summarize text

doSummary.py

from bs4 import BeautifulSoup
# https://pypi.python.org/pypi/sumy
from sumy.parsers.html import HtmlParser
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
from sumy.utils import get_stop_words

# USE PYTHON3

# what language
LANGUAGE = 'english'
# how many sentences do you want
SENTENCES_COUNT = 2

if __name__ == '__main__':
    summarizer = Summarizer(Stemmer(LANGUAGE))
    summarizer.stop_words = get_stop_words(LANGUAGE)
    tok = Tokenizer(LANGUAGE)
    # pretty much you gotta extract the text you want to be summarized
    # or use beautiful soup to iterate over the html and when you find the
    # tag gets its text or a combination of that
    """
    parser = PlaintextParser.from_string('', tok)
    for sentence in map(lambda x: str(x), summarizer(parser.document, SENTENCES_COUNT)):
        print(sentence)
    """

    """
    with open('htmlFile.html' 'r') as iin:
        info = BeautifulSoup(iin, 'lxml').find(class_='whatever')
        for ul in info.find_all('ul'):
            li = ul.find('li')
            em = li.find('em')
            strong = li.find('strong').text
            emt = em.text
            parser = HtmlParser.from_string(str(li), None, tok)
            for sentence in map(lambda x: str(x), summarizer(parser.document, SENTENCES_COUNT)):
                print(sentence)
    """