HTML文件XPath测试

html_dom_test.py

# 导入 etree类
from lxml import etree

# 作为示例的 html文本
f = open("test.html",encoding='utf-8')
html = f.read()

dom = etree.HTML(html)

for b in range(len(dom.xpath('/html/body/table/tbody/tr/td[2]/text()'))):
    i = b + 1
    # name = dom.xpath('/html/body/table/tbody/tr[' + str(i) + ']/td[2]/text()')[0] + ' ' + \
    #        dom.xpath('/html/body/table/tbody/tr[' + str(i) + ']/td[1]/text()')[0]
    name = dom.xpath('/html/body/table/tbody/tr[' + str(i) + ']/td[1]/text()')[0]
    url = dom.xpath('/html/body/table/tbody/tr[' + str(i) + ']/td[3]')[0].attrib['endpoint'].replace('http://', '').replace(
        '/', '')
    en_name = url.split('.')[0]

    print('''
++ %s
menu = %s
title = DigitalOcean %s
host = %s''' % (en_name, en_name, name, url))