1.0.7 • Published 7 years ago

a-spider v1.0.7

Weekly downloads
34
License
-
Repository
github
Last release
7 years ago

spider.js

A simple node spider

Install

npm install a-spider --save

Usage

  • Definition
/**
 * Web Spider
 * 
 * @param {Array|string} list - page urls
 * @param {function} callback - handle callback, (html,url)=>next url
 * @param {object}   options  - advanced options 
 * <pre>
 * {
    spiderDelay = 0, //get delay (ms)
    spiderBrowserSim = true, //simulate a browser
    spiderBrowserSimType = "pc", //simulate browser type, available now : pc, android, iphone, ipad
    spiderComplete, //complete callback
    spiderConcurrency = 1, //max concurrency
    ...rpOptions //other request options, see https://www.npmjs.com/package/request-promise
  }
  </pre>
 */
export default function spider(
  list,
  callback,
  {
    spiderDelay = 0, //get delay (ms)
    spiderBrowserSim = true, //simulate a browser
    spiderBrowserSimType = "pc", //simulate browser type, available now : pc, android, iphone, ipad
    spiderComplete, //complete callback
    ...rpOptions //other request options, see https://www.npmjs.com/package/request-promise
  }
) 
  • Example
var spider = require("a-spider");
//test
spider(
  "your start url or url list",
  html => {
    //your handle code    
  }
);

Debug Info

set DEBUG=*,-spider.js    # hide debug info, see https://www.npmjs.com/package/debug
1.0.7

7 years ago

1.0.6

7 years ago

1.0.5

7 years ago

1.0.4

7 years ago

1.0.3

7 years ago

1.0.2

7 years ago

1.0.1

7 years ago

1.0.0

7 years ago