mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-02-06 23:21:33 +08:00
157ddfb21b
Comprehensive translation of Chinese text to English across the entire codebase: - api/: FastAPI server documentation and logger messages - cache/: Cache abstraction layer comments and docstrings - database/: Database models and MongoDB store documentation - media_platform/: All platform crawlers (Bilibili, Douyin, Kuaishou, Tieba, Weibo, Xiaohongshu, Zhihu) - model/: Data model documentation - proxy/: Proxy pool and provider documentation - store/: Data storage layer comments - tools/: Utility functions and browser automation - test/: Test file documentation Preserved: Chinese disclaimer header (lines 10-18) for legal compliance 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
56 lines
1.7 KiB
Python
56 lines
1.7 KiB
Python
# -*- coding: utf-8 -*-
|
|
# Copyright (c) 2025 relakkes@gmail.com
|
|
#
|
|
# This file is part of MediaCrawler project.
|
|
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/tools/utils.py
|
|
# GitHub: https://github.com/NanmiCoder
|
|
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
|
|
#
|
|
|
|
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
|
# 1. 不得用于任何商业用途。
|
|
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
|
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
|
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
|
# 5. 不得用于任何非法或不当的用途。
|
|
#
|
|
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
|
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
|
|
|
|
|
import argparse
|
|
import logging
|
|
|
|
from .crawler_util import *
|
|
from .slider_util import *
|
|
from .time_util import *
|
|
|
|
|
|
def init_loging_config():
|
|
level = logging.INFO
|
|
logging.basicConfig(
|
|
level=level,
|
|
format="%(asctime)s %(name)s %(levelname)s (%(filename)s:%(lineno)d) - %(message)s",
|
|
datefmt='%Y-%m-%d %H:%M:%S'
|
|
)
|
|
_logger = logging.getLogger("MediaCrawler")
|
|
_logger.setLevel(level)
|
|
|
|
# Disable httpx INFO level logs
|
|
logging.getLogger("httpx").setLevel(logging.WARNING)
|
|
|
|
return _logger
|
|
|
|
|
|
logger = init_loging_config()
|
|
|
|
def str2bool(v):
|
|
if isinstance(v, bool):
|
|
return v
|
|
if v.lower() in ('yes', 'true', 't', 'y', '1'):
|
|
return True
|
|
elif v.lower() in ('no', 'false', 'f', 'n', '0'):
|
|
return False
|
|
else:
|
|
raise argparse.ArgumentTypeError('Boolean value expected.')
|