爬小说（第一次编写爬虫）

import requests
import re
html = 'http://www.jingcaiyuedu.com/book/317834.html'
response = requests.get(html)
'''while(str(response)!="<Response [200]>"):
    response = requests.get(html)
    print(response)
'''
response.encoding = 'utf-8'
html = response.text
title =re.findall(r'<meta property="og:novel:book_name" content="(.*?)"/>',html)[0]
dl = re.findall(r'<dl id="list">.*?</dl>',html,re.S)[0]
chapter_info_list = re.findall(r'href="(.*?)">(.*?)<',dl)
fb = open ("%s.txt"%title,"w",encoding = "utf-8")
for chapter_info in chapter_info_list:
    chapter_url,chapter_title = chapter_info

    chapter_url ='http://www.jingcaiyuedu.com%s' % chapter_url
    chapter_response = requests.get(chapter_url)
    chapter_response.encoding = 'utf-8'
    chapter_html = chapter_response.text
    chapter_content = re.findall(r'<script>a1();</script>(.*?)<script>a2();</script>',chapter_html,re.S)[0]
    chapter_content = chapter_content.replace('<br /><br />&nbsp;&nbsp;&nbsp;&nbsp;','')
    chapter_content = chapter_content.replace('&nbsp;','')
    chapter_content = chapter_content.replace('        ','')
    fb.write(chapter_title)
    fb.write(chapter_content)
    fb.write('
')
    print(chapter_url)
    
#print(chapter_info_list) 

第一次使用爬虫，python的功能由衷的强大，不过遭遇的运程主机的强行关闭，基本只能下载前几章就会遭遇强行关闭，下一价段争取解决