免费小说下载爬虫

freetxt.py

#coding=utf-8
import requests
import re
print('数据来源于https://www.biqubao.com/ 如需到此网更新书籍')
bookurl = input('该本小说网站(直接回车自动跳转一本)：')
if bookurl == '':
    bookurl = 'https://www.biqubao.com/book/34203/'
homeurl =  'https://www.biqubao.com/'
A = requests.get(bookurl).content.decode('gb2312')
B = re.split(r'<dd><a href=|</a></dd>',A)
PAGE = []
for html in B:
    if 'html' in html and '\n' not in html:
        PAGE.append(html)

def page_new(P):
    PP=int(P)-1
    ok = re.split(r'"/|">',PAGE[PP])
    oneurl = homeurl+ok[1]
    print('_'*70)
    print('|'+ok[2]+oneurl)
    D = requests.get(oneurl).content.decode('gb2312')
    E = re.split(r'<br />|&nbsp;&nbsp;&nbsp;&nbsp;|</div>|<h1>|</h1>|\n',D)
    for text in E:
        if text !='' and '<a href=' not in text:
            really = 0
            for i in text:
                if '\u4e00' <= i <= '\u9fff':
                    really +=1
            if  really > 0:
                print('|'+text)
    print('——'*15)
    
textpage = 0
if __name__ == '__main__':
    while True:
        old = textpage
        textpage = input('跳转书页|回车下一章next>>')
        if textpage == '':
            textpage = int(old) +1
        page_new(textpage)

文档：freetxt.exe
链接：http://note.youdao.com/noteshare?id=11eeac80bf7f4570a087ae850f9ea4e1