reason: "Bundeszentrale für politische Bildung"
|
|
- match: "*.bmbf.de"
|
|
add: 0.50
|
|
reason: "BMBF"
|
|
- match: "*.iqb.hu-berlin.de"
|
|
add: 0.50
|
|
reason: "IQB Bildungsstandards"
|
|
|
|
# Landesministerien
|
|
- match: "*.bayern.de"
|
|
add: 0.45
|
|
reason: "Bayern offiziell"
|
|
- match: "*.nrw.de"
|
|
add: 0.45
|
|
reason: "NRW offiziell"
|
|
- match: "*.berlin.de"
|
|
add: 0.45
|
|
reason: "Berlin offiziell"
|
|
- match: "*.sachsen.de"
|
|
add: 0.45
|
|
reason: "Sachsen offiziell"
|
|
- match: "*.niedersachsen.de"
|
|
add: 0.45
|
|
reason: "Niedersachsen offiziell"
|
|
- match: "*.hessen.de"
|
|
add: 0.45
|
|
reason: "Hessen offiziell"
|
|
- match: "*.brandenburg.de"
|
|
add: 0.45
|
|
reason: "Brandenburg offiziell"
|
|
- match: "*.thueringen.de"
|
|
add: 0.45
|
|
reason: "Thüringen offiziell"
|
|
|
|
# Bildungsserver der Länder
|
|
- match: "*.nibis.de"
|
|
add: 0.40
|
|
reason: "Niedersachsen Bildungsserver"
|
|
- match: "*.learnline.nrw.de"
|
|
add: 0.40
|
|
reason: "NRW Bildungsserver"
|
|
- match: "*.schule-bw.de"
|
|
add: 0.40
|
|
reason: "BW Bildungsserver"
|
|
|
|
# Universitäten
|
|
- match: "*.uni-*.de"
|
|
add: 0.30
|
|
reason: "Deutsche Universität"
|
|
- match: "*.tu-*.de"
|
|
add: 0.30
|
|
reason: "Technische Universität"
|
|
- match: "*.fh-*.de"
|
|
add: 0.25
|
|
reason: "Fachhochschule"
|
|
|
|
# Etablierte Portale
|
|
- match: "*.zum.de"
|
|
add: 0.25
|
|
reason: "ZUM - Zentrale für Unterrichtsmedien"
|
|
- match: "*.lehrer-online.de"
|
|
add: 0.20
|
|
reason: "Lehrer-Online Portal"
|
|
- match: "*.4teachers.de"
|
|
add: 0.20
|
|
reason: "4teachers Portal"
|
|
|
|
tld_boosts:
|
|
- tld: ".gov"
|
|
add: 0.40
|
|
reason: "Government TLD"
|
|
- tld: ".edu"
|
|
add: 0.35
|
|
reason: "Education TLD"
|
|
|
|
penalties:
|
|
# URL-Muster die Werbung/Tracking andeuten
|
|
- if_url_contains: ["utm_", "affiliate", "partner=", "ref="]
|
|
add: -0.10
|
|
reason: "Tracking/Affiliate Parameter"
|
|
|
|
# Kommerzielle Signale
|
|
- if_url_contains: ["shop", "kaufen", "bestellen", "warenkorb"]
|
|
add: -0.20
|
|
reason: "E-Commerce Signale"
|
|
|
|
# SEO-Spam Indikatoren
|
|
- if_url_contains: ["gratis-", "kostenlos-download", "sofort-"]
|
|
add: -0.15
|
|
reason: "SEO-Spam Muster"
|
|
|
|
# Content-basierte Strafen (werden vom Extractor gesetzt)
|
|
content_penalties:
|
|
- if_ad_density_gt: 0.20
|
|
add: -0.30
|
|
reason: "Hoher Werbeanteil"
|
|
|
|
- if_link_density_gt: 0.40
|
|
add: -0.20
|
|
reason: "Hohe Link-Dichte (Linkfarm)"
|
|
|
|
- if_content_length_lt: 200
|
|
add: -0.25
|
|
reason: "Sehr wenig Content"
|