爬虫基础：Requests库

Requests库

Requests使用Python语言编写，基于urllib，采用Apache2 Licensed开源协议的HTTP库。
它比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。存在大量的API方便调用。

一句话--Python实现的简单易用的HTTP库。基本上能用urllib的部分都可以用Requests代替。

安装

pip install requests

用法

实例引入

import requests
response = requests.get("https://www.baidu.com/")
print(type(response))
# 状态码
print(response.status_code)
# 响应内容
print(response.text)
print(response.cookies)

各种请求方式

import requests
#httpbin.org 测试网站
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')

基本GET请求

基本写法：

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

带参数GET请求

#参数也就是?name=germey&age=22部分
#直接写在url上比较繁琐
import requests
response = requests.get("http://httpbin.org/get?name=germey&age=22")
print(response.text)
# 使用params传入字典构造参数
import requests
data = {
    'name':'germey',
    'age':22
}
response = requests.get("http://httpbin.org/get",params=data)
print(response.text)

解析json:自带了json方法

import requests
import json
response = requests.get("http://httpbin.org/get")
print(type(response.text))
print(response.json())
print(json.loads(response.text))
print(type(response.json()))

获取二进制数据（图片，视频，音频）

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

## 保存
with open('favicon.ico','wb') as f:
    f.write(response.content)
    f.close()

添加headers

# 不加headers，可能会被直接禁止，比如百度没有header就不会有结果
## https://www.baidu.com/s?wd=风景
## https://www.zhihu.com/explore
import requests
data = {
    'wd':'风景'
}
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36',
    'Host':'www.baidu.com'

}
response = requests.get("https://www.baidu.com/s",params=data,headers=headers)
print(response.text)

基本POST请求

基本是以form表单形式提交

import requests
data = {'name':'germey','age':'22'}
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36',
}
response = requests.post("http://httpbin.org/post",data=data,headers=headers)
print(response.json())

响应

response属性

import requests
response = requests.get('http://www.jianshu.com')
# 常用属性
print(type(response.status_code),response.status_code)
print(type(response.headers),response.headers)
print(type(response.cookies),response.cookies)
print(type(response.url),response.url)
print(type(response.history),response.history

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 successful")

高级操作

文件上传

# 文件上传
import requests
files = {'file':open('favicon.ico','rb')}
response = requests.post('http://httpbin.org/post',files=files)
print(response.text)

获取cookies

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: Session

## 模拟登陆
import requests
# 先设置cookies，再查看cookies
requests.get('http://httpbin.org/cookies/set/number/123456789')
response = requests.get('http://httpbin.org/cookies')
print(response.text)
# 其实相当于两次独立的请求
# 需要声明Session对象，用于维持同一次会话
s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)

证书验证:cert or verify

# 直接访问12306，会出错
import requests
response = requests.get('https://www.12306.cn')
print(response.status_code)
# 方法1：在参数中关闭SSL验证
## 通过requests的原生包urllib3，取消警告
from requests.packages import urllib3
urllib3.disable_warnings()
response = requests.get('https://www.12306.cn',verify=False)
print(response.status_code)
# 方法2：传入一个认证
response = requests.get('https://www.12306.cn',cert=('path/server.crt','path/key'))

代理设置:proxies

# 普通的http和https代理
import requests
proxies = {
    'http':'http://127.0.0.1:9743',
    'https':'htpps://127.0.0.1:9743'
    'http':'http://user:password@127.0.0.1:9743'
}
response = requests.get('https://www.taobao.com','proxies=proxies')
print(response.status_code)
# 如果是shadowsocks代理
# 需要先安装requests[sockes]
# pip3 install requests[socks]
import requests
proxies = {
    'http':'socks5:127.0.0.1:9742'
    'https':'socks5:127.0.0.1:9742'
}
response = requests.get('https://www.baidu.com',proxies=proxies)

超时设置:timeout

import requests
from requests.exceptions import ReadTimeout
#response = requests.get('https://www.taobao.com',timeout=1)
#response = requests.get('httpb://httpbin.org/get',timeout=1)
#查看官方对异常的定义，捕获异常
try:
    response = requests.get('http://httpbin.org/get',timeout=0.1)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')

认证设置:auth

import requests
from requests.auth import HTTPBasicAuth
r1 = requests.get('http://120.27.34.24:9001',auth=HTTPBasicAuth('user','123'))
r2 = requests.get('http://120.27.34.24:9001',auth=('user','123'))
print(r2.status_code)

异常处理

# 从子类异常到父类异常
import requests
from requests.exceptions import ReadTimeout, HTTPError, RequestException
try:
    response = requests.get('http://httpbin.org/get',timeout=0.1)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')
except ConnectionError:
    print('ConnectionError')
except RequestException:
    print('Error')

推荐阅读:http://blog.csdn.net/qq_18863573/article/details/52775130