DISCAS scraping

discas.py

# -*- coding: utf-8 -*-

import lxml.html

URLFORMAT = 'http://www.discas.net/netdvd/cd/goodsDetail.do?titleID=%010d'

# XPathをコンパイルして再利用する
find_title = lxml.etree.XPath(
    'string(//head/meta[@property="og:title"]/@content)')
is_available = lxml.etree.XPath(
    'boolean(id("sectionGoods")//form[@name="UpdateWishListForm"])')


def getinfo(titleid):
    url = URLFORMAT % titleid

    # libxml2がWindows-31Jを認識してくれないのでCP932を渡す
    parser = lxml.html.HTMLParser(encoding='cp932')
    tree = lxml.html.parse(url, parser)

    # タイトルを取得
    title = find_title(tree)

    # 「単品リストに追加」フォームを探す
    available = is_available(tree)

    return title, available


if __name__ == '__main__':
    wishlist = [683928, 1209833, 1795844]
    for titleid in wishlist:
        title, available = getinfo(titleid)
        print ('x', 'o')[available], title