# pywb config file
# ========================================
#
# Settings for each collection
collections:
# <name>: <cdx_path>
# collection will be accessed via /<name>
# <cdx_path> 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*']
pywb-filt-2:
index_paths: './sample_archive/cdx/'
filters: ['!filename:dupe*']
pywb-nonframe:
index_paths: './sample_archive/cdx/'
framed_replay: false
# collection of non-surt CDX
pywb-nosurt:
index_paths: './sample_archive/non-surt-cdx/'
surt_ordered: false
# live collection
live: $liveweb
# coll with fallback
pywb-fallback:
index_paths: ./sample_archive/cdx/
fallback: live
pywb-norange:
index_paths: ./sample_archive/cdx/
enable_ranges: false
pywb-non-exact:
index_paths: ./sample_archive/cdx/
redir_to_exact: false
pywb-cdxj:
index_paths: ./sample_archive/cdxj/
# 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)/
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:<warc> as key
archive_paths: ['./invalid/path/to/ignore/', './sample_archive/warcs/']
# ==== Optional UI: HTML/Jinja2 Templates ====
# template for <head> insert into replayed html content
head_insert_html: templates/head_insert.html
# template to for 'calendar' query,
# eg, a listing of captures in response to a ../*/<url>
#
# may be a simple listing or a more complex 'calendar' UI
# if omitted, will list raw cdx in plain text
query_html: templates/query.html
# template for search page, which is displayed when no search url is entered
# in a collection
search_html: templates/search.html
# template for home page.
# if no other route is set, this will be rendered at /, /index.htm and /index.html
home_html: templates/index.html
# error page temlpate for may formatting error message and details
# if omitted, a text response is returned
error_html: templates/error.html
# template for 404 not found error, may be customized per collection
not_found_html: templates/not_found.html
# ==== Other Paths ====
# Rewrite urls with absolute paths instead of relative
absoulte_paths: true
# List of route names:
# <route>: <package or file path>
static_routes:
static/test/route: pywb/static/
static/__pywb: pywb/static/
# Enable simple http proxy mode
enable_http_proxy: true
# Additional proxy options (defaults)
proxy_options:
use_default_coll: pywb
cookie_resolver: false
use_client_rewrite: true
use_wombat: true
#enable coll info JSON
enable_coll_info: true
# enable cdx server api for querying cdx directly (experimental)
#enable_cdx_api: True
# or specify suffix
enable_cdx_api: -cdx
# test different port
port: 9000
# optional reporter callback func
# if set, called with request and cdx object
reporter: !!python/object/new:tests.fixture.PrintReporter []
# custom rules for domain specific matching
#domain_specific_rules: rules.yaml
# Use lxml parser, if available
# use_lxml_parser: true
# Replay content in an iframe
framed_replay: true
# ==== New / Experimental Settings ====
# Not yet production ready -- used primarily for testing
#perms_checker: !!python/object/new:pywb.cdx.perms.AllowAllPerms []
perms_policy: !!python/name:tests.perms_fixture.perms_policy
# not testing memento here
enable_memento: False
# Debug Handlers
debug_echo_env: True
debug_echo_req: True