sumyvsextruct
sumy is a Python library for automatic summarization of text documents. It can be used to extract summaries from various input formats such as plaintext, HTML, and URLs. It supports multiple languages and multiple summarization algorithms, including Latent Semantic Analysis (LSA), Luhn, Edmundson, TextRank, and SumBasic.
extruct is a library for extracting embedded metadata from HTML markup.
Currently, extruct supports:
- W3C's HTML Microdata
- embedded JSON-LD
- Microformat via mf2py
- Facebook's Open Graph
- (experimental) RDFa via rdflib
- Dublin Core Metadata (DC-HTML-2003)
Example Use
# -*- coding: utf-8 -*-
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals
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
LANGUAGE = "english"
SENTENCES_COUNT = 10
if __name__ == "__main__":
url = "https://en.wikipedia.org/wiki/Automatic_summarization"
parser = HtmlParser.from_url(url, Tokenizer(LANGUAGE))
# or for plain text files
# parser = PlaintextParser.from_file("document.txt", Tokenizer(LANGUAGE))
# parser = PlaintextParser.from_string("Check this out.", Tokenizer(LANGUAGE))
stemmer = Stemmer(LANGUAGE)
summarizer = Summarizer(stemmer)
summarizer.stop_words = get_stop_words(LANGUAGE)
for sentence in summarizer(parser.document, SENTENCES_COUNT):
print(sentence)
# retrieve HTML content
import httpx
response = httpx.get('https://webscraping.fyi/lib/python/extruct')
import extruct
all_data = extruct.extract(response.text, response.url)
# or we can extract specific metadata format by importing individuals extractors:
extractor = extruct.MicrodataExtractor()
microdata = extractor.extract(response.text)
extractor = extruct.JsonLdExtractor()
jsonld = extractor.extract(response.text)