requests库的get请求（加上head，加上get参数请求）

#coding:utf-8
# 导入requests
import requests

# 构建url
url = 'http://www.baidu.com'

# 发送请求，获取响应
# response = requests.get(url)
response = requests.head(url)

# 检查状态码
# print (response.status_code)

# 检查url
# print (response.url)

# 检查请求头
# print (response.request.headers)

# 检查响应头
# print (response.headers)

# 检查源码
# print (response.content)
# print (response.content.decode())
#
# response.encoding='utf-8'
# print (response.text)
# print (response.encoding)

　　带headers的请求

#coding:utf-8
import requests
import time

# 构建url
url = 'http://www.baidu.com'

# 构建请求头
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36'
}


# 发送请求
response = requests.get(url, headers=headers)
print (len(response.content))

time.sleep(2)
response1 = requests.get(url)
print (len(response1.content))

　　

带get传参的请求

#coding:utf-8
import requests

# 构建url
url = 'https://www.baidu.com/s'
# 构建headers
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36'
}

# 构建参数
params = {
    "wd": "深圳"
}

# 发送请求
response = requests.get(url, headers=headers, params=params)

# 验证url
# print(response.url)

with open('baidu.html','w')as f:
    f.write(response.content.decode())

get带有代理的请求：

#coding:utf-8
import requests

# 构建一个url
url = 'http://www.itcast.cn'
# 构建headers
headers = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36'
        }
# 构建代理
# proxies = {
#     "http": "http://106.14.51.145:8118",
#     "https": "https://106.14.51.145:8118",
# }
# 付费代理
proxies = {
    "http": "http://morganna_mode_g:ggc22qxp@117.48.199.230:16816",
    "https": "https://morganna_mode_g:ggc22qxp@117.48.199.230:16816",
}

# 发送请求
response = requests.get(url,headers=headers,proxies=proxies)


#？ 如何验证代理是否使用成功
# 运用超时抛出异常来判断是否成功，一般0.5-1秒
# response = requests.get(url, timeout=3)