本文地址:http://blog.csdn.net/shanglianlm/article/details/70188385
最近由于工作需要,写了一个小的爬虫,主要用于爬取网易汽车车型库(http://product.auto.163.com/)上的不同品牌/车标(共175个车标)下不同车系(共1650个系列)的的图片(各八张)
代码下载
代码如下:
共CarBrand.java,CarCrawer.java,CarCrawerDemo.java三个文件。
实体
CarBrand.java
package com.mingo.crawer;import java.util.ArrayList;public class CarBrand {private String ppName; private String ppUrl; private ArrayList<CarBrand> ppList;private String cxName; private String cxUrl; private ArrayList<CarBrand> cxList;private String cxTpName; private String cxTpUrl; private ArrayList<CarBrand> cxTpList;private String tpName;private String tpNameUrl;//getter() 和 setter() 省略}
具体实现
CarCrawer.java
package com.mingo.crawer;import java.io.BufferedReader;
import java.io.File;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.RandomAccessFile;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;public class CarCrawer {public static String carUrl = "http://product.auto.163.com";public static String SendGet(String url) { // 定义一个字符串用来存储网页内容 String result = ""; // 定义一个缓冲字符输入流 BufferedReader in = null; try { // 将string转成url对象 URL realUrl = new URL(url); // 初始化一个链接到那个url的连接 URLConnection connection = realUrl.openConnection(); // 开始实际的连接 connection.connect(); // 初始化 BufferedReader输入流来读取URL的响应 in = new BufferedReader(new InputStreamReader( connection.getInputStream(), "GB2312")); // 用来临时存储抓取到的每一行的数据 String line; while ((line = in.readLine()) != null) { // 遍历抓取到的每一行并将其存储到result里面 result += line; } } catch (Exception e) { System.out.println("发送GET请求出现异常!" + e); e.printStackTrace(); } // 使用finally来关闭输入流 finally { try { if (in != null) { in.close(); } } catch (Exception e2) { e2.printStackTrace(); } } return result; } /*** 下载文件到本地** @param urlString* 被下载的文件地址* @param filename* 本地文件名* @throws Exception* 各种异常*/public static void download(String urlString, String filename,String savePath) throws Exception { // 构造URL URL url = new URL(urlString); // 打开连接 URLConnection con = url.openConnection(); //设置请求超时为5s con.setConnectTimeout(5*1000); // 输入流 InputStream is = con.getInputStream(); // 1K的数据缓冲 byte[] bs = new byte[1024]; // 读取到的数据长度 int len; // 输出的文件流 File sf=new File(savePath); if(!sf.exists()){ sf.mkdirs(); } OutputStream os = new FileOutputStream(sf.getPath()+"\\"+filename); // 开始读取 while ((len = is.read(bs)) != -1) { os.write(bs, 0, len); } // 完毕,关闭所有链接 os.close(); is.close(); } public static void writeTxtFile(String content,String txtfilename)throws Exception{ FileWriter writer = new FileWriter(txtfilename, true); writer.write(content); writer.close(); } public static ArrayList<CarBrand> removeDuplicate(ArrayList<CarBrand> list) {List<CarBrand> newlist= new ArrayList<CarBrand>();Set<String> set=new HashSet<String>();for (CarBrand car:list) {if (car == null) {continue;}String str = car.getCxName();if (str != null) {if (!set.contains(str)) { //set中不包含重复的set.add(str);newlist.add(car);} } }return (ArrayList<CarBrand>) newlist;}/** @param url* 示例 http://product.auto.163.com/brand/a/*/public static ArrayList<CarBrand> getPpUrl(String url) throws Exception {ArrayList<CarBrand> ppList = new ArrayList<CarBrand>();String content = CarCrawer.SendGet(url);Pattern patternName = Pattern.compile("title=\"进入.{1,20}品牌频道");Pattern patternUrl = Pattern.compile("<a href='/brand/[a-z]/.{1,20}' title");Matcher matcherName = patternName.matcher(content); Matcher matcherUrl = patternUrl.matcher(content);while(matcherName.find()&&matcherUrl.find()){CarBrand carBrand = new CarBrand();carBrand.setPpName(matcherName.group(0).substring(9, matcherName.group(0).length()-4));carBrand.setPpUrl(carUrl+matcherUrl.group(0).substring(9, matcherUrl.group(0).length()-7));//System.out.println(carBrand.getPpName()+": "+carBrand.getPpUrl());ppList.add(carBrand);}return ppList;}/** @param url* 示例 http://product.auto.163.com/brand/a/*/public static ArrayList<CarBrand> getCxUrl(String url) throws Exception {ArrayList<CarBrand> cxPicList = new ArrayList<CarBrand>();String content = CarCrawer.SendGet(url);//Pattern pattern = Pattern.compile("class=\"group\">.*<div class=\"gbox gbox2\" >");//Matcher matcher = pattern.matcher(content); int i=0;while(content.indexOf("class=\"group\">",i)>0){int subS = content.indexOf("class=\"group\">",i);int subE = content.indexOf("<div class=\"gbox gbox2\" >",i);String subContent = content.substring(subS, subE);i=subE+10; //System.out.println("subContent "+subContent);Pattern patternTitle = Pattern.compile("频道\">进入.{1,20}品牌频道</a>]</span>");Matcher matcherTitle = patternTitle.matcher(subContent);String strtitle= null;if(matcherTitle.find()){strtitle = matcherTitle.group(0).substring(6, matcherTitle.group(0).length()-16);}Pattern patternName = Pattern.compile("\"查看.{1,20}图片\">");Pattern patternUrl = Pattern.compile("/series/photo/.{10,20}\"");Matcher matcherName = patternName.matcher(subContent); Matcher matcherUrl = patternUrl.matcher(subContent);while(matcherName.find()&&matcherUrl.find()){CarBrand carBrand = new CarBrand();carBrand.setPpName(strtitle);//System.out.println(carBrand.getPpName());carBrand.setCxName(matcherName.group(0).substring(3, matcherName.group(0).length()-4));carBrand.setCxUrl(carUrl+matcherUrl.group(0).substring(0, matcherUrl.group(0).length()-1));//System.out.println(carBrand.getCxName()+": "+carBrand.getCxUrl());cxPicList.add(carBrand);}}return cxPicList;}/** @param url* 示例 http://product.auto.163.com/series/photo/2350.html#CX001*/public static ArrayList<CarBrand> getCxPic(String url) throws Exception {ArrayList<CarBrand> cxPicList = new ArrayList<CarBrand>();String content = CarCrawer.SendGet(url);Pattern pattern = Pattern.compile("http://product.auto.163.com/picture/photoview.{30,40}.html");Matcher matcher = pattern.matcher(content); int num=1;while(matcher.find()&&num<9){CarBrand carBrand = new CarBrand();if(num==1){ carBrand.setCxTpName("左前");} else if(num==2){ carBrand.setCxTpName("正前"); }else if(num==3){ carBrand.setCxTpName("正侧"); } else if(num==4){ carBrand.setCxTpName("左后"); }else if(num==5){ carBrand.setCxTpName("正后"); } else if(num==6){ carBrand.setCxTpName("车顶"); }else if(num==7){ carBrand.setCxTpName("前大灯局部"); } else if(num==8){ carBrand.setCxTpName("后大灯局部"); }else{ System.out.println("Error: num = "+num); return null;}carBrand.setCxTpUrl(matcher.group(0));//System.out.println(carBrand.getCxTpName()+": "+matcher.group(0));num = num + 1;cxPicList.add(carBrand);}return cxPicList;}public static String getBigPic(String url) throws Exception {String bigPicUrl = null;String content = CarCrawer.SendGet(url);Pattern pattern = Pattern.compile("<img class=\"main_photo hidden\" data-src=\".{60,70}.jpg"); Matcher matcher = pattern.matcher(content); if(matcher.find()){//System.out.println(matcher.group(0).substring(41));bigPicUrl = matcher.group(0).substring(41);}return bigPicUrl;}}
调用
CarCrawerDemo.java
package com.mingo.crawer;import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.Calendar;
import java.util.HashSet;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;public class CarCrawerDemo {public static String carUrl = "http://product.auto.163.com";public static void main(String[] args) throws Exception {// TODO Auto-generated method stub//保存路径 D:\\CarPic\\String savePath = "D:\\CarTp\\";//文件名 奥迪__奥迪Q5_2017款_左后.jpgString filename = "";//txt文件名String txtfilename=savePath+"output.txt";String url = "http://product.auto.163.com/brand/";System.out.println(url);ArrayList<CarBrand> pplist = CarCrawer.getPpUrl(url);System.out.println(pplist.size());ArrayList<CarBrand> cxUrllistNew = new ArrayList<CarBrand>();Set<String> ppUrlSet=new HashSet<String>();for(CarBrand pp:pplist){ String ppUrlStr= pp.getPpUrl().substring(0, 36);if (!ppUrlSet.contains(ppUrlStr)) { //set中不包含重复的ppUrlSet.add(ppUrlStr); ArrayList<CarBrand> cxUrllist = CarCrawer.getCxUrl(pp.getPpUrl()); cxUrllistNew.addAll(cxUrllist); }}System.out.println(cxUrllistNew.size());CarCrawer.writeTxtFile("\nCalendar: "+Calendar.getInstance(),txtfilename);for(CarBrand cxUrlNew:cxUrllistNew){//System.out.println(cxUrlNew.getPpName()+" "+cxUrlNew.getCxName()+" "+cxUrlNew.getCxUrl());ArrayList<CarBrand> cxTplist = CarCrawer.getCxPic(cxUrlNew.getCxUrl());for(CarBrand cxTp:cxTplist){ String tpName = cxUrlNew.getPpName()+"_"+cxUrlNew.getCxName()+"_"+cxTp.getCxTpName()+".jpg";String tpNameUrl = CarCrawer.getBigPic(cxTp.getCxTpUrl());//System.out.println(tpName+" "+tpNameUrl);CarCrawer.writeTxtFile("\n"+tpName+" "+tpNameUrl,txtfilename);if(tpName!=null&&tpNameUrl!=null){CarCrawer.download(tpNameUrl, tpName, savePath);}}}System.out.println("finished!");}
}
下载结果:
改进点:
1 没有爬取每个车系的年款;
2 库有点小,车辆主要是小型车,
3 代码速度要进一步优化。
版权声明:本站所有资料均为网友推荐收集整理而来,仅供学习和研究交流使用。
工作时间:8:00-18:00
客服电话
电子邮件
admin@qq.com
扫码二维码
获取最新动态