Python实现提取文章摘要的方法

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""Get a summary of the TEXT-format document"""
def get_summary(text, count):
  u"""Get the first `count` characters from `text`
    >>> text = u'Welcome 这是一篇关于Python的文章'
    >>> get_summary(text, 12) == u'Welcome 这是一篇'
    True
  """
  assert(isinstance(text, unicode))
  return text[0:count]
if __name__ == '__main__':
  import doctest
  doctest.testmod()

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""Get a raw summary of the HTML-format document"""
from HTMLParser import HTMLParser
class SummaryHTMLParser(HTMLParser):
  """Parse HTML text to get a summary
    >>> text = u'<p>Hi guys:</p><p>This is a example using SummaryHTMLParser.</p>'
    >>> parser = SummaryHTMLParser(10)
    >>> parser.feed(text)
    >>> parser.get_summary(u'...')
    u'<p>Higuys:Thi...</p>'
  """
  def __init__(self, count):
    HTMLParser.__init__(self)
    self.count = count
    self.summary = u''
  def feed(self, data):
    """Only accept unicode `data`"""
    assert(isinstance(data, unicode))
    HTMLParser.feed(self, data)
  def handle_data(self, data):
    more = self.count - len(self.summary)
    if more > 0:
      # Remove possible whitespaces in `data`
      data_without_whitespace = u''.join(data.split())
      self.summary += data_without_whitespace[0:more]
  def get_summary(self, suffix=u'', wrapper=u'p'):
    return u'<{0}>{1}{2}</{0}>'.format(wrapper, self.summary, suffix)
if __name__ == '__main__':
  import doctest
  doctest.testmod()

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""Get a raw summary of the HTML-format document"""
import re
def get_summary(text, count, suffix=u'', wrapper=u'p'):
  """A simpler implementation (vs `SummaryHTMLParser`).
    >>> text = u'<p>Hi guys:</p><p>This is a example using SummaryHTMLParser.</p>'
    >>> get_summary(text, 10, u'...')
    u'<p>Higuys:Thi...</p>'
  """
  assert(isinstance(text, unicode))
  summary = re.sub(r'<.*?>', u'', text) # key difference: use regex
  summary = u''.join(summary.split())[0:count]
  return u'<{0}>{1}{2}</{0}>'.format(wrapper, summary, suffix)
if __name__ == '__main__':
  import doctest
  doctest.testmod()