Simple test of trafilatura

trafilatura.py

from trafilatura.core import bare_extraction, extract
from pathlib import Path
import json
from sentence_splitter import SentenceSplitter

html_path = Path("data") / "testfile-3.html"
html = html_path.read_text()
result_json_text = extract(
    output_format="json",
    filecontent=html,
    include_images=True,
    include_formatting=True
    )

result = json.loads(result_json_text)
splitter = SentenceSplitter(language="en")
sentences = splitter.split(result["text"])
print(json.dumps(result,indent=2))
print("===")
print(json.dumps(sentences,indent=2))

testfile-3.html is this file downloaded locally: https://lisn-tests.netlify.app/rich-content.html