使用Python读写Excel文件（1）

blackyellow

盛大、

fyzhangyi

想学习一下

zay7065346

朕想知道

LOVEE

..

szbin

朕想知道

cclovepython

朕想知道

老司基

朕想知道

斯林

朕想知道

掩耳盗驴

朕想知道

binggod

朕想知道

暗夜之隐

1. import urllib.request
   
2. 
   
3. from bs4 import BeautifulSoup as bs
   
4. 
   
5. import re
   
6. 
   
7. import openpyxl
   
8. 
   
9. def urlopen(url):
   
10. 
    
11.     head = {}
    
12. 
    
13.     head['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'
    
14.     head['Accept-Language'] = 'zh-CN,zh;q=0.9'
    
15.     head['Cache-Control'] = 'no-cache'
    
16.     head['Connection'] = 'keep-alive'
    
17.    
    
18.     head['Cookie']='bid=Wv1u2my5GJI; gr_user_id=ec943490-8875-40fe-b5b9-538d784cbf84; _vwo_uuid_v2=D6C966AC33758154BD3FC61FB43687FE2|718456dd9cd6126870e9d38c3a11a25e; douban-fav-remind=1; viewed="26820803_1200840_30209224"; ps=y; dbcl2="186505260:SSyljm2guj8"; push_noty_num=0; push_doumail_num=0; ck=giUI; ap_v=0,6.0; _pk_ref.100001.4cf6=%5B%22%22%2C%22%22%2C1541515329%2C%22https%3A%2F%2Ffishc.com.cn%2Fthread-94979-1-1.html%22%5D; _pk_ses.100001.4cf6=*; __utma=30149280.1606666109.1528767205.1540645031.1541515329.9; __utmb=30149280.0.10.1541515329; __utmc=30149280; __utmz=30149280.1541515329.9.4.utmcsr=fishc.com.cn|utmccn=(referral)|utmcmd=referral|utmcct=/thread-94979-1-1.html; __utma=223695111.832413198.1541515329.1541515329.1541515329.1; __utmb=223695111.0.10.1541515329; __utmc=223695111; __utmz=223695111.1541515329.1.1.utmcsr=fishc.com.cn|utmccn=(referral)|utmcmd=referral|utmcct=/thread-94979-1-1.html; __yadk_uid=VJnac125pQedgBMAqBXBVd9hGRBckHeH; _pk_id.100001.4cf6=607e87647801a894.1541515329.1.1541515370.1541515329.'
    
19.     head['Host']='movie.douban.com'
    
20.     head['Pragma']='no-cache'
    
21.     head['Upgrade-Insecure-Requests']='1'
    
22.     head['User-Agent']='Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    
23. 
    
24. 
    
25.     req = urllib.request.Request(url,headers = head)
    
26.    
    
27.     html = urllib.request.urlopen(req)
    
28. 
    
29.     html = html.read()
    
30. 
    
31.     return html
    
32. 
    
33. def xia():
    
34. 
    
35.    
    
36. 
    
37.     ye =0
    
38. 
    
39.     wb = openpyxl.Workbook()
    
40. 
    
41.     ws = wb.active
    
42. 
    
43.     for i in range(10):
    
44. 
    
45.         url = 'https://movie.douban.com/top250?start={}&filter='.format (ye)
    
46. 
    
47.         ye = ye+25
    
48. 
    
49.         html = urlopen(url)
    
50. 
    
51.         html = html.decode('utf-8')
    
52. 
    
53.         htm = bs(html,'lxml')
    
54. 
    
55.         data = htm.ol
    
56. 
    
57.         da = str(data)
    
58. 
    
59.         url_name = re.findall(r'(href=".*?)">\n<span class="title">(.*?)<',da)
    
60. 
    
61.         dao =re.findall(r'\n                            (.*?)<br',da)
    
62. 
    
63.         pin = re.findall(r'property="v:average">(.*?)<',da)
    
64. 
    
65.         for i in range(25):
    
66.             print('电影名：'+url_name[i][1])
    
67. 
    
68.             print('链接：'+url_name[i][0])
    
69. 
    
70.             print('导演：'+dao[i])
    
71. 
    
72.             print('电影评分'+pin[i]+'\n\n')
    
73. 
    
74. 
    
75. 
    
76.             ws.append([url_name[i][1],pin[i],url_name[i][0],dao[i]])
    
77. 
    
78.     wb.save('电影.xlsx')
    
79.    
    
80. xia()
    

复制代码

wy6616753

怎么才能从txt文件中读出来以后，再写到excel中呢

水瓶座

牛逼

sslas

朕想知道

dengwenxzuan

“朕想知道

qingfengjd

I love FishC.com!

月满霜华

朕想知道

肖嘉远

朕想知道

xingyunlz

那个小明

z