-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #50 from Umar-Azam/main
modified config.ts to fix containerized execution
- Loading branch information
Showing
1 changed file
with
3 additions
and
26 deletions.
There are no files selected for viewing
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,31 +1,8 @@ | ||
import { Page } from "playwright"; | ||
import { Config } from "./src/config"; | ||
|
||
type Config = { | ||
/** URL to start the crawl */ | ||
url: string; | ||
/** Pattern to match against for links on a page to subsequently crawl */ | ||
match: string; | ||
/** Selector to grab the inner text from */ | ||
selector: string; | ||
/** Don't crawl more than this many pages */ | ||
maxPagesToCrawl: number; | ||
/** File name for the finished data */ | ||
outputFileName: string; | ||
/** Optional cookie to be set. E.g. for Cookie Consent */ | ||
cookie?: { name: string; value: string }; | ||
/** Optional function to run for each page found */ | ||
onVisitPage?: (options: { | ||
page: Page; | ||
pushData: (data: any) => Promise<void>; | ||
}) => Promise<void>; | ||
/** Optional timeout for waiting for a selector to appear */ | ||
waitForSelectorTimeout?: number; | ||
}; | ||
|
||
export const config: Config = { | ||
export const defaultConfig: Config = { | ||
url: "https://www.builder.io/c/docs/developers", | ||
match: "https://www.builder.io/c/docs/**", | ||
selector: `.docs-builder-container`, | ||
maxPagesToCrawl: 50, | ||
outputFileName: "../data/output.json", | ||
}; | ||
}; |