爬虫之requests 高级用法

1. 文件上传

import requests
 
files = {'file': open('favicon.ico', 'rb')}
r = requests.post("http://httpbin.org/post", files=files)
print(r.text)

{
  "args": {}, 
  "data": "", 
  "files": {
    "file": "data:application/octet-stream;base64,AAAAAA...="
  }, 
  "form": {}, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Content-Length": "6665", 
    "Content-Type": "multipart/form-data; boundary=809f80b1a2974132b133ade1a8e8e058", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.10.0"
  }, 
  "json": null, 
  "origin": "60.207.237.16", 
  "url": "http://httpbin.org/post"
}

2. Cookies

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

<RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>, <Cookie __bsi=13533594356813414194_00_14_N_N_2_0303_C02F_N_N_N_0 for .www.baidu.com/>]>
BDORZ=27315
__bsi=13533594356813414194_00_14_N_N_2_0303_C02F_N_N_N_0

import requests
 
cookies = 'q_c1=31653b264a074fc9a57816d1ea93ed8b|1474273938000|1474273938000; d_c0="AGDAs254kAqPTr6NW1U3XTLFzKhMPQ6H_nc=|1474273938"; __utmv=51854390.100-1|2=registration_date=20130902=1^3=entry_date=20130902=1;a_t="2.0AACAfbwdAAAXAAAAso0QWAAAgH28HQAAAGDAs254kAoXAAAAYQJVTQ4FCVgA360us8BAklzLYNEHUd6kmHtRQX5a6hiZxKCynnycerLQ3gIkoJLOCQ==";z_c0=Mi4wQUFDQWZid2RBQUFBWU1DemJuaVFDaGNBQUFCaEFsVk5EZ1VKV0FEZnJTNnp3RUNTWE10ZzBRZFIzcVNZZTFGQmZn|1474887858|64b4d4234a21de774c42c837fe0b672fdb5763b0'
jar = requests.cookies.RequestsCookieJar()
headers = {
    'Host': 'www.zhihu.com',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36'
}
for cookie in cookies.split(';'):
    key, value = cookie.split('=', 1)
    jar.set(key, value)
r = requests.get("http://www.zhihu.com", cookies=jar, headers=headers)
print(r.text)

3. 会话维持

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

{
  "cookies": {
    "number": "123456789"
  }
}

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

4. SSL证书验证

import requests
 
response = requests.get('https://www.12306.cn')
print(response.status_code)

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

5. 代理设置

import requests
 
proxies = {
  "http": "http://10.10.1.10:3128",
  "https": "http://10.10.1.10:1080",
}
 
requests.get("https://www.taobao.com", proxies=proxies)

当然，直接运行这个实例可能不行，因为这个代理可能是无效的，请换成自己的有效代理试验一下。

若代理需要使用HTTP Basic Auth，可以使用类似http://user:password@host:port这样的语法来设置代理，示例如下：

import requests
 
proxies = {
    "http": "http://user:password@10.10.1.10:3128/",
}
requests.get("https://www.taobao.com", proxies=proxies)

除了基本的HTTP代理外，requests还支持SOCKS协议的代理。

首先，需要安装socks这个库：

pip3 install 'requests[socks]'

 然后就可以使用SOCKS协议代理了，示例如下：

import requests
 
proxies = {
    'http': 'socks5://user:password@host:port',
    'https': 'socks5://user:password@host:port'
}
requests.get("https://www.taobao.com", proxies=proxies)

6. 超时设置

import requests
 
r = requests.get("https://www.taobao.com", timeout = 1)
print(r.status_code)

实际上，请求分为两个阶段，即连接（connect）和读取（read）。

上面设置的timeout将用作连接和读取这二者的timeout总和。

如果要分别指定，就可以传入一个元组：

r = requests.get('https://www.taobao.com', timeout=(5,11, 30))

7. 身份认证

import requests

r = requests.post('http://localhost/Admin/Public/login.html', data=({'uid':'admin', 'pwd':'admin123'}))
print(r.status_code)
print(r.text)

8. Prepared Request

from requests import Request, Session
 
url = 'http://httpbin.org/post'
data = {
    'name': 'germey'
}
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36'
}
s = Session()
req = Request('POST', url, data=data, headers=headers)
prepped = s.prepare_request(req)
r = s.send(prepped)
print(r.text)

这里我们引入了Request，然后用url、data和headers参数构造了一个Request对象，这时需要再调用Session的prepare_request()方法将其转换为一个Prepared Request对象，然后调用send()方法发送即可，运行结果如下：

{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "name": "germey"
  }, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Connection": "close", 
    "Content-Length": "11", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36"
  }, 
  "json": null, 
  "origin": "182.32.203.166", 
  "url": "http://httpbin.org/post"
}