[已解决]请教网页数据抓取问题

yizhih

前一贴可能没说清楚，另发一贴请教。
网页http://www.ygqq.com/goods/goods831-54.html，要取“第54期”中的“所有参与记录”选项卡中共237页的“时间，昵称，参与人次”3个字段的数据，“昵称”中的照片不要，“参与人次”中只要前面的数字，隐藏其中的“查看夺宝码”几个字及后面的夺宝码都不要。谢谢！

最佳答案

月排行榜 / 总排行榜

xdragon

2016-4-4 08:08

整理了下，完整代码如下。。。

1. Sub main()
   
2.     Dim Size As String, result()
   
3.     Size = Split(Split(getResponsetext("gid=831&pid=54&size=1"), "total"":")(1), ",")(0)
   
4.     InvenstDetail = getResponsetext("gid=831&pid=54&size=" & Size) '后续就是对InvestArr的处理。需要的字段为 bytime ,bytimes, nicname,
   
5.     tmp = Split(InvenstDetail, "buyTimes"":")
   
6.     ReDim result(Size, 1 To 3)
   
7.     For i = 1 To UBound(tmp) '参与人次
   
8.         result(i, 3) = Split(tmp(i), ",")(0)
   
9.     Next
   
10.     tmp = Split(InvenstDetail, "buyTime"":")
    
11.     For i = 1 To UBound(tmp) '时间
    
12.         result(i, 1) = FROM_UNIXTIME(Split(tmp(i), ",")(0))
    
13.     Next
    
14.     tmp = Split(InvenstDetail, "nickname"":""") '昵称
    
15.     InvenstDetail = ""
    
16.     For i = 1 To UBound(tmp)
    
17.         result(i, 2) = Split(tmp(i), "")(0)
    
18.     Next
    
19.     Erase tmp
    
20.     result(0, 1) = "时间": result(0, 2) = "昵称": result(0, 3) = "参与人次"
    
21.     Cells.Clear
    
22.     Range("A1").Resize(UBound(result), 3) = result
    
23. End Sub
    
24. 
    
25. Function getResponsetext(sendStr As String)
    
26.     With CreateObject("MSXML2.XMLHTTP")
    
27.         .Open "POST", "http://www.ygqq.com/goods/timeline.do?t=0.7006472381931250", False '登录
    
28.         .setrequestheader "Referer", "http://www.ygqq.com/goods/goods831-54.html"
    
29.         .setrequestheader "User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:45.0) Gecko/20100101 Firefox/45.0"
    
30.         .setrequestheader "Accept", "application/json, text/javascript, */*; q=0.01"
    
31.         .setrequestheader "X-Requested-With", "XMLHttpRequest"
    
32.         .setrequestheader "Content-Length", "22"
    
33.         .setrequestheader "Host", "www.ygqq.com"
    
34.         .setrequestheader "Content-Type", "application/x-www-form-urlencoded; charset=UTF-8"
    
35.         .setrequestheader "Accept-Language", "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3"
    
36.         .setrequestheader "Accept-Encoding", "gzip, deflate"
    
37.         .send sendStr '获取记录条数
    
38.         getResponsetext = .responsetext
    
39.     End With
    
40. End Function
    
41. 
    
42. Function FROM_UNIXTIME(UNIXTIME) As String
    
43.     FROM_UNIXTIME = Format((UNIXTIME / 1000 + 8 * 3600) / 86400 + 70 * 365 + 19, "yyyy-mm-dd hh:mm:ss:") & Right(UNIXTIME, 3)
    
44. End Function
    

复制代码

跳转到最佳答案楼层

02761752696

http://www.excelpx.com/thread-387018-1-1.html

xdragon

见下楼。。。。

xdragon

整理了下，完整代码如下。。。

1. Sub main()
   
2.     Dim Size As String, result()
   
3.     Size = Split(Split(getResponsetext("gid=831&pid=54&size=1"), "total"":")(1), ",")(0)
   
4.     InvenstDetail = getResponsetext("gid=831&pid=54&size=" & Size) '后续就是对InvestArr的处理。需要的字段为 bytime ,bytimes, nicname,
   
5.     tmp = Split(InvenstDetail, "buyTimes"":")
   
6.     ReDim result(Size, 1 To 3)
   
7.     For i = 1 To UBound(tmp) '参与人次
   
8.         result(i, 3) = Split(tmp(i), ",")(0)
   
9.     Next
   
10.     tmp = Split(InvenstDetail, "buyTime"":")
    
11.     For i = 1 To UBound(tmp) '时间
    
12.         result(i, 1) = FROM_UNIXTIME(Split(tmp(i), ",")(0))
    
13.     Next
    
14.     tmp = Split(InvenstDetail, "nickname"":""") '昵称
    
15.     InvenstDetail = ""
    
16.     For i = 1 To UBound(tmp)
    
17.         result(i, 2) = Split(tmp(i), "")(0)
    
18.     Next
    
19.     Erase tmp
    
20.     result(0, 1) = "时间": result(0, 2) = "昵称": result(0, 3) = "参与人次"
    
21.     Cells.Clear
    
22.     Range("A1").Resize(UBound(result), 3) = result
    
23. End Sub
    
24. 
    
25. Function getResponsetext(sendStr As String)
    
26.     With CreateObject("MSXML2.XMLHTTP")
    
27.         .Open "POST", "http://www.ygqq.com/goods/timeline.do?t=0.7006472381931250", False '登录
    
28.         .setrequestheader "Referer", "http://www.ygqq.com/goods/goods831-54.html"
    
29.         .setrequestheader "User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:45.0) Gecko/20100101 Firefox/45.0"
    
30.         .setrequestheader "Accept", "application/json, text/javascript, */*; q=0.01"
    
31.         .setrequestheader "X-Requested-With", "XMLHttpRequest"
    
32.         .setrequestheader "Content-Length", "22"
    
33.         .setrequestheader "Host", "www.ygqq.com"
    
34.         .setrequestheader "Content-Type", "application/x-www-form-urlencoded; charset=UTF-8"
    
35.         .setrequestheader "Accept-Language", "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3"
    
36.         .setrequestheader "Accept-Encoding", "gzip, deflate"
    
37.         .send sendStr '获取记录条数
    
38.         getResponsetext = .responsetext
    
39.     End With
    
40. End Function
    
41. 
    
42. Function FROM_UNIXTIME(UNIXTIME) As String
    
43.     FROM_UNIXTIME = Format((UNIXTIME / 1000 + 8 * 3600) / 86400 + 70 * 365 + 19, "yyyy-mm-dd hh:mm:ss:") & Right(UNIXTIME, 3)
    
44. End Function
    

复制代码

yizhih

xdragon 发表于 2016-4-4 08:08
整理了下，完整代码如下。。。

万分感谢，像这样类似的网站太不容易抓取数据了，您的水平相当高，再一次感谢您！