remove useless .py files

# -*- coding: utf-8 -*-

"""LectureNoteDownload.ipynb

Automatically generated by Colaboratory.

Original file is located at

    https://colab.research.google.com/drive/1aE4KuvnzlfpXyd1fefTsj_jqoHnNkqxy

"""

from urllib import request

from bs4 import BeautifulSoup

import re

url=r'http://u.math.biu.ac.il/~solomyb/TEACH/18/GMT/index.html'

link=r'http://u.math.biu.ac.il/~solomyb/TEACH/18/GMT/'

# proxy={'http':'http://localhost:80'}

headers = ("User-Agent"," Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36")  #这里模拟浏览器  

opener = request.build_opener()  

opener.addheaders = [headers]

request.install_opener(opener)

# 添加 header 模拟浏览器, 可兼容 urlretrieve.

contents = request.urlopen(url).read().decode()

soup = BeautifulSoup(contents,"html.parser")

n=1

for tag in soup.find_all('a'): 

    pdf = tag.get('href')

    pdfurl = link+pdf

    print(pdfurl+"\n")

    pdfdir = 'C:/Users/whzec/Desktop/'+pdf

    request.urlretrieve(pdfurl,pdfdir)

    n=n+1

# urlretrieve 用来保存文件, py3 在 urllib.request内, py2在urllib

# -*- coding: utf-8 -*-

"""douban.ipynb

Automatically generated by Colaboratory.

Original file is located at

    https://colab.research.google.com/drive/1qg0hwEsZ4IjUxPMAlKT0DwKyUgnjc6Zx

# 提取豆瓣电影Top250

"""

#coding:utf-8  

# 文件导出版本

''''' 

@author: jsjxy 

@origin: https://www.cnblogs.com/xisheng/p/9130156.html

'''  

from urllib import request 

from bs4 import BeautifulSoup  

import re

#from distutils.filelist import findall   

def doubantop(N):

    with open('./douban-top-%s.txt'%str(N),'w') as f:

        f.write("豆瓣电影TOP"+str(N)+'\n') 

        f.write('%-13s%-5s%-15s%-40s\n'%('影片名','评分','评价人数','链接'))

        for n in range(N//25):

            url = 'https://movie.douban.com/top250?start='+str(25*n)+'&filter='  

            page = request.urlopen(url)   

            contents = page.read()   

         #print(contents)  

            soup = BeautifulSoup(contents,"html.parser")  

            for tag in soup.find_all('div', class_='info'):    

               # print tag  

                m_name = tag.find('span', class_='title').get_text()        

                m_rating_score = float(tag.find('span',class_='rating_num').get_text())          

                m_people = tag.find('div',class_="star")  

                m_span = m_people.findAll('span')  

                m_peoplecount = re.sub(r'[^0-9]','',m_span[3].contents[0])

                # 剔除了`人评价`字样, 只保留人数数字

                m_url=tag.find('a').get('href')  

                f.write('%s\t%s\t%s\t%s\n'% (m_name,str(m_rating_score), m_peoplecount ,m_url) )

            n=n+1

    print('请查看文件douban-top-%s!' %str(N))

num = input("你想要看豆瓣电影TOP榜单的前几名(小于等于250且最好是25的倍数):")

num = int(num)

doubantop(num)

# print 查看版本

#coding:utf-8  

''''' 

@author: jsjxy 

@origin: https://www.cnblogs.com/xisheng/p/9130156.html

'''  

from urllib import request 

from bs4 import BeautifulSoup  

import re

#from distutils.filelist import findall   

all_list = []

for n in range(10):

    url = 'https://movie.douban.com/top250?start='+str(25*n)+'&filter='  

    page = request.urlopen(url)   

    contents = page.read()   

 #print(contents)  

    soup = BeautifulSoup(contents,"html.parser")  

    for tag in soup.find_all('div', class_='info'):    

       # print tag  

        m_name = tag.find('span', class_='title').get_text()        

        m_rating_score = float(tag.find('span',class_='rating_num').get_text())          

        m_people = tag.find('div',class_="star")  

        m_span = m_people.findAll('span')  

        m_peoplecount = re.sub(r'[^0-9]','',m_span[3].contents[0])

        # 剔除了`人评价`字样, 只保留人数数字

        m_url=tag.find('a').get('href')  

        all_list.append('%s\t%s\t%s\t%s\n'% (m_name,str(m_rating_score), m_peoplecount ,m_url)) 

def doubantop(N,n=1):

    print("豆瓣电影TOP "+str(n)+' - '+str(N)+'\n'+'%-13s%-5s%-15s%-40s\n'%('影片名','评分','评价人数','链接'))

    for movie in all_list[n-1:N]:

        print(movie)

#num = input("你想要看豆瓣电影TOP250榜单的范围")

#num = int(num)

doubantop(30)

# -*- coding: utf-8 -*-

"""replacetxt.ipynb

Automatically generated by Colaboratory.

Original file is located at

    https://colab.research.google.com/drive/1eXL6qy3DWAte-dKIzPmKEaKpBviXpLTK

# 文件的读取与写入

首先我们给出一个非常有用的例子, 即文件的替换.

"""

# replace some words by python

import re

f=open(r'C:\Users\whzec\Desktop\1.md','r') #加上r是为了能使用反斜杠的地址,否则使用斜杠,或者双反斜杠.

alllines=f.readlines()

f.close()

f=open(r'C:\Users\whzec\Desktop\1.md','w+')

for eachline in alllines:

    a=re.sub('List','cctvcctv',eachline)

    f.writelines(a)

f.close()

#!/usr/bin/env python

# coding: utf-8

from urllib import request

from bs4 import BeautifulSoup

import re

url='https://ss.freeshadowsocks.biz/'

# proxy={'http':'http://localhost:80'}

headers = ("User-Agent"," Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36")  #这里模拟浏览器  

opener = request.build_opener()  

opener.addheaders = [headers]

request.install_opener(opener)

# 添加 header 模拟浏览器, 可兼容 urlretrieve.

contents = request.urlopen(url).read().decode()

soup = BeautifulSoup(contents,"html.parser")

n=1

for tag in soup.find_all('div',class_='shot-item'):

    img = tag.find('a').get('href')

    imgurl = url+img

    print(imgurl+"\n")

    if n<=3:

        imgdir = 'D:/Desktop/'+'ss-%d'% n+'.png'

    else:

        imgdir = 'D:/Desktop/'+'ssr-%d'% int(n-3) +'.png'

    request.urlretrieve(imgurl,imgdir)

    n=n+1

# urlretrieve 用来保存文件, py3 在 urllib.request内, py2在urllib