A few months ago, I created a program that goes to a Youtube channel and grabs the captions from all of the channels videos and then counts the amount of times a certain word is said, and when I created this program it worked perfectly. Now I have come back to this program, but my problem is that for some reason the code no longer works.
Here is my code:
from apiclient.discovery import buildfrom youtube_transcript_api import YouTubeTranscriptApifrom pytube import YouTubeimport os# Your Google API Keyapi_key = "Your Youtube API here"# The Youtube channel you want to extract data fromchannel_id = "Youtube channel here"# Youtube Buildyoutube = build('youtube', 'v3', developerKey=api_key)def get_channel_videos(channel_id): # get Uploads playlist id res = youtube.channels().list(id=channel_id, part='contentDetails').execute() playlist_id = res['items'][0]['contentDetails']['relatedPlaylists']['uploads'] videos = [] next_page_token = None while 1: res = youtube.playlistItems().list(playlistId=playlist_id, part='snippet', maxResults=50, pageToken=next_page_token).execute() videos += res['items'] next_page_token = res.get('nextPageToken') if next_page_token is None: break return videosvideos = get_channel_videos(channel_id)video_ids = [] # list of all video_id of channelvideo_titles = []# Word to search forword1 = "firework"# Counter for the text filescounter = 1for video in videos: video_ids.append(video['snippet']['resourceId']['videoId'])# Loops through every video on the youtube channelfor video_id in video_ids: try: # Gets the transcripts of youtube videos. Only gets English transcripts. responses = YouTubeTranscriptApi.get_transcript( video_id, languages=['en']) # Get's the youtube video's link yt = YouTube("https://www.youtube.com/watch?v="+str(video_id)) #print('\n'+"Video: "+"https://www.youtube.com/watch?v="+str(video_id)+'\n'+'\n'+"Captions:") print("\n"+"Video Number: "+str(counter)+'\n'+"Video: "+"https://www.youtube.com/watch?v="+str(video_id)+'\n'+'Title: '+yt.title+'\n'+"Firework/s Wordcount:") # This is for text file generation filename = "video #" + str(counter) +".txt" # Generates text file with open(filename, "w") as file: # Writes the title of the Youtube video at the top of the text file file.write(yt.title) # Whitespace file.write("\n") # Writes all the data grabbed from the transcripts into a text file # in text form. for i in responses: file.write("{}\n".format(i)) counter += 1 file.close() # This reads data from all the generated files, # then converts all the data within the file to lowercase, # then it counts the amount of times that the word you are searching # for is used within each file that is generated. fileTest = open(filename, "r") read_data = fileTest.read() word_count = read_data.lower().count(word1) file.close() # Prints out the word count. print(word_count) for response in responses: text = response['text'] except Exception as e: print(e)#for i in responses:Here is the error I get:
Traceback (most recent call last): File "D:\Downloads\YouTube-Caption-Project-main\main.py", line 47, in <module> videos = get_channel_videos(channel_id) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Downloads\YouTube-Caption-Project-main\main.py", line 30, in get_channel_videos playlist_id = res['items'][0]['contentDetails']['relatedPlaylists']['uploads'] ~~~^^^^^^^^^KeyError: 'items'I found this problem that is of a similar vain to mine, but it didn't solve my problem: Performing google search in python with API, returned with KeyError
I tried placing the suggested code in the link, just below theres = youtube.channels().list(id=channel_id,part='contentDetails').execute() code, but in-turn, it gave me this error:
Traceback (most recent call last): File "D:\Downloads\YouTube-Caption-Project-main\main.py", line 62, in <module> for video in videos:TypeError: 'NoneType' object is not iterable