[Python] 纯文本查看 复制代码 import os, traceback
from lxml import etree
text = '''
<tbody>
<tr><td style="height: 0.01px; width: 364px;"></td><td style="height: 0.01px; width: 364px;"></td><td style="height: 0.01px; width: 362px;"></td></tr>
<tr ><td title="类型一" >类型一</td><td title="标题一">标题一</td><td title="型号一">型号一</td></tr>
<tr ><td title="类型二" >类型</td><td title="标题二">标题二</td><td title="型号二">型号二</td></tr>
<tr><td title="类型三" >类型</td><td title="标题三">标题三</td><td title="型号三">型号三</td></tr>
<tr><td title="类型二" >类型</td><td title="标题四">标题四</td><td title="型号四">型号四</td></tr>
<tr><td title="类型三" >类型</td><td title="标题五">标题五</td><td title="型号五">型号五</td></tr>
</tbody>
'''
html = etree.HTML(text)
s = etree.tostring(html).decode()
html_data = html.xpath('/html/body/tbody/tr')
for i in html_data:
#print(i.xpath('td/@title'))
if(len(i.xpath('td/@title'))>0 and i.xpath('td/@title')[0]=='类型二'):
print(i.xpath('td/@title'))
|