#coding:utf8
# BeautifulSoup可以将lxml作为默认的解析器使用，lxml亦可以单独使用;
# 比较BeautifulSoup和lxml：
#（1）
#BeaufulSoup基于DOM，会在如整个文档，解析整个DOM树，比较消耗内存和时间；
#lxml是使用XPath技术查询和处理HTML/XML文档库，只会局部遍历，所以速度较快。
#现在BeautifulSoup可以使用lxml作为默认解析库’
#（2）
#BeautifulSoup较简单，API非常人性化，支持CSS选择器。
# lxml的XPath比较麻烦，开发效率不如BeautifulSoup

#使用lxml解析网页，实例：
from lxml import etree
html_str = """

The Dormouse's story

Once upon a time there were three little sisters; and their names were , and Tillie; and they lived at the bottom of a well.

...

""" html = etree.HTML(html_str) result = etree.tostring(html) print result #lxml还可以自动修正html代码 #除了读取字符串之外，lxml还可以直接读取html文件 #将html_str存储为index.html文件，理由parse方法进行解析： from lxml import etree html = etree.parse('index.html') result = etree.tostring(html, pretty_print=True) print result #用XPath语法抽取所有的URL: html = etree.HTML(html_str) urls = html.xpath(".//*[@class='sister']/@href") print urls