GetContent
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
- 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 ...
- 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 ...
- 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 ...
- 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> ...
- 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 ...
- 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 ...
- 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 ...
- [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 ...
- HttpUrlConnection 基础使用
From https://developer.android.com/reference/java/net/HttpURLConnection.html HttpUrlConnection: A UR ...
随机推荐
- VS添加节点
很喜欢添加节点来减少代码的长度,方便阅读:VS快捷键和相关设置
- quartz-job实现实时或定时发送短信任务
存放调度器(Job 和 Trigger)信息的xml配置文件: 这是某个指定的要实现的定时任务: <!-- 每天给项目经理发送短信避免短信服务挂了 定时每天08:30执行--> <j ...
- oracle_存储过程小记
# 刷新会员标签函数 {color:red} fun_refresh_code{color} {noformat}CREATE OR REPLACE FUNCTION fun_refresh_code ...
- JS方法的使用
$("#yingxiang_id li").each(function () { if ($(this).find(".div-relative").attr( ...
- NSDictionary打印编码改中文的方法
1,转NSData NSData *jsonData = [NSJSONSerialization dataWithJSONObject:json options:NSJSONWritingPrett ...
- PHP多进程并行执行php脚本
<?php //fork.php $cmds = [ '/data/wwwroot/default/test1.php', '/data/wwwroot/default/test2.php', ...
- 使整个页面变灰的css代码
* { filter:progid:DXImageTransform.Microsoft.BasicImage(grayscale=); -webkit-filter: grayscale(%); - ...
- [c/c++]指针(3)
在指针2中提到了怎么用指针申配内存,但是,指针申配的内存不会无缘无故地 被收回.很多poj上的题都是有多组数据,每次地数组大小会不同,所以要重新申请 一块内存.但是原来的内存却不会被收回,也是说2.3 ...
- Git 基础笔记整理1
Git 官网:http://git-scm.com/ git教程1:http://www.yiibai.com/git/home.html git教程2 :http://www.liaoxuefeng ...
- Python3基础 生成器推导式 简单示例
Python : 3.7.0 OS : Ubuntu 18.04.1 LTS IDE : PyCharm 2018.2.4 Conda ...