get_training_data.py 文件源码

def scrape(webpage, extension=".mid"):
    # Get all the files of a given extension from a webpage
    http = httplib2.Http()
    status, response = http.request(webpage)
    files = []
    for link in BeautifulSoup(response, parseOnlyThese=SoupStrainer('a')):
        if link.has_attr('href'):
            linkname = link['href']
            if linkname[-len(extension):] == extension:
                files += [linkname]
    return files