用python爬虫爬取饿了么外卖店铺排名
#!/usr/bin/env python
# encoding: utf-8
"""
@version: ??
@author: phpergao
@license: Apache Licence
@file: elm_paiming.py
@time: 2016/8/2 11:18
"""
import requests,re,urllib,codeop,urllib.request,nturl2path,macurl2path
User_Agent = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36"#伪装成浏览器访问
headers = ('User-Agent', User_Agent)
opener = urllib.request.build_opener()
opener.addheaders =
def paiming(latitude,longitude):
a=0
flag=True
num=0
while flag:
url ="https://www.ele.me/restapi/shopping/restaurants?extras%5B%5D=activities&geohash=ws0edemxcy4&latitude={}&limit=24&longitude={}&offset={}".format(latitude,longitude,a)
a+=24
ret = opener.open(url).read()
html = re.findall(r'''"latitude".*?"longitude":.*?,"name":"(.*?)","next_business_time":".*?","only_use_poi":.*?,"opening_hours":''', str(ret,'utf8'))
for i in html:
num += 1
#print(i)
if '72' in i:
address=re.findall(r"latitude=(.*?)&limit=24&longitude=(.*?)&offset=",url)
print("店铺名:{},排名{},定位地址坐标:纬度{}经度{}.".format(i,num,address,address))
flag=False
break
if __name__ == '__main__':
urlslist=["23.13445,113.32062",
"23.12102,113.28648",
"23.10144,113.32775"
]
for i in urlslist:
latitude, longitude=i.split(',')
paiming(latitude,longitude)
执行结果：
页:
[1]