以文本方式查看主题 - Foxtable(狐表) (http://foxtable.com/bbs/index.asp) -- 专家坐堂 (http://foxtable.com/bbs/list.asp?boardid=2) ---- 采集问题 (http://foxtable.com/bbs/dispbbs.asp?boardid=2&id=49717) |
-- 作者:qianqian1530 -- 发布时间:2014/4/23 9:31:00 -- 采集问题 <a href="/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0CCcQFjAA&url=https%3A%2F%2Ftwitter.com%2Fqianqian1530&ei=yRZXU5LmDNXg8AWUuYKQDA&usg=AFQjCNES11WK2hesooh-A1SPS_cas9xI9w" data-href="https://twitter.com/qianqian1530">qianqian1530 on Twitter</a> 我想采集的是 data-href="内容" 的 但 每次 我都采集到 qianqian1530 on Twitter 怎么解决呢? \'\'\' Dim web As New System.Windows.Forms.WebBrowser Dim ide As Integer For ide= 0 To 1 Step 1 Dim ides As Integer e.Form.Controls("Label15").text = ide ides = ide *10 web.Navigate("https://www.google.co.jp/#filter=0&q=%E5%9C%B0%E7%90%83&start=" & ides) Do Until web.ReadyState = 4 Application.DoEvents Loop Dim elems As System.Windows.Forms.HtmlElementCollection Elems = web.Document.GetElementsByTagName("OL") \'根据标签得到数据集合 For Each elem As System.Windows.Forms.Htmlelement In elems Dim sa As Integer If elem.GetAttribute("Id") Like "rso" Then For sa= 0 To 100 Step 1 If elem.GetElementsByTagName("H3").Count =sa Then Exit For Else Dim e_Info As System.Windows.Forms.HtmlElement = elem.GetElementsByTagName("H3")(sa) Dim e1 As System.Windows.Forms.HtmlElement = e_Info.GetElementsByTagName("A")(0) Dim e_Info1 As System.Windows.Forms.HtmlElement = elem.GetElementsByTagName("A")(sa) Dim r As Row = Tables("表A").AddNew r("网页名") = e1.InnerText r("URL") = e_Info1.InnerText End If Next End If Next Next |
-- 作者:Bin -- 发布时间:2014/4/23 9:35:00 -- r("URL") = e_Info1.GetAttribute("data-href") |