爬虫之Xpath应用

from lxml import etree

#用来获取解析后的数据
html = etree.HTML(text)#用来解析文本
html = etree.parse(“index2.html”)#用来解析html文档

#1获取文档中的所有标签
books = html.xpath("//book")

#2第一个book
first_book = book[0]

#3 获取第一本book中的href标签
href = first_book.xpath(".//@href")
print(href,111111111)

#4获取当前节点的父节点的所有book标签的href属性
book_hrefs = first_book.xpath("…/book/@href")
print(book_hrefs)

#5获取价格大于40的book书名
book_name = html.xpath("//book[price>40]/title/text()")
print(book_name)

#6获取价格等于99.5的书名
book_name = html.xpath("//book[price=99.95]/title/text()")
print(book_name)

#7获取book标签下面的title和price标签
title_price = html.xpath("//book/title | //book/price")
print(title_price)

#8.获取bookstore下面的最前面的两个标签，并获取它的书名
book_name2 = html.xpath("/bookestore/book[positon()❤️]/title/text()")
print(book_name2)

#9获取所有节点属性
nodes = html.xpath("//@*")
print(nodes)

#10获取所有带有属性的title标签，并获取书名
book_name3 = html.xpath("//title[@*]")
print(book_name3)

#11获取属性href为http://www.langlang2017.com/的book标签，获取他的兄弟标签下的title书名
book_name4 = html.xpath("//book[@href=‘http://www.langlang2017.com/’]/following-sibling::book/title/text()")
print(book_name4)

#12获取所有的书名,child 是zi标签
book_name6 = html.xpath("//book/child::title/text()")
print(book_name6)