C# 读取搜索结果

最新推荐文章于 2021-11-20 14:20:35 发布

yimeng_1985

最新推荐文章于 2021-11-20 14:20:35 发布

阅读量958

点赞数

分类专栏：工作备忘文章标签： c# regex string class query stream

本文链接：https://blog.csdn.net/yimeng_1985/article/details/6702564

版权

工作备忘专栏收录该内容

18 篇文章 0 订阅

订阅专栏

怕丢了，说不定以后会用到，存在这里。

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Net;
using System.Text.RegularExpressions;
using System.IO;
using System.Web;

namespace RegexPractice
{
    #region Get reserch result 
    /// <summary>
    /// 访问google或者百度主页，输入查询关键字，保存查询结果
    /// </summary>
    class Program
    {
        static void Main(string[] args)
        {
            string[] queryList = { "张柏芝", "黎姿", "梁洛施", "大s", "李小冉", "董洁" };
            using (StreamWriter sw = new StreamWriter(@"c:\abc.tsv", false))
            {
                foreach (string query in queryList)
                {
                    string encodedQuery = HttpUtility.UrlEncode(query, Encoding.GetEncoding("utf-8"));
                    string url = string.Format("http://www.google.com.hk/search?hl=zh-CN&q={0}", encodedQuery);
                    HttpWebRequest request = HttpWebRequest.Create(new Uri(url)) as HttpWebRequest;
                    request.CookieContainer = new CookieContainer();
                    string webContent = string.Empty;
                    WebResponse response = request.GetResponse();
                    using (Stream responseStream = response.GetResponseStream())
                    {
                        using (StreamReader sr = new StreamReader(responseStream, Encoding.GetEncoding("gb2312")))
                        {
                            webContent = sr.ReadToEnd();
                        }
                    }

                    //Regex regex = new Regex("(?s)<table cellpadding=\"0\" cellspacing=\"0\" class=\"result\" id=\"(?<id>.*?)\">.*?target=\"_blank\">(?<title>.*?)</a>");
                    //Regex regex = new Regex("(?s)<li class=g>.*?class=l>(?<title>.*?)</a>");
                    List<string> titleList = new List<string>();
                    List<string> linkList = new List<string>();

                    Regex regex = new Regex("(?s)<li class=g(?<type>.*?)>.*?<h3.*?href=\"(?<link>.*?)\".*?>(?<title>.*?)</a>");

                    MatchCollection mc = regex.Matches(webContent);
                    foreach (Match m in mc)
                    {
                        if ((!m.Groups["type"].Value.Contains("id=newsbox")) && (!m.Groups["type"].Value.Contains("id=imagebox")))
                        {
                            string title = m.Groups["title"].Value;
                            string link = m.Groups["link"].Value;
                            Regex emRegex = new Regex("</?em>");
                            title = emRegex.Replace(title, "");

                            titleList.Add(title);
                            linkList.Add(link);
                        }
                    }
                    for (int i = 0; i < linkList.Count; i++)
                    {
                        sw.WriteLine(string.Format("{0}\t{1}\t{2}\t{3}", query, i.ToString(), titleList[i], linkList[i]));
                    }
                }
            }
        }
    }