Python爬虫 requests库 get/post请求 获取响应内容

import requests
r=requests.get('http://www.lingzhilab.com/resources/getAllRes?page=1')
# u'文本内容'  bytes 类型
print(r.content)

# 获取内容并设置编码
print(r.content.decode('utf-8')) 

# 文本编码
print(r.apparent_encoding) # utf-8

# 响应状态码
print(r.status_code) # 200

# 文本内容
print(r.text)

# JSON解码器
print(r.json())

传递URL参数：

GET请求

import requests
key_dist={'page':1,'page':2}

# 原本url地址：http://www.lingzhilab.com/resources/getAllRes?page=1
r=requests.get('http://www.lingzhilab.com/resources/getAllRes',params=key_dist)

# url正确编码
print(r.url) # http://www.lingzhilab.com/resources/getAllRes?page=2

# u'文本内容'
print(r.text)

POST请求

import requests
import json
key_dist={'page':1,'page':2}

# 原本url地址：http://www.lingzhilab.com/resources/getAllRes?page=1
#r=requests.post('http://www.lingzhilab.com/resources/getAllRes',data=key_dist)

r=requests.post('http://www.lingzhilab.com/resources/getAllRes',data=json.dumps(key_dist)) # json参数

# url正确编码
print(r.url) # http://www.lingzhilab.com/resources/getAllRes

# u'文本内容'
print(r.text)

设置超时时间

秒数设置为0.001秒，会抛出异常，一般会把这个值设置为20秒

import requests
link="http://www.lingzhilab.com/resources/getAllRes?page=1"

# 原本url地址：http://www.lingzhilab.com/resources/getAllRes?page=1
r=requests.get(link,timeout=0.001)

定制请求头

import requests
headers={
'Host': 'www.lingzhilab.com',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'
}
r=requests.get('http://www.lingzhilab.com/',headers=headers)
print(r.status_code) # 200

构造session

headers={
'session':'JSESSIONID',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'
}

reqeusts底层是urllib库

参考：Python3 Requests 模块 - 梦徒 - 博客园