Python爬虫 #003 requests

目录

• 3.1-普通使用
• 3.2-get带参
• 3.3-post 带参
• 3.4-ip代理

3.1-普通使用

import requests

url = 'https://movie.douban.com/top250'

# 伪装成浏览器
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3730.400 QQBrowser/10.5.3805.400'
}

response = requests.get(url, headers = headers)
response.encoding = 'utf-8'

# 状态码为 200 访问成功
print(response.status_code)
#打印数据文本
print(response.text)
print('------------------')
#二进制打印数据
print(response.content)

---

3.2-get带参

import requests

url = 'http://httpbin.org/get'

response = requests.get(url, data = {'name':'刘', 'age':20})
print(response.text)

---

3.3-post 带参

import requests

url = 'http://httpbin.org/post'

response = requests.post(url, data = {'name':'刘', 'age':20})
print(response.text)

---

3.4-ip代理

import requests

url = 'http://httpbin.org/get'

# 设置响应时间为2s，2s内没响应跳出
# 普通IP
response = requests.get(url, proxies = {'http':'183.166.96.49:9999'}, timeout = 2)
print(response.text)

#独享IP，需要设置账号（如：ABC）和密码（如：123）
# response = requests.get(url, proxies = {'http':'http://ABC:123@183.166.96.49:9999'}, timeout = 2)