[code]使用正則擷取網頁裡的特定內容

注
: 代碼1的正則將會在html裡迴圈尋找,代碼2的正則只會尋找第一個匹配的項

 

代碼1:

package utils.net;<br />import java.io.BufferedReader;<br />import java.io.IOException;<br />import java.io.InputStreamReader;<br />import java.net.MalformedURLException;<br />import java.net.URL;<br />import java.util.ArrayList;<br />import java.util.List;<br />import java.util.regex.Matcher;<br />import java.util.regex.Pattern;<br />/**<br /> * 學習使用<br /> *<br /> * @author loocao<br /> *<br /> * (代碼無著作權,歡迎強姦)<br /> */<br />public class LoadWebSite1 {<br />/**<br /> * @param args<br /> */<br />public static void main(String[] args) {<br />String url = "http://www.qx121.com/web/plug/weather2.asp";<br />String html = getHtml(url);<br />System.out.println(html);<br />System.out.println();<br />String s[] = queryString(html,<br />"<a target=/"_blank/" href=/".{20}/" >(.{2,100})</a>");<br />for (String str : s) {<br />System.out.println(str);<br />}<br />}<br />/**<br /> * 擷取url的HTML內容 <br/><br /> * URL的使用方法是在網上找到的,瞭解更多,請參考Apache Client<br /> *<br /> * @param url<br /> * @return<br /> */<br />public static String getHtml(String url) {<br />StringBuffer html = new StringBuffer();<br />try {<br />URL u = new URL(url);<br />BufferedReader reader = new BufferedReader(new InputStreamReader(u<br />.openStream()));<br />String temp;<br />while ((temp = reader.readLine()) != null) {<br />html.append(temp);<br />}<br />} catch (MalformedURLException e) {<br />e.printStackTrace();<br />} catch (IOException e) {<br />e.printStackTrace();<br />}<br />return html.toString();<br />}<br />/**<br /> * 根據regex尋找字串<br /> *<br /> * @param html<br /> * @param regex<br /> * @return<br /> */<br />public static String[] queryString(String html, String regex) {<br />Pattern p = Pattern.compile(regex);<br />Matcher m = p.matcher(html);<br />List<String> list = new ArrayList<String>();<br />while (m.find()) {<br />for (int i = 0; i < m.groupCount(); i++) {<br />list.add(m.group(i + 1));<br />}<br />}<br />return list.toArray(new String[list.size()]);<br />}<br />}<br />

 

代碼2:

package utils.net;<br />import java.io.BufferedReader;<br />import java.io.IOException;<br />import java.io.InputStreamReader;<br />import java.net.MalformedURLException;<br />import java.net.URL;<br />import java.util.regex.Matcher;<br />import java.util.regex.Pattern;<br />/**<br /> * 學習使用<br /> *<br /> * @author loocao<br /> *<br /> * (代碼無著作權,歡迎強姦)<br /> */<br />public class LoadWebSite2 {<br />/**<br /> * @param args<br /> */<br />public static void main(String[] args) {<br />String url = "http://www.qx121.com/web/plug/weather2.asp";<br />String html = getHtml(url);<br />System.out.println(html);<br />System.out.println();<br />String[] s = queryString(<br />html,<br />"<a target=/"_blank/" href=/".{0,255}/" >"<br />+ "(.{4,20})</a></td> <td height=/"20/" "<br />+ "align=/"center/" valign=/"middle/">"<br />+ "<a target=/"_blank/" href=/".{0,255}/" >"<br />+ "(.{2,10})</a></td> <td height=/"20/" "<br />+ "align=/"center/" valign=/"middle/">"<br />+ "<a target=/"_blank/" href=/".{0,255}/" >"<br />+ "(.{4,100})</a>");<br />for (String str : s) {<br />System.out.println(str);<br />}<br />}<br />/**<br /> * 擷取url的HTML內容 <br/><br /> * URL的使用方法是在網上找到的,瞭解更多,請參考Apache Client<br /> *<br /> * @param url<br /> * @return<br /> */<br />public static String getHtml(String url) {<br />StringBuffer html = new StringBuffer();<br />try {<br />URL u = new URL(url);<br />BufferedReader reader = new BufferedReader(new InputStreamReader(u<br />.openStream()));<br />String temp;<br />while ((temp = reader.readLine()) != null) {<br />html.append(temp);<br />}<br />} catch (MalformedURLException e) {<br />e.printStackTrace();<br />} catch (IOException e) {<br />e.printStackTrace();<br />}<br />return html.toString();<br />}<br />/**<br /> * 根據regex尋找字串<br /> *<br /> * @param html<br /> * @param regex<br /> * @return<br /> */<br />public static String[] queryString(String html, String regex) {<br />Pattern p = Pattern.compile(regex);<br />Matcher m = p.matcher(html);<br />String s[] = new String[m.groupCount()];<br />if (m.find()) {<br />for (int i = 0; i < s.length; i++) {<br />s[i] = m.group(i + 1);<br />}<br />}<br />return s;<br />}<br />}