爬虫基础--lxml库和Xpath语法

from lxml import etree

"""
1.读取html字符串
"""
text = \
"""
<tr class="hots">
    <td class="1">hot1</td>
    <td class="2">hot2</td>
    <td class="3">hot3</td>
    <td class="4">hot4</td>
    <td class="5">hot5
    <td class="6">爬虫
</tr>
"""
#利用了etree.HTML,将字符串解析为HTML文档【能帮助我们进行标签补全】
html = etree.HTML(text)
print(type(html))
#打印解析后的htmL页面[解析后的文档是一个bytes流数据]，要先编码再解码
result = etree.tostring(html,encoding='utf8').decode('utf8')
print(result)


"""
2.直接解析html文件
【默认使用xml解析器】
"""
#自定义一个HTML解析器
parser = etree.HTMLParser(encoding='utf8')

html = etree.parse(r"/Users/dx/Desktop/（凡博）Python爬虫资料/3.Python爬虫数据提取-Xpath语法/课程资料/test.html",parser=parser)
result = etree.tostring(html,encoding='utf8').decode('utf8')
print(result)

text = \
"""
<ul class="ullist" padding="1" spacing="1">
    <li>
        <div id="top">
            <span class="position" width="350">职位名称</span>