python 爬虫学习第二课

Posted 2022-11-30 helenandyoyo

python 爬虫学习之requests模块

• • request响应内容
  • request post请求
  • 状态码
  • 文件上传
  • 获取cookie
  • 会话维持
  • 解析json
  • 添加header
  • 认证设置一
  • 认证设置二
  • 异常处理

request响应内容

#request响应内容
import requests

response = requests.get('http://www.baidu.com')
print(type(response))
print(response.status_code)
print(type(response.text))
print(response.text)
print(response.cookies)
print(response.content)
print(response.content.decode('utf-8'))

request post请求

#request post请求
import requests

data = 
    "name":"sun",
    "age":"25"


response = requests.get('http://www.baidu.com', params=data)
print(response.url)
print(response.content.decode('utf-8'))

状态码

#状态码

import requests

response = requests.get('http://www.baidu.com')
if response.status_code == requests.codes.ok:
    print('访问成功')

文件上传

#文件上传
import requests

files = "files" : open("test.jpg","rb")
response = requests.post('http://httpbin.org/post', files= files)
print(response.text)

获取cookie

#获取cookie
import requests

response = requests.get('http://www.baidu.com')
print(response.cookies)

for key, value in response.cookies.items():
    print(key+ "=" + value)

会话维持

#会话维持
import requests
s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456')
response = s.get('http://httpbin.org/cookies')
print(response.text) 

解析json

#解析json
import requests
import json

response = requests.get('http://httpbin.org/get')
print(type(response.text))
print(response.json())
print(json.loads(response.text))
print(type(response.json()))

添加header

#添加header
import requests

headers = 
     "User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_4) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/58.0.3029.110 Safari/537.36"

response = requests.get('https://www.zhihu.com', headers= headers)
print(response.text)

认证设置一

#认证设置一
import requests
from requests.auth import HTTPBasicAuth

response = requests.get('http://120.27.34.24:9001/', auth = HTTPBasicAuth("user","123"))
print(response.status_code)

认证设置二

#认证设置二
import requests

response = requests.get('http://120.27.34.24:9001/',auth =("user","123"))
print(response.status_code)

异常处理

#异常处理
import requests
from requests.exceptions import Timeout, ConnectionError, RequestException

try:
    response = requests.get('http://httpbin.org/get', timeout= 0.1)
    print(response.status_code)
except Timeout:
    print("timeout!")
except ConnectionError:
    print('connection error!')
except RequestException:
    print('error')

注：学习资料来源：https://www.cnblogs.com/zhaof/p/6915127.html