Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import pandas as pd | |
| from googleapiclient.discovery import build | |
| from googleapiclient.errors import HttpError | |
| import time | |
| # Streamlit UI | |
| st.title("YouTube Video Comments Extractor") | |
| # User input for API key and video ID | |
| api_key = st.text_input("Enter your YouTube API Key", type="password") | |
| video_id = st.text_input("Enter the Video ID") | |
| # Function to extract comments from a video | |
| def get_video_comments(api_key, video_id): | |
| youtube = build('youtube', 'v3', developerKey=api_key) | |
| comments = [] | |
| next_page_token = None | |
| progress_bar = st.progress(0) # Initialize progress bar | |
| while True: | |
| try: | |
| response = youtube.commentThreads().list( | |
| part='snippet,replies', | |
| videoId=video_id, | |
| maxResults=100, | |
| pageToken=next_page_token | |
| ).execute() | |
| for item in response['items']: | |
| comment = item['snippet']['topLevelComment']['snippet'] | |
| comments.append({ | |
| 'VideoID': video_id, | |
| 'Channel': comment.get('authorChannelUrl', ''), | |
| 'CommentedDateTime': comment['publishedAt'], | |
| 'NumOfCommentlikes': comment['likeCount'], | |
| 'NumOfCommentDislikes': 0, | |
| 'NumOfReplies': item['snippet']['totalReplyCount'], | |
| 'Comment': comment['textDisplay'], | |
| 'CommentedUserID': comment['authorChannelId']['value'], | |
| 'RepliedUserID': '', | |
| 'Reply': '', | |
| 'RepliesLikes': 0, | |
| 'RepliesDislike': 0, | |
| 'ToWhomTheyReplied': '', | |
| 'Comment|repliedTime': comment['updatedAt'], | |
| 'VideoUploadedtimeanddate': '' | |
| }) | |
| # Handle replies (if any) | |
| if 'replies' in item: | |
| for reply in item['replies']['comments']: | |
| reply_snippet = reply['snippet'] | |
| comments.append({ | |
| 'VideoID': video_id, | |
| 'Channel': reply_snippet.get('authorChannelUrl', ''), | |
| 'CommentedDateTime': reply_snippet['publishedAt'], | |
| 'NumOfCommentlikes': reply_snippet['likeCount'], | |
| 'NumOfCommentDislikes': 0, | |
| 'NumOfReplies': 0, | |
| 'Comment': '', | |
| 'CommentedUserID': '', | |
| 'RepliedUserID': reply_snippet['authorChannelId']['value'], | |
| 'Reply': reply_snippet['textDisplay'], | |
| 'RepliesLikes': reply_snippet['likeCount'], | |
| 'RepliesDislike': 0, | |
| 'ToWhomTheyReplied': reply_snippet['parentId'], | |
| 'Comment|repliedTime': reply_snippet['updatedAt'], | |
| 'VideoUploadedtimeanddate': '' | |
| }) | |
| next_page_token = response.get('nextPageToken') | |
| if not next_page_token: | |
| break | |
| # Update the progress bar (you may want to adjust the value) | |
| progress_bar.progress(min(100, len(comments) // 10)) | |
| except HttpError as e: | |
| st.error(f"An error occurred: {e}") | |
| break | |
| return comments | |
| # Action button | |
| if st.button("Extract Comments"): | |
| if api_key and video_id: | |
| st.text("Extracting comments... This might take a while.") | |
| comments_data = get_video_comments(api_key, video_id) | |
| progress_bar = st.progress(100) | |
| time.sleep(1) # Just to simulate completion delay | |
| progress_bar.empty() | |
| if comments_data: | |
| df_comments = pd.DataFrame(comments_data) | |
| csv_file = f"{video_id}.csv" | |
| df_comments.to_csv(csv_file, index=False) | |
| st.success(f"Comments extracted and saved to {csv_file}") | |
| # Show dataframe details | |
| st.write("First 5 rows of the extracted comments:") | |
| st.dataframe(df_comments.head()) | |
| st.write("DataFrame Info:") | |
| buffer = st.text("") | |
| df_comments.info(buf=buffer) | |
| st.text(buffer) | |
| st.write("DataFrame Description:") | |
| st.dataframe(df_comments.describe()) | |
| st.download_button(label="Download CSV", data=df_comments.to_csv(index=False), file_name=csv_file, mime='text/csv') | |
| else: | |
| st.warning("No comments found or an error occurred.") | |
| else: | |
| st.warning("Please enter both API key and Video ID.") | |