日期:2014-5-18 浏览次数:20337次

C#抓取谷歌的搜索结果
大家好,怎么用C#抓取谷歌的搜索结果,哪个高手有写过呢。谢谢

------解决方案--------------------
http://blog.csdn.net/lsgy2008/article/details/6308544
------解决方案--------------------
做过获取百度的 用的HtmlAgilityPack
给你找下代码
------解决方案--------------------
private void button10_Click(object sender, EventArgs e)
{
if (ValidData.IsEmpty(textBox1.Text, "关键字不能为空,请核对!") == false) { textBox2.Focus(); return; }
else if (ValidData.IsEmpty(textBox2.Text, "长度不能为空,请核对!") == false) { textBox2.Focus(); return; }
else if (ValidData.IsNumber(textBox2.Text, "数量必须为整数") == false) { textBox2.Focus(); return; }

if (int.Parse(textBox2.Text) > 100)
{
MessageBox.Show("数量不能超过100(百度内置上限)", "系统提示", MessageBoxButtons.OK, MessageBoxIcon.Error);
return;
}

string url = "http://www.baidu.com/s?wd=" + textBox1.Text + "&rn=" + int.Parse(textBox2.Text) + "";
HtmlAgilityPack.HtmlDocument hd = GetHtmlDocumentFromLink(url);

this.Text = getTitle(hd);
MainContent(hd);
}






public void MainContent(HtmlAgilityPack.HtmlDocument hd)
{
if (hd == null)
return;
richTextBox3.Text = "";
//贴吧、新闻、商品搜索、软件
SpecialType(hd);

for (int i = 0; i < int.Parse(textBox2.Text)+10; i++)
{
try
{
HtmlNode navNode = hd.GetElementbyId(i.ToString());
string allXPath = navNode.XPath + "/tr[1]/td[1]/h3[1]";
string title = hd.DocumentNode.SelectSingleNode(allXPath).InnerText;
richTextBox3.AppendText("标题:" + title.Trim() + "\r\n");
////地址
string adr = hd.DocumentNode.SelectSingleNode(allXPath + "/a[1]").Attributes["href"].Value;
richTextBox3.AppendText("地址:" + adr + "\r\n");

//百度快照日期
string pDateXPath = navNode.XPath + "/tr[1]/td[1]/font[1]/span[1]";
string pDate = hd.DocumentNode.SelectSingleNode(pDateXPath).InnerText;
if (pDate != string.Empty)
{
richTextBox3.AppendText("百度快照:" + pDate + "\r\n");
string dataP = Regex.Match(pDate, @"\d{4}([-/])\d{1,2}\1\d{1,2}").Value;
richTextBox3.AppendText("快照日期:" + dataP + "\r\n\r\n");
}
else
richTextBox3.AppendText("\r\n\r\n");
}
catch (Exception)
{
richTextBox3.AppendText("\r\n");
}
}
}