Spaces:
Sleeping
Sleeping
File size: 2,476 Bytes
d684f95 35581ce d684f95 35581ce d684f95 35581ce d684f95 35581ce d684f95 35581ce d684f95 35581ce d684f95 35581ce d684f95 af5df29 35581ce d684f95 35581ce d684f95 af5df29 d684f95 af5df29 d684f95 35581ce d684f95 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
import requests
from pprint import pprint
def get_comments(video_id, max_comment_size, api_key):
"""Yields all `commentThreads` from a YouTube video in batches."""
# Get comments from the first page
response = get_response(video_id, api_key, max_results=100)
comment_list = response_to_comments(response, max_comment_size)
# Get comments from the other pages
while 'nextPageToken' in response.keys():
response = get_response(
video_id, api_key, page_token=response['nextPageToken'])
comment_list += (response_to_comments(response, max_comment_size))
return comment_list
def get_response(video_id, api_key, page_token=None, max_results=100):
"""Gets the response from YouTube API and converts it to JSON."""
url = 'https://youtube.googleapis.com/youtube/v3/commentThreads'
payload = {
'videoId': video_id,
'key': api_key,
'maxResults': max_results,
'part': 'snippet',
'pageToken': page_token,
}
response = requests.get(url, params=payload)
return response.json()
def response_to_comments(response, max_comment_size):
"""Converts JSON response to `comment_list` dict."""
comment_list = []
for full_comment in response['items']:
comment = full_comment['snippet']
can_reply = comment['canReply']
total_reply_count = comment['totalReplyCount']
comment = comment['topLevelComment']
comment_id = comment['id']
comment = comment['snippet']
# Skip if comment is too long
if len(comment['textDisplay']) > max_comment_size:
continue
try:
comment_list.append({
'comment_id': comment_id,
'video_id': comment['videoId'],
'channel_id': comment['authorChannelId']['value'],
'author_display_name': comment['authorDisplayName'],
'text_original': comment['textOriginal'],
'text_display': comment['textDisplay'],
'published_at': comment['publishedAt'].replace('T', ' ')[:-1],
'updated_at': comment['updatedAt'].replace('T', ' ')[:-1],
'like_count': comment['likeCount'],
'can_reply': can_reply,
'total_reply_count': total_reply_count,
})
except Exception as e:
print(f"Error: {e}\nComment:")
pprint(full_comment)
return comment_list
|