wsh爬虫

前言

了解学习了下wsh爬虫，虽然只能简单的爬取，但是还是挺方便的。vbs语法还不太会，只能单页爬取，下面js代码可以爬取某多页的文档的内容。

请在控制台中运行，否则的话，你将会出现N多弹框。
以下是js运行结果：

js

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
var html = new ActiveXObject("htmlfile")
var http = new ActiveXObject("Msxml2.ServerXMLHTTP")

var PageNum = 0;
while (PageNum < 42) {
  PageNum++;
  html.designMode = "on"
  var url = "http://www.doczj.com/doc/0f47f800a6c30c2259019e5e-" + PageNum + ".html";
  http.open("GET", url)
  http.send
  strHtml = http.responseText
 
  html.write(strHtml)
  var text = html.getElementById("contents")
  WSH.Echo (text.innerText)
  WSH.Echo("--------------------------------------------------------------------------------------------")
  html.designMode = "off"
}

vbs

1
2
3
4
5
6
7
8
9
10
11
12
Set html = CreateObject("htmlfile")
Set http = CreateObject("Msxml2.ServerXMLHTTP")
 
html.designMode = "on" 'enable edit mode
 
http.open "GET", "http://www.doczj.com/doc/0f47f800a6c30c2259019e5e-1.html", False
http.send
strHtml = http.responseText
 
html.write strHtml 'write data
Set bln = html.getElementById("contents")
WSH.Echo (bln.innerText)

参考文献

Method of parsing HTML document by VBS (htmlfile)