piaoquan_crawler/weixinzhishu/weixinzhishu_main/search_key.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2023/2/10
import json
import os
import sys
import time
from appium import webdriver
from selenium.webdriver.common.by import By
sys.path.append(os.getcwd())
from common.common import Common
from common.feishu import Feishu


class Searchkey:
    @classmethod
    def start_wechat(cls, log_type, crawler):
        try:
            # Common.logger(log_type, crawler).info('启动"微信"')
            # print('启动"微信"')
            desired_caps = {'app': r"C:\Program Files (x86)\Tencent\WeChat\WeChat.exe"}
            driver = webdriver.Remote(
                command_executor='http://127.0.0.1:4723',
                desired_capabilities=desired_caps)
            driver.implicitly_wait(10)

            # Common.logger(log_type).info('点击"聊天窗口"')
            # driver.find_element(By.NAME, '聊天').click()
            #
            # Common.logger(log_type).info('点击"爬虫群"')
            # driver.find_elements(By.NAME, '爬虫群')[0].click()

            # Common.logger(log_type, crawler).info('点击微信指数')
            driver.find_elements(By.NAME, '消息')[-1].click()
            # Common.logger(log_type, crawler).info('休眠 3 秒，退出微信')
            time.sleep(3)
            driver.quit()
        except Exception as e:
            Common.logger(log_type, crawler).error(f'start_wechat异常:{e}\n')

    @classmethod
    def get_search_key(cls, log_type, crawler):
        try:
            # charles 抓包文件保存目录
            chlsfile_path = f"./{crawler}/{crawler}_chlsfiles/"
            # chlsfile_path = f"../weixinzhishu_chlsfiles/"
            all_file = os.listdir(chlsfile_path)
            chlsfile_list = []
            if len(all_file) == 0:
                Common.logger(log_type, crawler).info("chlsfile文件夹为空，等待10s")
                cls.start_wechat(log_type, crawler)
                time.sleep(10)
                cls.get_search_key(log_type, crawler)
            else:
                for file in all_file:
                    if file.endswith("chlsj") is False:
                        os.remove(f"./{crawler}/{crawler}_chlsfiles/{file}")
                    else:
                        chlsfile_list.append(file)
            if len(chlsfile_list) == 0:
                Common.logger(log_type, crawler).info('未找到chlsfile文件，重新获取')
                cls.start_wechat(log_type, crawler)
                time.sleep(10)
                cls.get_search_key(log_type, crawler)
            else:
                # 获取最新的 chlsfile
                chlsfile = chlsfile_list[-1]
                # 分离文件名与扩展名
                new_file = os.path.splitext(chlsfile)

                # 重命名文件后缀
                os.rename(os.path.join(chlsfile_path, chlsfile),
                          os.path.join(chlsfile_path, new_file[0] + ".txt"))

                with open(f"{chlsfile_path}{new_file[0]}.txt", encoding='utf-8-sig', errors='ignore') as f:
                    contents = json.load(f, strict=False)

                if "search.weixin.qq.com" not in [text['host'] for text in contents]:
                    return "未找到search_key"
                else:
                    for content in contents:
                        if content["host"] == "search.weixin.qq.com" and content["path"] == "/cgi-bin/wxaweb/wxindexgetusergroup":
                            text = content['request']['body']['text']
                            search_key = json.loads(text)['search_key']
                            return search_key
        except Exception as e:
            Common.logger(log_type, crawler).exception(f"get_search_key异常:{e}\n")
            return None

    @classmethod
    def remove_file(cls, log_type, crawler):
        try:
            all_file_path = f"./{crawler}/{crawler}_chlsfiles/"
            if not os.path.exists(all_file_path):
                os.mkdir(all_file_path)
            all_file = os.listdir(f"./{crawler}/{crawler}_chlsfiles/")
            for file in all_file:
                os.remove(f"./{crawler}/{crawler}_chlsfiles/{file}")
        except Exception as e:
            Common.logger(log_type, crawler).error(f"remove_file异常:{e}\n")

    @classmethod
    def del_search_key_from_feishu(cls, log_type, crawler):
        try:
            sheet = Feishu.get_values_batch(log_type, crawler, 'sVL74k')
            print(len(sheet))
            if len(sheet) <= 21:
                # print('<=20行')
                return
            else:
                Feishu.dimension_range(log_type, crawler, 'sVL74k', 'ROWS', 22, 22)
                cls.del_search_key_from_feishu(log_type, crawler)
        except Exception as e:
            Common.logger(log_type, crawler).error(f"del_search_key_from_feishu异常:{e}\n")

    @classmethod
    def write_search_key_to_feishu(cls, log_type, crawler):
        Common.logger(log_type, crawler).info('清除 chlsfiles 文件夹')
        cls.remove_file(log_type, crawler)
        Common.logger(log_type, crawler).info('启动微信指数小程序')
        cls.start_wechat(log_type, crawler)
        Common.logger(log_type, crawler).info('获取 search_key')
        while True:
            search_key = cls.get_search_key(log_type, crawler)
            if search_key is None or search_key == "未找到search_key":
                time.sleep(3)
                Common.logger(log_type, crawler).info('未找到search_key，重启打开微信指数，获取 search_key')
                cls.start_wechat(log_type, crawler)
                cls.get_search_key(log_type, crawler)
            else:
                Common.logger(log_type, crawler).info(f'已获取 search_key:{search_key}')
                Feishu.insert_columns(log_type, crawler, 'sVL74k', 'ROWS', 1, 2)
                time.sleep(1)
                time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(int(time.time())))
                Feishu.update_values(log_type, crawler, 'sVL74k', 'A2:B2', [[time_str, search_key]])
                cls.del_search_key_from_feishu(log_type, crawler)
                Common.logger(log_type, crawler).info(f"search_key:{search_key}写入飞书表成功\n")
                return


if __name__ == '__main__':
    # Searchkey.start_wechat('searchkey', 'weixinzhishu')
    Searchkey.write_search_key_to_feishu('searchkey', 'weixinzhishu')
    pass