Java 爬虫-Jsoup

<!--Jsoup-->
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.10.3</version>
</dependency>

示例，爬取该网站的品牌，通过select选择器，先选择div块，再读取div中按标签的内容

@GetMapping("/reptile")
    public CommonResult<?> reptile() {
        //    解析url地址
        Document document = null;
        try {
            document = Jsoup.parse(new URL("http://o2**.****.com/search?"), 1000);
        } catch (IOException e) {
            e.printStackTrace();
        }
        //获取title的内容
        Element title = document.select("div.brand_cen").first();
        MachineBrand machineBrand = null;
        List<MachineBrand> brandList = new ArrayList<>();
        char c;
        for (c = 'A'; c <= 'Z'; ++c) {
            if (String.valueOf(c).equals("U")) {
                continue;
            }
            final String divClass = "div.brand_box" + c;
            final Element div = title.select(divClass).first();
            final ListIterator<Element> a = div.select("a").listIterator();
            int sort = 0;
            while (a.hasNext()) {
                final Element next = a.next();
                final String text = next.text();
                machineBrand = new MachineBrand();
                machineBrand.setName(text);
                machineBrand.setSort(sort);
                machineBrand.setType(String.valueOf(c));
                brandList.add(machineBrand);
                sort++;
            }
        }
        brandService.saveBatch(brandList);
        return CommonResult.success("1");
    }