163 reader

get163book.py

import requests
import base64
from bs4 import BeautifulSoup

cookie = open('cookie163.txt').read().strip()
bookid = '23c816b98303491ab82e898d349f6154_4&tradeId='

bookinfo = requests.get('http://yuedu.163.com/getBook.do?id='+bookid).json()
content = ''
for p in bookinfo['portions']:
    c = requests.get("http://yuedu.163.com/getArticleContent.do?"
            "sourceUuid={}&articleUuid={}&bigContentId={}".format(
                bookid, p['id'], p['bigContentId']),
            headers={'Cookie':cookie}).json()
    cnt = base64.decodestring(c['content'])
    print p['title'], len(cnt)
    content += '\n' + cnt

soup = BeautifulSoup(content)
content = '\n'.join(soup.findAll(text=True))
content = '\n\n'.join(filter(lambda l: bool(l.strip()), content.split('\n')))

open(bookinfo['title'] + '.txt', 'w').write(content.encode('utf8'))