17-xpath入门解析02

from lxml import html

etree = html.etree

# 加载html文件
tree = etree.parse("b.html", etree.HTMLParser())  # ['百度', '谷歌', '搜狗']
# result = tree.xpath("/html/body/ul/li[1]/a/text()")  # ['百度', '谷歌', '搜狗']
# result = tree.xpath("/html/body/ul/li[1]/a/text()")  # ['百度']  xpath下标从1开始
# result = tree.xpath("/html/body/ol/li/a[@href='dapao']/text()")  # 通过  @属性值  来通过属性筛选
# 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中继续去寻找  ./代表当前节点
#     print(result)
#     result2 = li.xpath("./a/@href")  # 可以通过这种方式拿到属性的值
#     print(result2)
#
# print(tree.xpath("/html/body/ul/li/a/@href"))

# 小技巧，打开哦我们的网页后，右键选择检查，我们页面显示的顺序是和element模块中的代码相对应的。找到我们想要的那一行代码，右键可以复制xPath
print(tree.xpath("/html/body/div[1]/text()"))  # ['李嘉诚']