|
| 1 | +package com.silence.util; |
| 2 | + |
| 3 | +import java.io.BufferedReader; |
| 4 | +import java.io.File; |
| 5 | +import java.io.FileOutputStream; |
| 6 | +import java.io.IOException; |
| 7 | +import java.io.InputStream; |
| 8 | +import java.io.InputStreamReader; |
| 9 | +import java.net.HttpURLConnection; |
| 10 | +import java.net.URL; |
| 11 | +import java.net.URLConnection; |
| 12 | + |
| 13 | +import org.jsoup.Jsoup; |
| 14 | +import org.jsoup.nodes.Document; |
| 15 | +import org.jsoup.nodes.Element; |
| 16 | +import org.jsoup.select.Elements; |
| 17 | + |
| 18 | +/** |
| 19 | + * Java开发图片批量采集 |
| 20 | + * @author cx112 |
| 21 | + * @version v1.0 |
| 22 | + */ |
| 23 | + |
| 24 | +public class GrabPicture { |
| 25 | + /** |
| 26 | + * 根据网站的地址和页面的编码集来获取网页的源代码 |
| 27 | + * |
| 28 | + * @author cx112 |
| 29 | + * @param url |
| 30 | + * 网址路径 |
| 31 | + * @param encoding |
| 32 | + * 编码集 |
| 33 | + * @return String 网页的源代码 |
| 34 | + */ |
| 35 | + public static String gethtmlResourceByURL(String url, String encoding) { |
| 36 | + // 用于存储网页源代码 |
| 37 | + StringBuffer buf = new StringBuffer(); |
| 38 | + URL urlObj = null; |
| 39 | + URLConnection uc = null; |
| 40 | + InputStreamReader isr = null; |
| 41 | + BufferedReader buffer = null; |
| 42 | + try { |
| 43 | + // 建立网络连接 |
| 44 | + urlObj = new URL(url); |
| 45 | + // 打开网络连接 |
| 46 | + uc = urlObj.openConnection(); |
| 47 | + // 将连接网络的输入流转换 |
| 48 | + isr = new InputStreamReader(uc.getInputStream(), encoding); |
| 49 | + // 建立缓冲写入流 |
| 50 | + buffer = new BufferedReader(isr); |
| 51 | + String line = null; |
| 52 | + while ((line = buffer.readLine()) != null) { |
| 53 | + buf.append(line + "\n");// 一行一行的追加代码 |
| 54 | + } |
| 55 | + } catch (Exception e) { |
| 56 | + System.out.println("test"); |
| 57 | + e.printStackTrace(); |
| 58 | + } finally { |
| 59 | + try { |
| 60 | + if (isr != null) { |
| 61 | + isr.close(); |
| 62 | + } |
| 63 | + } catch (IOException e) { |
| 64 | + // TODO Auto-generated catch block |
| 65 | + e.printStackTrace(); |
| 66 | + } |
| 67 | + } |
| 68 | + return buf.toString(); |
| 69 | + } |
| 70 | + |
| 71 | + /** |
| 72 | + * 根据图片的网络地址，下载图片带本地服务器 |
| 73 | + * |
| 74 | + * @author cx112 |
| 75 | + * @param filePath |
| 76 | + * 文件保存的路径 |
| 77 | + * @param imgURL |
| 78 | + * 图片的网络地址 |
| 79 | + */ |
| 80 | + public static void DownImages(String filePath, String imgURL) { |
| 81 | + String fileName = imgURL.substring(imgURL.lastIndexOf("/")); |
| 82 | + |
| 83 | + try { |
| 84 | + // 创建文件目录 |
| 85 | + File files = new File(filePath); |
| 86 | + // 判断是否存在文件夹 |
| 87 | + if (!files.exists()) { |
| 88 | + files.mkdirs(); |
| 89 | + } |
| 90 | + // 获取下载地址 |
| 91 | + URL url = new URL(imgURL); |
| 92 | + // 连接网络地址 |
| 93 | + HttpURLConnection huc = (HttpURLConnection) url.openConnection(); |
| 94 | + // 获取连接的输出流 |
| 95 | + InputStream is = huc.getInputStream(); |
| 96 | + // 创建文件 |
| 97 | + File file = new File(filePath + fileName); |
| 98 | + // 创建输入流，写入文件 |
| 99 | + FileOutputStream out = null; |
| 100 | + if (file.getName().endsWith("jpg") || file.getName().endsWith("png") |
| 101 | + || file.getName().endsWith("jpeg") || file.getName().endsWith("jpg") ){ |
| 102 | + out = new FileOutputStream(file); |
| 103 | + int i = 0; |
| 104 | + while ((i = is.read()) != -1) { |
| 105 | + out.write(i); |
| 106 | + } |
| 107 | + is.close(); |
| 108 | + out.close(); |
| 109 | + } |
| 110 | + |
| 111 | + } catch (Exception e) { |
| 112 | + e.printStackTrace(); |
| 113 | + } |
| 114 | + } |
| 115 | + |
| 116 | + public static void getImage(String url, String encoding,String path){ |
| 117 | + String htmlResouce = gethtmlResourceByURL(url, encoding); |
| 118 | + // 解析网页源代码 |
| 119 | + Document document = Jsoup.parse(htmlResouce); |
| 120 | + // 获取所以图片的地址<img src="" alt= "" width= "" height=""/> |
| 121 | + Elements elements = document.getElementsByTag("img"); |
| 122 | + for (Element element : elements) { |
| 123 | + String imgSrc = element.attr("src"); |
| 124 | + if (!"".equals(imgSrc) && imgSrc.startsWith("http://")) { |
| 125 | + System.out.println("下载图片的地址===" + imgSrc); |
| 126 | + DownImages(path, imgSrc); |
| 127 | + } |
| 128 | + } |
| 129 | + } |
| 130 | + |
| 131 | + public static void main(String[] args) { |
| 132 | + // 根据网页地址和网页的编码集 获取网页的内容 |
| 133 | + String url = "http://www.tripadvisor.cn"; |
| 134 | + String encoding = "gb2312"; |
| 135 | + getImage(url, encoding, "e:\\test"); |
| 136 | + } |
| 137 | + |
| 138 | +} |
0 commit comments