day_1：Requests

常用的发出请求的方法

r = requests.get('https://www.baidu.com')
r = requests.post('https://www.baidu.com')
.....

URL传参使用参数param:httpbin.org/get?key1=val1&key2=val2

param = {"key1":"val1","key2":"val2"}
r = requests.get('https://httpbin.org/get', params=param)

响应内容

r = requests.get('https://www.baidu.com')
print(r.encoding) # 文本编码
r.encoding = 'utf-8'
print(r.text)    # 文本内容
print(r.content) # 二进制文本
print(r.json()) # json文本

套接字响应内容

url = 'https://www.baidu.com'

r = requests.get(url=url, stream=True) # stream=True 必须设置

print(r.raw)  # <urllib3.response.HTTPResponse object at 0x10eb15e10>
print(r.iter_content(100)) # <generator object iter_slices at 0x10eafdeb8>

# r.raw原始的字节流 - 它不会转换响应内容
# r.iter_content 将自动解码gzip和deflate 传输编码

自定义标题

url = 'https://api.github.com/some/endpoint'
headers = {'user-agent': 'my-app/0.0.1'}
r = requests.get(url, headers=headers)

POST请求（处理表单请求）

payload = {'key1': 'value1', 'key2': 'value2'}
r = requests.post("https://httpbin.org/post", data=payload)
print(r.text)

响应状态代码r.status_code和r.raise_for_status()（当status_code=200时raise_for_status()为None 否则报错）

url = 'https://www.baidu.com'
try:
    r = requests.get(url=url) 
    print(r.status_code)
    r.raise_for_status()
except:
    pass

服务器响应头和cookeis：r.headers、r.cookeis

url = 'https://www.baidu.com'
try:
    r = requests.get(url=url) 
    print(r.status_code)
    r.raise_for_status()
    r.headers
    r.cookies
except:
    pass

重定向和历史

url = 'https://www.baidu.com'
try:
    r = requests.get(url=url, allow_redirects=False)  # 禁止重定向
    r.raise_for_status()
    r.history
except:
    pass

设置超时时间(秒)

url = 'https://www.baidu.com'
try:
    r = requests.get(url=url,time=5) 
    r.raise_for_status()
    r.history
except:
    pass

会话Session(保持cookies等登录状态)

s = requests.Session()
s.auth = ('user', 'pass')
s.headers.update({'x-test': 'true'})

# both 'x-test' and 'x-test2' are sent
s.get('https://httpbin.org/headers', headers={'x-test2': 'true'})

SSL证书验证

url = 'https://www.baidu.com'
try:
    r = requests.get(url=url, verify=False) # 忽略ssl证书验证
    r.raise_for_status()
except:
    pass

代理

proxies = {
  'http': 'http://10.10.1.10:3128',
  'https': 'http://10.10.1.10:1080',
}

proxies = {'http': 'http://user:[email protected]:3128/'} # 带用户密码

requests.get('http://example.org', proxies=proxies)