Diarios-Oficiais-ALEMS/diarios/models.py

from django.db import models
import PyPDF2
import json


class PDFDocument(models.Model):
    title = models.CharField(max_length=255)
    file = models.FileField(upload_to="pdfs/")
    content = models.TextField(blank=True)
    uploaded_at = models.DateTimeField(auto_now_add=True)
    page_content = models.TextField(blank=True)

    def __str__(self):
        return self.title

    def save(self, *args, **kwargs):
        if self.file:
            pdf = PyPDF2.PdfReader(self.file)
            texto = []
            pages_data = []

            for i, pagina in enumerate(pdf.pages):
                page_text = pagina.extract_text()
                pages_data.append(
                    {
                        "number": i + 1,
                        "content": page_text,
                    }
                )
                texto.append(pagina.extract_text())
            self.content = "\n".join(texto)
            self.page_content = json.dumps(pages_data)

        super().save(*args, **kwargs)