python爬虫的requests库详解，看懂这些帮你轻松解决就业问题

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)

基本POST请求

---

import requests

data = {‘name’: ‘germey’, ‘age’: ‘22’}

response = requests.post(“http://httpbin.org/post”, data=data)

print(response.text)

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

============================================================

reponse属性

---

import requests

response = requests.get(‘http://www.jianshu.com’)

print(type(response.status_code), response.status_code)

print(type(response.headers), response.headers)

print(type(response.cookies), response.cookies)

print(type(response.url), response.url)

print(type(response.history), response.history)

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’)

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’),

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

---

模拟登录

import requests

requests.get(‘http://httpbin.org/cookies/set/number/123456789’)

response = requests.get(‘http://httpbin.org/cookies’)

print(response.text)

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

---

import requests

response = requests.get(‘https://www.12306.cn’)

print(response.status_code)

import requests

from requests.packages import urllib3

urllib3.disable_warnings()

response = requests.get(‘https://www.12306.cn’, verify=False)

print(response.status_code)

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://127.0.0.1:9743”,

“https”: “https://127.0.0.1:9743”,

}

response = requests.get(“https://www.taobao.com”, proxies=proxies)

print(response.status_code)

import requests

proxies = {

“http”: “http://user:password@127.0.0.1:9743/”,

}

response = requests.get(“https://www.taobao.com”, proxies=proxies)

print(response.status_code)

pip3 install ‘requests[socks]’

import requests

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

自我介绍一下，小编13年上海交大毕业，曾经在小公司待过，也去过华为、OPPO等大厂，18年进入阿里一直到现在。

深知大多数Python工程师，想要提升技能，往往是自己摸索成长或者是报班学习，但对于培训机构动则几千的学费，着实压力不小。自己不成体系的自学效果低效又漫长，而且极易碰到天花板技术停滞不前！

因此收集整理了一份《2024年Python开发全套学习资料》，初衷也很简单，就是希望能够帮助到想自学提升又不知道该从何学起的朋友，同时减轻大家的负担。

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上Python开发知识点，真正体系化！

由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新

如果你觉得这些内容对你有帮助，可以添加V获取：vip1024c （备注Python）

一、Python所有方向的学习路线

Python所有方向路线就是把Python常用的技术点做整理，形成各个领域的知识点汇总，它的用处就在于，你可以按照上面的知识点去找对应的学习资源，保证自己学得较为全面。

二、学习软件

工欲善其事必先利其器。学习Python常用的开发软件都在这里了，给大家节省了很多时间。

三、入门学习视频

我们在看视频学习的时候，不能光动眼动脑不动手，比较科学的学习方法是在理解之后运用它们，这时候练手项目就很适合了。

常用的技术点做整理，形成各个领域的知识点汇总，它的用处就在于，你可以按照上面的知识点去找对应的学习资源，保证自己学得较为全面。

二、学习软件

工欲善其事必先利其器。学习Python常用的开发软件都在这里了，给大家节省了很多时间。

三、入门学习视频

我们在看视频学习的时候，不能光动眼动脑不动手，比较科学的学习方法是在理解之后运用它们，这时候练手项目就很适合了。