python 爬虫获取商家信息_Python利用百度地图爬取商家信息

import requests

import json

import pandas as pd

def request_hospital_data():

ak="换成自己的 AK" # 换成自己的 AK，需要申请

ct = ('衢州','宁波','台州','温州','丽水','杭州','湖州','金华')

keywords=('粥')

url = ["http://api.map.baidu.com/place/v2/search?query="+keywords+"&page_size=20&scope=1&region=" + cs + "&output=json&ak=" + ak for cs in ct]

params = {'page_num':0} # 请求参数，页码

for url1 in url:

#print(url1)

request = requests.get(url1,params=params)

#print(request)# 请求数据

total = json.loads(request.text)['total'] # 数据的总条数

#print(total)

total_page_num = (total+19) // 20 # 每个页面大小是20，计算总页码

items = [] # 存放所有的记录，每一条记录是一个元素

for i in range(total_page_num):

params['page_num'] = i

request = requests.get(url1,params=params)

for item in json.loads(request.text)['results']:

if "telephone" in item:

name = item['name']

telephone = item.get('telephone', '')

province = item['province']

city = item['city']

area = item['area']

address = item['address']

#print(name,telephone,province,city,area,address)

new_item = (name,telephone,province,city,area,address)

#print(new_item)

items.append(new_item)

#使用pandas的DataFrame对象保存二维数组

df = pd.DataFrame(items, columns=['name','telephone','province','city','area','address'])

print(df)

#df.drop_duplicates(inplace=True)

df.to_csv('粥1.csv', index=False,encoding='',mode='a')

request_hospital_data()

本文地址：https://blog.csdn.net/weixin_45206990/article/details/108251724

希望与广大网友互动？？

点此进行留言吧！