Sub GetContent(ByVal URL As String, ByVal SheetName As String)
Dim strText As String
Dim i As Long
Dim OneSpan
Dim IsContent As Boolean With CreateObject("MSXML2.XMLHTTP")
.Open "GET", URL, False
.Send
strText = .responsetext
End With Dim arr() As String
ReDim arr(1 To 1) As String With CreateObject("htmlfile")
.write strText
i = 0
For Each OneSpan In .getElementsByTagName("span")
s = RegReplace(OneSpan.innerhtml, "<.*?>")
s = Replace(s, " ", "") If s = " 排行榜" Then IsContent = False
If IsContent Then
i = i + 1
ReDim Preserve arr(1 To i)
arr(i) = s
'Debug.Print s
'If i = 100 Then Exit For
End If
If s = "分类:" Then IsContent = True Next
End With Dim brr() As String
ReDim brr(1 To 1) brr(1) = arr(1)
M = 1
For n = 2 To i
If RegTest(arr(n - 1), "[A-D].") Or RegTest(arr(n - 1), "^\d*?.??$") Then
brr(M) = brr(M) & arr(n)
Else
M = M + 1
ReDim Preserve brr(1 To M)
brr(M) = arr(n)
End If
Next n For i = 1 To M
'Debug.Print brr(i)
If i = 150 Then Exit For
Next i Set sht = AddWorksheet(ThisWorkbook, SheetName) With sht
.Cells.ClearContents
.Range("A1:A1").Value = Array("内容")
.Range("A2").Resize(M, 1).Value = _
Application.WorksheetFunction.Transpose(brr)
End With End Sub Sub TestRegReplace()
s = "215MY"
s = RegReplace(s, "[A-Z]")
Debug.Print s
End Sub
Public Function RegReplace(ByVal OrgText As String, ByVal Pattern As String, Optional RepStr As String = "") As String
'传递参数 :原字符串, 匹配模式 ,替换字符
Dim Regex As Object
Dim newText As String
Set Regex = CreateObject("VBScript.RegExp")
With Regex
.Global = True
.Pattern = Pattern
End With
newText = Regex.Replace(OrgText, RepStr)
RegReplace = newText
Set Regex = Nothing
End Function Public Function RegTest(ByVal OrgText As String, ByVal Pattern As String) As Boolean
'传递参数 :原字符串, 匹配模式
Dim Regex As Object
Set Regex = CreateObject("VBScript.RegExp")
With Regex
.Global = True
.Pattern = Pattern
End With
RegTest = Regex.TEST(OrgText)
Set Regex = Nothing
End Function Sub dd()
Debug.Print RegTest("13.", "^\d+?.$")
End Sub Function AddWorksheet(ByVal Wb As Workbook, ByVal ShtName As String, Optional ReplaceSymbol As Boolean = True) As Worksheet
Dim sht As Worksheet
If Len(ShtName) = 0 Or Len(ShtName) > 31 Then
Set AddWorksheet = Nothing
MsgBox "Worksheet名称长度不符!", vbInformation, "AddWorksheet"
Exit Function
Else
On Error Resume Next
Set sht = Wb.Worksheets(ShtName)
If Err.Number = 9 Then
Set sht = Wb.Worksheets.Add(After:=Wb.Worksheets(Wb.Worksheets.Count))
Err.Clear
On Error GoTo 0
On Error Resume Next
sht.Name = ShtName
If Err.Number = 1004 Then
Err.Clear
On Error GoTo 0
If ReplaceSymbol Then
arr = Array("/", "\", "?", "*", "[", "]")
For i = LBound(arr) To UBound(arr)
ShtName = Replace(ShtName, arr(i), "")
Next i
Set AddWorksheet = AddWorksheet(Wb, ShtName) '再次调用
Else
Set AddWorksheet = Nothing
MsgBox "Worksheet名称含有特殊符号!", vbInformation, "AddWorksheet"
End If
Else
Set AddWorksheet = sht
End If
ElseIf Err.Number = 0 Then
Set AddWorksheet = sht
End If
End If
End Function

  

GetContent的更多相关文章

  1. 对Get-Content参数-readcount的解释

    绝大多数用户更关心最新的日志,下面给出一个简单的例子演示从一个文本日志中获取最后的某几行文本行:   # 显示windowsupdate.log 文件的最新5行日志 $logs = Get-Conte ...

  2. Why should i use url.openStream instead of of url.getContent?

    I would like to retrieve the content of a url. Similar to pythons: html_content = urllib.urlopen(&qu ...

  3. RecyclerView使用大全

    RecylerView介绍 RecylerView是support-v7包中的新组件,是一个强大的滑动组件,与经典的ListView相比,同样拥有item回收复用的功能,这一点从它的名字recyler ...

  4. HttpClient的替代者 - RestTemplate

    需要的包 ,除了Spring的基础包外还用到json的包,这里的数据传输使用json格式 客户端和服务端都用到一下的包 <!-- Spring --> <dependency> ...

  5. Socket聊天程序——Common

    写在前面: 上一篇记录了Socket聊天程序的客户端设计,为了记录的完整性,这里还是将Socket聊天的最后一个模块--Common模块记录一下.Common的设计如下: 功能说明: Common模块 ...

  6. Socket聊天程序——客户端

    写在前面: 上周末抽点时间把自己写的一个简单Socket聊天程序的初始设计和服务端细化设计记录了一下,周二终于等来毕业前考的软考证书,然后接下来就是在加班的日子度过了,今天正好周五,打算把客户端的详细 ...

  7. PowerShell过滤文件中的重复内容

    Get-Content -Path E:\test11\data.txt | Sort-Object | Get-Unique 源文件: AA0001 2014-06-30 15:27:13.073 ...

  8. [转]利用URLConnection来发送POST和GET请求

    URL的openConnection()方法将返回一个URLConnection对象,该对象表示应用程序和 URL 之间的通信链接.程序可以通过URLConnection实例向该URL发送请求.读取U ...

  9. HttpUrlConnection 基础使用

    From https://developer.android.com/reference/java/net/HttpURLConnection.html HttpUrlConnection: A UR ...

随机推荐

  1. Object-C-系统类型对象归档

    系统类型主要是指NSString NSDictionary,NSArray,NSData,NSNumber 类型数据(包括对应可变类型); 这些类型已经实现了NSCoding协议,支持归档, 写入方法 ...

  2. CQRS/ES框架调研

    1.Enode一个C#写的CQRS/ES框架,由汤雪华设计及实现,github上有相关源码,其个人博客上有详细的孵化.设计思路.版本迭代及最新的完善: 2.axon framwork,java编写,网 ...

  3. [转载]INNER JOIN连接两个表、三个表、五个表的SQL语句

    SQL INNER JOIN关键字表示在表中存在至少一个匹配时,INNER JOIN 关键字返回行. 1.连接两个数据表的用法: FROM Member INNER JOIN MemberSort O ...

  4. web前端----JavaScript的DOM(二)

    前面在DOM一中我们知道了属性操作,下面我们来了解一下节点操作.很重要!! 一.节点操作 创建节点:var ele_a = document.createElement('a');添加节点:ele_p ...

  5. MySQL Crash Course #10# Chapter 19. Inserting Data

    INDEX BAD EXAMPLE Improving Overall Performance Inserting Multiple Rows INSTEAD OF Inserting a Singl ...

  6. Python Web学习笔记之TCP/IP、Http、Socket的区别

    经常在笔试.面试或者工作的时候听到这些协议,虽然以前没怎么涉及过,但至少知道这些是和网络编程密不可分的知识,作为一个客户端开发程序员,如果可以懂得网络编程的话,他的作用和能力肯定会提升一个档次.原因很 ...

  7. Java随机获取32位密码且必须包含大小写字母、数字和特殊字符,四种的任意三种

    Java随机获取32位密码且必须包含大小写字母.数字和特殊字符,四种的任意三种 Java随机获取32位密码且必须包含大小写字母.数字和特殊字符,四种的任意三种,代码如下: import java.ut ...

  8. Python之CMDB资产管理系统

    最近正好在给公司做CMDB资产管理系统,现在做的也差不多了,现在回头吧思路整理下. CMDB介绍 CMDB --Configuration Management Database 配置管理数据库, C ...

  9. WIFI模块对比介绍

    一.ESP8266(官网 https://espressif.com/)1 简介 乐鑫智能互联平台——ESCP 拥有高性能无线SOC,给移动平台设计师带来福音,它 以最低成本提供最大实用性,为WiFi ...

  10. Java 创建多线程的三种方法

    1. 继承Thread类2. 实现Runnable接口3. 匿名类的方式 注: 启动线程是start()方法,run()并不能启动一个新的线程