wizards_scraper.py 文件源码

def scrape_fullspoil(url="http://magic.wizards.com/en/articles/archive/card-image-gallery/hour-devastation", setinfo={"code": "HOU"}, showRarityColors=False, showFrameColors=False, manual_cards=[], delete_cards=[]):
    if 'name' in setinfo:
        url = 'http://magic.wizards.com/en/articles/archive/card-image-gallery/' + setinfo['name'].lower().replace('of', '').replace(
            '  ', ' ').replace(' ', '-')
    page = requests.get(url)
    tree = html.fromstring(page.content)
    cards = []
    cardtree = tree.xpath('//*[@id="content-detail-page-of-an-article"]')
    for child in cardtree:
        cardElements = child.xpath('//*/p/img')
        cardcount = 0
        for cardElement in cardElements:
            card = {
                "name": cardElement.attrib['alt'].replace(u"\u2019", '\'').split(' /// ')[0],
                "img": cardElement.attrib['src']
            }
            card["url"] = card["img"]
            #card["cmc"] = 0
            #card["manaCost"] = ""
            #card["type"] = ""
            #card["types"] = []
            #card["text"] = ""
            #card["colorIdentity"] = [""]

            # if card['name'] in split_cards:
            #    card["names"] = [card['name'], split_cards[card['name']]]
            #    card["layout"] = "split"
            #notSplit = True
            # for backsplit in split_cards:
            #    if card['name'] == split_cards[backsplit]:
            #        notSplit = False
            # if not card['name'] in delete_cards:
            cards.append(card)
            cardcount += 1
    fullspoil = {"cards": cards}
    print "Spoil Gallery has " + str(cardcount) + " cards."
    download_images(fullspoil['cards'], setinfo['code'])
    fullspoil = get_rarities_by_symbol(fullspoil, setinfo['code'])
    fullspoil = get_mana_symbols(fullspoil, setinfo['code'])
    #fullspoil = get_colors_by_frame(fullspoil, setinfo['code'])
    return fullspoil