批量用title的内容命名html文件,使用<title>标记重命名HTML文件

下面是我刚写的一个python脚本：import os

import re

from lxml import etree

class MyClass(object):

def __init__(self, dirname=''):

self.dirname = dirname

self.exp_title = "

(.*)"

self.re_title = re.compile(self.exp_title)

def rename(self):

for afile in os.listdir(self.dirname):

if os.path.isfile(afile):

originfile = os.path.join(self.dirname, afile)

with open(originfile, 'rb') as fp:

contents = fp.read()

try:

html = etree.HTML(contents)

title = html.xpath("//title")[0].text

except Exception as e:

try:

title = self.re_title.findall(contents)[0]

except Exception:

title = ''

if title:

newfile = os.path.join(self.dirname, title)

os.rename(originfile, newfile)

>>> test = MyClass('/path/to/your/dir')

>>> test.rename()