Closed aryan1107 closed 2 years ago
Hi, sumy is not meant as an article parser. It's just a minor feature to ease the article summarization on the web. The algorithm is far from perfect and uses breadability. You should use the library for the text extraction as newspaper, justText or alternatives in its readme.
But if you really want you can do this to get the full article from the parser: " ".join(map(str, parser.document.sentences))
.
For example in newspaper python library you can do article.text for getting entire text.
Any similar command for sumy?