我正在尝试下载
" https://www.google.com/search?sclient=psy-ab&biw=1472&bih=740&espv=2&tbm=vid&btnG=Search&q=%25%25%25#q=iran&tbm=nws&#34 ;;
通过以下代码:
string url = "https://www.google.com/search?sclient=psy-ab&biw=1472&bih=740&espv=2&tbm=vid&btnG=Search&q=%25%25%25#q=iran&tbm=nws";
try
{
string htmlPage = "";
//http request preparing
CookieContainer CC = new CookieContainer();
HttpWebRequest objRequest = (HttpWebRequest)WebRequest.Create(url);
objRequest.Timeout = 60000;
objRequest.Proxy = null;
objRequest.UseDefaultCredentials = true;
objRequest.KeepAlive = false; //THIS DOES THE TRICK
objRequest.ProtocolVersion = HttpVersion.Version10; // THIS DOES THE TRICK
objRequest.CookieContainer = CC;
//http request sending
using (HttpWebResponse objResponse = (HttpWebResponse)objRequest.GetResponse())
{
using (Stream strm = objResponse.GetResponseStream())
{
using (StreamReader objStreamReader = new StreamReader(strm))
{
htmlPage = objStreamReader.ReadToEnd();
}
}
};
if (htmlPage.Contains("No results found for") || htmlPage.Contains("(without quotes):") || htmlPage.Contains("Make sure all words are spelled correctly."))
{
return dtResult;
}
else
{
Regex objEgEx = new Regex(@"[\r\n][ ]+\.[\r\n][ ]+");
htmlPage = objEgEx.Replace(htmlPage, string.Empty);
int startIndex = htmlPage.IndexOf("<div class =\"g\">");
if (startIndex == -1)
{ Console.Write("problem in parsing"); }
但是HttpWebRequest下载谷歌的第一页而不是我为它保存的网址,这是Google搜索结果的视频搜索服务的地址&#39;页。 我该怎么做才能下载我想要的网址?
答案 0 :(得分:1)
您正在下载页面,而不是查询。由于搜索谷歌没有加载新页面但更新页面。也许看看google search api