工作之余,学习了一下正则表达式,鉴于实践是检验真理的唯一标准,于是便写了一个利用正则表达式抓取百度百家文章的例子,具体过程请看下面源码:
一:获取百度百家网页内容
1 public List<string[]> GetUrl() 2 { 3 try 4 { 5 string url = "http://baijia.baidu.com/"; 6 WebRequest webRequest = WebRequest.Create(url); 7 WebResponse webResponse = webRequest.GetResponse(); 8 StreamReader reader = new StreamReader(webResponse.GetResponseStream()); 9 string result = reader.ReadToEnd(); 10 reader.Close(); 11 webResponse.Close(); 12 return AnalysisHtml(result); 13 } 14 catch (Exception ex) 15 { 16 throw ex; 17 } 18 }
二:通过正则表达式筛选
1 public List<string[]> AnalysisHtml(string htmlContent) 2 { 3 List<string[]> list = new List<string[]>(); 4 string strPattern = "<h3><a\\s*.*>(?<Title>[^<]+)</a></h3>.*\\s*<p\\s*class=\"feeds-item-text\">(?<Abstract>[^<]+)<a\\s*href=\"(?<Url>.*)\"\\s*target=\"_blank\"\\s*class=\"feeds-item-more\"\\s*mon=\".*\\s*\">.*\\s*</a></p>"; 5 Regex regex = new Regex(strPattern, RegexOptions.IgnoreCase | RegexOptions.Multiline | RegexOptions.CultureInvariant); 6 if (regex.IsMatch(htmlContent)) 7 { 8 MatchCollection matchCollection = regex.Matches(htmlContent); 9 foreach (Match match in matchCollection) 10 { 11 string[] str = new string[3]; 12 str[0] = match.Groups[1].Value;//获取到的是列表数据的标题 13 str[1] = match.Groups[2].Value;//获取到的是内容 14 str[2] = match.Groups[3].Value;//获取到的是链接到的地址 15 list.Add(str); 16 } 17 } 18 return list; 19 }