爬蟲必會的xpath

from lxml import etreehtml #用來獲取解析後的數據 html = etree.HTML(text)#用來解析文本 html = etree.parse(「index2.html」)#用來解析html文檔node #1獲取文檔中的全部標籤 books = html.xpath("//book")web #2第一個book first_book = book[0]svg #3

>>阅读原文<<