学习笔记(10):第一章：数据提取与清洗策略-Python中的lxml模块

立即学习:https://edu.csdn.net/course/play/25650/308708?utm_source=blogtoedu

import lxml.etree as le

with open('edu.html','r',encoding='utf-8') as f:
    html=f.read()
    # print(html)
    html_x=le.HTML(html)
    # print(html_x)
    div_x_s=html_x.xpath('//div[contains(@class,"classify_cList")]')
    # print(div_x_s)
    data_s=[]
    for div_x in div_x_s:
        category_1=div_x.xpath('./h3/a/text()')[0]
        # print(category_1)
        category_2_s=div_x.xpath('./div/span/a/text()')
        # print(category_2_s)

        data_s.append(
            {
                'category_1':category_1,
                'category_2_s':category_2_s,
            }
        )
    print(data_s)
    for data in data_s:
        print(data['category_1'])
        for category_2 in data['category_2_s']:
            print('     ',category_2)