爬虫

import requests,re,os
dir_name='guimi'
if not os.path.exists('guimi'):
    os.makedirs('guimi')
response=requests.get('https://www.bqg99.cc/book/1476058/')
html=response.text
regular=re.compile('<dd><a href ="(.*?)">(.*?)</a></dd>')
urls=re.findall(regular,html)
for url in urls:
    novel_title=url[1]
    print(novel_title)
    response=requests.get(url[0])
    html=response.text
    regular=re.compile('<div id="content" class="showtxt">(.*?)</div>',re.S)
    novel_content=re.findall(regular,html)
    novel_content=novel_content[0]
    novel_content=novel_content.replace(r'<br />','')
    novel_content=novel_content.replace('请记住本书首发域名：www.bqg99.cc。笔趣阁手机版更新最快网址：m.bqg99.cc','')
    blank_line=re.compile(r'\r\r\u3000\u3000',re.S)
    novel_content=re.sub(blank_line,'\n',novel_content)
    # novel_content=novel_content.replace(r'\r\r\u3000\u3000','')
    with open(r'guimi\诡秘之主.txt','a') as f:
        f.write('\n'+novel_title+'\n')
    with open(r'guimi\诡秘之主.txt','a') as f:
                f.write(novel_content)