matcher-neighbour.pu

import time
import pandas as pd
import requests

# Set headers for the OpenStreetMap API request
headers = {
    "User-Agent": "MyPythonApp/1.0 ([email protected])"
}

# Read the CSV file
df = pd.read_csv('neighhbourdata.csv')

# Counter to keep track of the number of rows processed
counter = 0

# Iterate over the rows of the DataFrame
for index, row in df.iterrows():
    print(counter)
    if row["Read"] == True:
        print("True line")
  
    if row["Read"] == False:
        print("False line")        
        if counter >= 1000 :  # Stop after processing 3 rows
            break
      
        # Format the query for the OpenStreetMap API
        query = f'{row["CityName"].replace(" ", "")}, {row["DistrictName"]}, {row["neighbourhood"]}'
        url = f'https://nominatim.openstreetmap.org/search?q={query}&format=json'
        print(url)
     
        response = requests.get(url, headers=headers)   
      
        if response.status_code == 200:
            data = response.json()
            print(data)
            if data:  # Check if data is not empty
                # Update the DataFrame with the latitude and longitude
                df.at[index, 'Lat'] = data[0]["lat"]  # Latitude
                df.at[index, 'Long'] = data[0]["lon"]  # Longitude
                df.at[index, 'Read'] = True  # Mark the row as read
                df.at[index, 'URL'] = url
                df.at[index, 'Emoty'] = False
                print(f"Processed row {index}: {query} -> Lat: {data[0]['lat']}, Lon: {data[0]['lon']}")
            if not data:
                df.at[index, 'Lat'] = ""
                df.at[index, 'Long'] = ""
                df.at[index, 'Read'] = True  # Mark the row as read
                df.at[index, 'URL'] = url
                df.at[index, 'Emoty'] = True

        else:
            print(f"Failed to fetch data for: {query}")
     
        counter += 1

        # Add a delay to avoid hitting API rate limits
        time.sleep(5)

   

# Save the updated DataFrame to a new CSV file (or overwrite the existing one)
df.to_csv('neighhbourdata.csv', index=False)

# Print the updated DataFrame
print("\nUpdated DataFrame:")
print(df)