webMagic 获取图片

发表于 分类于 阅读次数： 阅读次数： Changyan： 本文字数： 2.3k 阅读时长 ≈ 2 分钟 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
package com.webmagic;

import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.selector.Selectable;

import java.io.File;
import java.io.FileOutputStream;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.stream.IntStream;

import static java.util.stream.Collectors.toList;

public class W3PdfProcessor implements PageProcessor {
    public static final String D_DEV_SOUP_SRC_MAIN_RESOURCES_W3_PDF = "D:\\dev\\soup\\src\\main\\resources\\w3Pdf\\";
    private Site site = Site.me().setRetryTimes(3).setSleepTime(1000);

    static Pdf pdf = new Pdf("上****娃）",316,"******/4ff5fff9005d59bbf09fd0/"
            ,"******************");


    @Override
    public void process(Page page) {
        byte[] bytes = page.getBytes();
        Selectable url = page.getUrl();
        List<String> strings = Arrays.asList(url.get().split("/"));
        Collections.reverse(strings);
        try {
            saveFile(pdf.getName()+"\\"+strings.get(0)+"."+pdf.getName()+".png",bytes);
        } catch (Exception e) {
            e.printStackTrace();
        }


    }

    @Override
    public Site getSite() {
        return site;
    }

    public static void main(String[] args) {
        new File(D_DEV_SOUP_SRC_MAIN_RESOURCES_W3_PDF+pdf.getName()).mkdir();
        List<String> collect = IntStream.rangeClosed(1, pdf.getPage())
                .mapToObj(e -> pdf.getPreUrl() + e).collect(toList());
        Spider
                .create(new W3PdfProcessor())
                .addUrl(collect.toArray(new String[0]))
                .thread(10)
                .run();
    }

    /**
     * 将字节流转换成文件
     * @param filename
     * @param data
     * @throws Exception
     */
    public static void saveFile(String filename,byte [] data)throws Exception{
        if(data != null){
            String filepath = D_DEV_SOUP_SRC_MAIN_RESOURCES_W3_PDF + filename;
            File file = new File(filepath);
            if(file.exists()){
                file.delete();
            }
            FileOutputStream fos = new FileOutputStream(file);
            fos.write(data,0,data.length);
            fos.flush();
            fos.close();
        }
    }
}
@Data
@AllArgsConstructor
@NoArgsConstructor
class Pdf{
    String name;
    int page;
    String preUrl;
    String pdfOnlineUrl;
}