python - 如何使用 YouTube API v3 和 Python 从视频中获取评论？

Question

我一直在尝试使用 Python(作为学习这门语言的练习)从 YouTube 上的给定视频中获取评论(线程和回复)。

根据官方网站(https://developers.google.com/youtube/v3/docs/commentThreads/list)给出的示例，我能够得到一些评论，但不是全部。我尝试添加一些代码来处理多个页面，但我无法获取只有一个页面的视频的评论。

例如，https://www.youtube.com/watch?v=Gd_L7DVKTA8有 17 条评论(包括回复)，但我只能获得 7 个线程和 2 个回复。有趣的是，我使用上面链接提供的 API Explorer 得到了相同的结果(只有 7 个线程)。

我的代码如下:

#!/usr/bin/python

# Usage:
# python scraper.py --videoid='<video_id>'

from apiclient.errors import HttpError
from oauth2client.tools import argparser
from apiclient.discovery import build

YOUTUBE_API_SERVICE_NAME = "youtube"
YOUTUBE_API_VERSION = "v3"
DEVELOPER_KEY = 'key'


def get_comment_threads(youtube, video_id, comments):
   threads = []
   results = youtube.commentThreads().list(
     part="snippet",
     videoId=video_id,
     textFormat="plainText",
   ).execute()

  #Get the first set of comments
  for item in results["items"]:
    threads.append(item)
    comment = item["snippet"]["topLevelComment"]
    text = comment["snippet"]["textDisplay"]
    comments.append(text)

  #Keep getting comments from the following pages
  while ("nextPageToken" in results):
    results = youtube.commentThreads().list(
      part="snippet",
      videoId=video_id,
      pageToken=results["nextPageToken"],
      textFormat="plainText",
    ).execute()
    for item in results["items"]:
      threads.append(item)
      comment = item["snippet"]["topLevelComment"]
      text = comment["snippet"]["textDisplay"]
      comments.append(text)

  print "Total threads: %d" % len(threads)

  return threads


def get_comments(youtube, parent_id, comments):
  results = youtube.comments().list(
    part="snippet",
    parentId=parent_id,
    textFormat="plainText"
  ).execute()

  for item in results["items"]:
    text = item["snippet"]["textDisplay"]
    comments.append(text)

  return results["items"]

if __name__ == "__main__":
  argparser.add_argument("--videoid", help="Required; ID for video for which the comment will be inserted.")
  args = argparser.parse_args()
  youtube = build(YOUTUBE_API_SERVICE_NAME, YOUTUBE_API_VERSION, developerKey=DEVELOPER_KEY)

  try:
    output_file = open("output.txt", "w")
    comments = []
    video_comment_threads = get_comment_threads(youtube, args.videoid, comments)

    for thread in video_comment_threads:
      get_comments(youtube, thread["id"], comments)

    for comment in comments:
      output_file.write(comment.encode("utf-8") + "\n")

    output_file.close()
    print "Total comments: %d" % len(comments)

  except HttpError, e:
    print "An HTTP error %d occurred:\n%s" % (e.resp.status, e.content)

提前感谢您的任何建议!

Answer 1

我正在使用这段代码

import os
import pickle
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):
    comments = []
    results = service.commentThreads().list(**kwargs).execute()
    while results:
        for item in results['items']:
            comment = item['snippet']['topLevelComment']['snippet']['textDisplay']
            comments.append(comment)
        # Check if another page exists
        if 'nextPageToken' in results:
            kwargs['pageToken'] = results['nextPageToken']
            results = service.commentThreads().list(**kwargs).execute()
        else:
            break

    return comments


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, part='snippet', videoId=videoId, textFormat='plainText')

print(len(comments),comments)

祝你好运