Created
September 16, 2022 15:45
-
-
Save cigzigwon/c81078861d28090b7de9fdbc36d49df4 to your computer and use it in GitHub Desktop.
Crawly Config for WAFs and JL File Writer
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
config :revo, | |
:user_agent, | |
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:84.0) Gecko/20100101 Firefox/84.0" | |
config :revo, :wait_intervals, [30_000, 45_000, 60_000, 65_000, 76_000] | |
config :crawly, | |
concurrent_requests_per_domain: 1, | |
closespider_timeout: 1, | |
manager_operations_timeout: 5 * 60_000, | |
middlewares: [ | |
Crawly.Middlewares.DomainFilter, | |
Crawly.Middlewares.UniqueRequest, | |
{Crawly.Middlewares.UserAgent, | |
user_agents: [ | |
# "Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)", | |
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:84.0) Gecko/20100101 Firefox/84.0" | |
]}, | |
{Crawly.Middlewares.RequestOptions, [timeout: 16_000]} | |
], | |
pipelines: [ | |
Crawly.Pipelines.JSONEncoder, | |
{Crawly.Pipelines.WriteToFile, folder: "/app/priv/data", extension: "jl"} | |
] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment