爬小说（第一次编写爬虫）

 1 import requests
 2 import re
 3 html = ‘http://www.jingcaiyuedu.com/book/317834.html‘
 4 response = requests.get(html)
 5 ‘‘‘while(str(response)!="<Response [200]>"):
 6     response = requests.get(html)
 7     print(response)
 8 ‘‘‘
 9 response.encoding = ‘utf-8‘
10 html = response.text
11 title =re.findall(r‘<meta property="og:novel:book_name" content="(.*?)"/>‘,html)[0]
12 dl = re.findall(r‘<dl id="list">.*?</dl>‘,html,re.S)[0]
13 chapter_info_list = re.findall(r‘href="(.*?)">(.*?)<‘,dl)
14 fb = open ("%s.txt"%title,"w",encoding = "utf-8")
15 for chapter_info in chapter_info_list:
16     chapter_url,chapter_title = chapter_info
17 
18     chapter_url =‘http://www.jingcaiyuedu.com%s‘ % chapter_url
19     chapter_response = requests.get(chapter_url)
20     chapter_response.encoding = ‘utf-8‘
21     chapter_html = chapter_response.text
22     chapter_content = re.findall(r‘<script>a1\(\);</script>(.*?)<script>a2\(\);</script>‘,chapter_html,re.S)[0]
23     chapter_content = chapter_content.replace(‘<br /><br />&nbsp;&nbsp;&nbsp;&nbsp;‘,‘‘)
24     chapter_content = chapter_content.replace(‘&nbsp;‘,‘‘)
25     chapter_content = chapter_content.replace(‘        ‘,‘‘)
26     fb.write(chapter_title)
27     fb.write(chapter_content)
28     fb.write(‘\n‘)
29     print(chapter_url)
30     
31 #print(chapter_info_list)