Python:爬虫之获取中国地区名称

获取城市名称

存在一个没有解决的问题：用csv读写每个词都被逗号分开，实在没有办法了，用的普通的读写文件

第一个确实可以，但是我不能很好的把第二个中的正则表达式用进去，所以只能这样了

#获取城市名称1
import re
import csv
import time
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.support.select import Select


def get_url():
    url = 'http://www.maps7.com/china_province.php'  # http://www.maps7.com/china_province.php
    return url


def get_urlText(url):
    try:
        kv = {'user-agent': 'Mozilla/5.0'}
        r = requests.get(url, headers=kv)
        r.raise_for_status()
        r.encoding = r.apparent_encoding  # 使其encoding更准确
        # print (r.text)  #1
        return r.text
    except:
        print('error 1')
        return


def get_parseText(parse_url):
    try:
        city_list = []
        soup = BeautifulSoup(parse_url, 'html.parser')
        for elem in soup.find_all('a'):
            city_list.append(elem.text)
        return city_list
    except:
        print("error 2")
        return


url = get_url()
parse_text = get_urlText(url)
cityList = get_parseText(parse_text)
with open('cityname.csv', 'w', newline='\n', encoding='utf8') as f:
    f = csv.writer(f)
    for row in cityList:
        f.writerow(row)





       

 

#获取城市名称2
def get_urlText(url):
    try:
        kv = {'user-agent': 'Mozilla/5.0'}
        r = requests.get(url, headers=kv)
        r.raise_for_status()
        r.encoding = r.apparent_encoding  # 使其encoding更准确
        # print (r.text)  #1
        return r.text
    except:
        print('error 1')
        return

def get_lists(parse_url):
    try:
        province= ''
        city=''
        lists=[]
        for num in range(0, 34):
            if (num == 33):
                text = re.findall('<a name="33"(.*)</a>',parse_url)
            else:
                text = re.findall('<a name="' + str(num) + '" href=.*?>(.*?)<a name="' + str(num + 1) + '" href=.*?>',parse_url)
            for i in text:
                if (num == 0): #北京
                    province = re.findall('(.*?)</a></h4>', i)
                else:
                    province = re.findall('<h4>(.*?)</h4>', i)
                city = re.findall('<a href="/china/dianziditu.*?>(.*?)</a>', i)
            for i in province:
                if (len(city) != 0):
                    for j in city:
                        lists.append(i+''+j)
                else:
                    lists.append(i+' '+i)
        return lists
    except:
        print("error 2")
        return

url = 'http://www.maps7.com/china_province.php'
parse_text = get_urlText(url)
cityList=get_lists(parse_text)
f=open('cityname.txt','w',encoding='utf-8')
for elem in cityList:
    f.write(elem)
    f.write('\r')
f.close()