一个java版本的简单邮箱小爬虫
//趁着有空回头复习了一把正则表达式
/*
以下代码以百度某个贴吧的 URL 作为源,实现了读取 EmailAddress 并写入文件保存起来的两个功能,如果要爬取其它信息,可以改写正则实现相应功能
要点看引入的包可知：
1.应用到 IO 读写缓冲字符流
2.应用到正则表达式
3.URL 对象获取网页信息
4.util 包的集合框架 ArrayList
*/
import java.io.*;import java.util.regex.*;
import java.net.*;
import java.util.*;
class Spider{
public static void main(String [] args) throws Exception{
URL url=new URL("http://tieba.baidu.com/p/2314539885");
//String [] emailAddress=
ArrayList<String> emailList=getEmailByURL(url);
for(String emailAddress:emailList){
System.out.println(emailAddress);
}
String qualifiedName="c://users//ghc//desktop//test//emailAddress.txt";
writeEmailToFile(qualifiedName,emailList);
}
// Read html from url
public static ArrayList<String> getEmailByURL(URL url) throws Exception{
URLConnection urlconn=url.openConnection();
BufferedReader bufreader =new BufferedReader(new InputStreamReader(urlconn.getInputStream()));
//regex match pattern
String regex="\\w+@\\w+(\\.\\w+)+";
Pattern p=Pattern.compile(regex);
ArrayList<String> emailList=new ArrayList<String>();
String line=null;
while((line=bufreader.readLine())!=null){
Matcher m=p.matcher(line);
// Start to iterator the one matches
while(m.find()){
emailList.add(m.group());
//System.out.println(m.group());
}
//System.out.println(line);
}
return emailList;
}
public static void writeEmailToFile(String qualifiedName,ArrayList<String> emailList) throws Exception{
BufferedWriter bufwriter=new BufferedWriter(new FileWriter(qualifiedName));
for(int i=0;i<emailList.size();i++){
bufwriter.write(emailList.get(i));
bufwriter.newLine();
bufwriter.flush();
}
}
}
/*读取键盘输入的 三种形式 */import java.io.*;
import java.util.*;
import java.util.Scanner;
class MyTest{
public static void main(String [] args) throws Exception{
//方法一
Scanner scanner =new Scanner(System.in);
String inputStr=scanner.nextLine();
System.out.println(inputStr);
//方法二
BufferedReader bufreader=new BufferedReader(new InputStreamReader(System.in));
String line=null;
while((line=bufreader.readLine())!=null){
System.out.println(line);
}
}
}
/* 把叠词 简化 */
class AbrreviateDemo{
public static void main(String [] args){
String str="II...LLL...ove..ee.....you!";
String regex="\\.+";
String replaceStr="";
str=retriveStr(str,regex,replaceStr);
regex="(.)\\1+";
replaceStr="$1";
str=retriveStr(str,regex,replaceStr);
System.out.println(str);
}
public static String retriveStr(String str,String regex,String replaceStr){
return str.replaceAll(regex,replaceStr);
}
}
/* 将一堆杂乱的 IP 地址进行排序 */
import java.util.*;
class SortIP{
public static void main(String [] args){
String IP="192.168.0.5 2.2.3.4 127.0.0.1";
printAfterSort(IP);
}
public static void printAfterSort(String str){
String regex="(0*\\d+)";
str=str.replaceAll(regex,"00$1");
regex="0*(\\d{3})";
str=str.replaceAll(regex,"$1");
System.out.println(str);
regex=" +";
String [] strArray=str.split(regex);
Arrays.sort(strArray);
for(int i=0;i<strArray.length;i++){
System.out.println(strArray[i].replaceAll("0*(\\d+)","$1"));
}
//System.out.println(str);
}
}
/* 邮箱地址校验 */
class checkMailDemo{
public static void main(String [] args){
String str="liyu@gchchina.com.cn";
System.out.println("result: "+checkMail(str));
//String regex="";
}
public static boolean checkMail(String str){
String regex="[a-zA-Z0-9_]+[@][a-zA-Z0-9]+(\\.[a-zA-Z]+){1,3}";
regex="\\w+@\\w+(\\.\\w+){1,3}";
return str.matches(regex);
}
}
/* 从一堆杂乱的字符串中获取需要的手机号码 */
import java.util.regex.*;
class RegexDemo{
public static void main(String [] args){
String str="1afasdf13874057617weojfjlj";
String regex="[1-9][3,5,8]\\d{9}";
retriveStr(str,regex);
}
public static void retriveStr(String str,String regex){
Pattern p=Pattern.compile(regex);
Matcher m=p.matcher(str);
while(m.find()){
String tempstr=m.group();
System.out.println(tempstr);
}
}
}
/* 读取键盘标准输入流并大写方式打印到控制台 */
import java.io.*;
import java.util.*;
class UpercaseSystemIn{
public static void main(String [] args) throws IOException{
InputStream in=System.in;
doUpcaseReadIn(in);
}
public static void doUpcaseReadIn(InputStream in) throws IOException{
BufferedReader bufr=new BufferedReader(new InputStreamReader(in));
String str=null;
while((str=bufr.readLine())!=null){
System.out.println(str.toUpperCase());
if(str.equalsIgnoreCase("exit")) System.exit(0); //break
}
}
}
/* 读取某个贴吧邮箱地址并打印到控制台 注意这里的正则*/
import java.net.*;
import java.io.*;
import java.util.*;
import java.util.regex.*;
class SpiderTest{
public static void main(String [] args) throws Exception{
URL url=new URL("http://tieba.baidu.com/p/2314539885");
getEmailAddressFromURL(url);
}
public static void getEmailAddressFromURL(URL url) throws Exception{
URLConnection urlconn=url.openConnection();
BufferedReader bufreader = new BufferedReader(new InputStreamReader(urlconn.getInputStream()));
String line=null;
String regex="\\w+@\\w+(\\.\\w+)+";
Pattern p=Pattern.compile(regex);
while ((line=bufreader.readLine())!=null){
Matcher m = p.matcher(line);
while(m.find()){
System.out.println(m.group());
}
// System.out.println(line);
}
}
}
/* 实现本地二进制文件拷贝 */
import java.io.*;
class CopyImg{
public static void main(String [] args){
BufferedInputStream bufinps=null;
BufferedOutputStream bufotps=null;
try{
bufinps=new BufferedInputStream(new FileInputStream("psb.jpg"));
bufotps=new BufferedOutputStream(new FileOutputStream("psb_copy.jpg"));
byte [] buf=new byte[8192];
int len=0;
while((len=bufinps.read(buf))>0){
bufotps.write(buf,0,len);
//bufotps.flush();
}
}
catch(IOException ioe){
ioe.printStackTrace();
}
finally{
if(bufinps!=null)
try{
bufinps.close();
}
catch(IOException ioe){
ioe.printStackTrace();
}
if(bufotps!=null)
try{
bufotps.close();
}
catch(IOException ioe){
ioe.printStackTrace();
}
}
}
}
/* 从某个网页爬取符合规则的邮箱地址并保存到本地磁盘路径下 */
import java.io.*;
import java.util.regex.*;
import java.net.*;
import java.util.*;
class Spider{
public static void main(String [] args) throws Exception{
URL url=new URL("http://tieba.baidu.com/p/2314539885");
//String [] emailAddress=
ArrayList<String> emailList=getEmailByURL(url);
for(String emailAddress:emailList){
System.out.println(emailAddress);
}
String qualifiedName="c://users//ghc//desktop//test//emailAddress.txt";
writeEmailToFile(qualifiedName,emailList);
}
// Read html from url
public static ArrayList<String> getEmailByURL(URL url) throws Exception{
URLConnection urlconn=url.openConnection();
BufferedReader bufreader =new BufferedReader(new InputStreamReader(urlconn.getInputStream()));
//regex match pattern
String regex="\\w+@\\w+(\\.\\w+)+";
Pattern p=Pattern.compile(regex);
ArrayList<String> emailList=new ArrayList<String>();
String line=null;
while((line=bufreader.readLine())!=null){
Matcher m=p.matcher(line);
// Start to iterator the one matches
while(m.find()){
emailList.add(m.group());
//System.out.println(m.group());
}
//System.out.println(line);
}
return emailList;
}
public static void writeEmailToFile(String qualifiedName,ArrayList<String> emailList) throws Exception{
BufferedWriter bufwriter=new BufferedWriter(new FileWriter(qualifiedName));
for(int i=0;i<emailList.size();i++){
bufwriter.write(emailList.get(i));
bufwriter.newLine();
bufwriter.flush();
}
}
}
/* 从某个网页爬取图片的 URL 地址然后 进行 下载到本地磁盘路径 基本功能已经实现，但是正则需要自行调整 */
import java.net.*;
import java.io.*;
import java.util.regex.*;
import java.util.*;
class ImgSpider{
public static void main(String [] args){
saveImgFromURL("http://image.baidu.com/","c:/users/ghc/desktop/test/");
System.gc();
}
public static boolean downLoadImg(String line,String path){
boolean flag=true;
FileOutputStream fos=null;
BufferedInputStream bufinpts=null;
BufferedOutputStream bufopts=null;
path=path.replace("<","");
/* System.out.println(line);
System.out.println(path); */
try{
bufinpts=new BufferedInputStream((new URL(line)).openConnection().getInputStream());
fos=new FileOutputStream(path);
bufopts=new BufferedOutputStream(fos);
byte [] buf=new byte[1024];
int len=-1;
while((len=bufinpts.read(buf))!=-1){
bufopts.write(buf,0,buf.length);
}
}
catch(IOException ioe){
ioe.printStackTrace();
flag=false;
}
finally{
if(bufopts!=null)
try{
bufopts=null;
bufopts.close();
}
catch(IOException ioe){
ioe.printStackTrace();
}
if(fos!=null)
try{
fos=null;
fos.close();
}
catch(IOException ioe){
ioe.printStackTrace();
}
}
return flag;
}
public static boolean saveImgFromURL(String urlStr,String folder){
boolean flag=true;
URL url=null;
//InputStream in=null;
String line=null;
BufferedReader bufr=null;
Pattern p=null;
Matcher m=null;
ArrayList<String> imgList=null;
try{
url=new URL(urlStr);
URLConnection urlconn=url.openConnection();
bufr=new BufferedReader(new InputStreamReader(urlconn.getInputStream()));
imgList=new ArrayList<String>();
String regex="<img.*src=(.*?)[^>]*?>";
p=Pattern.compile(regex);
while((line=bufr.readLine())!=null){
m=p.matcher(line);
while(m.find()){
System.out.println(m.group());
imgList.add(m.group());
}
//System.out.println(line);
}
Iterator<String> it=imgList.iterator();
while(it.hasNext()){
line=it.next();
folder+=line.substring(line.lastIndexOf("/",2) + 1,
3)+".png";
//http://www.jb51.net/images/logo.gif
m=Pattern.compile("http://(\\w+\\.)+[a-z]+/images/(\\w+\\.)+[a-z]{3}").matcher(line);
while(m.find()){
line=m.group();
//System.out.println(line);
downLoadImg(line,folder);
}
}
}
catch(MalformedURLException mfe){
mfe.printStackTrace();
flag=false;
}
catch(IOException ioe){
ioe.printStackTrace();
flag=false;
}
finally{
if (bufr!=null)
try{
bufr=null;
bufr.close();
}
catch(IOException ie){ ie.printStackTrace();
}
}
return flag;
}
}
/*正则 小练习 */
class Demo{
public static void main(String [] args){
String qq="1212345";
boolean checkResult=checkQQ(qq);
System.out.println(checkResult ? qq+" is right": qq+" is wrong!!!");
String telnumber="15974097817";
checkResult=checkTel(telnumber);
System.out.println(checkResult ? telnumber+" is right": telnumber+" is wrong!!!");
String path="c:\\users\\frank\\abqqcdkkkefghhijkkkkkl.txt";
String regex="(.)\\1+"; //叠词切割注意引入组的概念,\n 代表引用第几组 + 出现1次或多次 qq 或者 kkk 均会被当作切割符
printAfterSplit(path,regex);
System.out.println("=================");
regex="\\.";
printAfterSplit(path,regex);
String str="abcddeffffg";
regex="(.)\\1{3,}";
String replaceStr="$1";
printAfterReplaceStr(str,regex,replaceStr);
}
// 以下两个均是正则匹配 校验字符串的函数
public static boolean checkTel(String telnumber){
String regex="[1][3,5,8]\\d{9}";
return telnumber.matches(regex);
}
public static boolean checkQQ(String qq){
//boolean result=false;
String regex="[1-9][0-9]{4,14}";
regex="[1-9]\\d{4,14}";
return qq.matches(regex);
/* int len=qq.length();
if(len<5 || len>15 || qq.startsWith("0")){
System.out.println("length or startWith issue!!!");
//return result;
}
else {
char [] ary=qq.toCharArray();
for(int i=0;i<ary.length;i++){
if(!(ary[i]>='0' && ary[i]<='9'))
{
System.out.println("not between 0 and 9 !!!");
break;
//return result;
}
else
result=true;
}
} */
//return result;
}
// 以下两个均是正则 切割字符串的函数
public static void printAfterSplit(String path,String regex){
String [] ary=path.split(regex);
for(String s:ary){
System.out.println(s);
}
}
// 以下两个均是自定义正则替换字符串函数
public static void printAfterReplaceStr(String str,String regex,String replaceStr){
String resultStr=str.replaceAll(regex,replaceStr);
System.out.println(resultStr);
}
}
以上是 一个java版本的简单邮箱小爬虫 的全部内容， 来源链接： utcz.com/z/390769.html
