mythic_scraper.py 文件源码

 复制代码def scrape_mythic_card_page(url):
    r = requests.get(url)

    soup = BS(r.text, "html.parser")

    comments = soup.find_all(string=lambda text: isinstance(text, Comment))

    card = {}

    for comment in comments:
        if comment == 'CARD NAME':
            card['name'] = comment.next_element.strip().replace('"', '')
        elif comment == 'MANA COST':
            try:
                card['manaCost'] = comment.next_element.strip().replace('"', '')
            except:
                pass
        elif comment == 'TYPE':
            card['type'] = comment.next_element.strip().replace('"', '')
        elif comment == 'CARD TEXT':
            buildText = ''
            for element in comment.next_elements:
                try:
                    if not element.strip() in ['CARD TEXT', 'FLAVOR TEXT', '']:
                        if buildText != '':
                            buildText += '\n'
                        buildText += element.strip()
                    if element.strip() == 'FLAVOR TEXT':
                        card['text'] = buildText
                        break
                except:
                    pass
        elif comment == 'Set Number':
            try:
                card['number'] = comment.next_element.strip()
            except:
                pass
        elif comment == 'P/T':
            try:
                if comment.next_element.strip().split('/')[0] != '':
                    card['power'] = comment.next_element.strip().split('/')[0]
                    card['toughness'] = comment.next_element.strip().split('/')[1]
            except:
                pass

    return card