本文实例讲述了Python转换HTML到Text纯文本的方法。分享给大家供大家参考。具体分析如下：
今天项目需要将HTML转换为纯文本，去网上搜了一下，发现Python果然是神通广大，无所不能，方法是五花八门。
拿今天亲自试的两个方法举例，以方便后人：
方法一：
1. 安装nltk，可以去pipy装
（注：需要依赖以下包：numpy, PyYAML）
2.测试代码：
复制代码 代码如下:
>>> import nltk
>>> aa = r'''''
<html>
<body>
<b>Project:</b> DeHTML<br>
<b>Description</b>:<br>
This small script is intended to allow conversion from HTML markup to
plain text.
</body>
</html>
'''
>>> aa
'\n<html>\n <body>\n <b>Project:</b> DeHTML<br>\n <b>Description</b>:<br>\n This small script is intended to allow conversion from HTML markup to \n plain text.\n </body>\n </html>\n '
>>> <strong>print nltk.clean_html(aa)</strong>
Project: DeHTML
Description :
This small script is intended to allow conversion from HTML markup to
plain text.
>>> aa = r'''''
<html>
<body>
<b>Project:</b> DeHTML<br>
<b>Description</b>:<br>
This small script is intended to allow conversion from HTML markup to
plain text.
</body>
</html>
'''
>>> aa
'\n<html>\n <body>\n <b>Project:</b> DeHTML<br>\n <b>Description</b>:<br>\n This small script is intended to allow conversion from HTML markup to \n plain text.\n </body>\n </html>\n '
>>> <strong>print nltk.clean_html(aa)</strong>
Project: DeHTML
Description :
This small script is intended to allow conversion from HTML markup to
plain text.
方法二：
如果觉得nltk太笨重，大材小用的话，可以自己写代码，代码如下:
复制代码 代码如下:
from HTMLParser import HTMLParser
from re import sub
from sys import stderr
from traceback import print_exc
class _DeHTMLParser(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.__text = []
def handle_data(self, data):
text = data.strip()
if len(text) > 0:
text = sub('[ \t\r\n]+', ' ', text)
self.__text.append(text + ' ')
def handle_starttag(self, tag, attrs):
if tag == 'p':
self.__text.append('\n\n')
elif tag == 'br':
self.__text.append('\n')
def handle_startendtag(self, tag, attrs):
if tag == 'br':
self.__text.append('\n\n')
def text(self):
return ''.join(self.__text).strip()
def dehtml(text):
try:
parser = _DeHTMLParser()
parser.feed(text)
parser.close()
return parser.text()
except:
print_exc(file=stderr)
return text
def main():
text = r'''''
<html>
<body>
<b>Project:</b> DeHTML<br>
<b>Description</b>:<br>
This small script is intended to allow conversion from HTML markup to
plain text.
</body>
</html>
'''
print(dehtml(text))
if __name__ == '__main__':
main()
from re import sub
from sys import stderr
from traceback import print_exc
class _DeHTMLParser(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.__text = []
def handle_data(self, data):
text = data.strip()
if len(text) > 0:
text = sub('[ \t\r\n]+', ' ', text)
self.__text.append(text + ' ')
def handle_starttag(self, tag, attrs):
if tag == 'p':
self.__text.append('\n\n')
elif tag == 'br':
self.__text.append('\n')
def handle_startendtag(self, tag, attrs):
if tag == 'br':
self.__text.append('\n\n')
def text(self):
return ''.join(self.__text).strip()
def dehtml(text):
try:
parser = _DeHTMLParser()
parser.feed(text)
parser.close()
return parser.text()
except:
print_exc(file=stderr)
return text
def main():
text = r'''''
<html>
<body>
<b>Project:</b> DeHTML<br>
<b>Description</b>:<br>
This small script is intended to allow conversion from HTML markup to
plain text.
</body>
</html>
'''
print(dehtml(text))
if __name__ == '__main__':
main()
运行结果：
>>> ================================ RESTART ================================
>>>
Project: DeHTML
Description :
This small script is intended to allow conversion from HTML markup to plain text.
希望本文所述对大家的Python程序设计有所帮助。
