Crawler notes: Detailed explanation of the Requests library

What is Requests

I explained the crawler notes before : The detailed explanation of the Urllib library found that there are indeed inconveniences, such as adding a proxy, cookie, and sending post requests are more cumbersome.
The Request library can accomplish this in a few sentences.

Requests is
an HTTP library written in Python, based on urllib and using the Apache2 Licensed open source protocol.
It is more convenient than urllib, can save us a lot of work, and fully meet the
HTTP testing requirements.
One sentence-simple and easy-to-use HTTP library installation implemented by Python

pip3 install requests
或者
pip install requests

Usage explanation

Instance introduction

import requests

response = requests.get(r'https://www.2345.com/?38001')
print(type(response))
print(response.status_code)#状态码
print(type(response.text))
print(response.text)#文本
print(response.cookies)#cookies
print('结束')

Various request methods

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')

Basic get request

import requests

response = requests.get('http://httpbin.org/get')
print(response.text)

Get request with parameters
(splicing after the url, it needs to be separated by ?, and connected with ampersand)

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

The parameters are in args

Get request with parameters (before using ?& is more complicated, you can use a dictionary to pass values)

import requests

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

Parse json

import requests
import json

response = requests.get("http://httpbin.org/get")
print(type(response.text))
print(response.json())#response直接解析成json
print(json.loads(response.text))#通过json解析库来解析
print(type(response.json()))

Get binary data
Binary data refers to pictures or videos

import requests

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

Picture download

import requests

response = requests.get("https://github.com/favicon.ico")
with open('favicon.ico', 'wb') as f:
    f.write(response.content)
    f.close()

Adding headers
It is necessary to add headers when crawling, if you don’t add it, it is likely to ban you

import requests

headers = {
    
    'User-Agent':
           'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36'}
response = requests.get("https://blog.csdn.net/KOBEYU652453/", headers=headers)
print(response.text)

Basic POST request

import requests

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

With headers

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())

response attribute

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)#请求头
print(type(response.cookies), response.cookies)#cookies
print(type(response.url), response.url)#网址
print(type(response.history), response.history)#访问历史记录

Status code judgment

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'),

import requests

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

Advanced operation

File Upload

import requests

files = {
    
    'file': open('meinv.jpg', 'rb')}#打开本地文件
response = requests.post("http://httpbin.org/post", files=files)
print(response.text)

Get cookie

import requests

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

Mock login

Set cookies first, then get cookies

import requests

requests.get('http://httpbin.org/cookies/set/number/123456789')#先设置cookies ：number/123456789
response = requests.get('http://httpbin.org/cookies')#拿到cookies
print(response.text)

The cookie is empty, because the two get ls in the code are independent requests. It means that a cookie is set in one browser, and then another browser is used to access it.

If you want to maintain, you must first declare the session object.

import requests

s = requests.Session()#打开一个会话
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)

Proxy settings

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

Timeout setting

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')

Exception handling

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:#超时
    print('Timeout')
except ConnectionError:#网络问题
    print('Connection error')
except RequestException:#其他问题
    print('Error')

Authentication settings

import requests
from requests.auth import HTTPBasicAuth

r = requests.get('http://120.27.34.24:9001', auth=HTTPBasicAuth('user', '123'))
print(r.status_code)

import requests

r = requests.get('http://120.27.34.24:9001', auth=('user', '123'))
print(r.status_code)

Author: Electrical - Yu Dengwu