scraper_vod.py 文件源码

def get_categories():

    url = "http://sexyhotplay.com.br/categorias/"
    html = client.request(url, headers={'Cookie': 'disclaimer-sexyhotplay=1;'})

    soup = bs(html)
    div = soup.find('div', attrs={'class': 'colunas-3-15'})

    links = div.findAll('a', attrs={'class': 'link'}, recursive=True)

    results = []
    for link in links:
        label = link.find('strong').string
        url = 'http://sexyhotplay.com.br' + link['href']
        results.append({
            'name': label,
            # 'clearlogo': os.path.join(artPath, 'logo_sexyhot.png'),
            'url': url
        })

    return results