Python调用YouTube API上传视频触发违规政策被设为私密问题排查

通过Python脚本调用YouTube API上传视频时，平台会自动将上传的视频设为私密状态，提示违反垃圾内容、欺骗性行为及诈骗相关政策；但完全相同的视频通过YouTube官方网页端上传时无任何报错，可成功发布。

• API凭证/项目信誉问题：网页端上传走普通用户账号风控链路，只要账号完成真人验证、有正常使用记录，风控阈值很低；但API上传会额外校验绑定的Google Cloud项目状态——如果项目还处于测试阶段、未完成OAuth应用审核，或者对应凭证之前被用于批量上传低质内容，哪怕视频文件和网页端上传的完全一致，也会因为API端信誉分不足触发更严格的风控规则，直接标记违规并设为私密。
• 元数据触发垃圾内容检测：当前代码的默认标题为Test Title、默认描述为Test Description，如果上传时没有替换成和网页端上传完全一致的标题、描述、标签、分类，这类测试占位文本是垃圾内容检测的高命中特征——大量批量发垃圾内容的自动化脚本都使用这类默认值，API端检测到就会直接拦截。
• 上传行为特征匹配异常：代码中配置chunksize=-1，即整个视频文件单块一次性上传，和普通用户网页端分片上传的行为特征不符；如果同时存在短时间内频繁上传、使用机房IP/代理IP上传的情况，会被判定为自动化脚本批量发布垃圾内容，直接触发违规标记。
• 风控流程差异：API上传没有网页端的前置校验引导环节，只要命中风控规则就直接将视频锁为私密，不会像网页端那样提前提示可能存在问题的内容模块、给用户调整修正的机会。

#!/usr/bin/python

import http.client
import httplib2
import os
import random
import sys
import time

from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
from googleapiclient.http import MediaFileUpload
from oauth2client.client import flow_from_clientsecrets
from oauth2client.file import Storage
from oauth2client.tools import argparser, run_flow


# 显式配置底层HTTP传输库不自动重试，重试逻辑由代码自行实现
httplib2.RETRIES = 1

# 上传失败最大重试次数
MAX_RETRIES = 10

# 触发重试的异常类型
RETRIABLE_EXCEPTIONS = (httplib2.HttpLib2Error, IOError, http.client.NotConnected,
  http.client.IncompleteRead, http.client.ImproperConnectionState,
  http.client.CannotSendRequest, http.client.CannotSendHeader,
  http.client.ResponseNotReady, http.client.BadStatusLine)

# 触发重试的HTTP状态码
RETRIABLE_STATUS_CODES = [500, 502, 503, 504]

# 存储OAuth2.0凭证的文件名，需从Google API控制台获取，且要为对应项目启用YouTube Data API
CLIENT_SECRETS_FILE = "client_secret_web.json"

# 视频上传权限范围
YOUTUBE_UPLOAD_SCOPE = "https://www.googleapis.com/auth/youtube.upload"
YOUTUBE_API_SERVICE_NAME = "youtube"
YOUTUBE_API_VERSION = "v3"

# 凭证文件缺失时的提示信息
MISSING_CLIENT_SECRETS_MESSAGE = """
WARNING: Please configure OAuth 2.0

To make this sample run you will need to populate the client_secrets.json file
found at:

   %s

with information from the API Console
""" % os.path.abspath(os.path.join(os.path.dirname(__file__),
                                   CLIENT_SECRETS_FILE))

VALID_PRIVACY_STATUSES = ("public", "private", "unlisted")


def get_authenticated_service(args):
  flow = flow_from_clientsecrets(CLIENT_SECRETS_FILE,
    scope=YOUTUBE_UPLOAD_SCOPE,
    message=MISSING_CLIENT_SECRETS_MESSAGE)

  storage = Storage("%s-oauth2.json" % sys.argv[0])
  credentials = storage.get()

  if credentials is None or credentials.invalid:
    credentials = run_flow(flow, storage, args)

  return build(YOUTUBE_API_SERVICE_NAME, YOUTUBE_API_VERSION,
    http=credentials.authorize(httplib2.Http()))

def initialize_upload(youtube, options):
  tags = None
  if options.keywords:
    tags = options.keywords.split(",")

  body=dict(
    snippet=dict(
      title=options.title,
      description=options.description,
      tags=tags,
      categoryId=options.category
    ),
    status=dict(
      privacyStatus=options.privacyStatus
    )
  )

  # 调用videos.insert接口创建并上传视频
  insert_request = youtube.videos().insert(
    part=",".join(body.keys()),
    body=body,
    media_body=MediaFileUpload(options.file, chunksize=-1, resumable=True)
  )

  resumable_upload(insert_request)

# 指数退避策略实现断点续传/失败重试
def resumable_upload(insert_request):
  response = None
  error = None
  retry = 0
  while response is None:
    try:
      print("Uploading file...")
      status, response = insert_request.next_chunk()
      if response is not None:
        if 'id' in response:
          print("Video id '%s' was successfully uploaded." % response['id'])
        else:
          exit("The upload failed with an unexpected response: %s" % response)
    except HttpError as e:
      if e.resp.status in RETRIABLE_STATUS_CODES:
        error = "A retriable HTTP error %d occurred:\n%s" % (e.resp.status,
                                                             e.content)
      else:
        raise
    except RETRIABLE_EXCEPTIONS as e:
      error = "A retriable error occurred: %s" % e

    if error is not None:
      print(error)
      retry += 1
      if retry > MAX_RETRIES:
        exit("No longer attempting to retry.")

      max_sleep = 2 ** retry
      sleep_seconds = random.random() * max_sleep
      print("Sleeping %f seconds and then retrying..." % sleep_seconds)
      time.sleep(sleep_seconds)

if __name__ == '__main__':
  argparser.add_argument("--file", required=True, help="Video file to upload")
  argparser.add_argument("--title", help="Video title", default="Test Title")
  argparser.add_argument("--description", help="Video description",
    default="Test Description")
  argparser.add_argument("--category", default="22",
    help="Numeric video category. ")
  argparser.add_argument("--keywords", help="Video keywords, comma separated",
    default="")
  argparser.add_argument("--privacyStatus", choices=VALID_PRIVACY_STATUSES,
    default=VALID_PRIVACY_STATUSES[0], help="Video privacy status.")
  args = argparser.parse_args()

  if not os.path.exists(args.file):
    exit("Please specify a valid file using the --file= parameter.")

  youtube = get_authenticated_service(args)
  try:
    initialize_upload(youtube, args)
  except HttpError as e:
    print("An HTTP error %d occurred:\n%s" % (e.resp.status, e.content))

视频因违反垃圾内容、欺骗性行为及诈骗相关政策，已被自动设置为私密状态。

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