LongArticlesJob-fork/spider/weixinCategoryCrawler.py

"""
@author: luojunhui
抓取全局品类文章
"""
import json
import time

from applications import WeixinSpider


class weixinCategory(object):
    """
    微信全局品类账号抓取
    """

    def __init__(self, spider_client):
        self.spider_client = spider_client
        self.spider = WeixinSpider()

    def getAccountList(self):
        """
        获取账号
        :return:
        """
        now_time = int(time.time())
        twenty_hours_ago = now_time - 3600 * 20
        sql = f"""select * from long_article_accounts_outside where latest_article_timestamp < {twenty_hours_ago};"""
        account_tuple = self.spider_client.select(sql)
        result = [
            {
                "gh_id": i[0],
                "platform": i[1],
                "account_name": i[2],
                "category": i[3],
                "latest_timestamp": i[4]
            } for i in account_tuple
        ]
        return result

    def update_data_into_mysql(self, msg_list):
        """
        将数据更新到数据库
        :return:
        """
        for obj in msg_list['data']['data']:
            print(json.dumps(obj, ensure_ascii=False, indent=4))

    def updateEachAccountArticles(self, gh_id, latest_time_stamp):
        """
        更新账号文章
        :return:
        """
        index = None
        msg_list = self.spider.update_msg_list(ghId=gh_id, index=index)
        latest_time_stamp_in_this_msg = msg_list['data']['data'][-1]['BaseInfo']
        print(latest_time_stamp_in_this_msg)


if __name__ == '__main__':
    wc = weixinCategory(spider_client="123")
    wc.updateEachAccountArticles("gh_ddafea4bcc29", latest_time_stamp=1)