import requests

import re

url = 'http://www.92kshu.cc/69509/'

response = requests.get(url)

response.encoding = 'gbk'

html = response.text

title = re.findall(r'<meta property="og:novel:book_name" content="(.*?)"/>', html)[0]

fb = open('%s.txt' % title, 'w', encoding='utf-8')

# 获取每章的内容

# print(html)

dl = re.findall(r'<dl><dt><i class="icon"></i>正文</dt>(.*?)</dl>', html)[0]

print(dl)

chapter_info_list = re.findall(r'<dd><a href="(.*?)">(.*?)</a></dd>', dl)

print(chapter_info_list)

for chapter_info in chapter_info_list:

    chapter_url, chapter_title = chapter_info

    chapter_url = "http://www.92kshu.cc%s" % chapter_url

    # print(chapter_url)

    chapter_response = requests.get(chapter_url)

    chapter_response.encoding = 'gbk'

    chapter_html = chapter_response.text

    chapter_content = re.findall(r'<div class="chapter">(.*?)><br>', chapter_html)[0]

    # print(chapter_content)

    chapter_content = chapter_content.replace('<p>', '')

    chapter_content = chapter_content.replace('</p>', '')

    fb.write(chapter_title)

    fb.write(chapter_content)

    fb.write('\n')

    print(chapter_url)