python-requests 库使用

python-requests 库使用

"""
安装
pip install requests
"""

# 使用
import requests
response = requests.get('https://www.baidu.com/')
print(type(response)) # <class 'requests.models.Response'>
print(response.status_code) # 200
print(type(response.text)) # <class 'str'>
print(response.text)
print(response.cookies) # <RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>]>

各种请求方式

import requests
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')

get请求

# 基础的get请求
import requests
response = requests.get('http://httpbin.org/get')
print(response.text)

# 带参数的get请求
import requests
response = requests.get("http://httpbin.org/get?name=germey&age=22")
print(response.text)

# 另一种方法给get请求的 url设置参数
import requests
data = {
    'name': 'germey',
    'age': 22
}
response = requests.get("http://httpbin.org/get", params=data)
print(response.text)

响应结果json

import requests
import json

response = requests.get("http://httpbin.org/get")
print(type(response.text))
print(type(response.json()))
# 接收json
print(json.loads(response.text))
print(response.json())

获取二进制数据

response = requests.get("https://github.com/favicon.ico")
# <class 'str'> <class 'bytes'>
print(type(response.text), type(response.content)) 

print(response.text)
print(response.content)

# 保存二进制文件 ico是图片 图标
import requests
response = requests.get("https://github.com/favicon.ico")
with open('favicon.ico', 'wb') as f:
    f.write(response.content)
    f.close()

添加请求头

# 不加请求头，有些服务会直接报500的错误
import requests
response = requests.get("https://www.zhihu.com/explore")
print(response.text)

# 添加请求头
import requests
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.get("https://www.zhihu.com/explore", headers=headers)
print(response.text)

post请求

import requests
data = {'name': 'germey', 'age': '22'}
response = requests.post("http://httpbin.org/post", data=data)
print(response.text)

# 带参数
import requests

data = {'name': 'germey', 'age': '22'}

headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}

response = requests.post("http://httpbin.org/post", data=data, headers=headers)
print(response.json())

响应的属性

import requests

response = requests.get('http://www.jianshu.com')
print(type(response.status_code), response.status_code) #状态码
print(type(response.headers), response.headers) # 头
print(type(response.cookies), response.cookies) # cookies
print(type(response.url), response.url) # 请求的url
print(type(response.history), response.history) # 历史记录
"""
<class 'int'> 403
<class 'requests.structures.CaseInsensitiveDict'> {'Date': 'Sat, 05 Jan 2019 13:57:47 GMT', 'Content-Type': 'text/html', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Server': 'Tengine', 'Strict-Transport-Security': 'max-age=31536000; includeSubDomains; preload', 'Content-Encoding': 'gzip', 'X-Via': '1.1 pingwangtong38:5 (Cdn Cache Server V2.0), 1.1 wt61:9 (Cdn Cache Server V2.0)'}
<class 'requests.cookies.RequestsCookieJar'> <RequestsCookieJar[]>
<class 'str'> https://www.jianshu.com/
<class 'list'> [<Response [301]>]
"""

状态码判断

import requests
response = requests.get('http://www.jianshu.com/hello.html')
exit() if not response.status_code == requests.codes.not_found else print('404 Not Found')

import requests
response = requests.get('http://www.jianshu.com')
exit() if not response.status_code == 200 else print('Request Successfully')

# 状态码 对应关系
"""
100: ('continue',),
101: ('switching_protocols',),
102: ('processing',),
103: ('checkpoint',),
122: ('uri_too_long', 'request_uri_too_long'),
200: ('ok', 'okay', 'all_ok', 'all_okay', 'all_good', '\\o/', '✓'),
201: ('created',),
202: ('accepted',),
203: ('non_authoritative_info', 'non_authoritative_information'),
204: ('no_content',),
205: ('reset_content', 'reset'),
206: ('partial_content', 'partial'),
207: ('multi_status', 'multiple_status', 'multi_stati', 'multiple_stati'),
208: ('already_reported',),
226: ('im_used',),

# Redirection.
300: ('multiple_choices',),
301: ('moved_permanently', 'moved', '\\o-'),
302: ('found',),
303: ('see_other', 'other'),
304: ('not_modified',),
305: ('use_proxy',),
306: ('switch_proxy',),
307: ('temporary_redirect', 'temporary_moved', 'temporary'),
308: ('permanent_redirect',
      'resume_incomplete', 'resume',), # These 2 to be removed in 3.0

# Client Error.
400: ('bad_request', 'bad'),
401: ('unauthorized',),
402: ('payment_required', 'payment'),
403: ('forbidden',),
404: ('not_found', '-o-'),
405: ('method_not_allowed', 'not_allowed'),
406: ('not_acceptable',),
407: ('proxy_authentication_required', 'proxy_auth', 'proxy_authentication'),
408: ('request_timeout', 'timeout'),
409: ('conflict',),
410: ('gone',),
411: ('length_required',),
412: ('precondition_failed', 'precondition'),
413: ('request_entity_too_large',),
414: ('request_uri_too_large',),
415: ('unsupported_media_type', 'unsupported_media', 'media_type'),
416: ('requested_range_not_satisfiable', 'requested_range', 'range_not_satisfiable'),
417: ('expectation_failed',),
418: ('im_a_teapot', 'teapot', 'i_am_a_teapot'),
421: ('misdirected_request',),
422: ('unprocessable_entity', 'unprocessable'),
423: ('locked',),
424: ('failed_dependency', 'dependency'),
425: ('unordered_collection', 'unordered'),
426: ('upgrade_required', 'upgrade'),
428: ('precondition_required', 'precondition'),
429: ('too_many_requests', 'too_many'),
431: ('header_fields_too_large', 'fields_too_large'),
444: ('no_response', 'none'),
449: ('retry_with', 'retry'),
450: ('blocked_by_windows_parental_controls', 'parental_controls'),
451: ('unavailable_for_legal_reasons', 'legal_reasons'),
499: ('client_closed_request',),

# Server Error.
500: ('internal_server_error', 'server_error', '/o\\', '✗'),
501: ('not_implemented',),
502: ('bad_gateway',),
503: ('service_unavailable', 'unavailable'),
504: ('gateway_timeout',),
505: ('http_version_not_supported', 'http_version'),
506: ('variant_also_negotiates',),
507: ('insufficient_storage',),
509: ('bandwidth_limit_exceeded', 'bandwidth'),
510: ('not_extended',),
511: ('network_authentication_required', 'network_auth', 'network_authentication'),

"""

文件上传

import requests

files = {'file': open('favicon.ico', 'rb')}
response = requests.post("http://httpbin.org/post", files=files)
print(response.text)

获取cookies

import requests

response = requests.get("https://www.baidu.com")
print(response.cookies)
for key, value in response.cookies.items():
    print(key + '=' + value)

维持会话，模拟登陆

import requests

requests.get('http://httpbin.org/cookies/set/number/123456789')
response = requests.get('http://httpbin.org/cookies')
print(response.text)
"""
{
  "cookies": {}
}
这是因为我们两次的get请求是独立的，没有关联的。
可以想象成是用两个浏览器 发送了两次get请求，两个浏览器分别操作的
我们需要模拟成在一个浏览器内 连续两次get请求
"""

import requests

s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)
"""
{
  "cookies": {
    "number": "123456789"
  }
}
创建一个session对象，来维持这个会话状态
"""

证书验证

"""
访问https的页面，经常会出现证书问题，告诉你这个是不安全的，是否继续前往
这种时候，普通的请求就会报ssl错误
"""

import requests
from requests.packages import urllib3
urllib3.disable_warnings() # 去除警告信息
response = requests.get('https://www.12306.cn', verify=False)
print(response.status_code)


# 手动设置证书
mport requests

response = requests.get('https://www.12306.cn', cert=('/path/server.crt', '/path/key'))
print(response.status_code)

代理设置

import requests

proxies = {
  "http": "http://127.0.0.1:9743",
  "https": "https://127.0.0.1:9743",
}

response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

# 如果代理有用户名和密码 user用户名 password密码
import requests

proxies = {
    "http": "http://user:[email protected]:9743/",
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

# 如果不是http https代理 是socks代理
$ pip3 install 'requests[socks]'
import requests
# socks5 socks4
proxies = {
    'http': 'socks5://127.0.0.1:9742', 
    'https': 'socks5://127.0.0.1:9742'
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

超时设置

import requests
from requests.exceptions import ReadTimeout
try:
    response = requests.get("http://httpbin.org/get", timeout = 0.5)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')

认证设置

"""
有些网站，会弹窗让输入用户名和密码，才能看到网站的内容
"""
import requests
from requests.auth import HTTPBasicAuth
r = requests.get('http://120.27.34.24:9001', auth=HTTPBasicAuth('user', '123'))
print(r.status_code)

# 更简单的方法
import requests
r = requests.get('http://120.27.34.24:9001', auth=('user', '123'))
print(r.status_code)

异常处理

import requests
from requests.exceptions import ReadTimeout, ConnectionError, RequestException
try:
    response = requests.get("http://httpbin.org/get", timeout = 0.5)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')
except ConnectionError:
    print('Connection error')
except RequestException:
    print('Error')