python解析html

获取html中数据

# coding=utf-8
import sys
from bs4 import BeautifulSoup as bs


def read_html(filepath):
    '''
    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
    :param filepath: 要解析的html文件路径
    :return: 返回文件内容
    '''
    try:
        f = open(filepath)
    except IOError as e:
        print(e)
    else:
        content = f.read()
    return content
# htmlpath2 = "/Users/.../Pycharms/DEL/Test/overview.html"
htmlpath = sys.argv[1]
htmlcontent = read_html(htmlpath)
html3 = bs(htmlcontent, 'html.parser')
passed = int(html3.find_all('td', attrs={"class": "passed number"})[0].string)
skiped = int(html3.find_all('td', attrs={"class": "zero number"})[0].string)
errored = int(html3.find_all('td', attrs={"class": "failed number"})[0].string)
print(passed)
print(skiped)
print(errored)

参考：https://blog.csdn.net/qq_36411874/article/details/83784101