spoilers.py 文件源码

def scrape_masterpieces(url='http://www.mtgsalvation.com/spoilers/181-amonkhet-invocations', mtgscardurl='http://www.mtgsalvation.com/cards/amonkhet-invocations/'):
    page = requests.get(url)
    tree = html.fromstring(page.content)
    cards = []
    cardstree = tree.xpath('//*[contains(@class, "log-card")]')
    for child in cardstree:
        childurl = mtgscardurl + \
            child.attrib['data-card-id'] + '-' + child.text.replace(' ', '-')
        cardpage = requests.get(childurl)
        tree = html.fromstring(cardpage.content)
        cardtree = tree.xpath('//img[contains(@class, "card-spoiler-image")]')
        try:
            cardurl = cardtree[0].attrib['src']
        except:
            cardurl = ''
            pass
        card = {
            "name": child.text,
            "url": cardurl
        }
        cards.append(card)
    return cards