python爬虫小说实例源码_python爬虫小说源代码

from urllib import request

import re

import os

#获取网页源代码

url = 'https://www.xs4.cc/dushizhiwozhendewudi/'

html = request.urlopen(url).read()

html = html.decode('gbk')

#获取章节链接和小说标题

#提取想要的数据 re正则表达式

reg = '

(.*?)'

urls = re.findall(reg,html)

reg1='

(.*?)

'

dir_name = re.findall(reg1,html)[-1]

print(dir_name)

if not os.path.exists(dir_name):

os.mkdir(dir_name)

for url in urls:

#小说链接

# novel_url = url[0]

#小说标题

# novel_title = url[1]

novel_url,novel_title = url

novel_title = novel_title.replace('正文 ','')

#获取章节源代码

chapt = request.urlopen(novel_u