如何用c#编写程序,读入一个网站的网页,查找其中的字符,并输入?
如何用c#编写程序,读入一个网站的网页,查找其中的字符,并输入?
最近看论坛,好多人跟帖,但是作者的发言好难找
能不能编写段代码,来自动列出作者的发言?
思路:
打开网页
读入此网页的源文件
搜索此文件的作者名及发言
但是,如何使用c#读入此网页源文件呢?
高手请指教!!!!!
------解决方案--------------------
我觉得你这个就是一个小偷程序吧
public void show5()
{
Encoding gb2312 = Encoding.GetEncoding("gb2312");
String web_url = "http://china.fxstreet.com/fundamental/economic-calendar/";
//要获取的网址URL
String code = String.Empty;
//存放网页的源文件
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(web_url);
WebResponse response = request.GetResponse();
StreamReader sr = new StreamReader(response.GetResponseStream(), gb2312);
//获取源文件
code = sr.ReadToEnd();
sr.Close();
ArrayList list = new ArrayList();
//用来存放链接
String reg = @"<td align=.left.>\d*:\d*</td><td>\D*</td><td><a.*return false;.>.*</a></td>.*<img.*</td><td id=.*</td><td>.*nowrap=.nowrap.>.*</td>";
String reg1 = @"<td align=.left.>\d*:\d*</td>";
String reg2 = @"<td>\D*</td><td><a";
String reg3 = @"return false;.>.*</a></td>";
String reg4 = @"</a></td><td><img.*alt=.* expected. /></td>";
String reg5 = @"<td id=.*</td><td>.*</td><td nowrap";
String reg6 = @"nowrap=.nowrap.>.*</td><td><img";
//链接的正则表达式
Regex regex = new Regex(reg, RegexOptions.IgnoreCase);
MatchCollection mc = regex.Matches(code);
//存放匹配的集合
for (int i = 0; i < mc.Count; i++)
{
Regex regex1 = new Regex(reg1, RegexOptions.IgnoreCase);
MatchCollection mc1 = regex1.Matches(mc[i].Value.ToString());
Regex regex2 = new Regex(reg2, RegexOptions.IgnoreCase);
MatchCollection mc2 = regex2.Matches(mc[i].Value.ToString());
Regex regex3 = new Regex(reg3, RegexOptions.IgnoreCase);
MatchCollection mc3 = regex3.Matches(mc[i].Value.ToString());
Regex regex4 = new Regex(reg4, RegexOptions.IgnoreCase);
MatchCollection mc4 = regex4.Matches(mc[i].Value.ToString());
Regex regex5 = new Regex(reg5, RegexOptions.IgnoreCase);
MatchCollection mc5 = regex5.Matches(mc[i].Value.ToString());
Regex regex6 = new Regex(reg6, RegexOptions.IgnoreCase);
MatchCollection mc6 = regex6.Matches(mc[i].Value.ToString());
bool hasExist = false;
//链接存在与否的标记
if (mc1.Count < 1)
{
continue;
}
String ctime = mc1[0].Value;
String carea = mc2[0].Value;
String ctitle = mc3[0].Value;
String ccurrent = mc4[0].Value;
String cforecast = mc5[0].Value;
String clast = mc6[0].Value;
ctime = ctime.Substring(ctime.Length - 10, 5);
carea = carea.Replace("</td>", "");
carea = carea.Replace("<td>", "");
carea = carea.Replace("<a", "");
ctitle = ctitle.Replace("return false;\">", "");