Python爬虫之——爬去湖北所有网吧名和位置信息（附爬去数据表）

表链接 

https://pan.baidu.com/s/1ZDmSqRoJTNyG8YvTRVnhpw

源码

import requests
import re

# 获取网吧信息
def getWB(url,head,city_name):
page = requests.get(url,head)
html = page.text
wb_name = re.findall('<li><a href="/ditu/wangbawk.*?>(.*?)</a></li>',html)
wb_addre = re.findall('<strong>地址：</strong>(.*?)</li>',html)
w = open('C:\\Users\\EDZ\\Desktop\\测试\\新建文本文档.txt','a')
print('开始抓取'+city_name+'网吧数据...')
for i in range(0,len(wb_name)):
w.write(wb_name[i]+' '+wb_addre[i]+' '+city_name+'\r\n')
print(city_name+'网吧数据抓取完成。')
w.close()
#获取网页
def getCityCode():
citys_code = ['wuhan','enshi','jingmen','xiaogan','huanggang','ezhou','xianning','jingzhou','yichang','suizhou','shiyan','huangshi','xiangyang','tianmenshi','xiantaoshi','qianjiang']
return citys_code
#获取城市名
def getCityName():
citys_name = ['武汉市', '恩施土家苗族自治州', '荆门市', '孝感市', '黄冈市', '鄂州市', '咸宁市', '荆州市', '宜昌市', '随州市', '十堰市', '黄石市', '襄阳市',
'天门市', '仙桃市', '潜江市']
return citys_name

if __name__ == '__main__':
#请求头
head ={
'Usear-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3573.0 Safari/537.36'
}


citys_code = getCityCode()
citys_name = getCityName()
for index in range(0,len(citys_name)):
city_code = citys_code[index]
city_name = citys_name[index]
for i in range(1,20):
url = 'http://www.go007.com/ditu/wangbawk_'+city_code+'/p'+str(i)+'/'
# 爬取网吧数据
# print(city_name+ ' '+city_code)
getWB(url,head,city_name)
print('over')