gistfile1.txt

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import lxml.html
import re
import requests
import sqlite3

def procedure():
    url = 'https://24h.pchome.com.tw/?m=store&f=book_show&RG_NO=DJAZ&pageType=0'

    r = requests.get(url);
    r.encoding = 'big5';

    html = lxml.html.fromstring(r.text)

    book_date_re = re.compile('出版日：\s*(\S+)/', re.M)
    book_publisher_re = re.compile('出版社：\s*(\S+)/', re.M)

    for td_raw in html.cssselect('#StoreBodyContainer table[width="360"]'):
        td = td_raw.cssselect('.text13')
        book_name = td[0].text_content()

        txt = td_raw.text_content()

        book_date = book_date_re.search(txt)[0]
        book_publisher = book_publisher_re.search(txt)

        print('%s - %s - %s' % (book_name, book_publisher, book_date))

if __name__ == '__main__':
    procedure()