Python lxml解析HTML并用xpath获取元素的方法

#-*- coding: UTF-8 -*-from lxml import etreesource = u'''<div><p class="p1" data-a="1">测试数据1</p><p class="p1" data-a="2">测试数据2</p><p class="p1" data-a="3" style="height:100px;"><strong class="s">测试数据3</strong></p><p class="p1" data-a="4" width="200"><img src="1.jpg" class="img"/><br/>图片</p>'''# 从字符串解析page = etree.HTML(source)# 元素列表ps = page.xpath("//p")for p in ps:  print u"属性：%s" % p.attrib  print u"文本：%s" % p.text# 文本列表ts = page.xpath("//p/text()")for t in ts:  print t# xpath定位 ls = page.xpath('//p[@class="p1"][last()]/img')for l in ls:  print l.attrib