NLP（十一） 提取文本摘要

原文链接：http://www.one2know.cn/nlp11/

• gensim.summarization库的函数
  
  gensim.summarization.summarize(text, ratio=0.2, word_count=None, split=False)
  
  Parameters（参数）：
  
  text : str
  
  Given text.
  
  ratio : float, optional
  
  Number between 0 and 1 that determines the proportion of the number of
  
  sentences of the original text to be chosen for the summary.
  
  word_count : int or None, optional
  
  Determines how many words will the output contain.
  
  If both parameters are provided, the ratio will be ignored.
  
  split : bool, optional
  
  If True, list of sentences will be returned. Otherwise joined
  
  strings will bwe returned.
• 代码

from gensim.summarization import summarize # 基于文本排序的摘要算法
from bs4 import BeautifulSoup # 用于解析HTML文档的BeautifulSoup库
import requests # 用于下载HTTP资源的库
urls = { # 题目:网站 字典
    'Deconstructing Voice-over-IP':
    'http://scigen.csail.mit.edu/scicache/269/scimakelatex.25977.A.+G.+Hassan.html',
    'Exploration of the Location-Identity Split':
    'http://scigen.csail.mit.edu/scicache/270/scimakelatex.26087.Ali+Veli.Veli+Ali.Vel+Al.html',
}
# 摘要(真实的)：
# 1.The implications of ambimorphic archetypes have been far-reaching and pervasive. After years of natural research into consistent hashing, we argue the simulation of public-private key pairs, which embodies the confirmed principles of theory. Such a hypothesis might seem perverse but is derived from known results. Our focus in this paper is not on whether the well-known knowledge-based algorithm for the emulation of checksums by Herbert Simon runs in Θ( n ) time, but rather on exploring a semantic tool for harnessing telephony (Swale).
# 2.Superblocks must work. Given the current status of homogeneous configurations, security experts particularly desire the simulation of 802.11b. we consider how the Internet can be applied to the refinement of Scheme.
for key in urls.keys():
    url = urls[key]
    r = requests.get(url)
    soup = BeautifulSoup(r.text,'html.parser')
    data = soup.get_text() # HTML去标签后的文本
    pos1 = data.find('1 Introduction') + len('1 Introduction')
    pos2 = data.find('Related Work')
    text = data[pos1:pos2].strip() # 提取pos1与pos2之间的引言部分
    print('PAPER URL: {}'.format(url))
    print('TITLE: {}'.format(key))
    print('GENERATED SUMMARY: {}'.format(summarize(text)))
    print()

输出：

PAPER URL: http://scigen.csail.mit.edu/scicache/269/scimakelatex.25977.A.+G.+Hassan.html
TITLE: Deconstructing Voice-over-IP
GENERATED SUMMARY: 。。。。。。

PAPER URL: http://scigen.csail.mit.edu/scicache/270/scimakelatex.26087.Ali+Veli.Veli+Ali.Vel+Al.html
TITLE: Exploration of the Location-Identity Split
GENERATED SUMMARY: 。。。。。。