#爬取搜狗首页的页面源码数据
import requests
#1.指定url
url = ‘https://www.sogou.com/‘
#2.请求发送get:get返回值是一个响应对象
response = requests.get(url=url)
#3.获取响应数据 
page_text = response.text #返回的是字符串形式的响应数据
#4.持久化存储
with open(‘sogou.html‘,‘w‘,encoding=‘utf-8‘) as fp:
    fp.write(page_text)

#实现一个简易的网页采集器
#需要让url携带的参数动态化
url = ‘https://www.sogou.com/web‘
#实现参数动态化
wd = input(‘enter a key:‘)
params = {
    ‘query‘:wd
}
#在请求中需要将请求参数对应的字典作用到params这个get方法的参数中
response = requests.get(url=url,params=params)

page_text = response.text
fileName = wd+‘.html‘
with open(fileName,‘w‘,encoding=‘utf-8‘) as fp:
    fp.write(page_text)

#解决乱码

url = ‘https://www.sogou.com/web‘
#实现参数动态化
wd = input(‘enter a key:‘)
params = {
    ‘query‘:wd
}
#在请求中需要将请求参数对应的字典作用到params这个get方法的参数中
response = requests.get(url=url,params=params)
response.encoding = ‘utf-8‘ #修改响应数据的编码格式
page_text = response.text
fileName = wd+‘.html‘
with open(fileName,encoding=‘utf-8‘) as fp:
    fp.write(page_text)

#解决UA检测
url = ‘https://www.sogou.com/web‘
#实现参数动态化
wd = input(‘enter a key:‘)
params = {
    ‘query‘:wd
}
headers = {
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/76.0.3809.132 Safari/537.36‘
}
#在请求中需要将请求参数对应的字典作用到params这个get方法的参数中
response = requests.get(url=url,params=params,headers=headers)
response.encoding = ‘utf-8‘ #修改响应数据的编码格式
page_text = response.text
fileName = wd+‘.html‘
with open(fileName,encoding=‘utf-8‘) as fp:
    fp.write(page_text)

# 爬取豆瓣排行
url = ‘https://movie.douban.com/j/chart/top_list‘
start = input(‘您想从第几部电影开始获取:‘)
limit = input(‘您想获取多少电影数据:‘)
dic = {
    ‘type‘: ‘13‘,‘interval_id‘: ‘100:90‘,‘action‘: ‘‘,‘start‘: start,‘limit‘: limit,}
response = requests.get(url=url,params=dic,headers=headers)
page_text = response.json() #json()返回的是序列化好的实例对象
for dic in page_text:
    print(dic[‘title‘]+‘:‘+dic[‘score‘])

#肯德基餐厅查询http://www.kfc.com.cn/kfccda/storelist/index.aspx
url = ‘http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword‘

adderss = input(‘请输入查询的关键字‘)
for i in range(1,5):
    dic = {
        ‘cname‘: ‘‘,‘pid‘: ‘‘,‘keyword‘: adderss,‘pageIndex‘: str(i),‘pageSize‘: ‘10‘,}
    response = requests.post(url=url,headers=headers,data=dic)
    page_text = response.json()

    for a in page_text[‘Table1‘]:
        print(‘餐厅名称:‘,a[‘storeName‘]+‘餐厅‘,‘---- 餐厅地址:‘,a[‘addressDetail‘])

# 国家药品监督管理局

import requests
url = ‘http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList‘
headers = {
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/76.0.3809.132 Safari/537.36‘
}
dic = {
    ‘on‘: ‘true‘,‘page‘: ‘1‘,‘pageSize‘: ‘15‘,‘productName‘:‘‘,‘conditionType‘: ‘1‘,‘applyname‘: ‘‘,‘applysn‘:‘‘,}
response = requests.post(url=url,data=dic)
page_text = response.json()
for page in page_text[‘list‘]:
    # print(page[‘EPS_NAME‘],page[‘ID‘])
    _url = ‘http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById‘
    _dic = {
        ‘id‘: page[‘ID‘]
    }
    _response = requests.get(url=_url,params=_dic)
    _page_text = _response.json()
    print(_page_text[‘epsName‘],‘-----‘,_page_text[‘legalPerson‘])