C# 爬虫DLL文件（网页分析DLL文件）附加简单Demo（如抓取百度上的天气预报）

// 通过节点名称以及节点的一个属性值在源码中过滤出相应的信息 public NodeList getNodeListByAttribute(string nodeName, string attributeName, string attributeValue, Parser paser) { NodeFilter nodeFilter = new TagNameFilter(nodeName); NodeFilter nameFilter = new HasAttributeFilter(attributeName, attributeValue); AndFilter andFilter = new AndFilter(nodeFilter, nameFilter); NodeList nodeList = paser.ExtractAllNodesThatMatch(andFilter); return nodeList; } // urlParam 网址，返回网页源代码 public string GetStringByResponse(string urlParam, string coding) { if (coding.Length == 0) // 如果传过来的编码类型为空 则默认为 UTF-8 coding = "UTF-8"; WebRequest request; // 实例一个请求对象 try { request = WebRequest.Create(urlParam); // 创建一个参数为下载页面的请求 } catch (UriFormatException) { request = null; } request.Credentials = CredentialCache.DefaultCredentials; // 若服务器需要，则设置凭据 HttpWebResponse response = null; // 设置响应为null Stream dataStream = null; // 设置服务器端的响应流为null StreamReader reader = null; string responseFromServer = null; // 从服务器中获得响应的字符串 try { response = (HttpWebResponse)request.GetResponse(); // 获得响应 if (response.StatusCode == HttpStatusCode.OK) // 请求成功 { dataStream = response.GetResponseStream(); // 从响应中获得响应的流信息 reader = new StreamReader(dataStream, Encoding.GetEncoding(coding)); responseFromServer = reader.ReadToEnd(); // 从streamReader中读出响应流string，得出相应的具体内容 } } catch (WebException) { return null; } finally { if (reader != null) reader.Close(); if (dataStream != null) dataStream.Close(); if (response != null) response.Close(); } return responseFromServer; ; }