java抓取全部網頁內容
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
*
* @author yaohucaizi
*/
public class Test {
/**
* 讀取網頁全部內容
*/
public String getHtmlContent(String htmlurl) {
URL url;
String temp;
StringBuffer sb = new StringBuffer();
try {
url = new URL(htmlurl);
BufferedReader in = new BufferedReader(new InputStreamReader(url.openStream(), "gbk"));// 讀取網頁全部內容
while ((temp = in.readLine()) != null) {
sb.append(temp);
}
in.close();
} catch (final MalformedURLException me) {
System.out.println("你輸入的URL格式有問題!");
me.getMessage();
} catch (final IOException e) {
e.printStackTrace();
}
return sb.toString();
}
/**
*
* @param s
* @return 獲得網頁標題
*/
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);
}
/**
*
* @param s
* @return 獲得鏈接
*/
public List<String> getLink(String s) {
String regex;
List<String> list = new ArrayList<String>();
regex = "<a[^>]*href=(\"([^\"]*)\"|\'([^\']*)\'|([^\\s>]*))[^>]*>(.*?)</a>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}
/**
*
* @param s
* @return 獲得腳本代碼
*/
public List<String> getScript(String s) {
String regex;
List<String> list = new ArrayList<String>();
regex = "<SCRIPT.*?</SCRIPT>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}
public List<String> getNews(String s) {
String regex = "<a.*?</a>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
List<String> list = new ArrayList<String>();
while (ma.find()) {
list.add(ma.group());
}
return list;
}
/**
*
* @param s
* @return 獲得CSS
*/
public List<String> getCSS(String s) {
String regex;
List<String> list = new ArrayList<String>();
regex = "<style.*?</style>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}
/**
*
* @param s
* @return 去掉標記
*/
public String outTag(final String s) {
return s.replaceAll("<.*?>", "");
}
public static void main(String[] args) {
Test t = new Test();
String content = t.getHtmlContent("http://www.taobao.com");
//content = content.replaceAll("(<br>)+?", "\n");// 轉化換行
//content = content.replaceAll("<p><em>.*?</em></p>", "");// 去圖片註釋
System.out.println(content);
System.out.println(t.getTitle(content));
List<String> a = t.getNews(content);
List<String> news = new ArrayList<String>();
for (String s : a) {
news.add(s.replaceAll("<.*?>", ""));
}
System.out.println(news);
//…… 獲取js、css等操作省略
}
}
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
*
* @author yaohucaizi
*/
public class Test {
/**
* 讀取網頁全部內容
*/
public String getHtmlContent(String htmlurl) {
URL url;
String temp;
StringBuffer sb = new StringBuffer();
try {
url = new URL(htmlurl);
BufferedReader in = new BufferedReader(new InputStreamReader(url.openStream(), "gbk"));// 讀取網頁全部內容
while ((temp = in.readLine()) != null) {
sb.append(temp);
}
in.close();
} catch (final MalformedURLException me) {
System.out.println("你輸入的URL格式有問題!");
me.getMessage();
} catch (final IOException e) {
e.printStackTrace();
}
return sb.toString();
}
/**
*
* @param s
* @return 獲得網頁標題
*/
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);
}
/**
*
* @param s
* @return 獲得鏈接
*/
public List<String> getLink(String s) {
String regex;
List<String> list = new ArrayList<String>();
regex = "<a[^>]*href=(\"([^\"]*)\"|\'([^\']*)\'|([^\\s>]*))[^>]*>(.*?)</a>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}
/**
*
* @param s
* @return 獲得腳本代碼
*/
public List<String> getScript(String s) {
String regex;
List<String> list = new ArrayList<String>();
regex = "<SCRIPT.*?</SCRIPT>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}
public List<String> getNews(String s) {
String regex = "<a.*?</a>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
List<String> list = new ArrayList<String>();
while (ma.find()) {
list.add(ma.group());
}
return list;
}
/**
*
* @param s
* @return 獲得CSS
*/
public List<String> getCSS(String s) {
String regex;
List<String> list = new ArrayList<String>();
regex = "<style.*?</style>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}
/**
*
* @param s
* @return 去掉標記
*/
public String outTag(final String s) {
return s.replaceAll("<.*?>", "");
}
public static void main(String[] args) {
Test t = new Test();
String content = t.getHtmlContent("http://www.taobao.com");
//content = content.replaceAll("(<br>)+?", "\n");// 轉化換行
//content = content.replaceAll("<p><em>.*?</em></p>", "");// 去圖片註釋
System.out.println(content);
System.out.println(t.getTitle(content));
List<String> a = t.getNews(content);
List<String> news = new ArrayList<String>();
for (String s : a) {
news.add(s.replaceAll("<.*?>", ""));
}
System.out.println(news);
//…… 獲取js、css等操作省略
}
}
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.