add tesseract-ocr

Dockerfile

@@ -2,11 +2,10 @@ FROM python:3.10
 
 WORKDIR /code
 # Install libgl1-mesa-glx
-RUN apt-get update && apt-get install -y libgl1-mesa-glx
+RUN apt-get update && apt-get install -y libgl1-mesa-glx tesseract-ocr libtesseract-dev 
 
 COPY ./requirements.txt /code/requirements.txt
 
-RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
 
 COPY ./app /code/app
 

app/main.py

@@ -1,9 +1,10 @@
-from fastapi import FastAPI, File, UploadFile
+from fastapi import FastAPI, File, UploadFile, HTTPException
 from fastapi.responses import JSONResponse
-from app.ocr import easyocr_ocr
+from app.ocr import easyocr_ocr, tesseract_ocr,tesseract_ocr_pdf
 
 app = FastAPI()
 
+
 @app.post("/upload/")
 async def upload_image(file: UploadFile = File(...)):
     try:
@@ -19,3 +20,26 @@ async def upload_image(file: UploadFile = File(...)):
 
     except Exception as e:
         return JSONResponse(content={"error": str(e)}, status_code=500)
+    
+@app.post("/tesseract/extract")
+async def upload_image(file: UploadFile = File(...)):
+    try:
+        # Save the uploaded file to a temporary location
+        contents = await file.read()
+        file_extension = file.filename.lower().split('.')[-1]
+        file_path = f"temp_{file.filename}"
+        print(file.filename.lower().endswith(('.pdf')))
+        with open(file_path, "wb") as f:
+            f.write(contents)
+        
+        if file_extension == 'png' or file_extension == 'jpg' or file_extension == 'jpeg':
+            ocr_result = await tesseract_ocr(file_path)
+        elif file_extension == 'pdf':
+            ocr_result = await tesseract_ocr_pdf(file_path)
+        else:
+            raise HTTPException(status_code=400, detail="Unsupported file format")
+        # ocr_result = await tesseract_ocr(file_path)
+        return JSONResponse(content={"result": ocr_result})
+        return JSONResponse(content={"formatted_output": formatted_output})
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)

app/ocr.py

@@ -1,4 +1,17 @@
 import easyocr
+import fitz
+import pytesseract
+from PIL import Image
+import cv2
+import io
+import pymupdf
+from fastapi  import HTTPException
+import numpy as np
+from pytesseract import Output
+import imutils
+
+
+pytesseract.pytesseract.tesseract_cmd = r'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
 
 def reformat_ocr_result(result):
     mapping = {
@@ -48,9 +61,77 @@ def reformat_ocr_result(result):
     print(formatted_output)
     return formatted_output
 
+async def detect_rotation(image):
+    # load the input image, convert it from BGR to RGB channel ordering,
+    # and use Tesseract to determine the text orientation
+    image = cv2.imread(image)
+    rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    results = pytesseract.image_to_osd(rgb, output_type=Output.DICT)
+    # display the orientation information
+    print("[INFO] detected orientation: {}".format(
+        results["orientation"]))
+    print("[INFO] rotate by {} degrees to correct".format(
+        results["rotate"]))
+    print("[INFO] detected script: {}".format(results["script"]))
+    # rotate the image to correct the orientation
+    rotated = imutils.rotate_bound(image, angle=results["rotate"])
+    return rotated
+
+
 def easyocr_ocr(image_path):
-    reader = easyocr.Reader(['en'])
+    reader = easyocr.Reader(['id'])
     result = reader.readtext(image_path)
     result_list = [f"{text} (confidence: {confidence:.4f})" for (bbox, text, confidence) in result]
     formatted_output = reformat_ocr_result(result_list)
     return formatted_output
+
+# Function to convert PDF page to PIL image
+def pdf_page_to_image(pdf_page):
+    # Convert PDF page to image using fitz and PIL
+    pix = pdf_page.get_pixmap()
+    img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+    return img
+
+async def tesseract_ocr_pdf(pdf_path):
+    try:
+        pdf_document = fitz.open(pdf_path)
+        text = ""
+
+        for page_number in range(len(pdf_document)):
+            page = pdf_document.load_page(page_number)
+            image = pdf_page_to_image(page)
+             # Save the image to a temporary path
+            temp_image_path = f"temp_page_{page_number}.png"
+
+            image.save(temp_image_path)
+            # Perform OCR on the saved image
+            page_text = await tesseract_ocr(temp_image_path)
+            text += page_text + "\n"
+
+        pdf_document.close()
+        return text
+    except Exception as e:
+        print(f"Error opening PDF: {e}")
+        raise HTTPException(status_code=400, detail="Error processing PDF file")
+
+async def tesseract_ocr(image_path):
+    # Grayscale, Gaussian blur, Otsu's threshold
+    image = await detect_rotation(image_path)
+    # image = cv2.imread(image_path)
+    
+    # corrected_image = correct_image_rotation(image)
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    blur = cv2.GaussianBlur(gray, (3,3), 0)
+    thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
+
+    # Morph open to remove noise and invert image
+    kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
+    opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
+    invert = 255 - opening
+    result = pytesseract.image_to_string( invert, config='--psm 6')
+    result = result.replace('\n', ' ').replace('\r', ' ').replace('  ', ' ')
+
+    return result
+
+
+

app/routers/flight.py

@@ -0,0 +1,39 @@
+from fastapi import APIRouter
+from pydantic import BaseModel
+from typing import List
+import requests
+from bs4 import BeautifulSoup
+
+router = APIRouter()
+
+# Example flight sites list
+flight_sites = [
+    {"url": "https://example.com/flight1", "threshold": 200},
+    {"url": "https://example.com/flight2", "threshold": 300},
+]
+
+class Flight(BaseModel):
+    url: str
+    threshold: float
+
+def check_price(url, threshold):
+    response = requests.get(url)
+    soup = BeautifulSoup(response.text, 'html.parser')
+    # Extracting price assuming a specific HTML class or tag
+    price = float(soup.find(class_="price").get_text().replace("$", ""))
+    return price
+
+@router.get("/", response_model=List[Flight])
+def read_flights():
+    return flight_sites
+
+@router.post("/", response_model=Flight)
+def add_flight(flight: Flight):
+    flight_sites.append(flight.dict())
+    return flight
+
+@router.delete("/", response_model=Flight)
+def remove_flight(url: str):
+    global flight_sites
+    flight_sites = [site for site in flight_sites if site["url"] != url]
+    return {"message": "Flight removed successfully", "url": url}

app/routers/webscrap.py

@@ -0,0 +1,8 @@
+from fastapi import APIRouter
+from app.routers import base
+
+router = APIRouter()
+
+@router.get("/webscrap", response_model=base.Response)
+async def webscrap():
+    return base.Response(status_code=200, detail="webscrap")

requirements.txt

@@ -1,4 +1,6 @@
 fastapi
 uvicorn
 easyocr
-pillow
+pillow
+pytesseract
+PyMuPDF