运用css选择器：
# -*- coding: utf-8 -*-
from lxml import html
page_html = '''
<html><body>
<input id="input_id" value="input value" name="input_a">
</body></html>
'''
page_tree = html.fromstring(page_html.decode('utf-8'))
ele = page_tree.cssselect('#input_id') # 用css选择器的id选择器获取网页内容
print html.tostring(ele[0]) # <input id="input_id" value="input value" name="input_a">
print ele # [<InputElement 30133f0 name='input_a' type='text'>]
print ele[0] # <InputElement 30133f0 name='input_a' type='text'>
print ele[0].get('value') # input value
获取标签里的内容：
# -*- coding: utf-8 -*-
from lxml import html
page_html = '''
<html><body>
<div class="cl">DIV1</div>
<div class="cl">DIV2</div>
</body></html>
'''
page_tree = html.fromstring(page_html.decode('utf-8'))
ele = page_tree.cssselect('body')[0].findall("div") # findall寻找所有的直接子标签
print ele[0].text_content().strip() # DIV1
若提示如下错误：
from lxml import html
ImportError: DLL load failed: %1 is not a valid Win32 application.
尝试重新安装lxml模块：
python -m pip uninstall lxml
python -m pip install lxml==3.6.0