# pywb config file # ======================================== # # Settings for each collection use_js_obj_proxy: true collections: # : # collection will be accessed via / # is a string or list of: # - string or list of one or more local .cdx file # - string or list of one or more local dirs with .cdx files # - a string value indicating remote http cdx server pywb: ./sample_archive/cdx/ # ex with filtering: filter CDX lines by filename starting with 'dupe' #pywb-filt: {'index_paths': './sample_archive/cdx/', 'filters': ['filename:dupe*']} # indicate if cdx files are sorted by SURT keys -- eg: com,example)/ # SURT keys are recommended for future indices, but non-SURT cdxs # are also supported # # * Set to true if cdxs start with surts: com,example)/ # * Set to false if cdx start with urls: example.com)/ # # default: # surt_ordered: true # list of paths prefixes for pywb look to 'resolve' WARC and ARC filenames # in the cdx to their absolute path # # if path is: # * local dir, use path as prefix # * local file, lookup prefix in tab-delimited sorted index # * http:// path, use path as remote prefix # * redis:// path, use redis to lookup full path for w: as key archive_paths: ./sample_archive/warcs/ # ==== Proxy Mode ==== # Enable simple http proxy mode enable_http_proxy: true # Additional proxy options (defaults) # proxy_options: # enable HTTPS proxy support (requires openssl library) # enable_https_proxy: false # # use cookies to switch collections and capture times # if not enabled, requires use of proxy auth # cookie_resolver: true # # default collection to start out in proxy mode # if not set, will ask the first time # use_default_coll: pywb # use wildcard certificates when creating certs in proxy mode # helps lower number of certs created, by may not be compatible # with older libraries # use_wildcard_certs: true # if true, will not add any banner to proxy mode replay # unaltered_replay: false # Default settings for CA used by proxy mode: # root_ca_file: ./ca/pywb-ca.pem # root_ca_name: pywb https proxy replay CA # certs_dir: ./ca/certs # ==== UI: HTML/Jinja2 Templates ==== # The following are default settings -- uncomment to change # Set to '' to disable the ui # template for insert into replayed html content #head_insert_html: ui/head_insert.html # # # template for just the banner modifications # set to False to disable completely #banner_html: banner.html # template to for 'calendar' query, # eg, a listing of captures in response to a ../*/ # # may be a simple listing or a more complex 'calendar' UI # if omitted, will list raw cdx in plain text #query_html: ui/query.html # template for search page, which is displayed when no search url is entered # in a collection #search_html: ui/search.html # template for home page. # if no other route is set, this will be rendered at /, /index.htm and /index.html #home_html: ui/index.html # error page temlpate for may formatting error message and details # if omitted, a text response is returned #error_html: ui/error.html # ==== Other Paths ==== # Rewrite urls with absolute paths instead of relative #absoulte_paths: true # List of route names: # : # default route static/__pywb for pywb bundled static files #static_routes: # static/__pywb: pywb/static/ # enable cdx server api for querying cdx directly (experimental) enable_cdx_api: true # custom rules for domain specific matching # set to false to disable #domain_specific_rules: rules.yaml # Memento support, enable enable_memento: true # Replay content in an iframe framed_replay: true # debugging utility -- echo request data # debug_echo_env: false