python实现对html文件内的每一行的特定标签的值的读取

from bs4 import BeautifulSoup

f = open("C:/Users/JIA/Desktop/数据结构/file.txt", "r")
lines = f.readlines()  # 读取全部内容
for line in lines:
    html = line
    # 用BeautifulSoup解析数据  python3 必须传入参数二'html.parser' 得到一个对象，接下来获取对象的相关属性
    html = BeautifulSoup(html, 'html.parser')
    attrs = html.a.attrs
    if attrs['data-type'] == "ppt":
        print(attrs['data-title'] + attrs['data-type'], attrs['data-url'])
    else:
        print(attrs['data-title'], attrs['data-url'])