1、web爬虫，requests请求

#!/usr/bin/env python
# -*- coding:utf8 -*-
import requests     #导入模拟浏览器请求模块

http =requests.get(url="http://www.iqiyi.com/")     #发送http请求
http.encoding = "utf-8"                             #http请求编码
neir = http.text                                    #获取http字符串代码
print(neir)

"utf-8" />
        "keywords" content="抽屉新热榜,资讯,段子,图片,公众场合不宜,科技,新闻,节操,搞笑" />

        "description" content="
            抽屉新热榜，汇聚每日搞笑段子、热门图片、有趣新闻。它将微博、门户、社区、bbs、社交网站等海量内容聚合在一起，通过用户推荐生成最热榜单。看抽屉新热榜，每日热门、有趣资讯尽收眼底。
            " />

        "robots" content="index,follow" />
        "GOOGLEBOT" content="index,follow" />
        "Author" content="搞笑" />
        "X-UA-Compatible" content="IE=EmulateIE8">
        "image/x-icon" href="/images/chouti.ico" rel="icon"/>
        "image/x-icon" href="/images/chouti.ico" rel="Shortcut Icon"/>
        "image/x-icon" href="/images/chouti.ico" rel="bookmark"/>
    "application/opensearchdescription+xml"

#!/usr/bin/env python
# -*- coding:utf8 -*-
import requests     #导入模拟浏览器请求模块

### 1、在没登录之前访问一下首页，获取cookie
i1 = requests.get(
    url="http://dig.chouti.com/",
    headers={‘Referer‘: ‘http://dig.chouti.com/‘}
)
i1.encoding = "utf-8"                               #http请求编码
i1_cookie = i1.cookies.get_dict()
print(i1_cookie)                                    #返回获取到的cookie
#返回：{‘JSESSIONID‘: ‘aaaTztKP-KaGLbX-T6R0v‘, ‘gpsd‘: ‘c227f059746c839a28ab136060fe6ebe‘, ‘route‘: ‘f8b4f4a95eeeb2efcff5fd5e417b8319‘}

#!/usr/bin/env python
# -*- coding:utf8 -*-
import requests     #导入模拟浏览器请求模块

### 1、在没登录之前访问一下首页，获取cookie
i1 = requests.get(
    url="http://dig.chouti.com/",
    headers={‘Referer‘:‘http://dig.chouti.com/‘}
)
i1.encoding = "utf-8"                               #http请求编码
i1_cookie = i1.cookies.get_dict()
print(i1_cookie)                                    #返回获取到的cookie
#返回：{‘JSESSIONID‘: ‘aaaTztKP-KaGLbX-T6R0v‘, ‘gpsd‘: ‘c227f059746c839a28ab136060fe6ebe‘, ‘route‘: ‘f8b4f4a95eeeb2efcff5fd5e417b8319‘}

### 2、用户登陆，携带上一次的cookie，后台对cookie中的随机字符进行授权
i2 = requests.post(
    url="http://dig.chouti.com/login",              #登录url
    data={                                          #登录字段
        ‘phone‘: "8615284816568",
        ‘password‘: "279819",
        ‘oneMonth‘: ""
    },
    headers={‘Referer‘:‘http://dig.chouti.com/‘},
    cookies=i1_cookie                               #携带cookie
)
i2.encoding = "utf-8"
dluxxi = i2.text
print(dluxxi)                                       #查看登录后服务器的响应
#返回：{"result":{"code":"9999", "message":"", "data":{"complateReg":"0","destJid":"cdu_50072007463"}}}  登录成功

#!/usr/bin/env python
# -*- coding:utf8 -*-
import requests     #导入模拟浏览器请求模块

### 1、在没登录之前访问一下首页，获取cookie
i1 = requests.get(
    url="http://dig.chouti.com/",
    headers={‘Referer‘:‘http://dig.chouti.com/‘}
)
i1.encoding = "utf-8"                               #http请求编码
i1_cookie = i1.cookies.get_dict()
print(i1_cookie)                                    #返回获取到的cookie
#返回：{‘JSESSIONID‘: ‘aaaTztKP-KaGLbX-T6R0v‘, ‘gpsd‘: ‘c227f059746c839a28ab136060fe6ebe‘, ‘route‘: ‘f8b4f4a95eeeb2efcff5fd5e417b8319‘}

### 2、用户登陆，携带上一次的cookie，后台对cookie中的随机字符进行授权
i2 = requests.post(
    url="http://dig.chouti.com/login",              #登录url
    data={                                          #登录字段
        ‘phone‘: "8615284816568",
        ‘password‘: "279819",
        ‘oneMonth‘: ""
    },
    headers={‘Referer‘:‘http://dig.chouti.com/‘},
    cookies=i1_cookie                               #携带cookie
)
i2.encoding = "utf-8"
dluxxi = i2.text
print(dluxxi)                                       #查看登录后服务器的响应
#返回：{"result":{"code":"9999", "message":"", "data":{"complateReg":"0","destJid":"cdu_50072007463"}}}  登录成功

### 3、访问需要登录才能查看的页面，携带着授权后的cookie访问
shouquan_cookie = i1_cookie
i3 = requests.get(
    url="http://dig.chouti.com/user/link/saved/1",
    headers={‘Referer‘:‘http://dig.chouti.com/‘},
    cookies=shouquan_cookie                        #携带着授权后的cookie访问
)
i3.encoding = "utf-8"
print(i3.text)                                     #查看需要登录才能查看的页面