Python爬虫–requests库基本用法

requests是python实现的简单易用的HTTP库。下面介绍其一些基本的用法。

1 、基本用法

import requests

response = requests.get('http://www.baidu.com')
#print(type(response)) # 查看类型
#print(dir(response)) # 查看response下的方法
print(response.status_code)  # 打印状态码
print(response.url)  # 打印请求URL
print(response.headers)  # 打印头信息
print(response.cookies)  # 打印cookie 信息
print(response.text)   # 以文本形式打印网页源码
print(response.content)  # 以字节流形式打印网页源码

2 、各种请求方式

import requests

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

requests.post('http://httpbin.org/post')
requests.put('http://httpbin.org/put')
requests.delete('http://httpbin.org/delete')
requests.head('http://httpbin.org/get')
requests.options('http://httpbin.org/get')

3、 带参数的get请求

方式一：直接将参数写在URL中

# 方式一：直接将参数写在URL中

import requests
response = requests.get('http://httpbin.org/get?name=Tony&age=23')
print(response.text)

结果如下：

方式二：先将参数写到dict字典中，然后在请求params参数指定

import requests

data = { 'name':'Tony','age':23}
response = requests.get('http://httpbin.org/get',data)
print(response.text)

结果同上。

例2：

import requests

params = { 'k1': 'v1', 'k2': [1, 2, 3]}
params2 = { 'k1': 'v1', 'k2': None}
r = requests.get('http://httpbin.org/get', params)
r2 = requests.get('http://httpbin.org/get', params2)

print(r.url)   # 输出：http://httpbin.org/get?k1=v1&k2=1&k2=2&k2=3
print(r2.url)  # 输出：http://httpbin.org/get?k1=v1

4、解析json

import requests
r = requests.get('https://github.com/timeline.json')
print(type(r.json()))
print(r.text)

5、二进制文件

# 图片做为二进制数据进行处理，获取图片的地址，然后通过二进制转换为图片并存储下来
import requests
from PIL import Image
from io import BytesIO
r = requests.get('https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1607513130911&di=3771dc5570d59ee9a87fa0cbce37c313&imgtype=0&src=http%3A%2F%2Fa4.att.hudong.com%2F22%2F59%2F19300001325156131228593878903.jpg')
image = Image.open(BytesIO(r.content))
image.save('pic.jpg')

结果在文件目录下生成对应的图片。

6、原始数据处理

以流数据存储一张照片

# 以流数据存储一张照片
import requests
r = requests.get('https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1607513518482&di=28c7f32ac01948bfca8da75030b7ca8c&imgtype=0&src=http%3A%2F%2Fa2.att.hudong.com%2F27%2F81%2F01200000194677136358818023076.jpg', stream = True)
with open('pic.jpg', 'wb+') as f:
    for chunk in r.iter_content(1024):
        f.write(chunk)

7、POSR请求提交表单

import requests
form = { 'username': 'user', 'password': 'pass'}
r = requests.post('http://httpbin.org/post', data=form)
print(r.text)    # form表单形式

输出结果：

{ 
  "args": { }, 
  "data": "", 
  "files": { }, 
  "form": { 
    "password": "pass", 
    "username": "user"
  }, 
  "headers": { 
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Content-Length": "27", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.22.0", 
    "X-Amzn-Trace-Id": "Root=1-5fd08ff0-0015ad7c77cea92a027d4294"
  }, 
  "json": null, 
  "origin": "124.160.154.21", 
  "url": "http://httpbin.org/post"
}

import requests
r = requests.post('http://httpbin.org/post', data=json.dumps(form))
print(r.text)   # data形式

输出结果：

{ 
  "args": { }, 
  "data": "{\"username\": \"user\", \"password\": \"pass\"}", 
  "files": { }, 
  "form": { }, 
  "headers": { 
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Content-Length": "40", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.22.0", 
    "X-Amzn-Trace-Id": "Root=1-5fd09067-18566b24664f50eb30792aa1"
  }, 
  "json": { 
    "password": "pass", 
    "username": "user"
  }, 
  "origin": "124.160.154.21", 
  "url": "http://httpbin.org/post"
}

8、获取cookie

import requests
url = 'http://www.baidu.com'
r = requests.get(url)
#字典对象
cookies = r.cookies
#遍历字典对象
for k, v in cookies.items():
    print(k, v)
    
输出结果：
BDORZ 27315

本文地址：https://blog.csdn.net/LOVEYSUXIN/article/details/110930213