python提取内容关键词的方法

本文实例讲述了python提取内容关键词的方法。分享给大家供大家参考。具体分析如下：

一个非常高效的提取内容关键词的python代码，这段代码只能用于英文文章内容，中文因为要分词，这段代码就无能为力了，不过要加上分词功能，效果和英文是一样的。

# coding=utf-8
import nltk
from nltk.corpus import brown
# this is a fast and simple noun phrase extractor (based on nltk)
# feel free to use it, just keep a link back to this post
# http://thetokenizer.com/2013/05/09/efficient-way-to-extract-the-main-topics-of-a-sentence/
# create by shlomi babluki
# may, 2013
 
# this is our fast part of speech tagger
#############################################################################
brown_train = brown.tagged_sents(categories='news')
regexp_tagger = nltk.regexptagger(
    [(r'^-?[0-9]+(.[0-9]+)?$', 'cd'),
     (r'(-|:|;)$', ':'),
     (r'\'*$', 'md'),
     (r'(the|the|a|a|an|an)$', 'at'),
     (r'.*able$', 'jj'),
     (r'^[a-z].*$', 'nnp'),
     (r'.*ness$', 'nn'),
     (r'.*ly$', 'rb'),
     (r'.*s$', 'nns'),
     (r'.*ing$', 'vbg'),
     (r'.*ed$', 'vbd'),
     (r'.*', 'nn')
])
unigram_tagger = nltk.unigramtagger(brown_train, backoff=regexp_tagger)
bigram_tagger = nltk.bigramtagger(brown_train, backoff=unigram_tagger)
#############################################################################
# this is our semi-cfg; extend it according to your own needs
#############################################################################
cfg = {}
cfg["nnp+nnp"] = "nnp"
cfg["nn+nn"] = "nni"
cfg["nni+nn"] = "nni"
cfg["jj+jj"] = "jj"
cfg["jj+nn"] = "nni"
#############################################################################
class npextractor(object):
    def __init__(self, sentence):
        self.sentence = sentence
    # split the sentence into singlw words/tokens
    def tokenize_sentence(self, sentence):
        tokens = nltk.word_tokenize(sentence)
        return tokens
    # normalize brown corpus' tags ("nn", "nn-pl", "nns" > "nn")
    def normalize_tags(self, tagged):
        n_tagged = []
        for t in tagged:
            if t[1] == "np-tl" or t[1] == "np":
                n_tagged.append((t[0], "nnp"))
                continue
            if t[1].endswith("-tl"):
                n_tagged.append((t[0], t[1][:-3]))
                continue
            if t[1].endswith("s"):
                n_tagged.append((t[0], t[1][:-1]))
                continue
            n_tagged.append((t[0], t[1]))
        return n_tagged
    # extract the main topics from the sentence
    def extract(self):
        tokens = self.tokenize_sentence(self.sentence)
        tags = self.normalize_tags(bigram_tagger.tag(tokens))
        merge = true
        while merge:
            merge = false
            for x in range(0, len(tags) - 1):
                t1 = tags[x]
                t2 = tags[x + 1]
                key = "%s+%s" % (t1[1], t2[1])
                value = cfg.get(key, '')
                if value:
                    merge = true
                    tags.pop(x)
                    tags.pop(x)
                    match = "%s %s" % (t1[0], t2[0])
                    pos = value
                    tags.insert(x, (match, pos))
                    break
        matches = []
        for t in tags:
            if t[1] == "nnp" or t[1] == "nni":
            #if t[1] == "nnp" or t[1] == "nni" or t[1] == "nn":
                matches.append(t[0])
        return matches
# main method, just run "python np_extractor.py"
def main():
    sentence = "swayy is a beautiful new dashboard for discovering and curating online content."
    np_extractor = npextractor(sentence)
    result = np_extractor.extract()
    print "this sentence is about: %s" % ", ".join(result)
if __name__ == '__main__':
    main()

希望本文所述对大家的python程序设计有所帮助。