爬虫爬取全国地名的中文和拼音

在做一些项目时需要用到全国地名的中文和拼音，因此我选取天气网站进行爬取。
结果是以两个列表的形式存放拼音和中文地名，有需要的可以自己进行修改扩充后使用。

# -*- coding: gbk -*-
import requests
from bs4 import BeautifulSoup
url ='https://lishi.tianqi.com'

def crwal(url):
    headers = {'User-Agent': 'Mozilla/5.0'}
    response = requests.get(url=url,  headers=headers,timeout=8)
    # response.raise_for_status()
    response.encoding = 'utf-8'
    page_text = response.text
    # print(page_text)

    bs = BeautifulSoup(page_text,"html.parser")
    test = []
    jiexi=bs.findAll('a')
    # print(jiexi)
    area_zwnameList=[]
    area_pinyinList=[]
    for i in jiexi:
        area_zwnameList.append(i.string)
        area_pinyinList.append(i['href'])
    # print(area_zwnameList)
    # print(area_pinyinList)
    # 输出地名拼音
    # print(area_pinyinList[77])
    # print(area_pinyinList[3430])
    # 输出地名中文
    # print(area_nameList[77])
    # print(area_nameList[3430])
    # 输出拼音+地名
    area_pinyinList_new = []
    area_zwnameList_new = []
    for i in range(77,3431):
        if int(len(area_zwnameList[i])) > 1 and int(len(area_pinyinList[i]) > 1):
            area_zwnameList_new.append(area_zwnameList[i])
            area_pinyinList_new.append(area_pinyinList[i].replace("/index.html","").replace("/",""))
    print(area_pinyinList_new)
    print(area_zwnameList_new)
crwal(url)