xpath特别用法

starts-with用法，方便获取多个类似标签内容

from lxml import etree

html = '''
<li class="tag-1"> 需要的内容1</li>
<li class="tag-1"> 需要的内容2</li>
<li class="tag-1"> 需要的内容3</li>
'''

selector = etree.HTML(html)
contents = selector.xpath('//li[starts-with(@class,"tag")]/text()')
for content in contents:
    print(content)

string(.)用法：当遇到标签套标签情况，可以通过string(.)拿到标签内所有文本内容

from lxml import etree

html = '''
<div class="red"> 需要的内容1
    <h1>需要的内容2</h1>
</div>
'''

selector = etree.HTML(html)
content1 = selector.xpath('//div[@class="red"]')[0]
content2 = content1.xpath('string(.)')
print(content2)