| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748 |
- import type { Page } from "playwright";
- export type Config = {
- /**
- * URL to start the crawl
- * @example "https://www.builder.io/c/docs/developers"
- * @default ""
- */
- url: string;
- /**
- * Pattern to match against for links on a page to subsequently crawl
- * @example "https://www.builder.io/c/docs/**"
- * @default ""
- */
- match: string | string[];
- /**
- * Selector to grab the inner text from
- * @example ".docs-builder-container"
- * @default ""
- */
- selector?: string;
- /**
- * Don't crawl more than this many pages
- * @default 50
- */
- maxPagesToCrawl: number;
- /**
- * File name for the finished data
- * @default "output.json"
- */
- 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;
- /** Optional resources to exclude
- *
- * @example
- * ['png','jpg','jpeg','gif','svg','css','js','ico','woff','woff2','ttf','eot','otf','mp4','mp3','webm','ogg','wav','flac','aac','zip','tar','gz','rar','7z','exe','dmg','apk','csv','xls','xlsx','doc','docx','pdf','epub','iso','dmg','bin','ppt','pptx','odt','avi','mkv','xml','json','yml','yaml','rss','atom','swf','txt','dart','webp','bmp','tif','psd','ai','indd','eps','ps','zipx','srt','wasm','m4v','m4a','webp','weba','m4b','opus','ogv','ogm','oga','spx','ogx','flv','3gp','3g2','jxr','wdp','jng','hief','avif','apng','avifs','heif','heic','cur','ico','ani','jp2','jpm','jpx','mj2','wmv','wma','aac','tif','tiff','mpg','mpeg','mov','avi','wmv','flv','swf','mkv','m4v','m4p','m4b','m4r','m4a','mp3','wav','wma','ogg','oga','webm','3gp','3g2','flac','spx','amr','mid','midi','mka','dts','ac3','eac3','weba','m3u','m3u8','ts','wpl','pls','vob','ifo','bup','svcd','drc','dsm','dsv','dsa','dss','vivo','ivf','dvd','fli','flc','flic','flic','mng','asf','m2v','asx','ram','ra','rm','rpm','roq','smi','smil','wmf','wmz','wmd','wvx','wmx','movie','wri','ins','isp','acsm','djvu','fb2','xps','oxps','ps','eps','ai','prn','svg','dwg','dxf','ttf','fnt','fon','otf','cab']
- */
- resourceExclusions?: string[];
- };
|