* 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
.openStream(), "utf-8"));// 读取网页全部内容
while ((temp = in.readLine()) != null) ...{
sb.append(temp);
}
in.close();
}catch(MalformedURLException me)...{
System.out.println("你输入的URL格式有问题!请仔细输入");
me.getMessage();
throw me;
}catch (IOException e) ...{
e.printStackTrace();
throw e;
}
return sb.toString();
}
/** *//**
*
* @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 = Pattern.compile(regex, Pattern.CANON_EQ);
Matcher ma = pa.matcher(s);
while (ma.find()) ...{
list.add(ma.group());
}
for (int i = 0; i < list.size(); i++) ...{
title = title + list.get(i);
}
return outTag(title);
}
*/
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
.openStream(), "utf-8"));// 读取网页全部内容
while ((temp = in.readLine()) != null) ...{
sb.append(temp);
}
in.close();
}catch(MalformedURLException me)...{
System.out.println("你输入的URL格式有问题!请仔细输入");
me.getMessage();
throw me;
}catch (IOException e) ...{
e.printStackTrace();
throw e;
}
return sb.toString();
}
/** *//**
*
* @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 = Pattern.compile(regex, Pattern.CANON_EQ);
Matcher ma = pa.matcher(s);
while (ma.find()) ...{
list.add(ma.group());
}
for (int i = 0; i < list.size(); i++) ...{
title = title + list.get(i);
}
return outTag(title);
}