backend/utils/metadata_extractor.py

"""VERIDEX — Metadata Extractor v4.0"""
import io


def extract_metadata(content: bytes, content_type: str) -> dict:
    meta = {}
    try:
        if content_type.startswith("image"):
            from PIL import Image
            from PIL.ExifTags import TAGS
            img = Image.open(io.BytesIO(content))
            meta["format"]     = img.format or "Unknown"
            meta["mode"]       = img.mode
            meta["dimensions"] = f"{img.width}x{img.height}"
            try:
                exif = img._getexif()
                if exif:
                    for k, v in exif.items():
                        tag = TAGS.get(k, k)
                        if tag in ("Make","Model","DateTime","GPSInfo","Software",
                                   "ExifVersion","FocalLength","ISOSpeedRatings",
                                   "ExposureTime","FNumber"):
                            meta[str(tag)] = str(v)[:120]
            except Exception:
                pass
        elif content_type == "application/pdf":
            try:
                import PyPDF2
                reader = PyPDF2.PdfReader(io.BytesIO(content))
                info   = reader.metadata
                if info:
                    for k, v in info.items():
                        meta[k.lstrip("/")] = str(v)[:120]
                meta["pages"] = str(len(reader.pages))
            except Exception:
                pass
    except Exception:
        pass
    return meta