python通用内容提取库的使用

from bluextracter import Extractor

if __name__ == '__main__':
    extacert = Extractor()#实例提取类
    url = 'https://m.huicaiba.com/ask/5426118.html'
    resp = requests.get(url)
    resp.encoding = 'utf-8'#手动设置网页源码
    source = resp.text
    extacert.extract(url,source)
    # print('得分:',extacert.score)#得分
    # print('标题:', extacert.title)  # 标题
    # print('文本链接比例:',extacert.link_text_ratio)#
    # print('图片数量:',extacert.img_count)
    # print('内容字数:',extacert.text_count)
    #
    # print('纯文本内容:',extacert.clean_text)#纯文本内容
    print('html内容:',extacert.format_text)#用html标签格式化的内容
    # top_node = extacert.top_node  #原始html是一个elem
    # cc = etree.tostring(top_node,encoding='utf-8').decode('utf-8')
    # print(unescape(cc))