HDOJ_Submitter.py 文件源码

def getTextFromSoup(htmlsoup):
    #print(htmlsoup)
    text = str(htmlsoup)
    imgurls = []
    imgs = htmlsoup.find_all('img')
    #print_list(imgs)
    for img in imgs:
        imgurls.append('http://acm.hdu.edu.cn%s' % img['src'])
    #print(htmlsoup)
    if len(imgurls) != 0:
        for url in imgurls:
            text, number = re.subn(r'<img.+?>', r'![image](%s)' % url, text)
    #print(text)
    text, number = re.subn(r'<br>', '\n', text)
    text, number = re.subn(r'<.+?>', '', text)
    return text
    #print(text)
    #print(seh.group())
    #print_list(imgurls)
    # res = htmlsoup.replace('<br/>', '\r\n')
    # result, number = re.subn('<.+?>', '', res)
    # print(result)
    # print(number)