C#网页数据采集（三）HttpWebRequest

<span style="font-family: Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255);">截取到网页数据是js加载完以后的</span>

 

 

 

<span style="white-space:pre">    </span>    HtmlWeb webClient = new HtmlWeb();
          string _url = "http://news.baidu.com/";
          HtmlAgilityPack.HtmlDocument html1 = webClient.Load(_url);//是你需要解析的url
          var end3 = html1.Encoding.BodyName;//获取页面编码格式
          string _htmlSource = GetHtmlSource(_url, System.Text.Encoding.GetEncoding(end3));//还是需要设置一次编码格式避免乱码 调用<span style="font-family: Arial, Helvetica, sans-serif;">GetHtmlSource方法</span>

 

public static string GetHtmlSource(string url, Encoding charset)
        {
            string _html = string.Empty;
            try
            {
                HttpWebRequest _request = (HttpWebRequest)WebRequest.Create(url);
                HttpWebResponse _response = (HttpWebResponse)_request.GetResponse();
                using (Stream _stream = _response.GetResponseStream())
                {
                    using (StreamReader _reader = new StreamReader(_stream, charset))
                    {
                        _html = _reader.ReadToEnd();
                    }
                }
            }
            catch (WebException ex)
            {
                using (StreamReader sr = new StreamReader(ex.Response.GetResponseStream()))
                {
                    _html = sr.ReadToEnd();
                }
            }
            catch (Exception ex)
            {
                _html = ex.Message;
            }
            return _html;
        }