Requests - python第三方请求包入门

简单例子

# 发送 get 请求
url = 'https://www.baidu.com'
res = requests.get(url)
print(res.text)

安装

pipe install requests

请求方法

get

get(url, params=None, **kwargs)

# 不带参数
get('https://huaban.com/search')
# 带参数
params = { 'q': '赛博朋克' } 
get(url, params)

post

post(url, data=None, json=None, **kwargs)

# 无参数
url= '...'
# data 可以为字典 or 元组

# data 为dict字典
dict_data = {'name': 'coco', 'age': 12}
post(url, data=dict_data)

# data 为元组列表
tulp_data = (('name', 'coco'), ('age', 12)) 
post(url, data=tulp_data)

# 接收json数据
post(url, data=json.dumps(dict_data))
# 直接使用json字段
post(url, json=dict_data)

# 文件上传
def_files = {'file': open('test.text', 'rb')}
post(url, files = def_files)
# 设置文件信息
name_files = {'file': ('report.xls', open('report.xls', 'rb'), 'application/vnd.ms-excel', {'Expires': '0'})}
post(url, files = name_files)

options

options(url, **kwargs)

options('http://httpbin.org/get')

head

head(url, **kwargs)

head('http://httpbin.org/get')

put

put(url, data=None, **kwargs)

put('http://httpbin.org/put', data = {'key':'value'})

patch

patch(url, data=None, **kwargs)

put('http://httpbin.org/patch', data = {'key':'value'})

delete

delete(url, **kwargs)

delete('http://httpbin.org/delete')

request

基础请求函数, 其他请求方法都是该方法的包装函数
request (self, method, url, params=None, data=None, headers=None, cookies=None, files=None, auth=None, timeout=None, allow_redirects=True, proxies=None, hooks=None, stream=None, verify=None, cert=None, json=None)

# get 请求函数
res = request('get', 'https://www.baidu.com', params={'id': 'xxx'})

获取响应内容

res = get('https://www.baidu.com')
# 文本格式内容
text_content = res.text
# json内容
json_content = res.json
# 二进制内容
byte_content = res.content

# buff流
res = get('https://www.baidu.com', stream=True)
# 读取指定长度内容
r.raw.read(100)
# 读取全部内容
r.raw.read()

响应状态码

r = requests.get('http://httpbin.org/get')
# 获取状态码
print(r.status_code)

# 捕获请求错误, 例如: 404,500 等
r = post('https://www.baidu.com/api')
try:
  # 如果请求错误，将抛出异常
  r.raise_for_status()
except Exception as e:
  print('ERROR: ', e)
内置预设状态码
from requests import get, codes
r = requests.get('http://httpbin.org/get')
print(r.status_code === codes.ok)

codes 列表

codes = {

    # Informational.
    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'),
}

响应头

响应头为字典类型， 不区分大小写

设置request响应头

url = '...'
headers = {'user-agent': 'my-app/0.0.1'}
r = get(url, headers=headers)
查看response响应头
url= 'https://www.baidu.com'  

r = get(url)

# 显示全部字段
print(r.headers)

# 查询指定字段
print(r.headers.get('Content-Type'))

cookie

设置request cookie

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

cookies = dict(
  id='xxx',
  name='yyy'
)
r = get(url,cookies=cookies)

获取response cookie

url= 'https://www.baidu.com'  
r = get(url,cookies=cookies)

print(r.cookies, type(r.cookies))
# <RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>]> <class 'requests.cookies.RequestsCookieJar'>
print(dict(r.cookies))
# {'BDORZ': '27315'}
print(r.cookies.get('BDORZ'))
# 27315

history 历史记录

Requests 将自动处理重定向, history 收集了重定向的请求体

r = get(url,cookies=cookies)
print(r.history)
# []
# 无重定向时，列表为空

timeout 请求超时

# 设置请求超时时长
get('http://github.com', timeout=0.001)