python爬虫lxml xpath测试

xpath测试1:
main.py

"""=== coding: UTF8 ==="""
from lxml import etree

xml = """
<book>
    <id>1</id>
    <name>春风</name>
    <price>1.56</price>
    <nick>万里</nick>
    <author>
        <nick id="10086">周大庆</nick>
        <nick id="10010">黄天山</nick>
        <nick class="joy">周谈浩</nick>
        <div>
            <nick>嘟嘟</nick>
        </div>
        <span>
            <nick>珊瑚</nick>
        </span>
    </author>
</book>
"""


"""
========================================
主函数功能测试
========================================
"""
if __name__ == '__main__':
    tree = etree.XML(xml)
    # result = tree.xpath("/book")  # /表示层级关系,第一个/是根节点
    # result = tree.xpath("/book/name/text()")  # text()拿文本
    # result = tree.xpath("/book/author//nick/text()")  # //后代
    result = tree.xpath("/book/author/*/nick/text()")  # *任意的节点,通配符
    print(result)

xpath测试2:
test.html

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>测试</title>
</head>
<body>
    <ul>
        <li><a href="http://www.baidu.com">百度</a></li>
        <li><a href="http://www.google.com">谷歌</a></li>
        <li><a href="http://www.sogou.com">搜狗</a></li>
    </ul>
    <ol>
        <li><a href="feiji">飞机</a></li>
        <li><a href="dapao">大炮</a></li>
        <li><a href="huoche">火车</a></li>
    </ol>
    <div class="job">高凡尔</div>
    <div class="common">刘珂</div>
</body>
</html>

main.py

"""=== coding: UTF8 ==="""
from lxml import etree


"""
========================================
主函数功能测试
========================================
"""
if __name__ == '__main__':
    parser = etree.HTMLParser(encoding='utf-8')
    tree = etree.parse("test.html", parser=parser)
    # result = tree.xpath("/html")  # /表示层级关系,第一个/是根节点
    # result = tree.xpath("/html/body/ul/li/a/text()")  # text()拿文本
    # result = tree.xpath("/html/body/ul/li[1]/a/text()")  # xpath的顺序是从1开始数的,[]表示索引
    # result = tree.xpath("/html/body/ol/li/a[@href='dapao']/text()")  # @xxx=xxx表示属性的筛选
    # print(result)
    ol_li_list = tree.xpath("/html/body/ol/li")

    for li in ol_li_list:
        # 从每一个li中提取到文字信息
        result = li.xpath("./a/text()")  # 在li中继续查找,相对查找
        print(result)
        result = li.xpath("./a/@href")  # 拿到属性值: @属性
        print(result)

    print(tree.xpath("/html/body/ul/li/a/@href"))
    print(tree.xpath("/html/body/div[1]/text()"))
    print(tree.xpath("/html/body/ol/li/a/text()"))


关注公众号,获取更多资料
python爬虫lxml xpath测试

上一篇:爬虫—lxml提取数据


下一篇:python爬虫中解决第三方模块lxml中没有etree方法