公司編輯妹子需要爬取網頁內容，叫我幫忙做了一簡單的爬取工具
這是爬取網頁內容，像是這對大家來說都是不難得，但是在這里有一些小改動，代碼獻上，大家參考
private string GetHttpWebRequest(string url) { HttpWebResponse result; string strHTML = string.Empty; try { Uri uri = new Uri(url); WebRequest webReq = WebRequest.Create(uri); WebResponse webRes = webReq.GetResponse(); HttpWebRequest myReq = (HttpWebRequest)webReq; myReq.UserAgent = "User-Agent:Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705"; myReq.Accept = "*/*"; myReq.KeepAlive = true; myReq.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5"); result = (HttpWebResponse)myReq.GetResponse(); Stream receviceStream = result.GetResponseStream(); StreamReader readerOfStream = new StreamReader(receviceStream, System.Text.Encoding.GetEncoding("utf-8")); strHTML = readerOfStream.ReadToEnd(); readerOfStream.Close(); receviceStream.Close(); result.Close(); } catch { Uri uri = new Uri(url); WebRequest webReq = WebRequest.Create(uri); HttpWebRequest myReq = (HttpWebRequest)webReq; myReq.UserAgent = "User-Agent:Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705"; myReq.Accept = "*/*"; myReq.KeepAlive = true; myReq.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5"); //result = (HttpWebResponse)myReq.GetResponse(); try { result = (HttpWebResponse)myReq.GetResponse(); } catch (WebException ex) { result = (HttpWebResponse)ex.Response; } Stream receviceStream = result.GetResponseStream(); StreamReader readerOfStream = new StreamReader(receviceStream, System.Text.Encoding.GetEncoding("gb2312")); strHTML = readerOfStream.ReadToEnd(); readerOfStream.Close(); receviceStream.Close(); result.Close(); } return strHTML; }這是根據url爬取網頁遠嗎，有一些小改動，很多網頁有不同的編碼格式，甚至有些網站做了反爬取的防范，這個方法經過能夠改動也能爬去
以下是爬取網頁所有的網址鏈接
/// <summary> /// 提取HTML代碼中的網址 /// </summary> /// <param name="htmlCode"></param> /// <returns></returns> private static List<string> GetHyperLinks(string htmlCode, string url) { ArrayList al = new ArrayList(); bool IsGenxin = false; StringBuilder weburlSB = new StringBuilder();//SQL StringBuilder linkSb = new StringBuilder();//展示數據 List<string> Weburllistzx = new List<string>();//新增 List<string> Weburllist = new List<string>();//舊的 string ProductionContent = htmlCode; Regex reg = new Regex(@"http(s)?://([/w-]+/.)+[/w-]+/?"); string wangzhanyuming = reg.Match(url, 0).Value; MatchCollection mc = Regex.Matches(ProductionContent.Replace("href=/"/", "href=/"" + wangzhanyuming).Replace("href='/", "href='" + wangzhanyuming).Replace("href=/", "href=" + wangzhanyuming).Replace("href=/"./", "href=/"" + wangzhanyuming), @"<[aA][^>]* href=[^>]*>", RegexOptions.Singleline); int Index = 1; foreach (Match m in mc) { MatchCollection mc1 = Regex.Matches(m.Value, @"[a-zA-z]+://[^/s]*", RegexOptions.Singleline); if (mc1.Count > 0) { foreach (Match m1 in mc1) { string linkurlstr = string.Empty; linkurlstr = m1.Value.Replace("/"", "").Replace("'", "").Replace(">", "").Replace(";", ""); weburlSB.Append("$-$"); weburlSB.Append(linkurlstr); weburlSB.Append("$_$"); if (!Weburllist.Contains(linkurlstr) && !Weburllistzx.Contains(linkurlstr)) { IsGenxin = true; Weburllistzx.Add(linkurlstr); linkSb.AppendFormat("{0}<br/>", linkurlstr); } } } else { if (m.Value.IndexOf("javascript") == -1) { string amstr = string.Empty; string wangzhanxiangduilujin = string.Empty; wangzhanxiangduilujin = url.Substring(0, url.LastIndexOf("/") + 1); amstr = m.Value.Replace("href=/"", "href=/"" + wangzhanxiangduilujin).Replace("href='", "href='" + wangzhanxiangduilujin); MatchCollection mc11 = Regex.Matches(amstr, @"[a-zA-z]+://[^/s]*", RegexOptions.Singleline); foreach (Match m1 in mc11) { string linkurlstr = string.Empty; linkurlstr = m1.Value.Replace("/"", "").Replace("'", "").Replace(">", "").Replace(";", ""); weburlSB.Append("$-$"); weburlSB.Append(linkurlstr); weburlSB.Append("$_$"); if (!Weburllist.Contains(linkurlstr) && !Weburllistzx.Contains(linkurlstr)) { IsGenxin = true; Weburllistzx.Add(linkurlstr); linkSb.AppendFormat("{0}<br/>", linkurlstr); } } } } Index++; } return Weburllistzx; }這塊的技術其實就是簡單的使用了正則去匹配！接下來獻上獲取標題，以及存儲到xml文件的方法
/// <summary> /// // 把網址寫入xml文件 /// </summary> /// <param name="strURL"></param> /// <param name="alHyperLinks"></param> private static void WriteToXml(string strURL, List<string> alHyperLinks) { XmlTextWriter writer = new XmlTextWriter(@"D:/HyperLinks.xml", Encoding.UTF8); writer.Formatting = Formatting.Indented; writer.WriteStartDocument(false); writer.WriteDocType("HyperLinks", null, "urls.dtd", null); writer.WriteComment("提取自" + strURL + "的超鏈接"); writer.WriteStartElement("HyperLinks"); writer.WriteStartElement("HyperLinks", null); writer.WriteAttributeString("DateTime", DateTime.Now.ToString()); foreach (string str in alHyperLinks) { string title = GetDomain(str); string body = str; writer.WriteElementString(title, null, body); } writer.WriteEndElement(); writer.WriteEndElement(); writer.Flush(); writer.Close(); } /// <summary> /// 獲取網址的域名后綴 /// </summary> /// <param name="strURL"></param> /// <returns></returns> private static string GetDomain(string strURL) { string retVal; string strRegex = @"(/.com/|/.net/|/.cn/|/.org/|/.gov/)"; Regex r = new Regex(strRegex, RegexOptions.IgnoreCase); Match m = r.Match(strURL); retVal = m.ToString(); strRegex = @"/.|/$"; retVal = Regex.Replace(retVal, strRegex, "").ToString(); if (retVal == "") retVal = "other"; return retVal; } /// <summary> /// 獲取標題 /// </summary> /// <param name="html"></param> /// <returns></returns> private static string GetTitle(string html) { string titleFilter = @"<title>[/s/S]*?</title>"; string h1Filter = @"<h1.*?>.*?</h1>"; string clearFilter = @"<.*?>"; string title = ""; Match match = Regex.Match(html, titleFilter, RegexOptions.IgnoreCase); if (match.Success) { title = Regex.Replace(match.Groups[0].Value, clearFilter, ""); } // 正文的標題一般在h1中，比title中的標題更干凈 match = Regex.Match(html, h1Filter, RegexOptions.IgnoreCase); if (match.Success) { string h1 = Regex.Replace(match.Groups[0].Value, clearFilter, ""); if (!String.IsNullOrEmpty(h1) && title.StartsWith(h1)) { title = h1; } } return title; }這就是所用的全部方法，還是有很多需要改進之處！大家如果有發現不足之處還請指出，謝謝！
以上就是本文的全部內容，希望對大家的學習有所幫助，也希望大家多多支持武林網。
新聞熱點
疑難解答
