mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-02-10 17:11:20 +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>
85 lines
2.9 KiB
Python
85 lines
2.9 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/proxy/base_proxy.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。
|
|
|
|
|
|
# -*- coding: utf-8 -*-
|
|
# @Author : relakkes@gmail.com
|
|
# @Time : 2023/12/2 11:18
|
|
# @Desc : Crawler IP acquisition implementation
|
|
# @Url : KuaiDaili HTTP implementation, official documentation: https://www.kuaidaili.com/?ref=ldwkjqipvz6c
|
|
import json
|
|
from abc import ABC, abstractmethod
|
|
from typing import List
|
|
|
|
import config
|
|
from cache.abs_cache import AbstractCache
|
|
from cache.cache_factory import CacheFactory
|
|
from tools.utils import utils
|
|
|
|
from .types import IpInfoModel
|
|
|
|
|
|
class IpGetError(Exception):
|
|
""" ip get error"""
|
|
|
|
|
|
class ProxyProvider(ABC):
|
|
@abstractmethod
|
|
async def get_proxy(self, num: int) -> List[IpInfoModel]:
|
|
"""
|
|
Abstract method to get IP, different HTTP proxy providers need to implement this method
|
|
:param num: Number of IPs to extract
|
|
:return:
|
|
"""
|
|
raise NotImplementedError
|
|
|
|
|
|
|
|
class IpCache:
|
|
def __init__(self):
|
|
self.cache_client: AbstractCache = CacheFactory.create_cache(cache_type=config.CACHE_TYPE_REDIS)
|
|
|
|
def set_ip(self, ip_key: str, ip_value_info: str, ex: int):
|
|
"""
|
|
Set IP with expiration time, Redis is responsible for deletion after expiration
|
|
:param ip_key:
|
|
:param ip_value_info:
|
|
:param ex:
|
|
:return:
|
|
"""
|
|
self.cache_client.set(key=ip_key, value=ip_value_info, expire_time=ex)
|
|
|
|
def load_all_ip(self, proxy_brand_name: str) -> List[IpInfoModel]:
|
|
"""
|
|
Load all unexpired IP information from Redis
|
|
:param proxy_brand_name: Proxy provider name
|
|
:return:
|
|
"""
|
|
all_ip_list: List[IpInfoModel] = []
|
|
all_ip_keys: List[str] = self.cache_client.keys(pattern=f"{proxy_brand_name}_*")
|
|
try:
|
|
for ip_key in all_ip_keys:
|
|
ip_value = self.cache_client.get(ip_key)
|
|
if not ip_value:
|
|
continue
|
|
all_ip_list.append(IpInfoModel(**json.loads(ip_value)))
|
|
except Exception as e:
|
|
utils.logger.error("[IpCache.load_all_ip] get ip err from redis db", e)
|
|
return all_ip_list
|