# Integrity Scanner — Konfiguration für bredelar.info target: "https://bredelar.info" user_agent: "integrity-scanner/1.0 (+security-monitoring)" request_timeout: 20 data_dir: "/home/dschlueter/Python_Programs/integrity_scanner_fuer_statische_Webseiten/bredelar.info/data" reports_dir: "/home/dschlueter/Python_Programs/integrity_scanner_fuer_statische_Webseiten/bredelar.info/reports" logs_dir: "/home/dschlueter/Python_Programs/integrity_scanner_fuer_statische_Webseiten/bredelar.info/logs" config_dir: "/home/dschlueter/Python_Programs/integrity_scanner_fuer_statische_Webseiten/bredelar.info/config" crawl: max_pages: 200 delay_seconds: 1.0 respect_robots_txt: false # Pfade, die vom Crawl und vom Vergleich komplett ausgeschlossen werden. # Nützlich für Bereiche mit gewollt häufig wechselnden Inhalten (RSS-Feeds, News-Archive). # Beispiel: ["/rss/", "/feed/", "/news/archiv/"] exclude_paths: [] skip_extensions: - ".jpg" - ".jpeg" - ".png" - ".gif" - ".webp" - ".svg" - ".ico" - ".pdf" - ".zip" - ".woff" - ".woff2" - ".ttf" - ".otf" - ".eot" - ".mp4" - ".mp3" - ".webm" - ".avi" - ".mov" scoring: new_external_domain: 50 new_internal_url: 30 missing_internal_url: 20 hidden_content: 40 unexpected_canonical: 35 meta_refresh: 40 unexpected_jsonld: 35 large_text_addition: 20 new_inline_script_suspicious: 30 comment_links: 25 new_broken_link: 20 suspicious_filename: 60 cloaking_extra_link: 60 cloaking_extra_text: 40 cloaking_vary_ua: 25 changed_script: 40 changed_stylesheet: 30 changed_asset: 20 thresholds: yellow: 20 red: 60 large_text_block_chars: 200 # Wöchentliche Zusatzprüfungen laufen automatisch beim täglichen `scan` mit. periodic_checks: enabled: true interval_days: 7 cloak_check: true ext_links: true assets: true alerting: min_level: "yellow" email: enabled: false smtp_host: "localhost" smtp_port: 587 smtp_tls: true smtp_user: "" smtp_password_env: "SCANNER_SMTP_PASSWORD" from: "scanner@bredelar.info" to: - "admin@bredelar.info" webhook: enabled: false url: "" normalization: strip_html_comments: true collapse_whitespace: true ignore_selectors: # - "#last-modified" # - ".timestamp" ignore_patterns: # - '\d{1,2}\.\d{1,2}\.\d{4}' # - 'Stand:\s+\S+' allowed_jsonld_types: - "Organization" - "WebSite" - "WebPage" - "Article" - "BreadcrumbList" - "ItemList" - "LocalBusiness" - "Place" - "Person" - "Event" - "FAQPage" - "Question" - "Answer" - "ImageObject" - "SiteLinksSearchBox" - "ContactPage" - "AboutPage" security_headers: - "Content-Security-Policy" - "Strict-Transport-Security" - "X-Content-Type-Options" - "Referrer-Policy"