python爬虫之Requests库详解

 

Requests库详解

 

什么是Requests

Requests 是⽤Python语⾔编写，基于 urllib，采⽤ Apache2 Licensed 开源协议的 HTTP 库。

它⽐ urllib 更加⽅便，可以节约我们⼤量的⼯作，完全满⾜ HTTP 测试需求。

⼀句话——Python实现的简单易⽤的HTTP库

安装requests

pip install requests -i https://pypi.douban.com/simple

import requests response = requests.get('https://www.baidu.com/') response.encoding='utf-8' print(type(response)) print(response.status_code) print(type(response.text)) print(response.text) print(response.cookies)

最简单的post请求

import requests response = requests.post('http://httpbin.org/post') 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.status_code) #打印状态码 print(response.text)

 

params参数

import requests data = { 'name':'germery', 'age':'22' } response = requests.get("http://httpbin.org/get",params=data) #params传输参数 print(response.status_code) print(response.text)

 

json解析

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

 

 

获取二进制文件

import requests response = requests.get("https://github.com/favicon.ico") print(type(response.text),type(response.content)) print(response.text) print(response.content)

保存文件favicon.ico

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headers请求

import requests headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'} response = requests.get("https://www.zhihu.com/explore",headers=headers) print(response.text)

 

基本POST请求

import requests data = {'name':'germey','age':'22'} headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'} response = requests.post("http://httpbin.org/post",headers=headers,data=data) print(response.text)

rrequests属性

import requests response = requests.get("https://www.jianshu.com") print(type(response.status_code),response.status_code) #状态码200表示成功 print(type(response.headers),response.headers) #打印请求头 print(type(response.cookies),response.cookies) #打印cookies print(type(response.url),response.url) #打印URL地址 print(type(response.history)) #打印历史记录

 

## 状态码判断 import requests response = requests.get('http://www.baidu.com') exit() if not response.status_code == requests.codes.ok else print('Request Successfully') import requests response = requests.get('http://www.jianshu.cn/hello.html') exit() if not response.status_code == requests.codes.not_found else print('404 Not Found') 可以用数字代替 import requests response = requests.get('http://www.baidu.com') exit() if not response.status_code == 200 else print('Request Successfully') 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'),

---

requests高级操作

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cookie

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

会话维持

模拟登陆

不能获取cookie信息，因为这样访问相当于不同的浏览器，各个浏览器访问了一次，所以不能获取cookie信息

import requests requests.get('http://httpbin.org/cookies/set/number/123456789') response = requests.get('http://httpbin.org/cookies') print(response.text) #不能获取cookie信息，因为这样访问相当于不同的浏览器，各个浏览器访问了一次，所以不能获取cookie信息

requests提供Session()对象相当于在同一个浏览器访问两次

import requests s = requests.Session() s.get('http://httpbin.org/cookies/set/number/123456789') response = s.get('http://httpbin.org/cookies') print(response.text)

证书验证

verify关闭证书验证

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

提供一个证书给他认证

import 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:#", "https": "https://127.0.0.1:#", #其中的#代表端口自己的代理自己设置 } response = requests.get("https://www.taobao.com", proxies=proxies) print(response.status_code)

有用户名和密码的

import requests proxies = { "http": "http://user:password@127.0.0.1:#/", #其中的#代表端口自己的代理自己设置 } response = requests.get("https://www.taobao.com", proxies=proxies) print(response.status_code) pip3 install 'requests[socks]'

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

import requests from requests.auth import HTTPBasicAuth r = requests.get('http://192.168.195.1:9003', auth=HTTPBasicAuth('user', '123')) print(r.status_code)

 

import requests r = requests.get('http://192.168.195.1:9003', auth=('user', '123')) print(r.status_code)

异常处理

mport 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')