File size: 1,743 Bytes
c9331c8 5b739e4 c9331c8 5b739e4 c9331c8 5b739e4 c9331c8 5b739e4 c9331c8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | from fastapi import FastAPI, UploadFile, File, HTTPException
from paddleocr import PaddleOCR
from PIL import Image
import io, numpy as np
import fitz # pymupdf
app = FastAPI()
ocr = PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False)
@app.get("/")
def health():
return {"status": "ok"}
@app.post("/ocr")
async def run_ocr(file: UploadFile = File(...)):
try:
contents = await file.read()
all_texts = []
# Handle PDF
if file.filename.lower().endswith(".pdf"):
pdf = fitz.open(stream=contents, filetype="pdf")
for page in pdf:
pix = page.get_pixmap(dpi=200)
img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
img_array = np.array(img)
result = ocr.ocr(img_array, cls=True)
if result and result[0]:
for line in result[0]:
all_texts.append({
"text": line[1][0],
"confidence": round(line[1][1], 4)
})
# Handle image (JPG, PNG, etc)
else:
image = Image.open(io.BytesIO(contents)).convert("RGB")
img_array = np.array(image)
result = ocr.ocr(img_array, cls=True)
if result and result[0]:
for line in result[0]:
all_texts.append({
"text": line[1][0],
"confidence": round(line[1][1], 4)
})
return {"filename": file.filename, "results": all_texts}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e)) |