#!/usr/bin/env python # -*- encoding: utf-8 -*- ''' @Contact : liuyuqi.gov@msn.cn @Time : 2021/03/02 01:38:04 @License : Copyright © 2017-2020 liuyuqi. All Rights Reserved. @Desc : 爬虫入口 ''' import os import sys import re import json import pandas url = r"http://ccgp-shaanxi.gov.cn/notice/list.do?noticetype=3&province=province" def getUrl(): """ param : return: """ with open("data/url.txt") as file: res = file.readlines().decode("utf8") print(res) def crwal(): """ param url: return: """ pass # 爬虫数据 # 设置标签,下次从标签处继续爬 # 存储到数据库 if __name__ == "__main__": crawl()