input.txt.example

# Reference only — not loaded automatically.
# Configure via web UI (Run audit → Settings) or: python -m src --config input.txt.example
# Requires DATABASE_URL (PostgreSQL). UI writes shadow file to DATA_DIR/pipeline-config.txt.
# Keys match web/src/lib/pipelineConfigSchema.ts (ALL_SCHEMA_KEYS).

# --- Crawl ---
start_url = 
max_pages = 20
concurrency = 8
timeout = 12
max_depth = 6
polite_delay = 0.2
ignore_robots = false
allow_external = false
store_outlinks = true
store_content_excerpt = true
content_excerpt_max_chars = 4096
store_page_html = false
max_stored_html_bytes = 2097152
run_content_analysis = false
content_analysis_strategy = main_only
content_analysis_workers = 4
preserve_crawl_history = true
crawl_stream_to_db = false
crawl_exclude_urls = 
crawl_discovery_mode = spider
crawl_url_list = 
crawl_user_agent_preset = default
crawl_user_agent_custom =
compare_mobile_desktop = false
crawl_auth_username =
crawl_auth_password = 
crawl_extra_headers = 
crawl_cookies = 
crawl_robots_txt_override = 
custom_extractors = 
# crawl_render_mode: static | javascript | auto (auto = static first, browser when SPA heuristics match)
crawl_render_mode = static
crawl_js_concurrency = 3
crawl_js_timeout = 30
crawl_js_wait_until = domcontentloaded
crawl_js_extra_wait_ms = 1500
crawl_js_block_resources = true
crawl_js_capture_console = true
crawl_js_console_levels = error,warning
crawl_js_capture_failed_requests = false
crawl_js_console_max_per_page = 20

# --- Report ---
outbound_domain_max_rows = 200
include_keyword_opportunities = true
site_name = Site
report_title = SEO report
max_fetch_for_edges = 300
same_domain_only = true
max_nodes_plot = 400
run_security_scan = true
security_scan_active = false
security_max_urls_probe = 20
probe_image_inventory = false
max_image_probe_urls = 500
image_probe_concurrency = 6
image_probe_timeout = 8
image_unoptimized_min_kb = 200
enable_subdomain_discovery = true
subdomain_ct_lookup = true
enable_rdap_org_lookup = true

# --- Lighthouse ---
lighthouse_url = 
lighthouse_mode = navigation
lighthouse_strategy = desktop
lighthouse_categories = performance,accessibility,best-practices,seo
lighthouse_iterations = 1
run_lighthouse = true
run_lighthouse_on_pages = true
enable_crux = false
enable_rich_results_validation = false
google_rich_results_api_key =
enable_axe = false
enable_spell_check = false
enable_html_validation = false
enable_amp_audit = false
enable_wayback_lookup = false
competitor_domains =
bing_webmaster_api_key =
serp_api_key =
export_logo_url =
custom_extraction_regex =
crawl_path_segments =
crawl_ignore_params =
lighthouse_max_pages = 2
lighthouse_concurrency = 2

# --- Content analysis ---
enable_duplicate_detection = true
enable_language_detection = true
analysis_fuzzy_threshold = 92
analysis_simhash_hamming = 0
analysis_simhash_max_urls = 800
analysis_fuzzy_max_urls = 600
analysis_dup_max_pages = 2000

# --- Audit steps ---
run_crawl = true
run_report = true
run_plot = true

# --- Google (GSC & GA4) ---
# Google OAuth: Integrations panel (gear icon) → saved in PostgreSQL (google_app_settings + properties)
enable_google_search_console = false
enable_google_analytics = false
google_date_range_days = 28
google_url_gap_list_limit = 200
# enrich_keywords_after_report: omit for auto, or set true/false to override Search Console toggle
# google_credentials_path: removed — use Integrations UI and PostgreSQL only

# --- Basics ---
keyword_max_pages = 200
keyword_gsc_max_rows = 25000
brand_name = 
keyword_seeds = 

# --- Expansion ---
enable_google_suggest = false
enable_google_trends = false
enable_wikipedia_topic = false
enable_datamuse = false
keyword_suggest_top_n = 20
keyword_max_suggest_results = 8

# --- Advanced ---
warning_mapper_input = 
warning_mapper_input_type = lighthouse

# AI insights (OpenAI, Gemini, Claude, Ollama): web UI Run audit → AI tab only (llm_config table).