python - 如何解决“charmap”编解码器无法编码字符错误

Question

我正在尝试从 YouTube 中提取评论，我得到：

Traceback (most recent call last):
File "<ipython-input-4-7667a2287691>", line 1, in <module>
    runfile('C:/Users/ACER/Desktop/fyp/comment_extractor.py', wdir='C:/Users/ACER/Desktop/fyp')
File "C:\Users\ACER\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 827, in runfile
    execfile(filename, namespace)
File "C:\Users\ACER\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 110, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)
File "C:/Users/ACER/Desktop/fyp/comment_extractor.py", line 120, in <module>
    search_videos_by_keyword(service, q=keyword, part='id,snippet', eventType='completed', type='video')
File "C:/Users/ACER/Desktop/fyp/comment_extractor.py", line 105, in search_videos_by_keyword
    write_to_csv(final_result)
File "C:/Users/ACER/Desktop/fyp/comment_extractor.py", line 55, in write_to_csv
    comments_writer.writerow(list(row))
File "C:\Users\ACER\Anaconda3\lib\encodings\cp1252.py", line 19, in encode
    return codecs.charmap_encode(input,self.errors,encoding_table)[0]
UnicodeEncodeError: 'charmap' codec can't encode characters in position 845-846: character maps to `<undefined>`

我正在尝试将这些评论提取到 Excel 表中。你能告诉我为什么会出现这些错误吗？

CLIENT_SECRETS_FILE = "client_secret.json"
SCOPES = ['https://www.googleapis.com/auth/youtube.force-ssl']
API_SERVICE_NAME = 'youtube'
API_VERSION = 'v3'

import os
import pickle
import google.oauth2.credentials
import csv 
from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
import google.oauth2.credentials

from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
from google_auth_oauthlib.flow import InstalledAppFlow
        
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 write_to_csv(comments):
    with open('comments.csv', 'w') as comments_file:
        comments_writer = csv.writer(comments_file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
        comments_writer.writerow(['Video ID', 'Title', 'Comment'])
        for row in comments:
            comments_writer.writerow(list(row))

def get_videos(service, **kwargs):
    final_results = []
    results = service.search().list(**kwargs).execute()

    i = 0
    max_pages = 3
    while results and i < max_pages:
        final_results.extend(results['items'])

        # Check if another page exists
        if 'nextPageToken' in results:
            kwargs['pageToken'] = results['nextPageToken']
            results = service.search().list(**kwargs).execute()
            i += 1
        else:
            break

    return final_results

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)

        if 'nextPageToken' in results:
            kwargs['pageToken'] = results['nextPageToken']
            results = service.commentThreads().list(**kwargs).execute()
        else:
            break

    return comments

def search_videos_by_keyword(service, **kwargs):
    results = get_videos(service, **kwargs)
    final_result = []
    for item in results:
        title = item['snippet']['title']
        video_id = item['id']['videoId']
        comments = get_video_comments(service, part='snippet', videoId=video_id, textFormat='plainText')
        final_result.extend([(video_id, title, comment) for comment in comments])
        
    write_to_csv(final_result)

keyword = input('Enter a keyword: ')
search_videos_by_keyword(service, q=keyword, part='id,snippet', eventType='completed', type='video')

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()

这是代码；你能建议改变吗？

标签： pythonencodingyoutube-apiextract