目录:
一、介绍
1 #介绍:使用requests可以模拟浏览器的请求,比起之前用到的urllib,requests模块的api更加便捷(本质就是封装了urllib3)
2
3 #注意:requests库发送请求将网页内容下载下来以后,并不会执行js代码,这需要我们自己分析目标站点然后发起新的request请求
4
5 #安装:pip3 install requests
6
7 #各种请求方式:常用的就是requests.get()和requests.post()
8 >>> import requests
9 >>> r = requests.get('https://api.github.com/events')
10 >>> r = requests.post('http://httpbin.org/post', data = {'key':'value'})
11 >>> r = requests.put('http://httpbin.org/put', data = {'key':'value'})
12 >>> r = requests.delete('http://httpbin.org/delete')
13 >>> r = requests.head('http://httpbin.org/get')
14 >>> r = requests.options('http://httpbin.org/get')
15
16
17 学习资源:http://docs.python-requests.org/en/master/
二、基于GET请求
1、基本请求
2、带参数的GET请求 -> params
3、带参数的GET请求 -> headers
4、带参数的GET请求->cookies
三 、基于POST请求
1、介绍
2、发送post请求,模拟浏览器的登录行为
2 浏览器输入https://github.com/login
3 然后输入错误的账号密码,抓包
4 发现登录行为是post提交到:https://github.com/session
5 而且请求头包含cookie
6 而且请求体包含:
7 commit:Sign in
8 utf8:✓
9 authenticity_token:lbI8IJCwGslZS8qJPnof5e7ZkCoSoMn6jmDTsL1r/m06NLyIbw7vCrpwrFAPzHMep3Tmf/TSJVoXWrvDZaVwxQ==
10 login:lucy123
11 password:123
12
13
14 二 流程分析
15 先GET:https://github.com/login拿到初始cookie与authenticity_token
16 返回POST:https://github.com/session, 带上初始cookie,带上请求体(authenticity_token,用户名,密码等)
17 最后拿到登录cookie
18
19 ps:如果密码时密文形式,则可以先输错账号,输对密码,然后到浏览器中拿到加密后的密码,github的密码是明文
20 '''
21
22 import requests
23 import re
24
25 #第一次请求
26 r1=requests.get('https://github.com/login')
27 r1_cookie=r1.cookies.get_dict() #拿到初始cookie(未被授权)
28 authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] #从页面中拿到CSRF TOKEN
29
30 #第二次请求:带着初始cookie和TOKEN发送POST请求给登录页面,带上账号密码
31 data={
32 'commit':'Sign in',
33 'utf8':'✓',
34 'authenticity_token':authenticity_token,
35 'login':'317828332@qq.com',
36 'password':'alex3714'
37 }
38 r2=requests.post('https://github.com/session',
39 data=data,
40 cookies=r1_cookie
41 )
42
43
44 login_cookie=r2.cookies.get_dict()
45
46
47 #第三次请求:以后的登录,拿着login_cookie就可以,比如访问一些个人配置
48 r3=requests.get('https://github.com/settings/emails',
49 cookies=login_cookie)
50
51 print('317828332@qq.com' in r3.text) #True
52
53 # requests.session()自动帮我们保存信息
54
55 import requests
56 import re
57
58 session=requests.session()
59 #第一次请求
60 r1=session.get('https://github.com/login')
61 authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] #从页面中拿到CSRF TOKEN
62
63 #第二次请求
64 data={
65 'commit':'Sign in',
66 'utf8':'✓',
67 'authenticity_token':authenticity_token,
68 'login':'317828332@qq.com',
69 'password':'alex3714'
70 }
71 r2=session.post('https://github.com/session',
72 data=data,
73 )
74
75 #第三次请求
76 r3=session.get('https://github.com/settings/emails')
77 print('317828332@qq.com' in r3.text) #True
78 requests.post(url='xxxxxxxx',
79 data={'xxx':'yyy'}) #没有指定请求头,#默认的请求头:application/x-www-form-urlencoed
80
81 #如果我们自定义请求头是application/json,并且用data传值, 则服务端取不到值
82 requests.post(url='',
83 data={'':1,},
84 headers={
85 'content-type':'application/json'
86 })
87
88
89 requests.post(url='',
90 json={'':1,},
91 ) #默认的请求头:application/json
四 响应Response
1、response属性
import requests
respone=requests.get('http://www.jianshu.com')
# respone属性
print(respone.text)
print(respone.content)
print(respone.status_code)
print(respone.headers)
print(respone.cookies)
print(respone.cookies.get_dict())
print(respone.cookies.items())
print(respone.url)
print(respone.history)
print(respone.encoding)
#关闭:response.close()
from contextlib import closing
with closing(requests.get('xxx',stream=True)) as response:
for line in response.iter_content():
pass
2、编码问题
3、获取二进制数据
import requests
response=requests.get('https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1509868306530&di=712e4ef3ab258b36e9f4b48e85a81c9d&imgtype=0&src=http%3A%2F%2Fc.hiphotos.baidu.com%2Fimage%2Fpic%2Fitem%2F11385343fbf2b211e1fb58a1c08065380dd78e0c.jpg')
with open('a.jpg','wb') as f:
f.write(response.content)
#stream参数:一点一点的取,比如下载视频时,如果视频100G,用response.content然后一下子写到文件中是不合理的
import requests
response=requests.get('https://gss3.baidu.com/6LZ0ej3k1Qd3ote6lo7D0j9wehsv/tieba-smallvideo-transcode/1767502_56ec685f9c7ec542eeaf6eac93a65dc7_6fe25cd1347c_3.mp4',
stream=True)
with open('b.mp4','wb') as f:
for line in response.iter_content():
f.write(line)
4、解析json
#解析json
import requests
response=requests.get('http://httpbin.org/get')
import json
res1=json.loads(response.text) #太麻烦
res2=response.json() #直接获取json数据
print(res1 == res2) #True
5、Redirection and History
By default Requests will perform location redirection for all verbs except HEAD.
We can use the history property of the Response object to track redirection.
The Response.history list contains the Response objects that were created in order to complete the request. The list is sorted from the oldest to the most recent response.
For example, GitHub redirects all HTTP requests to HTTPS:
>>> r = requests.get('http://github.com')
>>> r.url
'https://github.com/'
>>> r.status_code
200
>>> r.history
[<Response [301]>]
If you're using GET, OPTIONS, POST, PUT, PATCH or DELETE, you can disable redirection handling with the allow_redirects parameter:
>>> r = requests.get('http://github.com', allow_redirects=False)
>>> r.status_code
301
>>> r.history
[]
If you're using HEAD, you can enable redirection as well:
>>> r = requests.head('http://github.com', allow_redirects=True)
>>> r.url
'https://github.com/'
>>> r.history
[<Response [301]>]
import requests
import re
#第一次请求
r1=requests.get('https://github.com/login')
r1_cookie=r1.cookies.get_dict() #拿到初始cookie(未被授权)
authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] #从页面中拿到CSRF TOKEN
#第二次请求:带着初始cookie和TOKEN发送POST请求给登录页面,带上账号密码
data={
'commit':'Sign in',
'utf8':'✓',
'authenticity_token':authenticity_token,
'login':'317828332@qq.com',
'password':'alex3714'
}
#测试一:没有指定allow_redirects=False,则响应头中出现Location就跳转到新页面,r2代表新页面的response
r2=requests.post('https://github.com/session',
data=data,
cookies=r1_cookie
)
print(r2.status_code) #200
print(r2.url) #看到的是跳转后的页面
print(r2.history) #看到的是跳转前的response
print(r2.history[0].text) #看到的是跳转前的response.text
#测试二:指定allow_redirects=False,则响应头中即便出现Location也不会跳转到新页面,r2代表的仍然是老页面的response
r2=requests.post('https://github.com/session',
data=data,
cookies=r1_cookie,
allow_redirects=False
)
print(r2.status_code) #302
print(r2.url) #看到的是跳转前的页面https://github.com/session
print(r2.history) #[]
五 高级用法
1、SSL Cert Verification
#证书验证(大部分网站都是https)
import requests
respone=requests.get('https://www.12306.cn') #如果是ssl请求,首先检查证书是否合法,不合法则报错,程序终端
#改进1:去掉报错,但是会报警告
import requests
respone=requests.get('https://www.12306.cn',verify=False) #不验证证书,报警告,返回200
print(respone.status_code)
#改进2:去掉报错,并且去掉警报信息
import requests
from requests.packages import urllib3
urllib3.disable_warnings() #关闭警告
respone=requests.get('https://www.12306.cn',verify=False)
print(respone.status_code)
#改进3:加上证书
#很多网站都是https,但是不用证书也可以访问,大多数情况都是可以携带也可以不携带证书
#知乎百度等都是可带可不带
#有硬性要求的,则必须带,比如对于定向的用户,拿到证书后才有权限访问某个特定网站
import requests
respone=requests.get('https://www.12306.cn',
cert=('/path/server.crt',
'/path/key'))
print(respone.status_code)
2、使用代理
#官网链接: http://docs.python-requests.org/en/master/user/advanced/#proxies
#代理设置:先发送请求给代理,然后由代理帮忙发送(封ip是常见的事情)
import requests
proxies={
'http':'http://egon:123@localhost:9743',#带用户名密码的代理,@符号前是用户名与密码
'http':'http://localhost:9743',
'https':'https://localhost:9743',
}
respone=requests.get('https://www.12306.cn',
proxies=proxies)
print(respone.status_code)
#支持socks代理,安装:pip install requests[socks]
import requests
proxies = {
'http': 'socks5://user:pass@host:port',
'https': 'socks5://user:pass@host:port'
}
respone=requests.get('https://www.12306.cn',
proxies=proxies)
print(respone.status_code)
3、超时设置
#超时设置
#两种超时:float or tuple
#timeout=0.1 #代表接收数据的超时时间
#timeout=(0.1,0.2)#0.1代表链接超时 0.2代表接收数据的超时时间
import requests
respone=requests.get('https://www.baidu.com',
timeout=0.0001)
4、 认证设置
#官网链接:http://docs.python-requests.org/en/master/user/authentication/
#认证设置:登陆网站是,弹出一个框,要求你输入用户名密码(与alter很类似),此时是无法获取html的
# 但本质原理是拼接成请求头发送
# r.headers['Authorization'] = _basic_auth_str(self.username, self.password)
# 一般的网站都不用默认的加密方式,都是自己写
# 那么我们就需要按照网站的加密方式,自己写一个类似于_basic_auth_str的方法
# 得到加密字符串后添加到请求头
# r.headers['Authorization'] =func('.....')
#看一看默认的加密方式吧,通常网站都不会用默认的加密设置
import requests
from requests.auth import HTTPBasicAuth
r=requests.get('xxx',auth=HTTPBasicAuth('user','password'))
print(r.status_code)
#HTTPBasicAuth可以简写为如下格式
import requests
r=requests.get('xxx',auth=('user','password'))
print(r.status_code)
5、异常处理
#异常处理
import requests
from requests.exceptions import * #可以查看requests.exceptions获取异常类型
try:
r=requests.get('http://www.baidu.com',timeout=0.00001)
except ReadTimeout:
print('===:')
# except ConnectionError: #网络不通
# print('-----')
# except Timeout:
# print('aaaaa')
except RequestException:
print('Error')
6、上传文件
import requests
files={'file':open('a.jpg','rb')}
respone=requests.post('http://httpbin.org/post',files=files)
print(respone.status_code)