Java 爬虫-谷歌商店(Google play)--应用的版本号

pywanggui

于 2023-03-17 10:03:33 发布

阅读量501

点赞数

分类专栏： Google爬虫文章标签： java 爬虫开发语言

本文链接：https://blog.csdn.net/pywanggui/article/details/129612685

版权

Google爬虫专栏收录该内容

1 篇文章 0 订阅

订阅专栏

代码

HuToolHttp 这个工具类在爬下载量的文章里

 public static String getLastVersion(String packageName, String proxyType, String host, int port, String proxyUser, String proxyPass) {
        String location = onlineLocation(packageName, proxyType, host, port, proxyUser, proxyPass);
        if (location == null) {
            return null;
        }
        HttpResponse response = null;
        for (int i = 0; response == null && i < 5; i++) {
            response = HuToolHttp.get("https://apkcombo.com" + location
                    , new HashMap<String, String>() {{
                        put("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9");
                        put("Accept-Language", "zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7,zh-TW;q=0.6,pt;q=0.5");
                        put("cache-control", "max-age=0");
                        put("referer", "https://apkcombo.com" + location + "/download/apk");
                        put("sec-ch-ua", "\"Chromium\";v=\"104\", \" Not A;Brand\";v=\"99\", \"Google Chrome\";v=\"104\"");
                        put("sec-ch-ua-mobile", "?0");
                        put("sec-ch-ua-platform", "\"Windows\"");
                        put("Sec-Fetch-Dest", "document");
                        put("Sec-Fetch-Mode", "navigate");
                        put("Sec-Fetch-Site", "same-origin");
                        put("sec-fetch-user", "?1");
                        put("upgrade-insecure-requests", "1");
                        put("User-Agent", "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.60 Safari/537.36");
                    }}, proxyType, host, port, proxyUser, proxyPass, 3000);
        }
        if (response != null && response.isOk()) {
            String reg = "<div class=\"version\">.*</div>";
            Pattern pattern = Pattern.compile(reg);
            Matcher matcher = pattern.matcher(response.body());
            if (matcher.find()) {
                String result = matcher.group().replaceAll("<div class=\"version\">", "").replaceAll("</div>", "");
//                    log.info("获取最新版本 包名:" + packageName + ";版本:" + result);
                return result;
            }
        }
        return null;
    }