12.9

Author: injetlee

ModifyFilename.py

@@ -2,9 +2,10 @@
 dir=os.getcwd()
 subdir=os.listdir(dir)
 foriinsubdir:
-path=os.path.join(dir,i)
-ifos.path.isdir(path):
-end_dir=os.listdir(path)
-foriinrange(len(end_dir)):
-newname=end_dir[i][0:50]
-os.rename(os.path.join(path,end_dir[i]),os.path.join(path,newname))
+path=os.path.join(dir, i)
+ifos.path.isdir(path):
+end_dir=os.listdir(path)
+foriinrange(len(end_dir)):
+newname=end_dir[i][0:50]
+os.rename(os.path.join(path, end_dir[
+i]), os.path.join(path, newname))

biyingSpider.py

@@ -0,0 +1,14 @@
+importrequests
+importre
+importtime
+local=time.strftime("%Y.%m.%d")
+url='http://cn.bing.com/'
+con=requests.get(url)
+content=con.text
+reg=r"(http://s.cn.bing.net/az/hprichbg/rb/.*?.jpg)"
+a=re.findall(reg, content, re.S)[0]
+print(a)
+read=requests.get(a)
+f=open('%s.jpg'%local, 'wb')
+f.write(read.content)
+f.close()

douban_movie.py

@@ -1,12 +1,13 @@
 #!/usr/bin/env python
 # encoding=utf-8
-importrequests,re
+importrequests
+importre
 importcodecs
 frombs4importBeautifulSoup
 fromopenpyxlimportWorkbook
 wb=Workbook()
 dest_filename='电影.xlsx'
-ws1=wb.active
+ws1=wb.active
 ws1.title="电影top250"
 
 DOWNLOAD_URL='http://movie.douban.com/top250/'
@@ -24,56 +25,58 @@ def download_page(url):
 defget_li(doc):
 soup=BeautifulSoup(doc, 'html.parser')
 ol=soup.find('ol', class_='grid_view')
-name= [] #名字
-star_con= [] #评价人数
-score= [] #评分
-info_list= [] #短评
+name= [] # 名字
+star_con= [] # 评价人数
+score= [] #评分
+info_list= [] #短评
 foriinol.find_all('li'):
 detail=i.find('div', attrs={'class': 'hd'})
-movie_name=detail.find('span', attrs={'class': 'title'}).get_text() #电影名字
-level_star=i.find('span',attrs={'class':'rating_num'}).get_text() #评分
-star=i.find('div',attrs={'class':'star'})
-star_num=star.find(text=re.compile('评价')) #评价
+movie_name=detail.find(
+'span', attrs={'class': 'title'}).get_text() # 电影名字
+level_star=i.find(
+'span', attrs={'class': 'rating_num'}).get_text() # 评分
+star=i.find('div', attrs={'class': 'star'})
+star_num=star.find(text=re.compile('评价')) # 评价
 
-info=i.find('span',attrs={'class':'inq'}) #短评
-ifinfo: #判断是否有短评
+info=i.find('span',attrs={'class':'inq'}) #短评
+ifinfo: # 判断是否有短评
 info_list.append(info.get_text())
 else:
 info_list.append('无')
 score.append(level_star)
-
 
 name.append(movie_name)
 star_con.append(star_num)
-page=soup.find('span', attrs={'class': 'next'}).find('a') #获取下一页
+page=soup.find('span', attrs={'class': 'next'}).find('a') # 获取下一页
 ifpage:
-returnname,star_con,score,info_list,DOWNLOAD_URL+page['href']
-returnname,star_con,score,info_list,None
+returnname,star_con,score,info_list,DOWNLOAD_URL+page['href']
+returnname,star_con,score,info_list,None
 
 
 defmain():
 url=DOWNLOAD_URL
 name= []
-star_con=[]
+star_con=[]
 score= []
 info= []
 whileurl:
 doc=download_page(url)
-movie,star,level_num,info_list,url=get_li(doc)
+movie,star,level_num,info_list,url=get_li(doc)
 name=name+movie
 star_con=star_con+star
-score=score+level_num
-info=info+info_list
-for (i,m,o,p) inzip(name,star_con,score,info):
-col_A='A%s'%(name.index(i)+1)
-col_B='B%s'%(name.index(i)+1)
-col_C='C%s'%(name.index(i)+1)
-col_D='D%s'%(name.index(i)+1)
-ws1[col_A]=i
+score=score+level_num
+info=info+info_list
+for (i,m, o, p) inzip(name,star_con,score,info):
+col_A='A%s'%(name.index(i)+1)
+col_B='B%s'%(name.index(i)+1)
+col_C='C%s'%(name.index(i)+1)
+col_D='D%s'%(name.index(i)+1)
+ws1[col_A]=i
 ws1[col_B] =m
 ws1[col_C] =o
 ws1[col_D] =p
 wb.save(filename=dest_filename)
 
+
 if__name__=='__main__':
 main()

readExcel.py

@@ -3,15 +3,15 @@
 fromopenpyxl.cellimportget_column_letter
 wb=Workbook()
 dest_filename='empty_book2.xlsx'
-ws1=wb.active#第一个表
-ws1.title="range names"#第一个表命名
-#遍历第一个表的1到40行，赋值一个600内的随机数
-forrowinrange(1,40):
+ws1=wb.active# 第一个表
+ws1.title="range names"# 第一个表命名
+#遍历第一个表的1到40行，赋值一个600内的随机数
+forrowinrange(1,40):
 ws1.append(range(60))
 ws2=wb.create_sheet(title="Pi")
 ws2['F5'] =3.14
 ws3=wb.create_sheet(title="Data")
-forrowinrange(10,20):
-forcolinrange(27,54):
-_=ws3.cell(column=col,row=row,value="%s"%get_column_letter(col))
-wb.save(filename=dest_filename)
+forrowinrange(10,20):
+forcolinrange(27,54):
+_=ws3.cell(column=col,row=row,value="%s"%get_column_letter(col))
+wb.save(filename=dest_filename)