爬虫必会的xpath

from lxml import etreehtml #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node #1获取文档中的全部标签 books = html.xpath("//book")web #2第一个book first_book = book[0]svg #3

>>阅读原文<<