Fetch YouTube Comments

import os
import csv
import json
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
from google.oauth2.credentials import Credentials

def save_state(state):
    with open("fetch_state.json", "w") as f:
        json.dump(state, f)

def load_state():
    try:
        with open("fetch_state.json", "r") as f:
            return json.load(f)
    except FileNotFoundError:
        return None

def get_authenticated_service(clients_secret_file):
    creds = None
    if os.path.exists("token.json"):
        creds = Credentials.from_authorized_user_file("token.json", ['https://www.googleapis.com/auth/youtube.force-ssl'])
    if not creds or not creds.valid:
        if creds and creds.expired and creds.refresh_token:
            creds.refresh(Request())
        else:
            flow = InstalledAppFlow.from_client_secrets_file(clients_secret_file, ['https://www.googleapis.com/auth/youtube.force-ssl'])
            creds = flow.run_local_server(port=0)
        with open("token.json", 'w') as token:
            token.write(creds.to_json())
    return build('youtube', 'v3', credentials=creds)

def fetch_video_privacy(authentication, video_id):
    try:
        request = authentication.videos().list(
            part="status",
            id=video_id
        )
        response = request.execute()
        items = response.get('items', [])
        item = items[0] 
        privacy_status = item['status']['privacyStatus']
        return privacy_status
    except Exception as e:
        print(f"Error fetching details: {e}")
        return None
        
authentication = get_authenticated_service('YOUR_CLIENTS_SECRET_FILE')
channel_id = 'CHANNEL_ID'
start_date = 'YYYY-MM-DDT00:00:00Z'
end_date = 'YYYY-MM-DDT23:59:59Z'

with open('youtube_comments.csv', 'a', newline='', encoding='utf-8') as csvfile:
    writer = csv.writer(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_ALL)
    if csvfile.tell() == 0:
        writer.writerow(['Comment', 'User', 'Profile Picture', 'Video ID', 'Video Privacy', 'Time', 'Testimonial Worthy'])

    def fetch_comments_over_time(youtube, start_date, end_date):
        state = load_state()
        if state:
            next_page_token = state.get("next_page_token")
            if state.get("last_fetched_date") != None:
                last_fetched_date = state.get("last_fetched_date") 
                end_date = last_fetched_date
        else:
            next_page_token = None
            last_fetched_date = start_date

        all_comments = 0
        try:
            while True:
                response = youtube.commentThreads().list(
                    part="snippet",
                    allThreadsRelatedToChannelId=channel_id,
                    pageToken=next_page_token,
                    maxResults=100,  
                    textFormat="plainText",
                    order="time",
                ).execute()

                for item in response['items']:
                    comment = item['snippet']['topLevelComment']['snippet']['textDisplay']
                    user_name = item['snippet']['topLevelComment']['snippet']['authorDisplayName']
                    user_image = item['snippet']['topLevelComment']['snippet']['authorProfileImageUrl']
                    date = item['snippet']['topLevelComment']['snippet']['publishedAt']
                    video_id = item['snippet']['videoId']
                    video_privacy = fetch_video_privacy(youtube, video_id)
                    
                    if date < start_date:
                        raise Exception("Date out of range")
                    
                    if start_date <= date < end_date:
                        writer.writerow([comment, user_name, user_image, video_id, video_privacy, date, ''])  # Write each comment as fetched
                        last_fetched_date = date
                        all_comments = all_comments + 1
                        print(all_comments)

                save_state({
                "next_page_token": next_page_token,
                "last_fetched_date": last_fetched_date,
                })

                next_page_token = response.get('nextPageToken')
                if next_page_token:
                    print("Next Page Toke: " + next_page_token)
                if not next_page_token:
                    print("No more comments.")
                    break
              
        except Exception as e:
            print(f"Error during comment fetch: {e}")

    fetch_comments_over_time(authentication, start_date, end_date)