Python爬虫系列-Requests库详解

Requests基于urllib，比urllib更加方便，可以节约我们大量的工作，完全满足HTTP测试需求。

实例引入

 import requests

 response = requests.get('https://www.baidu.com/')
 print(type(response))
 print(response.status_code)
 print(type(response.text))
 print(response.cookies)

<class 'requests.models.Response'>

200

<class 'str'>

<RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>]>

各种请求方式

 import requests

 requests.post('http://httpbin.org/post')

<Response [200]>

 requests.put('http://httpbin.org/put')

<Response [200]>

 requests.delete('http://httpbin.org/delete')

<Response [200]>

 requests.head('http://httpbin.org/gett')

<Response [404]>

 requests.head('http://httpbin.org/get')

<Response [200]>

 requests.options('http://httpbin.org/get')

<Response [200]>

基本GET请求

 import requests

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

{

"args": {},

"headers": {

"Accept": "/",

"Accept-Encoding": "gzip, deflate",

"Connection": "close",

"Host": "httpbin.org",

"User-Agent": "python-requests/2.20.1"

},

"origin": "58.34.235.37",

"url": "http://httpbin.org/get"

}

带参数的GET请求

import requests
 response = requests.get('http://httpbin.org/get?name=germey&age=22')
 print(response.text)

{

"args": {

"age": "22",

"name": "germey"

},

"headers": {

"Accept": "/",

"Accept-Encoding": "gzip, deflate",

"Connection": "close",

"Host": "httpbin.org",

"User-Agent": "python-requests/2.20.1"

},

"origin": "58.34.235.37",

"url": "http://httpbin.org/get?name=germey&age=22"

}

import requests

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

{

"args": {

"age": "22",

"name": "germery"

},

"headers": {

"Accept": "/",

"Accept-Encoding": "gzip, deflate",

"Connection": "close",

"Host": "httpbin.org",

"User-Agent": "python-requests/2.20.1"

},

"origin": "58.34.235.37",

"url": "http://httpbin.org/get?name=germery&age=22"

}

解析json

 import requests

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

<class 'str'>

 print(response.json())  # 与json.loads(response.text)完全一样

{'args': {}, 'headers': {'Accept': '/', 'Accept-Encoding': 'gzip, deflate', 'Connection': 'close', 'Host': 'httpbin.org', 'User-Agent': 'python-requests/2.20.1'}, 'origin': '58.34.235.37', 'url': 'http://httpbin.org/get'}

 print(type(response.json()))

<class 'dict'>

获取二进制数据

import requests

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

<class 'str'> <class 'bytes'>

下载图片

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

添加headers

import requests
 headers = { 'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36' }
 response = requests.get('https://www.zhihu.com/explore',headers=headers)

基本POST请求

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

{

"args": {},

"data": "",

"files": {},

"form": {

"age": "22",

"name": "germey"

},

"headers": {

"Accept": "/",

"Accept-Encoding": "gzip, deflate",

"Connection": "close",

"Content-Length": "18",

"Content-Type": "application/x-www-form-urlencoded",

"Host": "httpbin.org",

"User-Agent": "python-requests/2.20.1"

},

"json": null,

"origin": "58.34.235.37",

"url": "http://httpbin.org/post"

}

添加headers

 import requests

 data = {'name':'germey','age':22}
 headers = { 'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36' }
 response = requests.post('http://httpbin.org/post',data=data,headers=headers)
 print(response.json())

{'args': {}, 'data': '', 'files': {}, 'form': {'age': '22', 'name': 'germey'}, 'headers': {'Accept': '/', 'Accept-Encoding': 'gzip, deflate', 'Connection': 'close', 'Content-Length': '18', 'Content-Type': 'application/x-www-form-urlencoded', 'Host': 'httpbin.org', 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36'}, 'json': None, 'origin': '58.34.235.37', 'url': 'http://httpbin.org/post'}

响应

response属性

import requests

 response = requests.get('http://www.jianshu.com')
print(type(response.status_code),response.status_code)

<class 'int'> 403

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

<class 'requests.structures.CaseInsensitiveDict'> {'Date': 'Tue, 27 Nov 2018 20:03:06 GMT', 'Content-Type': 'text/html', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Server': 'Tengine', 'Strict-Transport-Security': 'max-age=31536000; includeSubDomains; preload', 'Content-Encoding': 'gzip', 'X-Via': '1.1 dianxinxiazai180:5 (Cdn Cache Server V2.0), 1.1 PSjsntdx3xf38:1 (Cdn Cache Server V2.0)'}

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

<class 'requests.cookies.RequestsCookieJar'> <RequestsCookieJar[]>

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

<class 'str'> https://www.jianshu.com/

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

<class 'list'> [<Response [301]>]

状态码判断：

 import requests

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

 import requests

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

Requests高级操作

文件上传

 import requests

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

{

"args": {},

"data": "",

"files": {

"files": "内容省略"

},

"form": {},

"headers": {

"Accept": "/",

"Accept-Encoding": "gzip, deflate",

"Connection": "close",

"Content-Length": "148",

"Content-Type": "multipart/form-data; boundary=6e864227a6fd1cd7a1655802d20d7bd9",

"Host": "httpbin.org",

"User-Agent": "python-requests/2.20.1"

},

"json": null,

"origin": "58.34.235.37",

"url": "http://httpbin.org/post"

}

获取cookie值

import requests

 response = requests.get('http://www.baidu.com')
 print(response.cookies)

<RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>]>

 for key,value in response.cookies.items():
     print(key+'='+value)

BDORZ=27315

会话维持 模拟登录

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

<Response [200]>

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

{

"cookies": {}

}

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

<Response [200]>

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

{

"cookies": {

"number": "123456789"

}

}

证书验证

import requests

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

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

/home/dex/.local/lib/python3.6/site-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings

InsecureRequestWarning)

/home/dex/.local/lib/python3.6/site-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings

InsecureRequestWarning)

添加证书

response = requests.get('https://www.12306.cn',cert=('/path/server.crf','/path/key'))

代理设置

 import requests

 proxies = {
   'http':'http://222.74.61.98:53281',
 # 'http':'http://user:password@222.74.61.98:53281'  #添加密码
  'https':'https://114.119.116.92:61066'
  }

 response = requests.get('https://www.taobao.com',proxies=proxies)
 print(response.status_code)

使用socks代理设置

首先安装requests[socks]支持：

 pip3 install 'requests[socks]'

import requests
proxies = {
 'http':'socks5://127.0.0.1:1080',
 'https':'socks5://127.0.0.1:1080'
 }
 response = requests.get('https://www.taobao.com',proxies=proxies)
 print(response.status_code)

200

超时设置与捕获

import requests
from requests.exceptions import ReadTimeout
try:
     response = requests.get("http://www.taobao.com",timeout=0.01)
     print(response.status_code)
 except ReadTimeout:
     print('Timeout')

Timeout

认证设置

import requests
from requests.auth import HTTPBasicAuth

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

异常处理

import requests
 from requests.exceptions import ReadTimeout,ConnectionError,HTTPError,RequestException
 try:
     response = requests.get('http://httpbin.org/get',timeout=0.5)
     print(response.status_code)
 except ReadTimeout:
    print('Timeout')
 except ConnectionError:
    print('Timeout')
 except HTTPError:
     print('Http Error')
 except RequestException:
     print('Error')

200