<span style="font-size:18px;">#coding=utf-8
from lxml import etree
import sys
import chardet
import codecs
reload(sys)
sys.setdefaultencoding("utf-8")
html=u'''
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>测试常用规范</title>
</head>
<body>
<div id="content">
<ul id="useful">
<li>546545645645645</li>
<li>这是第一条信息</li>
<li>这是第一条信息</li>
</ul>
<ul id="useless">
<li>不需要信息</li>
<li>不需要信息</li>
<li>不需要信息</li>
</ul>
<div>
<a href="http://lotluck.com">lotluck专栏</a>
<a href="http://lotluck/68525233653.com" title=杜帅加油啊"">linux自学之旅</a>
</div>
</div>
</body>
</html>
'''
print html
selector = etree.HTML(html)
content = selector.xpath('//ul[@id="useful"]/li/text()')
print type(content)
for each in content:
print each
##提取属性
link = selector.xpath('//a/@href')
for each in link:
print each
print '开始'
title = selector.xpath('//a/@title')
f = open('5.txt','w')
f.write(title[0])
f.close()
f1 = open('5.txt','r')
fencoding = chardet.detect(f1.read())
print fencoding
print '结束'
print type(title[0])
#print title[0].decode('ascii').encode('utf-8')
print "我们是小青哇"
f3=codecs.open("6.htm","r","utf-8")
content1 = f3.read()
f3.close()
tree=etree.HTML(content1)
node= tree.xpath('//ul[@id="useful"]/li/text()')
for each in node:
print each
</span>
3万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
