Based on stvar' answer and the original publication here I built this code:
import os
import pickle
import csv
import json
import google.oauth2.credentials
from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
CLIENT_SECRETS_FILE = "client_secret.json" # for more information to create your credentials json please visit https://python.gotrained.com/youtube-api-extracting-comments/
SCOPES = ['https://www.googleapis.com/auth/youtube.force-ssl']
API_SERVICE_NAME = 'youtube'
API_VERSION = 'v3'
def get_authenticated_service():
credentials = None
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
credentials = pickle.load(token)
# Check if the credentials are invalid or do not exist
if not credentials or not credentials.valid:
# Check if the credentials have expired
if credentials and credentials.expired and credentials.refresh_token:
credentials.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
CLIENT_SECRETS_FILE, SCOPES)
credentials = flow.run_console()
# Save the credentials for the next run
with open('token.pickle', 'wb') as token:
pickle.dump(credentials, token)
return build(API_SERVICE_NAME, API_VERSION, credentials = credentials)
def get_video_comments(service, **kwargs):
request = service.commentThreads().list(**kwargs)
comments = []
while request:
response = request.execute()
for comment in response['items']:
reply_count = comment['snippet'] \
['totalReplyCount']
replies = comment.get('replies')
if replies is not None and \
reply_count != len(replies['comments']):
replies['comments'] = get_comment_replies(
service, comment['id'])
# 'comment' is a 'CommentThreads Resource' that has it's
# 'replies.comments' an array of 'Comments Resource'
# Do fill in the 'comments' data structure
# to be provided by this function:
comments.append(comment)
request = service.commentThreads().list_next(
request, response)
return comments
def get_comment_replies(service, comment_id):
request = service.comments().list(
parentId = comment_id,
part = 'id,snippet',
maxResults = 1000
)
replies = []
while request:
response = request.execute()
replies.extend(response['items'])
request = service.comments().list_next(
request, response)
return replies
if __name__ == '__main__':
# When running locally, disable OAuthlib's HTTPs verification. When
# running in production *do not* leave this option enabled.
os.environ['OAUTHLIB_INSECURE_TRANSPORT'] = '1'
service = get_authenticated_service()
videoId = input('Enter Video id : ') # video id here (the video id of https://www.youtube.com/watch?v=vedLpKXzZqE -> is vedLpKXzZqE)
comments = get_video_comments(service, videoId=videoId, part='id,snippet,replies', maxResults = 1000)
with open('youtube_comments', 'w', encoding='UTF8') as f:
writer = csv.writer(f, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
for row in comments:
# convert the tuple to a list and write to the output file
writer.writerow([row])
it returns a file called youtube_comments with this format:
"{'kind': 'youtube#commentThread', 'etag': 'gvhv4hkH0H2OqQAHQKxzfA-K_tA', 'id': 'UgzSgI1YEvwcuF4cPwN4AaABAg', 'snippet': {'videoId': 'tGTaBt4Hfd0', 'topLevelComment': {'kind': 'youtube#comment', 'etag': 'qpuKZcuD4FKf6BHgRlMunersEeU', 'id': 'UgzSgI1YEvwcuF4cPwN4AaABAg', 'snippet': {'videoId': 'tGTaBt4Hfd0', 'textDisplay': 'This is a comment', 'textOriginal': 'This is a comment', 'authorDisplayName': 'Gabriell Magana', 'authorProfileImageUrl': 'https://yt3.ggpht.com/ytc/AKedOLRGBvo2ZncDP1xGjlX6anfUufNYi9b3w9kYZFDl=s48-c-k-c0x00ffffff-no-rj', 'authorChannelUrl': 'http://www.youtube.com/channel/UCKAa4FYftXsN7VKaPSlCivg', 'authorChannelId': {'value': 'UCKAa4FYftXsN7VKaPSlCivg'}, 'canRate': True, 'viewerRating': 'none', 'likeCount': 8, 'publishedAt': '2019-05-22T12:38:34Z', 'updatedAt': '2019-05-22T12:38:34Z'}}, 'canReply': True, 'totalReplyCount': 0, 'isPublic': True}}"
"{'kind': 'youtube#commentThread', 'etag': 'DsgDziMk7mB7xN4OoX7cmqlbDYE', 'id': 'UgytsI51LU6BWRmYtBB4AaABAg', 'snippet': {'videoId': 'tGTaBt4Hfd0', 'topLevelComment': {'kind': 'youtube#comment', 'etag': 'NYjvYM9W_umBafAfQkdg1P9apgg', 'id': 'UgytsI51LU6BWRmYtBB4AaABAg', 'snippet': {'videoId': 'tGTaBt4Hfd0', 'textDisplay': 'This is another comment', 'textOriginal': 'This is another comment', 'authorDisplayName': 'Mary Montes', 'authorProfileImageUrl': 'https://yt3.ggpht.com/ytc/AKedOLTg1b1yw8BX8Af0PoTR_t5OOwP9Cfl9_qL-o1iikw=s48-c-k-c0x00ffffff-no-rj', 'authorChannelUrl': 'http://www.youtube.com/channel/UC_GP_8HxDPsqJjJ3Fju_UeA', 'authorChannelId': {'value': 'UC_GP_8HxDPsqJjJ3Fju_UeA'}, 'canRate': True, 'viewerRating': 'none', 'likeCount': 9, 'publishedAt': '2019-05-15T05:10:49Z', 'updatedAt': '2019-05-15T05:10:49Z'}}, 'canReply': True, 'totalReplyCount': 3, 'isPublic': True}, 'replies': {'comments': [{'kind': 'youtube#comment', 'etag': 'Tu41ENCZYNJ2KBpYeYz4qgre0H8', 'id': 'UgytsI51LU6BWRmYtBB4AaABAg.8uwduw6ppF79DbfJ9zMKxM', 'snippet': {'videoId': 'tGTaBt4Hfd0', 'textDisplay': 'this is first reply', 'parentId': 'UgytsI51LU6BWRmYtBB4AaABAg', 'authorDisplayName': 'JULIO EMPRESARIO', 'authorProfileImageUrl': 'https://yt3.ggpht.com/eYP4MBcZ4bON_pHtdbtVsyWnsKbpNKye2wTPhgkffkMYk3ZbN0FL6Aa1o22YlFjn2RVUAkSQYw=s48-c-k-c0x00ffffff-no-rj', 'authorChannelUrl': 'http://www.youtube.com/channel/UCrpB9oZZZfmBv1aQsxrk66w', 'authorChannelId': {'value': 'UCrpB9oZZZfmBv1aQsxrk66w'}, 'canRate': True, 'viewerRating': 'none', 'likeCount': 2, 'publishedAt': '2020-09-15T04:06:50Z', 'updatedAt': '2020-09-15T04:06:50Z'}}, {'kind': 'youtube#comment', 'etag': 'OrpbnJddwzlzwGArCgtuuBsYr94', 'id': 'UgytsI51LU6BWRmYtBB4AaABAg.8uwduw6ppF795E1w8RV1DJ', 'snippet': {'videoId': 'tGTaBt4Hfd0', 'textDisplay': 'the second replay', 'textOriginal': 'the second replay', 'parentId': 'UgytsI51LU6BWRmYtBB4AaABAg', 'authorDisplayName': 'Anatolio27 Diaz', 'authorProfileImageUrl': 'https://yt3.ggpht.com/ytc/AKedOLR1hOySIxEkvRCySExHjo3T6zGBNkvuKpPkqA=s48-c-k-c0x00ffffff-no-rj', 'authorChannelUrl': 'http://www.youtube.com/channel/UC04N8BM5aUwDJf-PNFxKI-g', 'authorChannelId': {'value': 'UC04N8BM5aUwDJf-PNFxKI-g'}, 'canRate': True, 'viewerRating': 'none', 'likeCount': 2, 'publishedAt': '2020-02-19T18:21:06Z', 'updatedAt': '2020-02-19T18:21:06Z'}}, {'kind': 'youtube#comment', 'etag': 'sPmIwerh3DTZshLiDVwOXn_fJx0', 'id': 'UgytsI51LU6BWRmYtBB4AaABAg.8uwduw6ppF78wwH6Aabh4y', 'snippet': {'videoId': 'tGTaBt4Hfd0', 'textDisplay': 'A third reply', 'textOriginal': 'A third reply', 'parentId': 'UgytsI51LU6BWRmYtBB4AaABAg', 'authorDisplayName': 'Voy detrás de mi pasión', 'authorProfileImageUrl': 'https://yt3.ggpht.com/ytc/AKedOLTgzZ3ZFvkmmAlMzA77ApM-2uGFfvOBnzxegYEX=s48-c-k-c0x00ffffff-no-rj', 'authorChannelUrl': 'http://www.youtube.com/channel/UCvv6QMokO7KcJCDpK6qZg3Q', 'authorChannelId': {'value': 'UCvv6QMokO7KcJCDpK6qZg3Q'}, 'canRate': True, 'viewerRating': 'none', 'likeCount': 2, 'publishedAt': '2019-07-03T18:45:34Z', 'updatedAt': '2019-07-03T18:45:34Z'}}]}}"
Now it is necessary a second step in order to information required. For this I a set of bash script toos like cut, awk and set:
cut -d ":" -f 10- youtube_comments | sed -e "s/', '/\n/g" -e "s/'//g" | awk '/replies/{print "------------------------****---------::: Replies: "$6" :::---------******--------------------------------"}!/replies/{print}' |sed '/^textOriginal:/,/^authorDisplayName:/{/^authorDisplayName/!d}' |sed '/^authorProfileImageUrl:\|^authorChannelUrl:\|^authorChannelId:\|^etag:\|^updatedAt:\|^parentId:\|^id:/d' |sed 's/<[^>]*>//g' | sed 's/{textDisplay/{\ntextDisplay/' |sed '/^snippet:/d' | awk -F":" '(NF==1){print "========================================COMMENT==========================================="}(NF>1){a=0; print $0}' | sed 's/textDisplay: //g' | sed 's/authorDisplayName/User/g' | sed 's/T[0-9]\{2\}:[0-9]\{2\}:[0-9]\{2\}Z//g' | sed 's/likeCount: /Likes:/g' | sed 's/publishedAt: //g' > output_file
The final result is a file called output_file with this format:
========================================COMMENT===========================================
This is a comment
User: Robert Everest
Likes:8, 2019-05-22
========================================COMMENT===========================================
This is another comment
User: Anna Davis
Likes:9, 2019-05-15
------------------------****---------::: Replies: 3, :::---------******--------------------------------
this is first reply
User: John Doe
Likes:2, 2020-09-15
the second replay
User: Caraqueno
Likes:2, 2020-02-19
A third reply
User: Rebeca
Likes:2, 2019-07-03
The python script requires of the file token.pickle to work, it is generated the first time the python script run and when it expired, it have to be deleted and generated again.
