导语:Java如何正则表达式分析读取网页内容?下面是小编给大家提供的代码实现,大家可以参考阅读,更多详情请关注应届毕业生考试网。
Java用正则表达式分析读取网页内容
package p;
import eredReader;
import ception;
import tStreamReader;
import ormedURLException;
import ;
import yList;
import Map;
import ;
import her;
import ern;
/** *//**
*
* @抓取雅虎知识堂的文章标题及内容(测试) 手动输入网址抓取,可进一步自动抓取整个知识堂的'全部内容
*
*/
public class WebContent ...{
/** *//**
* 读取一个网页全部内容
*/
public String getOneHtml(String htmlurl) throws IOException...{
URL url;
String temp;
StringBuffer sb = new StringBuffer();
try ...{
url = new URL(htmlurl);
BufferedReader in = new BufferedReader(new InputStreamReader(url
Stream(), "utf-8"));// 读取网页全部内容
while ((temp = Line()) != null) ...{
nd(temp);
}
e();
}catch(MalformedURLException me)...{
tln("你输入的URL格式有问题!请仔细输入");
essage();
throw me;
}catch (IOException e) ...{
tStackTrace();
throw e;
}
return ring();
}
/** *//**
*
* @param s
* @return 获得网页标题
*/
public String getTitle(String s) ...{
String regex;
String title = "";
List<String> list = new ArrayList<String>();
regex = "<title>.*?</title>";
Pattern pa = ile(regex, N_EQ);
Matcher ma = her(s);
while (()) ...{
(p());
}
for (int i = 0; i < (); i++) ...{
title = title + (i);
}
return outTag(title);
}
/** *//**
*
* @param s
* @return 获得链接
*/
public List<String> getLink(String s) ...{
String regex;
List<String> list = new ArrayList<String>();
regex = "<a[^>]*href=("([^"]*)"|'([^']*)'|([^s>]*))[^>]*>(.*?)</a>";
Pattern pa = ile(regex, LL);
Matcher ma = her(s);
while (()) ...{
(p());
}
return list;
}
/** *//**
*
* @param s
* @return 获得脚本代码
*/
public List<String> getScript(String s) ...{
String regex;
List<String> list = new ArrayList<String>();
regex = "<script.*?</script>";
Pattern pa = ile(regex, LL);
Matcher ma = her(s);
while (()) ...{
(p());
}
return list;
}
/** *//**
*
* @param s
* @return 获得CSS
*/
public List<String> getCSS(String s) ...{
String regex;
List<String> list = new ArrayList<String>();
regex = "<style.*?</style>";
Pattern pa = ile(regex, LL);
Matcher ma = her(s);
while (()) ...{
(p());
}
return list;
}
/** *//**
*
* @param s
* @return 去掉标记
*/
public String outTag(String s) ...{
return aceAll("<.*?>", "");
}