Python爬取YouTube数据时video_df返回空Dataframe的排查与解决

核心原因：get_video_details函数无返回值 #

你的video_df为空的直接原因是get_video_details函数收集完视频数据后没有返回结果，调用该函数时得到的是None，自然无法向video_df添加任何数据。

具体修正步骤 #

1. 给get_video_details添加返回语句 #

在函数末尾添加返回逻辑，将收集到的视频数据转换成DataFrame返回：

def get_video_details(youtube, video_ids):
    # 原有代码保持不变...
    
    all_video_info = []
    # 原有循环收集数据的代码...
    
    # 新增返回语句
    return pd.DataFrame(all_video_info)

2. 修正API字段拼写错误 #

YouTube API使用美式拼写，你代码里的favouriteCount要改成favoriteCount，否则该字段会始终返回None：

stats_to_keep = {'snippet': ['channelTitle', 'title', 'description', 'tags', 'publishedAt'],
                 'statistics': ['viewCount', 'likeCount', 'favoriteCount', 'commentCount'],  # 修正拼写
                 'contentDetails': ['duration', 'definition', 'caption']
                 }

3. 替换过时的append方法（推荐） #

Pandas的append方法已被弃用，建议用pd.concat合并DataFrame：

# 原代码
video_df = video_df.append(video_data, ignore_index=True)
comments_df = comments_df.append(comments_data, ignore_index=True)

# 替换为
video_df = pd.concat([video_df, video_data], ignore_index=True)
comments_df = pd.concat([comments_df, comments_data], ignore_index=True)

4. 添加Excel导出代码 #

在获取完数据后，添加以下代码将结果导出到Excel：

# 导出视频数据
video_df.to_excel('youtube_video_stats.xlsx', index=False)
# 导出评论数据（可选）
comments_df.to_excel('youtube_comments.xlsx', index=False)
print("数据已成功导出至Excel文件")

完整修正后的代码 #

import pandas as pd
import numpy as np
from googleapiclient.discovery import build

api_key = '<api key>'
channel_ids = ['<channel_id>',]

youtube = build('youtube', 'v3', developerKey=api_key)


def get_channel_stats(youtube, channel_ids):
    all_data = []
    request = youtube.channels().list(
        part='snippet,contentDetails,statistics',
        id=','.join(channel_ids))
    response = request.execute()

    for i in range(len(response['items'])):
        data = dict(channelName=response['items'][i]['snippet']['title'],
                    subscribers=response['items'][i]['statistics']['subscriberCount'],
                    views=response['items'][i]['statistics']['viewCount'],
                    totalVideos=response['items'][i]['statistics']['videoCount'],
                    playlistId=response['items'][i]['contentDetails']['relatedPlaylists']['uploads'])
        all_data.append(data)

    return pd.DataFrame(all_data)


def get_video_ids(youtube, playlist_id):
    request = youtube.playlistItems().list(
        part='contentDetails',
        playlistId=playlist_id,
        maxResults=50)
    response = request.execute()

    video_ids = []
    for i in range(len(response['items'])):
        video_ids.append(response['items'][i]['contentDetails']['videoId'])

    next_page_token = response.get('nextPageToken')
    more_pages = True

    while more_pages:
        if next_page_token is None:
            more_pages = False
        else:
            request = youtube.playlistItems().list(
                part='contentDetails',
                playlistId=playlist_id,
                maxResults=50,
                pageToken=next_page_token)
            response = request.execute()

            for i in range(len(response['items'])):
                video_ids.append(response['items'][i]['contentDetails']['videoId'])

            next_page_token = response.get('nextPageToken')

    return video_ids


def get_video_details(youtube, video_ids):
    all_video_info = []

    for i in range(0, len(video_ids), 50):
        request = youtube.videos().list(
            part="snippet,contentDetails,statistics",
            id=','.join(video_ids[i:i + 50])
        )
        response = request.execute()

        for video in response['items']:
            stats_to_keep = {'snippet': ['channelTitle', 'title', 'description', 'tags', 'publishedAt'],
                             'statistics': ['viewCount', 'likeCount', 'favoriteCount', 'commentCount'],
                             'contentDetails': ['duration', 'definition', 'caption']
                             }
            video_info = {}
            video_info['video_id'] = video['id']

            for k in stats_to_keep.keys():
                for v in stats_to_keep[k]:
                    try:
                        video_info[v] = video[k][v]
                    except:
                        video_info[v] = None

            all_video_info.append(video_info)
    
    # 新增返回语句
    return pd.DataFrame(all_video_info)


def get_comments_in_videos(youtube, video_ids):
    all_comments = []

    for video_id in video_ids:
        try:
            request = youtube.commentThreads().list(
                part="snippet,replies",
                videoId=video_id
            )
            response = request.execute()

            comments_in_video = [comment['snippet']['topLevelComment']['snippet']['textOriginal'] for comment in
                                 response['items'][0:10]]
            comments_in_video_info = {'video_id': video_id, 'comments': comments_in_video}

            all_comments.append(comments_in_video_info)

        except:
            print('Could not get comments for video ' + video_id)

    return pd.DataFrame(all_comments)

channel_data = get_channel_stats(youtube, channel_ids)

numeric_cols = ['subscribers', 'views', 'totalVideos']
channel_data[numeric_cols] = channel_data[numeric_cols].apply(pd.to_numeric, errors='coerce')

video_df = pd.DataFrame()
comments_df = pd.DataFrame()

for c in channel_data['channelName'].unique():
    print("Getting video information from channel: " + c)
    playlist_id = channel_data.loc[channel_data['channelName'] == c, 'playlistId'].iloc[0]
    video_ids = get_video_ids(youtube, playlist_id)

    video_data = get_video_details(youtube, video_ids)
    comments_data = get_comments_in_videos(youtube, video_ids)

    # 替换为pd.concat
    video_df = pd.concat([video_df, video_data], ignore_index=True)
    comments_df = pd.concat([comments_df, comments_data], ignore_index=True)

print(video_df)
# 导出Excel
video_df.to_excel('youtube_video_stats.xlsx', index=False)
comments_df.to_excel('youtube_comments.xlsx', index=False)
print("数据已成功导出至Excel文件")

内容的提问来源于stack exchange，提问作者youtube_tryhard