C#采集类

最新推荐文章于 2018-11-16 15:02:41 发布

原创最新推荐文章于 2018-11-16 15:02:41 发布 · 672 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#c# #stream #string #exception #html #url

本文介绍了一种高效获取网页源代码的方法，包括处理不同网页编码格式的技术细节。通过使用C#语言，提供了三种不同的方法来适应各种网页结构，确保能够准确地抓取到所需的网页内容。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

}class CaiJi { /// <summary> /// 取得网页源码 /// </summary> /// <param name="url">网页地址，eg:"http://www.yongfa365.com/" </param> /// <param name="charset">网页编码，eg:"utf-8"</param> /// <returns>返回网页源文件</returns> public static string GetHtmlSource(string url, string charset) { //编码处理 Encoding nowCharset; if (charset == "" || charset == null) { nowCharset = Encoding.Default; } else { nowCharset = Encoding.GetEncoding(charset); } //处理内容 string html = ""; try { //WebRequest myWebRequest = WebRequest.Create(url); //WebResponse myWebResponse = myWebRequest.GetResponse(); //Stream stream = myWebResponse.GetResponseStream(); //StreamReader reader = new StreamReader(stream, nowCharset); HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url); HttpWebResponse response = (HttpWebResponse)request.GetResponse(); Stream stream = response.GetResponseStream(); StreamReader reader = new StreamReader(stream, nowCharset); html = reader.ReadToEnd(); stream.Close(); } catch (Exception e) { } return html; } /// <summary> /// 取得网页源码 /// </summary> /// <param name="url">网页地址，eg: "http://www.yongfa365.com/" </param> /// <param name="charset">网页编码，eg: Encoding.UTF8</param> /// <returns>返回网页源文件</returns> public static string GetHtmlSource(string url, Encoding charset) { //处理内容 string html = ""; try { HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url); HttpWebResponse response = (HttpWebResponse)request.GetResponse(); Stream stream = response.GetResponseStream(); StreamReader reader = new StreamReader(stream, charset); html = reader.ReadToEnd(); stream.Close(); } catch (Exception e) { } return html; } /// <summary> /// 取得网页源码 /// 对于带BOM的网页很有效，不管是什么编码都能正确识别 /// </summary> /// <param name="url">网页地址，eg: "http://www.yongfa365.com/" </param> /// <returns>返回网页源文件</returns> public static string GetHtmlSource(string url) { //处理内容 string html = ""; try { HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url); HttpWebResponse response = (HttpWebResponse)request.GetResponse(); Stream stream = response.GetResponseStream(); StreamReader reader = new StreamReader(stream, Encoding.Default); html = reader.ReadToEnd(); stream.Close(); } catch (Exception e) { } return html; } }