Created
December 9, 2025 22:45
-
-
Save ricardocuellar/259d1fdbdb8d3a37e144f957376fdd48 to your computer and use it in GitHub Desktop.
Python + n8n - Section 4 - Analyze words (black list)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| SPANISH_STOPWORDS = { | |
| "de", "la", "que", "el", "en", "y", "a", "los", "del", "se", "las", | |
| "por", "un", "para", "con", "no", "una", "su", "al", "lo", "como", | |
| "más", "mas", "o", "pero", "sus", "le", "ya", "si", "porque", "cuando", | |
| "muy", "sin", "sobre", "también", "tambien", "me", "hasta", "hay", | |
| "donde", "han", "quien", "entre", "está", "esta", "ser", "son", | |
| } | |
| def tokenize(text: str) -> List[str]: | |
| text = text.lower() | |
| return re.findall(r"[a-záéíóúüñ]+", text, flags=re.IGNORECASE) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment