爬虫（三）：Requests库的基本使用

一：什么是Requests

Requests是用python语言基于urllib编写的，采用的是Apache2 Licensed开源协议的HTTP库
如果你看过上篇文章关于urllib库的使用，你会发现，其实urllib还是非常不方便的，而Requests它会比urllib更加方便，可以节约我们大量的工作。（用了requests之后，你基本都不愿意用urllib了）一句话，requests是python实现的最简单易用的HTTP库，建议爬虫使用requests库。

默认安装好python之后，是没有安装requests模块的，需要单独通过pip安装

二：Requests功能详解

实例引入：

import requests

response = requests.get('https://www.baidu.com/')
# 添加编码方式，解决乱码问题
response.encoding=response.apparent_encoding
# response.encoding="utf-8"
print(type(response)) 
print(response.status_code) # 状态码 
print(type(response.text)) 
print(response.text) # 响应的文本内容 
print(response.cookies) # 响应的cookie

各种请求方式：

import requests
requests.get('https://www.baidu.com/') # get
requests.post('http://httpbin.org/post') # 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')

 请求

基本GET请求

import requests

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

带参数的GET请求

# 方式一
import requests
# 直接加在url后面
response = requests.get("http://httpbin.org/get?name=germey&age=22")
print(response.text)

# 方式二
import requests

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

# 上述两种的结果是相同的，通过params参数传递一个字典内容，从而直接构造url
# 注意：第二种方式通过字典的方式的时候，如果字典中的参数为None则不会添加到url上

解析json

import requests
import json

response = requests.get("http://httpbin.org/get")
print(type(response.text))
print(response.json())  # 实际上是执行了json.loads(response.text)
print(json.loads(response.text))
print(type(response.json()))

获取二进制数据

import requests

# 获取并打印二进制数据
response = requests.get("https://github.com/favicon.ico")
print(type(response.text), type(response.content))
print(response.text)
print(response.content)

# 获取二进制数据并存入文件，通常如视频，图片，音乐等
response = requests.get("https://github.com/favicon.ico")
with open('favicon.ico', 'wb') as f:
    f.write(response.content)
    f.close()

添加headers

# 有些网站必须要带头部信息才能正常访问
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': ''} # 通过字典类型构造
response = requests.post("http://httpbin.org/post", data=data)
print(response.text)

响应

reponse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) # 头信息
print(type(response.cookies), response.cookies) # cookies
print(type(response.url), response.url) # url
print(type(response.history), response.history) # 访问列表

状态码判断：--》状态码大全

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'),

三：requests高级操作

文件上传

import requests
# 通过files参数上传，必须以二进制读取
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

# cookie的一个作用就是可以用于模拟登陆，做会话维持
import requests

s = requests.Session() # 通过session对象来维持cookie
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)

证书验证

# 现在的很多网站都是https的方式访问，所以这个时候就涉及到证书的问题

import requests
from requests.packages import urllib3
urllib3.disable_warnings()  # 取消警告（可以不要）
# 取消证书验证，默认是验证证书，如果证书不合法会报错
response = requests.get('https://www.12306.cn', verify=False)
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",
}
# 通过proxies来设置代理
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

‘‘‘
# 如果代理需要设置用户名和密码，则将字典改写成
proxies = {
"http":"http://user:password@127.0.0.1:9999"
}

# 如果代理是通过sokces这种方式，则需要：
pip install "requests[socks]" # 安装模块
proxies= {
"http":"socks5://127.0.0.1:9999",
"https":"sockes5://127.0.0.1:8888"
}
’’’

超时设置

import requests
from requests.exceptions import ReadTimeout
try:
# 通过timeout参数设置超时的时间
    response = requests.get("http://httpbin.org/get", timeout = 0.5)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')

认证设置

# 如果碰到需要认证的网站可以通过requests.auth模块实现
# 方式一
import requests
from requests.auth import HTTPBasicAuth

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

# 方式二
import requests

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

异常处理--》详情--》常用的异常继承关系

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')