from fastapi import FastAPI, Depends , Request,WebSocket from fastapi.security import OAuth2PasswordBearer import requests import webbrowser import base64 import logging import time import asyncio import PyPDF2 from docx import Document from PIL import Image import pytesseract import io app = FastAPI() oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token") # Replace these with your own values from the Google Developer Console # GOOGLE_CLIENT_ID = "" # GOOGLE_CLIENT_SECRET = "" # GOOGLE_REDIRECT_URI = "" GOOGLE_CLIENT_ID = "485753721652-5uta3e18va2g6cnkldib2d68q39t4vod.apps.googleusercontent.com" GOOGLE_CLIENT_SECRET = "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" GOOGLE_REDIRECT_URI = "https://omkar008-receipt-radar-test.hf.space/test" # Configure the logger logging.basicConfig(level=logging.DEBUG) logger = logging.getLogger(__name__) @app.get("/") async def login_google(): # oauth_url = f"https://accounts.google.com/o/oauth2/auth?response_type=code&client_id={GOOGLE_CLIENT_ID}&redirect_uri={GOOGLE_REDIRECT_URI}&scope=openid%20profile%20email&access_type=offline" #Below is the URL to prompt the user to login to his specified gmail account and also give a readonly access to his gmail oauth_url_hr = f"https://accounts.google.com/o/oauth2/auth?response_type=code&client_id={GOOGLE_CLIENT_ID}&redirect_uri={GOOGLE_REDIRECT_URI}&scope=openid%20profile%20email%20https://www.googleapis.com/auth/gmail.readonly&access_type=offline" return { "url_hr": oauth_url_hr } app.get("/test") async def test_google(code:str): token_url = "https://accounts.google.com/o/oauth2/token" print("Printing authorisation token") print(code) data = { "code": code, "client_id": GOOGLE_CLIENT_ID, "client_secret": GOOGLE_CLIENT_SECRET, "redirect_uri": GOOGLE_REDIRECT_URI, "grant_type": "authorization_code", } response = requests.post(token_url, data=data) access_token = response.json().get("access_token") print("printing access token , yo yo test") print(access_token) # if not access_token: # raise HTTPException(status_code=400, detail="Authorization code not provided") print("Entered this function, for testing purposes") brand_name = "louis vuitton" user_info = requests.get("https://www.googleapis.com/oauth2/v1/userinfo", headers={"Authorization": f"Bearer {access_token}"}) page_token = None messages = [] user_query = f"subject:((receipt {brand_name}) OR (receipts {brand_name}) OR (reçu {brand_name}) OR (reçus {brand_name}) OR (Quittung {brand_name}) OR (Quittungen {brand_name}) OR (aankoopbon {brand_name}) OR (aankoopbonnen {brand_name}) OR (recibo {brand_name}) OR (recibos {brand_name}) OR (ricevuta {brand_name}) OR (ricevute {brand_name}) OR (ontvangstbewijs {brand_name}) OR (ontvangstbewijzen {brand_name})) has:attachment" while True: # Construct Gmail API request with pageToken gmail_url = f"https://www.googleapis.com/gmail/v1/users/me/messages?q={user_query}" if page_token: gmail_url += f"&pageToken={page_token}" gmail_response = requests.get(gmail_url, headers={"Authorization": f"Bearer {access_token}"}) gmail_data = gmail_response.json() # Check if there are messages in the response if "messages" in gmail_data: messages.extend(gmail_data["messages"]) # Check if there are more pages if "nextPageToken" in gmail_data: page_token = gmail_data["nextPageToken"] else: break # No more pages, exit the loop unique_thread_ids = set() filtered_data_list = [] for entry in messages: thread_id = entry['threadId'] if thread_id not in unique_thread_ids: unique_thread_ids.add(thread_id) filtered_data_list.append(entry) attachments = [] attachment_no = 0 data_new = {} for i,message in enumerate(messages) : # print(i) # print(message) if message: message_id = message.get("id") print(message_id) if message_id: message_url = f"https://www.googleapis.com/gmail/v1/users/me/messages/{message_id}" message_response = requests.get(message_url, headers={"Authorization": f"Bearer {access_token}"}) message_data = message_response.json() if "payload" in message_data: payload = message_data["payload"] if "body" in payload and "data" in payload["body"]: body_data = payload["body"]["data"] body_content = base64.urlsafe_b64decode(body_data.encode("UTF-8")).decode("UTF-8") print("Body Content:") print(body_content) # Check for parts in the message payload if "payload" in message_data and "parts" in message_data["payload"]: for part in message_data["payload"]["parts"]: if "body" in part and "attachmentId" in part["body"]: attachment_id = part["body"]["attachmentId"] attachment_url = f"https://www.googleapis.com/gmail/v1/users/me/messages/{message_id}/attachments/{attachment_id}" attachment_response = requests.get(attachment_url, headers={"Authorization": f"Bearer {access_token}"}) attachment_data = attachment_response.json() data = attachment_data.get("data") filename = part.get("filename", "untitled.txt") if data: data_new[filename]=data # attachment_content = base64.urlsafe_b64decode(data) # extracted_text = await extract_text_from_attachment(filename, attachment_content) attachment_no+=1 return {"attachment_count":attachment_no,"attachment_content":data_new} @app.post("/auth/google") async def auth_google(request: Request): data = await request.json() code = data.get("access_token") brand_name = data.get("brand_name") print("Printing the access token") print(code) if not code: raise HTTPException(status_code=400, detail="Authorization code not provided") access_token_new = code user_info = requests.get("https://www.googleapis.com/oauth2/v1/userinfo", headers={"Authorization": f"Bearer {access_token_new}"}) page_token = None messages = [] user_query = f"subject:((receipt {brand_name}) OR (receipts {brand_name}) OR (reçu {brand_name}) OR (reçus {brand_name}) OR (Quittung {brand_name}) OR (Quittungen {brand_name}) OR (aankoopbon {brand_name}) OR (aankoopbonnen {brand_name}) OR (recibo {brand_name}) OR (recibos {brand_name}) OR (ricevuta {brand_name}) OR (ricevute {brand_name}) OR (ontvangstbewijs {brand_name}) OR (ontvangstbewijzen {brand_name})) has:attachment" while True: # Construct Gmail API request with pageToken gmail_url = f"https://www.googleapis.com/gmail/v1/users/me/messages?q={user_query}" if page_token: gmail_url += f"&pageToken={page_token}" gmail_response = requests.get(gmail_url, headers={"Authorization": f"Bearer {access_token_new}"}) gmail_data = gmail_response.json() # Check if there are messages in the response if "messages" in gmail_data: messages.extend(gmail_data["messages"]) # Check if there are more pages if "nextPageToken" in gmail_data: page_token = gmail_data["nextPageToken"] else: break # No more pages, exit the loop attachments = [] attachment_no = 0 data_new = {} for i,message in enumerate(messages) : # print(i) # print(message) if message: message_id = message.get("id") print(message_id) if message_id: message_url = f"https://www.googleapis.com/gmail/v1/users/me/messages/{message_id}" message_response = requests.get(message_url, headers={"Authorization": f"Bearer {access_token_new}"}) message_data = message_response.json() if "payload" in message_data: payload = message_data["payload"] if "body" in payload and "data" in payload["body"]: body_data = payload["body"]["data"] body_content = base64.urlsafe_b64decode(body_data.encode("UTF-8")).decode("UTF-8") print("Body Content:") print(body_content) # Check for parts in the message payload if "payload" in message_data and "parts" in message_data["payload"]: for part in message_data["payload"]["parts"]: if "body" in part and "attachmentId" in part["body"]: attachment_id = part["body"]["attachmentId"] attachment_url = f"https://www.googleapis.com/gmail/v1/users/me/messages/{message_id}/attachments/{attachment_id}" attachment_response = requests.get(attachment_url, headers={"Authorization": f"Bearer {access_token_new}"}) attachment_data = attachment_response.json() data = attachment_data.get("data") filename = part.get("filename", "untitled.txt") if data: data_new[filename]=data attachment_content = base64.urlsafe_b64decode(data) extracted_text = await extract_text_from_attachment(filename, attachment_content) attachment_no+=1 return {"attachment_count":attachment_no,"attachment_content":data_new} async def send_chunked_data(websocket: WebSocket, filename: str, data: str): chunk_size = 1024 # Set an appropriate chunk size for i in range(0, len(data), chunk_size): await websocket.send_json({"filename": filename, "data_chunk": data[i:i + chunk_size]}) await asyncio.sleep(0.4) await websocket.send_text("FinishedThisAttachment") async def extract_text_from_pdf(pdf_data): with io.BytesIO(pdf_data) as pdf_file: pdf_reader = PyPDF2.PdfReader(pdf_file) text = "" for page_num in range(len(pdf_reader.pages)): page = pdf_reader.pages[page_num] text += page.extract_text() return text async def extract_text_from_docx(docx_data): doc = Document(io.BytesIO(docx_data)) text = "" for para in doc.paragraphs: text += para.text + "\n" return text async def extract_text_from_attachment(filename, data): if filename.endswith('.pdf'): return await extract_text_from_pdf(data) elif filename.endswith('.docx'): return await extract_text_from_docx(data) else: # Add handling for other document types if needed return "Unsupported document type" @app.websocket("/ws") async def test_websocket(websocket: WebSocket): await websocket.accept() logger.info("Hi hi succefull in connecting !!") data = await websocket.receive_text() logger.info("Received JSON data: %s", data) def get_messages(code:str): logging.info("entered into the get_messages") access_token = code print("printing access_token") print(access_token) page_token = None messages = [] jobs_query = "subject:receipt OR subject:receipts has:attachment" while True: # Construct Gmail API request with pageToken print("into the gmail") gmail_url = f"https://www.googleapis.com/gmail/v1/users/me/messages?q={jobs_query}" if page_token: gmail_url += f"&pageToken={page_token}" gmail_response = requests.get(gmail_url, headers={"Authorization": f"Bearer {access_token}"}) logging.info(f"{gmail_response}") print(gmail_response) gmail_data = gmail_response.json() # Check if there are messages in the response if "messages" in gmail_data: messages.extend(gmail_data["messages"]) # Check if there are more pages if "nextPageToken" in gmail_data: page_token = gmail_data["nextPageToken"] else: break # No more pages, exit the loop print("returning the messages") unique_thread_ids = set() filtered_data_list = [] for entry in messages: thread_id = entry['threadId'] if thread_id not in unique_thread_ids: unique_thread_ids.add(thread_id) filtered_data_list.append(entry) return filtered_data_list async def event_generator(code:str): logging.info("entered into the event_generator") access_token = code messages=get_messages(access_token) print(len(messages)) await websocket.send_json({"total_messages":len(messages)}) await websocket.send_text("CompletedSendingTotalMessagesLength") attachments = [] prev_data="" data_new={} attachment_no=0 batch_size = 5 prev_filename = None for i,message in enumerate(messages) : print(i) logging.info(f"{i}") logging.info(f"{message}") print(message) if message: message_id = message.get("id") thread_id = message.get("threadId") print(message_id) if message_id: message_url = f"https://www.googleapis.com/gmail/v1/users/me/messages/{message_id}" message_response = requests.get(message_url, headers={"Authorization": f"Bearer {access_token}"}) message_data = message_response.json() # Check for parts in the message payload if "payload" in message_data and "parts" in message_data["payload"]: for part in message_data["payload"]["parts"]: if "body" in part and "attachmentId" in part["body"]: attachment_id = part["body"]["attachmentId"] print(attachment_id) attachment_url = f"https://www.googleapis.com/gmail/v1/users/me/messages/{message_id}/attachments/{attachment_id}" attachment_response = requests.get(attachment_url, headers={"Authorization": f"Bearer {access_token}"}) attachment_data = attachment_response.json() data = attachment_data.get("data",{}) filename = part.get("filename", "untitled.txt") if data: data_new[filename]=str(data[:10]) attachment_content = base64.urlsafe_b64decode(data) logging.info(filename) extracted_text = await extract_text_from_attachment(filename, attachment_content) logging.info(extracted_text) await send_chunked_data(websocket, filename, data) attachment_no+=1 await websocket.send_text("CompletedFetchingMessages") await event_generator(data) logging.info("Closing connection") await websocket.close()