40行代码爬取金庸所有武侠小说

 1 # -*- coding: utf-8 -*-
 2 import urllib.request  
 3 from bs4 import BeautifulSoup
 4 
 5 #get book‘s chapter
 6 def get_chapter(url):
 7     html = urllib.request.urlopen(url)  
 8     content = html.read().decode(‘utf8‘)
 9     html.close()
10     soup = BeautifulSoup(content, "lxml")
11     title = soup.find(‘h1‘).text    #chapter title
12     text = soup.find(‘div‘, id=‘htmlContent‘)    #chapter content
13     #processing the content to get nice style
14     content = text.get_text(‘\n‘,‘br/‘).replace(‘\n‘, ‘\n    ‘)
15     content = content.replace(‘　　‘, ‘\n　　‘)
16     return title, ‘    ‘+content
17         
18 def main():
19     books = [‘射雕英雄传‘,‘天龙八部‘,‘鹿鼎记‘,‘神雕侠侣‘,‘笑傲江湖‘,‘碧血剑‘,‘倚天屠龙记‘,20              ‘飞狐外传‘,‘书剑恩仇录‘,‘连城诀‘,‘侠客行‘,‘越女剑‘,‘鸳鸯刀‘,‘白马啸西风‘,21              ‘雪山飞狐‘]
22     order = [1,2,3,4,5,6,7,8,10,11,12,14,15,13,9]  #order of books to scrapy
23     #list to store each book‘s scrapying range
24     page_range = [1,43,94,145,185,225,248,289,309,329,341,362,363,364,375,385]
25 
26     for i,book in enumerate(books):
27         for num in range(page_range[i],page_range[i+1]):
28             url = "http://jinyong.zuopinj.com/%s/%s.html"%(order[i],num)
29             try:
30                 title, chapter = get_chapter(url)
31                 with open(‘E://%s.txt‘%book, ‘a‘, encoding=‘gb18030‘) as f:
32                     print(book+‘:‘+title+‘-->写入成功！‘)
33                     f.write(title+‘\n\n\n‘)
34                     f.write(chapter+‘\n\n\n‘)
35             except Exception as e:
36                 print(e) 
37     print(‘全部写入完毕!‘)
38 
39 main()