##示例1——使用lxml.etree模块获取HTML对象
from lxml import etree# 网页源代码
text = """
<div><ul><li class="item-0"><a href="link1.html">first item</a></li><li class="item-1"><a href="link2.html">second item</a></li><li class="item-inactive"><a href="link3.html">third item</a></li><li class="item-1"><a href="link4.html">fourth item</a></li><li class="item-0"><a href="link5.html">fifth item</a></li></ul></div>
"""# 使用etree.HTML()方法获取_Element对象，传入参数为待解析的源代码
htmlElement = etree.HTML(text)# 返回htmlElement的类型
print(type(htmlElement))# 返回htmlElement的内容
print(etree.tostring(htmlElement, encoding='utf-8').decode('utf-8'))

##示例2——使用lxml.etree对html文件进行解析
from lxml import etree# xml方式解析
def parse_file_xml():htmlElement = etree.parse("myfile.html")print(etree.tostring(htmlElement, encoding='utf-8').decode('utf-8'))# html方式解析
def parse_file_html():parser = etree.HTMLParser(encoding='utf-8')htmlElement = etree.parse('myfile.html',parser=parser)print(etree.tostring(htmlElement, encoding='utf-8').decode('utf-8'))if __name__ =='__main__':print('\nxml文件解析')parse_file_xml()print('\nhtml文件解析')parse_file_html()

<!源代码>
<table class="tablelist" cellpadding="0" cellspacing="0"><tr class="even"><td class="l square"><a target="_blank" href="position_detail.php?id=44256&keywords=&tid=0&lid=2218">25664-技术运营工程师（深圳）</a></td><td>技术类</td><td>2</td><td>深圳</td><td>2018-09-16</td></tr><tr class="odd"><td class="l square"><a target="_blank" href="position_detail.php?id=44252&keywords=&tid=0&lid=2218">15570-3D场景设计师（深圳）</a></td><td>设计类</td><td>1</td><td>深圳</td><td>2018-09-16</td></tr><tr class="even"><td class="l square"><a target="_blank" href="position_detail.php?id=44253&keywords=&tid=0&lid=2218">18425-国际支付产品软件测试工程师</a><spanclass="hot">&nbsp;</span></td><td>技术类</td><td>2</td><td>深圳</td><td>2018-09-16</td></tr>
</table>

##示例3——使用html.xpath选取节点(其返回的是一个列表)
from lxml import etree# 设置解析器并获取_Element对象
parser = etree.HTMLParser(encoding='utf-8')
html = etree.parse('example.html',parser=parser)# 获取所有tr标签
trs = html.xpath('//tr')    #[<Element tr at 0x2132da8c6c8>, <Element tr at 0x2132da8c708>, <Element tr at 0x2132da8c748>]# 获取第2个tr标签
tr2 = html.xpath('//tr[2]')[0]    #<Element tr at 0x2132da8c708># 获取所有class等于even的tr标签
tags= html.xpath('//tr[@class="even"]')    #[<Element tr at 0x20cd0b736c8>, <Element tr at 0x20cd0b73748>]# 获取所有a标签的href属性
hrefs = html.xpath('//a/@href')
#或hrefs = [element.get('href') for element in html.xpath('//a')]

‘’’

Output:

['position_detail.php?id=44256&keywords=&tid=0&lid=2218', 'position_detail.php?id=44252&keywords=&tid=0&lid=2218', 'position_detail.php?id=44253&keywords=&tid=0&lid=2218']

’’’

##示例4——综合演练，获取网页上所有职位信息
from lxml import etree# 获取_Element对象
parser = etree.HTMLParser(encoding='utf-8')
html = etree.parse('tencent.html',parser=parser)# 获取所有tr节点，并设置存放数据的容器position
trs = html.xpath('//tr')
positions = []# 依次遍历节点并存储数据
for tr in trs:href = tr.xpath('.//a/@href')[0]  title = tr.xpath('.//td[1]//text()')[0]category = tr.xpath('./td[2]//text()')[0]nums = tr.xpath('./td[3]//text()')[0]address = tr.xpath('./td[4]//text()')[0]pub_time = tr.xpath('./td[5]//text()')[0]data = {'url':href,'title':title,'category':category,'nums':nums,'address':address,'pub_time':pub_time}positions.append(data)for position in positions:print(position)