pup-crawler/dist/index.d.ts

A simple web crawler that extracts data from websites, using Node.js and Puppeteer.

import { Browser, LaunchOptions, Page } from 'puppeteer';
import type { IProps, CrawlOptions, CrawlOptionsCore, Target, obj } from './types.d.ts';
declare class PupCrawler {
    browser: Browser | undefined;
    url: string | undefined;
    host: string;
    states: obj;
    showLog?: boolean;
    constructor(props?: IProps);
    open(options?: LaunchOptions): Promise<void>;
    close(): Promise<void>;
    setValue(key: string, value: any): void;
    getValue(key: string): any;
    /** 循环获取 */
    loopQueue(result: obj, options: {
        target: any;
    }): Promise<obj>;
    /** 自循环 */
    recursionRun(result: obj, options: CrawlOptions): Promise<obj>;
    /** 自定义dom解析器 */
    domParser(win: any, values: Target['values']): obj[];
    /** 页面操作 */
    actionsPlug(page: Page, actions: any[]): Promise<true | undefined>;
    /** 爬取内容核心 */
    crawlCore(params: CrawlOptionsCore): Promise<obj>;
    /** 爬取静态页面 */
    crawlStaticPage(params: CrawlOptions): Promise<obj>;
    /** 爬取页面属性：CrawlPageOptions */
    crawlPage(params: CrawlOptions): Promise<obj>;
}
export { PupCrawler, CrawlOptions };