requests 模块的基本使用

写入excl表中！

import requests
import xlwt
import json
headers={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
}

# url="https://movie.douban.com/j/chart/top_list?type=17&interval_id=100%3A90&action=&start=0&limit=20"

url="https://movie.douban.com/j/chart/top_list?"



params={
    'type': '17',
    'interval_id': '100:90',
    'action': '',
    'start': '1',
    'limit': '300',
}
response=requests.get(url=url,params=params,headers=headers)
page_text=response.text
data=json.loads(page_text)
# print(data)

title=["title","score","types","actors"]

li=[]
for dic in data:
    li.append([
        dic["title"],dic["score"],dic["types"],dic["actors"]
    ])

wbk=xlwt.Workbook()
sheet=wbk.add_sheet("movie")

for i in range(len(title)):
    sheet.write(0,i,title[i])
    
for i in range(1,len(li)):
    for j in range(len(title)):
        sheet.write(i,j,li[i][j])
        
        
        
        
wbk.save("douban_movie.xls")
print("ok")

request

• 添加一个cell:a b
• 删除cell:x
• 双击:进入可编辑模式
• 切换cell的模式:
  • y:markdown->code
  • m:code->markdown
• tab:
• 执行cell:shift+enter
• 打开帮助文档:
  • shift+tab

编码流程:

• 指定url
• 发起了请求
• 获取响应数据
• 持久化存储

#爬取搜狗首页源码信息

import requests
#指定url
url="https://www.sogou.com/"
# 发起请求
response=requests.get(url=url)
# 获取响应数据
page_text=response.text
# 持久化存储
with open("sogou.html","w",encoding="utf-8")as f:
    f.write(page_text)

# 简易网页采集器
#https://www.sogou.com/web?query=周杰伦
import  requests
url="https://www.sogou.com/web"
# 设置动态参数
wd=input("enter a key word:")
params={
    "query":wd
}

# UA伪装
headers={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
}



# params 是一个字典，用来处理动态请求参数
response=requests.get(url=url,params=params,headers=headers)


# 指定格式
response.encoding="utf-8"


page_text=response.text
fileName=wd+'.html'

with open(fileName,'w',encoding='utf-8') as f:
    f.write(page_text)

print(fileName,'下载成功')

# 爬取肯德基餐厅位置信息
import requests

url="http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword"

city=input("enter a city:")
# UA伪装
headers={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
}
data={
        'cname': '',
        'pid': '',
        'keyword': city,
        'pageIndex': '1',
        'pageSize': '10'
}
response=requests.post(url=url,data=data,headers=headers)

json_data=response.json()
for dic in json_data["Table1"]:
    print(dic['storeName']+':'+dic["addressDetail"]+"
")

# 爬取药品信息
# url="http://125.35.6.84:81/xk/"


import requests

url="http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList"

# UA伪装
headers={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
}
page=int(input("共需要爬取页数："))
for num in range(1,page):
    data={
        'on': 'true',
        'page':str(num),
        'pageSize': '15',
        'productName': '',
        'conditionType': '1',
        'applyname': '',
        'applysn': '',
    }

    response=requests.post(url=url,data=data,headers=headers)

    json_data=response.json()

    for dic in json_data["list"]:
    #     print(dic["ID"],dic["EPS_NAME"],'第一梯队')

        url1="http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById"
        data={
            'id':dic["ID"]
        }
        response2=requests.post(url=url1,data=data,headers=headers)

        dic2=response2.json()
        print(dic2["epsName"],dic2["epsProductAddress"])

# 爬取豆瓣电影

import requests

url="https://movie.douban.com/j/chart/top_list?type=24&interval_id=100%3A90&action=&start=0&limit=20"

# UA伪装
headers={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
}


response=requests.get(url=url,headers=headers)
json_data=response.json()

# for dic in json_data:
#     print(dic["title"],dic["rating"][0])

#爬取图片
import requests

url="http://img.netbian.com/file/2019/0730/14d3739bf11dd92055abb56e3f792d3f.jpg"

response=requests.get(url=url)
content=response.content
with open("./meinv.jpg","wb") as f:
    f.write(content)

#基于urllib爬取图片
from urllib import request

url = 'https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1564654066124&di=47579504bdd90e51c50c387cbff21391&imgtype=0&src=http%3A%2F%2Fb-ssl.duitang.com%2Fuploads%2Fitem%2F201508%2F05%2F20150805214640_tY24E.jpeg'

request.urlretrieve(url,filename="./meishaonv.jpg")

两种爬取图片方式的区别：
　　是否可以进行UA伪装