50 lines
1.4 KiB
TOML
50 lines
1.4 KiB
TOML
# By Nic Weyand! Operator example; use absolute writable paths.
|
|
cache = "/var/lib/argand-site-registry/cache"
|
|
database = "/var/lib/argand-site-registry/import.sqlite"
|
|
generations = "/var/lib/argand-site-registry/generations"
|
|
|
|
[[downloads]]
|
|
source = "psl"
|
|
format = "psl_text"
|
|
url = "https://publicsuffix.org/list/public_suffix_list.dat"
|
|
snapshot = "{date}"
|
|
scope = "full"
|
|
maximum_bytes = 1000000
|
|
|
|
[[downloads]]
|
|
source = "wikidata"
|
|
format = "wikidata_entities"
|
|
url = "https://www.wikidata.org/w/api.php?action=wbgetentities&ids=Q355%7CQ3884&format=json&maxlag=5"
|
|
snapshot = "{date}"
|
|
scope = "selection:facebook-amazon"
|
|
maximum_bytes = 5000000
|
|
|
|
[[downloads]]
|
|
source = "majestic"
|
|
format = "majestic_csv"
|
|
url = "https://downloads.majestic.com/majestic_million.csv"
|
|
snapshot = "{date}"
|
|
scope = "full"
|
|
maximum_bytes = 250000000
|
|
|
|
[[downloads]]
|
|
source = "curlie"
|
|
format = "curlie_tar_gz"
|
|
url = "https://curlie.org/directory-dl"
|
|
snapshot = "{date}"
|
|
scope = "full"
|
|
maximum_bytes = 1000000000
|
|
|
|
# Optional pinned acquisitions; repeat [[inputs]] for each source.
|
|
# [[inputs]]
|
|
# input = "/data/source-object.gz"
|
|
# manifest = "/data/source.json"
|
|
|
|
# CrUX is deliberately opt-in: provide your authorized project, positive billing
|
|
# cap, and GOOGLE_OAUTH_ACCESS_TOKEN through the scheduler credential environment.
|
|
# [[crux]]
|
|
# project = "your-billing-project"
|
|
# month = "{previous_month}"
|
|
# country = "GB"
|
|
# maximum_bytes_billed = 1000000000
|
|
# maximum_output_bytes = 500000000
|