I have a Python script that fetches data from an API (specifically www.nseindia.com/api/corporate-announcements). When I run the script locally in PyCharm, it executes without any issues and fetches the data quickly. However, when I run the same script on PythonAnywhere, I encounter a timeout error:

HTTPSConnectionPool(host='www.nseindia.com', port=443): Read timed out. (read timeout=300)

My Python Code

import requests
import pandas as pd
import gspread
from oauth2client.service_account import ServiceAccountCredentials
import schedule
import time
import numpy as np


# Define Google Sheets credentials
scope = ['https://spreadsheets.google.com/feeds',
         'https://www.googleapis.com/auth/drive']
credentials = ServiceAccountCredentials.from_json_keyfile_name(
    'announcement-capture-7bef8a7ce6eb.json', scope)
client = gspread.authorize(credentials)

# Google Sheets document ID
sheet_id = '1NKSFgnIUB3dW7Y0ZHCfXRd-B6QEYmCdW3km8g61X_bM'

headers = {
    'Accept-Encoding': 'gzip, deflate, br, zstd',
    'Accept-Language': 'en-US,en;q=0.9',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
}

baseurl = 'https://www.nseindia.com/'
url = 'https://www.nseindia.com/api/corporate-announcements?index=equities'


def get_announcements_nse():
    try:
        session = requests.Session()
        request = session.get(baseurl, headers=headers, timeout=300)
        cookies = dict(request.cookies)

        data = session.get(url, headers=headers, timeout=300, cookies=cookies)
        data.raise_for_status()  # Raise HTTPError for bad responses
        json_data = data.json()
        if not json_data:  # Check if JSON data is empty
            print("No announcements found.")
            return pd.DataFrame(
                columns=['Symbol', 'Name', 'Description', 'Announcement_Date', 'Announcement_Text', 'Attachment_File'])
        else:
            # Select only the desired columns from the JSON response
            selected_columns = ['symbol', 'sm_name', 'desc', 'an_dt', 'attchmntText', 'attchmntFile']
            # Create the DataFrame with selected columns
            announcements = pd.DataFrame(json_data)[selected_columns]
            # Rename the columns to match your Google Sheets column names
            announcements.columns = ['Symbol', 'Name', 'Description', 'Announcement_Date', 'Announcement_Text',
                                     'Attachment_File']

            # Filter out announcements with specific keywords in 'Description' column
            keywords_to_skip = ['Disclosure', 'Certificate', 'Spurt', 'Loss', 'Duplicate', 'Share Certificate',
                                'Price Movement', 'Price']
            announcements_filtered = announcements[
                ~announcements['Description'].str.contains('|'.join(keywords_to_skip),
                                                           case=False)]
            return announcements_filtered
    except (requests.exceptions.RequestException, ValueError) as e:
        print(f"An error occurred: {e}")
        return pd.DataFrame(
            columns=['Symbol', 'Name', 'Description', 'Announcement_Date', 'Announcement_Text', 'Attachment_File'])


def update_google_sheet():
    # Get NSE announcements
    announcements_nse = get_announcements_nse()

    # Open the Google Sheets document by ID
    sheet = client.open_by_key(sheet_id).sheet1

    # Define the expected headers
    expected_headers = ['Symbol', 'Name', 'Description', 'Announcement_Date', 'Attachment_Text', 'Attachment_File']

    # If the sheet is empty with only column names, directly add all NSE announcements
    if len(sheet.get_all_values()) == 1:  # Check if the sheet has only column names
        # Replace NaN values with a placeholder
        announcements_nse.replace({np.nan: ''}, inplace=True)
        for index, row in announcements_nse.iterrows():
            # Construct the URL with the symbol
            url = f'https://www.nseindia.com/get-quotes/equity?symbol={row["Symbol"]}'
            # Insert the URL into the appropriate cell in the sheet
            sheet.insert_row([url] + row.tolist()[1:], index + 2)
    else:
        # Get existing data in the sheet
        existing_data = sheet.get_all_records(expected_headers=expected_headers)

        # Convert existing data to DataFrame
        existing_df = pd.DataFrame(existing_data)

        # Filter out existing announcements from new NSE announcements
        new_announcements_nse = announcements_nse.merge(existing_df, on=['Symbol', 'Name', 'Announcement_Date'],
                                                        how='left', indicator=True)
        new_announcements_nse = new_announcements_nse[new_announcements_nse['_merge'] == 'left_only'].drop(
            columns=['_merge'])

        # Replace NaN values with a placeholder
        new_announcements_nse.replace({np.nan: ''}, inplace=True)

        # Append new NSE announcements to the top of the sheet
        for index, row in new_announcements_nse.iterrows():
            # Construct the URL with the symbol
            url = f'https://www.nseindia.com/get-quotes/equity?symbol={row["Symbol"]}'
            # Insert the URL into the appropriate cell in the sheet
            sheet.insert_row([url] + row.tolist()[1:], index + 2)

    print("NSE data updated successfully!")



# Schedule the job to run every 120 seconds
schedule.every(120).seconds.do(update_google_sheet)

while True:
    schedule.run_pending()
    time.sleep(1)

The timeout occurs consistently on PythonAnywhere, even after adjusting timeout settings in the script. What could be causing this timeout issue on PythonAnywhere, and how can I troubleshoot or resolve it? Are there any specific configurations or settings I need to adjust on PythonAnywhere to prevent the timeout?

Any insights or suggestions would be greatly appreciated! Thank you.

I tried increasing the time also to 300, but still its giving the timeout error. I am expecting to run this wihtout error same as it was running in my local computer.