一、解析过程

本人使用锤子手机做测试，型号是YQ601，首先打开开发者模式确保手机能与mac相连，打开Appium客户端，配置参数如图

可以理解为Appuim继承自web端的selenium，同样可以执行一些自动化操作。Appium自带了一个XPATH选择器，给用户提供了选择结果，如图

这个选择器给出的结果太繁琐，所以可以改成通过查找ID的方式来构造爬虫程序。但是这里要注意，估计微信提升了自己的反爬能力，在测试时发现，每次重新连接手机，对应特定节点的ID都会发生变化，保险起见，每次重新连接手机，都要对节点ID作更新。

       这里把程序分为三部分：（1）模拟登陆（2）进入朋友圈（3）抓取动态（4）存入数据库

二、代码

import os
from appium import webdriver
from appium.webdriver.common.touch_action import TouchAction
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from pymongo import MongoClient
from time import sleep
from processor import Processor
from config import *class Moments():def __init__(self):"""初始化"""# 驱动配置self.desired_caps = {'platformName': PLATFORM,'deviceName': DEVICE_NAME,'appPackage': APP_PACKAGE,'appActivity': APP_ACTIVITY}self.driver = webdriver.Remote(DRIVER_SERVER, self.desired_caps)self.wait = WebDriverWait(self.driver, TIMEOUT)self.client = MongoClient(MONGO_URL)self.db = self.client[MONGO_DB]self.collection = self.db[MONGO_COLLECTION]# 处理器self.processor = Processor()def login(self):"""登录微信:return:"""# 登录按钮login = self.wait.until(EC.presence_of_element_located((By.ID, 'com.tencent.mm:id/d75')))login.click()# 手机输入phone = self.wait.until(EC.presence_of_element_located((By.ID, 'com.tencent.mm:id/hz')))phone.set_text(USERNAME)# 下一步next = self.wait.until(EC.element_to_be_clickable((By.ID, 'com.tencent.mm:id/alr')))next.click()# 密码password = self.wait.until(EC.presence_of_element_located((By.XPATH, '//*[@resource-id="com.tencent.mm:id/hz"][1]')))password.set_text(PASSWORD)# 提交submit = self.wait.until(EC.element_to_be_clickable((By.ID, 'com.tencent.mm:id/alr')))submit.click()# 是否查看通讯录yesORnot = self.wait.until(EC.element_to_be_clickable((By.ID, 'com.tencent.mm:id/an2')))yesORnot.click()def enter(self):"""进入朋友圈:return:"""# 选项卡tab = self.wait.until(EC.presence_of_element_located((By.XPATH, '//*[@resource-id="com.tencent.mm:id/b0w"][3]')))tab.click()# 朋友圈moments = self.wait.until(EC.presence_of_element_located((By.ID, 'com.tencent.mm:id/a7f')))moments.click()def crawl(self):"""爬取:return:"""while True:# 当前页面显示的所有状态items = self.wait.until(EC.presence_of_all_elements_located((By.XPATH, '//*[@resource-id="com.tencent.mm:id/d58"]//android.widget.FrameLayout')))# 上滑self.driver.swipe(FLICK_START_X, FLICK_START_Y + FLICK_DISTANCE, FLICK_START_X, FLICK_START_Y)# 遍历每条状态for item in items:try:# 昵称nickname = item.find_element_by_id('com.tencent.mm:id/as6').get_attribute('text')# 正文content = item.find_element_by_id('com.tencent.mm:id/ib').get_attribute('text')# 日期date = item.find_element_by_id('com.tencent.mm:id/dfw').get_attribute('text')# 处理日期date = self.processor.date(date)print(nickname, content, date)data = {'nickname': nickname,'content': content,'date': date,}# 插入MongoDBself.collection.update({'nickname': nickname, 'content': content}, {'$set': data}, True)sleep(SCROLL_SLEEP_TIME)except NoSuchElementException:passdef main(self):"""入口:return:"""# 登录self.login()# 进入朋友圈self.enter()# 爬取self.crawl()if __name__ == '__main__':moments = Moments()moments.main()

import time
import reclass Processor():def date(self, datetime):"""处理时间,转化成发布时间的时间戳:param datetime: 原始时间:return: 处理后时间"""if re.match('\d+分钟前', datetime):minute = re.match('(\d+)', datetime).group(1)datetime = time.strftime('%Y-%m-%d', time.localtime(time.time() - float(minute) * 60))if re.match('\d+小时前', datetime):hour = re.match('(\d+)', datetime).group(1)datetime = time.strftime('%Y-%m-%d', time.localtime(time.time() - float(hour) * 60 * 60))if re.match('昨天', datetime):datetime = time.strftime('%Y-%m-%d', time.localtime(time.time() - 24 * 60 * 60))if re.match('\d+天前', datetime):day = re.match('(\d+)', datetime).group(1)datetime = time.strftime('%Y-%m-%d', time.localtime(time.time()) - float(day) * 24 * 60 * 60)return datetime