Youtube data scrape locally

 import os

from googleapiclient.discovery import build

import csv

import time

# Replace with your API key

API_KEY = "###"

# Create a YouTube Data API client

youtube = build("youtube", "v3", developerKey=API_KEY)

def get_channel_videos(channel_id):

videos = []

next_page_token = None

# Get the "uploads" playlist ID for the channel

channels_response = youtube.channels().list(

id=channel_id,

part='contentDetails'

).execute()

uploads_playlist_id = channels_response['items'][0]['contentDetails']['relatedPlaylists']['uploads']

while True:

# Fetch the videos in the "uploads" playlist

playlist_items_request = youtube.playlistItems().list(

playlistId=uploads_playlist_id,

part='snippet',

# maxResults=50,

pageToken=next_page_token

)

playlist_items_response = playlist_items_request.execute()

# Extract video IDs

video_ids = [item['snippet']['resourceId']['videoId'] for item in playlist_items_response['items']]

# Fetch video details and statistics for each video ID

videos_request = youtube.videos().list(

part="snippet,statistics",

id=','.join(video_ids)

)

videos_response = videos_request.execute()

# Process each video

for item in videos_response['items']:

video = {

"title": item['snippet']['title'],

"views": item['statistics']['viewCount'],

"video_link": f"https://www.youtube.com/watch?v={item['id']}"

}

videos.append(video)

# Check if there are more pages of results

next_page_token = playlist_items_response.get("nextPageToken")

if not next_page_token:

break

return videos

def save_to_csv(videos, file_path):

# Define the field names (columns) for the CSV file

field_names = ["Title", "Views", "Video Link"]

# Write the video information to the CSV file

with open(file_path, mode="w", newline="", encoding="utf-8") as file:

writer = csv.DictWriter(file, fieldnames=field_names)

writer.writeheader()

for video in videos:

writer.writerow({

"Title": video["title"],

"Views": video["views"],

"Video Link": video["video_link"]

})

if __name__ == "__main__":

channel_id = "UCTA395IvJGrr7LBsqVAlJsw" # Replace with the channel ID of the target channel

videos = get_channel_videos(channel_id)

# Specify the path where you want to save the CSV file

csv_file_path = "/Users/jitendersingh/Downloads/hindi med knowledge 20 apr 12 am.csv"

# Save video information to the CSV file

save_to_csv(videos, csv_file_path)

print("Video information saved to", csv_file_path) Another file create for csv correction.

import pandas as pd

import os

import time

def synchronize_csv_files(old_csv_path, new_csv_path, output_csv_path):

# Read the old and new CSV files into DataFrames

old_df = pd.read_csv(old_csv_path)

new_df = pd.read_csv(new_csv_path)

# Find the matching value in the first column of the second row in the new CSV

matching_value = old_df.iloc[1, 0]

# Delete rows from the new CSV until the matching value is found in the first column

while new_df.iloc[1, 0] != matching_value:

new_df = new_df.iloc[1:]

# Reset the index of the new DataFrame

new_df.reset_index(drop=True, inplace=True)

# Combine the rows from both CSV files into a single DataFrame

combined_df = pd.concat([old_df, new_df], axis=1)

# Save the synchronized CSV to the output file

combined_df.to_csv(output_csv_path, index=False)

def calculate_numbers(input_csv_path, output_csv_path):

# Read the synchronized CSV file into a DataFrame

df = pd.read_csv(input_csv_path)

# Calculate the result in the 6th column based on the values in the 2nd and 5th columns

df['GAP'] = df['Views.1'] - df['Views']

# Save the modified CSV to the output file with a new name

df.to_csv(output_csv_path, index=False)

channel_name = "Tech Droid Hindi"

# Example usage:

old_csv_path = "/Users/jitendersingh/Downloads/"+channel_name+" 11 apr 11 am.csv"

new_csv_path = "/Users/jitendersingh/Downloads/"+channel_name+" 12 apr 11 am.csv"

output_csv_path = "/Users/jitendersingh/Downloads/temp_csv.csv"

synchronize_csv_files(old_csv_path, new_csv_path, output_csv_path)

# Example usage:

input_csv_path = "/Users/jitendersingh/Downloads/temp_csv.csv"

output_csv_path = "/Users/jitendersingh/Downloads/"+channel_name+" 24 hours.csv"

calculate_numbers(input_csv_path, output_csv_path)

time.sleep(1)

os.remove("/Users/jitendersingh/Downloads/temp_csv.csv")