java代码自动下载Spring Boot用户手册

本示例演示Spring Boot 1.5.9.RELEASE版本的用户手册下载

pom.xml

1<?xml version="1.0" encoding="UTF-8"?>
2<project xmlns="http://maven.apache.org/POM/4.0.0"
3         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
4         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
5    <modelVersion>4.0.0</modelVersion>
6
7    <groupId>com.nihaorz</groupId>
8    <artifactId>spring-boot-doc-download</artifactId>
9    <version>1.0-SNAPSHOT</version>
10
11    <dependencies>
12        <!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->
13        <dependency>
14            <groupId>org.jsoup</groupId>
15            <artifactId>jsoup</artifactId>
16            <version>1.11.2</version>
17        </dependency>
18        <!-- https://mvnrepository.com/artifact/commons-io/commons-io -->
19        <dependency>
20            <groupId>commons-io</groupId>
21            <artifactId>commons-io</artifactId>
22            <version>2.6</version>
23        </dependency>
24    </dependencies>
25
26</project>

Application.java

1package com.nihaorz;
2
3import org.apache.commons.io.FileUtils;
4import org.apache.commons.io.IOUtils;
5import org.jsoup.Jsoup;
6import org.jsoup.nodes.Document;
7import org.jsoup.nodes.Element;
8import org.jsoup.select.Elements;
9
10import java.io.File;
11import java.io.IOException;
12import java.net.URL;
13import java.nio.charset.Charset;
14
15/**
16 * @author Nihaorz
17 */
18public class Application {
19
20    private static final Charset CHARSET = Charset.forName("UTF-8");
21
22    /**
23     * doc站点地址
24     */
25    private static final String DOC_URL = "https://docs.spring.io/spring-boot/docs/";
26
27    /**
28     * doc起始页
29     */
30    private static final String HTML_URI = "/reference/html/";
31
32    /**
33     * URL分隔符
34     */
35    private static final String URL_SEPARATOR = "/";
36
37    /**
38     * html页面结束标记
39     */
40    private static final String HTML_END_STR = ".html";
41
42    public static void main(String[] args) throws IOException {
43        String storePath = "D:\\IDEA_WS\\OperationCenter_WS\\spring-boot-doc-download\\src\\main\\doc";
44        String version = "1.5.9.RELEASE";
45        generateHtmlDoc(storePath, version);
46    }
47
48    /**
49     * 生成文档
50     *
51     * @param storePath
52     * @param version
53     */
54    private static void generateHtmlDoc(String storePath, String version) throws IOException {
55        String indexPath = DOC_URL + version + HTML_URI;
56        String html = IOUtils.toString(new URL(indexPath), CHARSET);
57        saveHtml(storePath, indexPath, html);
58        Document document = Jsoup.parse(html);
59        Elements elements = new Elements();
60        elements.addAll(document.select("span.chapter>a"));
61        elements.addAll(document.select("span.part>a"));
62        elements.addAll(document.select("span.appendix>a"));
63        String urlPath;
64        System.out.println("共解析得到" + elements.size() + "个子页面");
65        for (Element element : elements) {
66            urlPath = element.attr("href");
67            if (urlPath != null && !"".equals(urlPath.trim())) {
68                if (!urlPath.startsWith("http")) {
69                    urlPath = indexPath + urlPath;
70                }
71            }
72            html = IOUtils.toString(new URL(urlPath), CHARSET);
73            saveHtml(storePath, urlPath, html);
74        }
75    }
76
77    private static void saveHtml(String storePath, String urlPath, String html) throws IOException {
78        if (!urlPath.contains(".html#")) {
79            if (!urlPath.endsWith(HTML_END_STR)) {
80                if (urlPath.endsWith(URL_SEPARATOR)) {
81                    urlPath = urlPath + "index" + HTML_END_STR;
82                } else {
83                    urlPath = urlPath + URL_SEPARATOR + "index" + HTML_END_STR;
84                }
85            }
86            urlPath = urlPath.substring(DOC_URL.length(), urlPath.length());
87            String localPath = storePath + File.separator + urlPath.replace(URL_SEPARATOR, File.separator);
88            File file = new File(localPath);
89            if (!file.exists()) {
90                file.getParentFile().mkdirs();
91            }
92            file.createNewFile();
93            FileUtils.write(file, html, CHARSET);
94            System.out.println("保存" + file.getAbsolutePath() + "成功");
95        }
96    }
97
98}

运行main函数会在D:\IDEA_WS\OperationCenter_WS\spring-boot-doc-download\src\main\doc\1.5.9.RELEASE\reference\html目录下生成html文件

将以下脚本批量为空字符串

<script>if(window.parent==window){(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)})(window,document,'script','//www.google-analytics.com/analytics.js','ga');ga('create','UA-2728886-23','auto',{'siteSpeedSampleRate':100});ga('send','pageview');}</script>

然后将html文件放到tomcat ROOT应用下访问index.html，使用Fiddler抓包会有如下几个文件404：

highlight.css

manual.css

manual-multipage.css

background.png

important.png

note.png

tip.png

warning.png

email-decode.min.js

他们的真是下载地址如下：

https://docs.spring.io/spring-boot/docs/1.5.9.RELEASE/reference/html/css/highlight.css

https://docs.spring.io/spring-boot/docs/1.5.9.RELEASE/reference/html/css/manual.css

https://docs.spring.io/spring-boot/docs/1.5.9.RELEASE/reference/html/css/manual-multipage.css

https://docs.spring.io/spring-boot/docs/1.5.9.RELEASE/reference/html/images/background.png

https://docs.spring.io/spring-boot/docs/1.5.9.RELEASE/reference/html/images/important.png

https://docs.spring.io/spring-boot/docs/1.5.9.RELEASE/reference/html/images/note.png

https://docs.spring.io/spring-boot/docs/1.5.9.RELEASE/reference/html/images/tip.png

https://docs.spring.io/spring-boot/docs/1.5.9.RELEASE/reference/html/images/warning.png

https://docs.spring.io/cdn-cgi/scripts/d07b1474/cloudflare-static/email-decode.min.js

将上面的文件下载下来依次放到html下的css、images、js目录下

在上面的html文件中全局搜索email-decode.min.js并替换为相对路径，然后一个新鲜离线版用户手册就诞生了，从tomcat中拿出来邮件浏览器打开即可使用，还不带google统计，跟官方在线版本简直一毛一样啊。

下面放大招

整理好的zip