piaoquan_crawler/kanyikan/kanyikan_session/kanyikan_session.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2023/9/25
import argparse
import json
import os
import sys
import time

sys.path.append(os.getcwd())
from common.common import Common
from common.scheduling_db import MysqlHelper


class KanyikanSession:
    chls_file_path = "./kanyikan/chlsfiles/"

    @classmethod
    def get_session(cls, log_type, crawler, env):
        while True:
            all_files = os.listdir(cls.chls_file_path)
            chls_files = []
            for chls_file in all_files:
                if "charles" in os.path.splitext(chls_file)[0]:
                    chls_files.append(chls_file)

            if len(chls_files) < 1:
                Common.logger(log_type, crawler).info("未找到chlsfile文件，等待60s重试")
                Common.logging(log_type, crawler, env, "未找到chlsfile文件，等待60s重试")
                time.sleep(60)
                continue

            chls_file = sorted(chls_files)[-1]
            Common.logger(log_type, crawler).info(f"chls_file:{chls_file}")
            chls_file_name = os.path.splitext(chls_file)[0]
            # 重命名文件后缀
            os.rename(os.path.join(cls.chls_file_path, chls_file),
                      os.path.join(cls.chls_file_path, f"{chls_file_name}.txt"))

            with open(os.path.join(cls.chls_file_path, f"{chls_file_name}.txt"), encoding='utf-8-sig',
                      errors='ignore') as f:
                contents = json.load(f, strict=False)

            kanyikan_request_list = []
            for content in contents:
                if "search.weixin.qq.com" in content["host"]:
                    kanyikan_request_list.append(content)
            if len(kanyikan_request_list) == 0:
                Common.logger(log_type, crawler).info("chlsfile文件中未找到:search.weixin.qq.com，等待60s重试")
                Common.logging(log_type, crawler, env, "chlsfile文件中未找到:search.weixin.qq.com，等待60s重试")
                time.sleep(60)
                continue

            for kanyikan_request in kanyikan_request_list:
                if kanyikan_request["path"] == "/cgi-bin/recwxa/recwxagetunreadmessagecnt":
                    Common.logger(log_type, crawler).info(f'query:{kanyikan_request["query"]}\n')
                    sessions = kanyikan_request["query"].split("session=")[-1].split("&")[0]
                    Common.logger(log_type, crawler).info(f"sessions:{sessions}\n")
                    for session in sessions:
                        if any(keyword in session for keyword in
                               ["vid", "offset", "wxaVersion", "limit", "scene", "count", "channelid", "subscene",
                                "clientVersion", "sharesearchid", "nettype", "switchprofile", "switchnewuser"]):
                            session = session.split("&")[0]
                            return session
                        return sessions

    @classmethod
    def del_chls_file(cls, log_type, crawler):
        all_file = sorted(os.listdir(cls.chls_file_path))
        for file in all_file:
            os.remove(os.path.join(cls.chls_file_path, file))
        Common.logger(log_type, crawler).info("删除 charles 缓存文件成功\n")

    @classmethod
    def save_session(cls, log_type, crawler, env, kanyikan_type):
        session = cls.get_session(log_type, crawler, env)
        Common.logger(log_type, crawler).info(session)
        if kanyikan_type == "kyk":
            update_sql = f""" UPDATE crawler_config SET config = JSON_SET (config, "$.token", "{session}"), update_time={int(time.time()*1000)} WHERE title="看一看推荐"; """
            MysqlHelper.update_values(log_type, crawler, update_sql, env, action="")
        elif kanyikan_type == "kykjk":
            update_sql = f""" UPDATE crawler_config SET config = JSON_SET (config, "$.token", "{session}"), update_time={int(time.time()*1000)} WHERE title="看一看健康"; """
            MysqlHelper.update_values(log_type, crawler, update_sql, env, action="")
        elif kanyikan_type == "kykln":
            update_sql = f""" UPDATE crawler_config SET config = JSON_SET (config, "$.token", "{session}"), update_time={int(time.time()*1000)} WHERE title="看一看老年"; """
            MysqlHelper.update_values(log_type, crawler, update_sql, env, action="")
        Common.logger(log_type, crawler).info("session 更新数据库成功")
        cls.del_chls_file(log_type, crawler)

    @classmethod
    def main(cls, log_type, crawler, env, kanyikan_type):
        Common.logger(log_type, crawler).info(f'开始抓取:看一看 session\n')
        Common.logging(log_type, crawler, env, f'开始抓取:看一看 session\n')
        cls.save_session(log_type, crawler, env, kanyikan_type)
        Common.del_logs(log_type, crawler)
        Common.logger(log_type, crawler).info('抓取一轮结束\n')
        Common.logging(log_type, crawler, env, '抓取一轮结束\n')


if __name__ == "__main__":
    parser = argparse.ArgumentParser()  ## 新建参数解释器对象
    parser.add_argument('--log_type', type=str)  ## 添加参数,注明参数类型
    parser.add_argument('--crawler')  ## 添加参数
    parser.add_argument('--kanyikan_type')  ## 添加参数
    parser.add_argument('--env')  ## 添加参数
    args = parser.parse_args()  ### 参数赋值，也可以通过终端赋值
    KanyikanSession.main(log_type=args.log_type,
                         crawler=args.crawler,
                         kanyikan_type=args.kanyikan_type,
                         env=args.env)