解决HttpWebRequest和HtmlAgilityPack采集网页中文乱码问题

作者：袖梨 2022-06-25

代码如下

复制代码

public Encoding GetEncoding(string CharacterSet)
{
switch (CharacterSet)
{
case "gb2312": return Encoding.GetEncoding("gb2312");
case "utf-8": return Encoding.UTF8;
default: return Encoding.Default;
}
}
public string HttpGet(string url)
{
string responsestr = "";
HttpWebRequest req = HttpWebRequest.Create(url) as HttpWebRequest;
req.Accept = "*/*";
req.Method = "GET";
req.UserAgent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1";
using (HttpWebResponse response = req.GetResponse() as HttpWebResponse)
{
Stream stream;
if (response.ContentEncoding.ToLower().Contains("gzip"))
{
stream = new GZipStream(response.GetResponseStream(), CompressionMode.Decompress);
}
else if (response.ContentEncoding.ToLower().Contains("deflate"))
{
stream = new DeflateStream(response.GetResponseStream(), CompressionMode.Decompress);
}
else
{
stream = response.GetResponseStream();
}
using (StreamReader reader = new StreamReader(stream, GetEncoding(response.CharacterSet)))
{
responsestr = reader.ReadToEnd();
stream.Dispose();
}
}
return responsestr;
}

调用HttpGet就可以获取网址的源码了，得到源码后，现在用一个利器HtmlAgility来解析html了，不会正则不要紧，此乃神器啊。老板再也不用担心我的正则表达式了。

至于这个神器的用法，园子文章很多，写的也都挺详细的，在此不赘余了。

下面是抓取园子首页的文章列表：

代码如下

复制代码

string html = HttpGet("http://www.111com.net/");
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(html);
//获取文章列表
var artlist = doc.DocumentNode.SelectNodes("//div[@class='post_item']");
foreach (var item in artlist)
{
HtmlDocument adoc = new HtmlDocument();
adoc.LoadHtml(item.InnerHtml);
var html_a = adoc.DocumentNode.SelectSingleNode("//a[@class='titlelnk']");
htm = htm&(string.Format("标题为：{0}，链接为：{1}
",html_a.InnerText,html_a.Attributes["href"].Value));
}

好了运行有中文的网页是没有问题的哦，取出来的截图我就不介绍了，当然大家可进行一些调整处理，本文章主要是介绍解决中文乱码问题。