requests（爬虫常用）库的使用

Requests库的使用

基于urllib改写的库

示例：

import requests

response=requests.get('http://www.baidu.com')#get请求
print(response.status_code,response.url,response.cookies,response.text,sep='
')

import requests
response=requests.post('http://httpbin.org/post')#post请求
print(response.text)#.text得到的都是字符串类型的值

带参数的get请求

import requests
data={
    'name':'abc',
    'age':15
}
response=requests.get('http://httpbin.org/get',params=data)#post的参数请求时data=data
print(response.text)

----------------------------------------------

#或者直接将参数拼接在url上
import requests
response=requests.get('http://httpbin.org/get？name=adas&age=12')
print(response.text)

将返回的结果变为json格式

import requests
import json
response=requests.get('http://httpbin.org/get')
print(response.json())
print(json.loads(response.text))#等价于上面的

获取二进制数据

import requests
response=requests.get('https://weibo.com/favicon.ico')
print(response.content)
with open('weibo.ico','wb')as f:
    f.write(response.content)

添加http的headers属性

import requests
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36"
}
response=requests.get('https://zhihu.com/',headers=headers)
print(response.status_code)
print(response.text)

---

带参数的post请求

import requests
data={
    'name':'wang',
    'age':88
}
headers={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36"
}
response=requests.post('http://httpbin.org/post',data=data,headers=headers)
print(response.text)

---

response的一些属性

import requests
response=requests.get('http://www.baidu.com')
print(response.headers)
print(response.text)
print(response.status_code)
print(response.content)
print(response.cookies)
#...还有就省略了

response状态码的判断

import requests
response=requests.get('http://www.baidu.com')
# if response.status_code==requests.codes.ok:
if response.status_code==200:
    print('ok')
else:
    print('error')

---

文件上传

import requests
files={
    'file':open('weibo.ico','rb')
}
response=requests.post('http://httpbin.org/post',files=files)
print(response.text)

获取cookie

import requests           
response=requests.get('htt
cook=response.cookies     
print(type(cook))         
for key,value in cook.item
    print(key,'=',value)  

维持会话

模拟登陆

import requests
s=requests.Session()#声明session对象，通过session请求网站
s.get('http://httpbin.org/cookies/set/name/123')
response=s.get('http://httpbin.org/cookies')
print(response.text)

证书验证

import requests
from requests.packages import urllib3
urllib3.disable_warnings()#去除py警告
response=requests.get('https://www.12306.cn',verify=False)#去除证书验证
print(response.status_code)

---

代理ip

import requests
proxies={
    'http': 'http://47.89.10.103:80/'
}
response=requests.get('http://www.geogle.com',proxies=proxies)
print(response.text)

有密码的代理ip

import requests
proxies={
    'http':'http://user.password@47.89.10.103:80'
}
response=requests.get('http://www.geogle.com',proxies=proxies)
print(response.text)

---

超时设置

import requests
from requests.exceptions import ReadTimeout
try:
    response=requests.get('https://taobao.com',timeout=0.1)
except ReadTimeout as e:
    print('timeout')

认证设置(需要直接登陆才能查看网站)

import requests
from requests import HTTPBasicAuth
response=requests.get('http://115.44.48.789:8888',auth=HTTPBasicAuth('user','123'))
print(response.status_code)

---

异常处理

import requests
from requests import ReadTimeout,ConnectionError,RequestException
try:
    response=requests.get('http://www.baidu.com',timeout=0.5)
    print(response.status_code)
except ReadTimeout:
    print('timeout')
except ConnectionError:
    print('connectionerror')
except RequestException:
    print('requesterror')