python爬虫爬取百度百科数据

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import json
import re
import requests
import datetime
from bs4 import BeautifulSoup
import os
import collections
import json 
import sys
import time 


reload(sys)
sys.setdefaultencoding('utf-8')
#获取当天的日期,并进行格式化,用于后面文件命名，格式:20200420
today = datetime.date.today().strftime('%Y%m%d')    

def crawl_wiki_data(city):
    """
    爬取百度百科中地区基础信息
    """
    headers = { 
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
    }
    url="""https://baike.baidu.com/item/{city}""".format(city=city)   
    polysemyURL ="""https://baike.baidu.com{href}"""
    try:
        time.sleep(1)
        response = requests.get(url,headers=headers,timeout=(3,7))
        count=0
        while response.status_code != 200: