获取微信公众号用户信息

1、使用 Java 获取微信公众号用户信息

① 简介

• 微信订阅号貌似没有获取用户的 data-id 和对应昵称的接口，所以只能头铁写个脚本进行获取

② 准备事项

• jdk 环境
• IDE 编辑器
• java 的 selenium jar 包
• Google Chrome 浏览器及对应的驱动

③ 脚本代码

package com.jeffrey.manager;


import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.support.ui.ExpectedCondition;
import org.openqa.selenium.support.ui.WebDriverWait;

import java.util.*;

/**
 * @author jeffrey
 * @ClassName: GetUserDataId
 * @Description: 获取用户 data-id 和 对应的昵称
 * @date: 2021/8/15 9:09 下午
 * @version: 1.0
 * @since JDK 1.8
 */


public class GetUserDataId {

    /**
     * @Description: 键为用户的 data-id 值为 data-id 对应的昵称
     */
    private static final Map<String, String> USER_DATA_MAP = new HashMap<>();
    /**
     * @Description: selenium 驱动路径
     */
    private static final String CHROMEDRIVER_DRIVER = "src/com/jeffrey/utils/chromedriver";
    /**
     * @Description: 操作间隔时间
     */
    private static final int SPEED = 2000;

    public static void main(String[] args) {
        System.setProperty("webdriver.chrome.driver", CHROMEDRIVER_DRIVER);

        WebDriver driver = new ChromeDriver();

        driver.get("https://mp.weixin.qq.com/");
        WebDriverWait wait = new WebDriverWait(driver, 100);
        System.out.println("等待扫码登录");
        wait.until(new ExpectedCondition<WebElement>() {
            @Override
            public WebElement apply(WebDriver webDriver) {

                return driver.findElement(By.xpath("//*[@id=\"app\"]/div[2]/div[2]/div[2]/ul[1]/li[3]/em/a"));
            }
        }).click();


        /**
         * @Description: 用户总条目数，用于最后与 USER_DATA_MAP 进行校验
         */
        int allUserCount = Integer.parseInt(driver.findElement(By.cssSelector("#groupsList > dl:nth-child(1) > dt > a > em")).getText().replace("(", "").replace(")", ""));

        while (true) {
            try {
                Thread.sleep(SPEED);
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
            String[] pn;
            try {

                List<WebElement> idEle = driver.findElements(By.className("js_msgSenderAvatar"));
                List<WebElement> nameEle = driver.findElements(By.className("remark_name"));

                for (int i = 0; i < idEle.size(); i++) {
                    USER_DATA_MAP.put(idEle.get(i).getAttribute("data-id"), nameEle.get(i).getText());
                }

                pn = wait.until(new ExpectedCondition<WebElement>() {
                    @Override
                    public WebElement apply(WebDriver webDriver) {
                        return driver.findElement(By.className("page_num"));
                    }
                }).getText().replace(" ", "").split("/");


            } catch (RuntimeException e) {
                e.printStackTrace();
                continue;
            } finally {
                System.out.println("已获取 " + USER_DATA_MAP.size() + " 个用户信息，共 " + allUserCount + " 位用户");
            }

            // 判断是否最后一页
            if (Integer.parseInt(pn[0]) == Integer.parseInt(pn[1])) {
                if (allUserCount == USER_DATA_MAP.size()) {
                    System.out.println("用户总数" + USER_DATA_MAP.size());
                    Set<Map.Entry<String, String>> entries = USER_DATA_MAP.entrySet();
                    for (Map.Entry<String, String> bean : entries) {
                        System.out.println("用户 id：" + bean.getKey() + "\n用户昵称：" + bean.getValue() + "\n----------\n");
                    }
                    driver.close();
                    break;
                } else {
                    throw new RuntimeException("获取到的用户信息条目数与总条目数不符");
                }
            } else {
                // 这里应该使用 full xpath 来定位，CssSelector 和 className 选择器的每个页面 #wxPagebar_ 属性都不同
                wait.until(new ExpectedCondition<WebElement>() {
                    @Override
                    public WebElement apply(WebDriver webDriver) {
                        return driver.findElement(By.xpath("/html/body/div[2]/div/div[3]/div/div/div[4]/div[2]/div[1]/div/div[3]/div/div/span[1]/a[3]"));
                    }
                }).click();
            }
        }
    }
}