爬虫学习---基础操作--抽屉新热榜自动点赞与豆瓣自动统一短评

 1 import requests,re
 2 from bs4 import BeautifulSoup
 3 headers={‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0‘
 4 }
 5 user=‘你的帐号‘
 6 pwd=‘你的密码‘
 7 def index_first():#抽屉网需要GET的COOKIES
 8     r1=requests.get(‘https://dig.chouti.com/‘,headers=headers)
 9     return r1.cookies.get_dict()
10 def login(cookies,user,pwd):
11     post_dict={ #登陆时要提交的数据
12         ‘phone‘:user,
13         ‘password‘:pwd,
14         ‘oneMonth‘:1
15     }
16     response = requests.post(#要登陆的网址
17          url="https://dig.chouti.com/login",
18          data=post_dict,
19         cookies=cookies,#带上cookies进行授权
20         headers=headers
21      )
22     print(response.text,‘url‘)
23     return
24 
25 def profiles(cookie_gpsd):#进入个人主页
26     response=requests.get(
27         url=‘https://dig.chouti.com/profile/bind‘,
28         cookies=cookie_gpsd,
29         headers=headers
30     )
31     soup =BeautifulSoup(response.text,features=‘html.parser‘)#python 内置转换的对象
32     phone=soup.find(id=‘bind-content‘)
33     #phone_nube=phone.find(‘class‘)
34     reg=r‘<div class="show-phoneCode">当前绑定号码为：(.*?)</div>‘
35     rest=re.findall(reg,response.text)#查找
36     print(‘‘,rest)
37     if rest[0]==‘+你的手机号‘:
38         print(‘进入个人设置成功‘)
39 
40 def dz(cookies_dict):
41     ret=requests.post(url=‘https://dig.chouti.com/link/vote?linksId=18760066‘,#要点赞的文章地址
42                   cookies=cookies_dict,
43                   headers=headers)
44     print(ret.text)
45 
46 
47 cookie_get=index_first()#先取得GET的cookies
48 login(cookie_get,user,pwd)#登陆进行cookies的授权
49 profiles(cookie_get)#可以进行后台
50 dz(cookie_get)#点赞

 1 import requests
 2 import re
 3 import json
 4 from bs4 import BeautifulSoup
 5 
 6 requests =requests.Session()#记录登录的状态
 7 if __name__ == ‘__main__‘:
 8     user=‘你的帐号‘
 9     pwd=‘你的密码‘
10     #请求头
11     headers={‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0‘
12     }
13 
14     def login():
15         response=requests.get(‘https://accounts.douban.com/login‘,headers=headers)
16         response.encoding=response.apparent_encoding  #返回网页的原先编码
17         result=response.text#取出文本即网页源码
18         reg=r‘<input type="hidden" name="captcha-id" value="(.*?)"/>‘#正则表达式
19         catpchaId=re.findall(reg,result)#查找 验证码对象ID
20         soup =BeautifulSoup(result,features=‘html.parser‘)#python 内置转换的对象
21         target=soup.find(id=‘captcha_image‘)#查找 验证码对象
22         img_url =target.attrs.get(‘src‘)#获取验证码图片URL
23         print(img_url,catpchaId)
24         response=requests.get(img_url,headers=headers)#获取验证码图片
25         codeimg=response.content#保存为二进制
26         print(codeimg,‘codeimg‘)
27         with open(‘code.png‘,‘wb‘) as f:#保存为PNG图片
28             f.write(codeimg)
29         post_dict={ #登陆时要提交的数据
30             ‘source‘:‘index_nav‘,
31             ‘form_email‘:user,#用户名
32             ‘form_password‘:pwd,#密码
33             ‘captcha-solution‘:input(‘请输入验证码:‘),#输入你保存的PNG图片中的验证码
34              ‘captcha-id‘:catpchaId
35         }
36         response = requests.post(#要登陆的网址
37              url="https://accounts.douban.com/login",
38              data=post_dict,
39             headers=headers
40          )
41         print(response.url,‘url‘)
42         # #print(response.text,‘text‘)
43         # cookie_dict=response.cookies.get_dict()#产生的cookie
44         # print(cookie_dict,‘cookie_dict‘)
45         if ‘莫柔落切的帐号‘ in response.text:
46             print(‘登录成功‘)
47         else:
48             print(‘登录失败，重新登录！‘)
49             login()
50             return
51     def comment(mid):#评论
52         data={#评论的表单数据格式
53             ‘ck‘:‘xVds‘,
54             ‘comment‘:‘我来留个名‘,
55             ‘foldcollect‘:‘F‘,
56             ‘interest‘:‘collect‘,
57             ‘rating‘:‘‘,
58             ‘tags‘:‘123‘
59         }
60         #进行提交
61         response=requests.post(‘https://movie.douban.com/j/subject/%s/interest‘%mid,data=data,headers=headers)
62         print(response.text,‘comment.text‘)
63     def getMoveId():#电影的ID  排行榜
64         response=requests.get(‘https://movie.douban.com/ithil_j/activity/movie_annual2017/widget/20‘,
65                                 headers=headers)
66         print(response.text)
67         result=response.json()#进行转换为文本
68 
69         print(type(result),‘类型‘)
70         return  result[‘res‘][‘subjects‘]#返回所要的数据
71 
72     login()
73     for i in getMoveId():#循环电影ID列表
74         print(i)
75         comment(i[‘id‘])#进行短评