解决一些网站文字不能复制的问题?java应用
2015-12-23 01:13
489 查看
package we;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Copy {
public static void main(String[] args) throws Exception {
File source = new File("H:\\333.htm");
BufferedReader in = new BufferedReader(new InputStreamReader(
new FileInputStream(source)));
File desc = new File("321.txt");
BufferedWriter out = new BufferedWriter(new OutputStreamWriter(
new FileOutputStream(desc), "UTF-8"));
String str = null;
String regex = "<p.*?>(.*?)</p>";
String regex1 = "<p><img";
String regex2 = "<p><em>";
Pattern p = Pattern.compile(regex);
Pattern p1 = Pattern.compile(regex1);
Pattern p2 = Pattern.compile(regex2);
while ((str = in.readLine()) != null) {
Matcher m = p.matcher(str);
Matcher m1 = p1.matcher(str);
Matcher m2 = p2.matcher(str);
while (m.find()) {
if (m1.find())
continue;
else if (m2.find())
continue;
out.write(m.group(1) + "\r\n");
out.flush();
}
}
out.close();
in.close();
}
}
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Copy {
public static void main(String[] args) throws Exception {
File source = new File("H:\\333.htm");
BufferedReader in = new BufferedReader(new InputStreamReader(
new FileInputStream(source)));
File desc = new File("321.txt");
BufferedWriter out = new BufferedWriter(new OutputStreamWriter(
new FileOutputStream(desc), "UTF-8"));
String str = null;
String regex = "<p.*?>(.*?)</p>";
String regex1 = "<p><img";
String regex2 = "<p><em>";
Pattern p = Pattern.compile(regex);
Pattern p1 = Pattern.compile(regex1);
Pattern p2 = Pattern.compile(regex2);
while ((str = in.readLine()) != null) {
Matcher m = p.matcher(str);
Matcher m1 = p1.matcher(str);
Matcher m2 = p2.matcher(str);
while (m.find()) {
if (m1.find())
continue;
else if (m2.find())
continue;
out.write(m.group(1) + "\r\n");
out.flush();
}
}
out.close();
in.close();
}
}
相关文章推荐
- 网站为什么只能重置密码,而不能真正的“找回密码”
- MySQL下高可用故障转移方案MHA的超级部署教程
- php+mysql制作的投票功能 适合网站做问卷调查活动
- LVS+keepalived+LNMP架构
- DS8880要将双控高端存储架构进行到底
- Android系统的基本架构
- 架构师应该做些什么
- 微网站
- 用curl抓取网站数据,仿造IP、防屏蔽终极强悍解决方式
- Cypress固件架构彻底解析及USB枚举
- 老李推荐:第1章3节《MonkeyRunner源码剖析》概述:架构
- Android应用架构之Android MVP使用
- Android中的四层架构,五块区域
- Android中的四层架构,五块区域
- 免费的论文查重网站
- [置顶] 应用系统架构设计
- [置顶] 应用系统架构设计
- [置顶] 应用系统架构设计
- 应用系统架构设计
- [置顶] 软件架构学习小结