Files
MediaCrawler/store/zhihu/__init__.py
程序员阿江(Relakkes) 0282e626c9 feat: 新增 JSONL 存储格式支持,默认存储格式改为 jsonl
JSONL(JSON Lines)每行一个 JSON 对象,采用 append 模式写入,
无需读取已有数据,大数据量下性能远优于 JSON 格式。

- 新增 AsyncFileWriter.write_to_jsonl() 核心方法
- 7 个平台新增 JsonlStoreImplement 类并注册到工厂
- 配置默认值从 json 改为 jsonl,CLI/API 枚举同步更新
- db_session.py 守卫条件加入 jsonl,避免误触 ValueError
- 词云生成支持读取 JSONL 文件,优先 jsonl 回退 json
- 原有 json 选项完全保留,向后兼容
- 更新相关文档和测试
2026-03-03 23:31:07 +08:00

134 lines
4.1 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/store/zhihu/__init__.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 -*-
from typing import List
import config
from base.base_crawler import AbstractStore
from model.m_zhihu import ZhihuComment, ZhihuContent, ZhihuCreator
from ._store_impl import (ZhihuCsvStoreImplement,
ZhihuDbStoreImplement,
ZhihuJsonStoreImplement,
ZhihuJsonlStoreImplement,
ZhihuSqliteStoreImplement,
ZhihuMongoStoreImplement,
ZhihuExcelStoreImplement)
from tools import utils
from var import source_keyword_var
class ZhihuStoreFactory:
STORES = {
"csv": ZhihuCsvStoreImplement,
"db": ZhihuDbStoreImplement,
"postgres": ZhihuDbStoreImplement,
"json": ZhihuJsonStoreImplement,
"jsonl": ZhihuJsonlStoreImplement,
"sqlite": ZhihuSqliteStoreImplement,
"mongodb": ZhihuMongoStoreImplement,
"excel": ZhihuExcelStoreImplement,
}
@staticmethod
def create_store() -> AbstractStore:
store_class = ZhihuStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
if not store_class:
raise ValueError("[ZhihuStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or mongodb or excel ...")
return store_class()
async def batch_update_zhihu_contents(contents: List[ZhihuContent]):
"""
Batch update Zhihu contents
Args:
contents:
Returns:
"""
if not contents:
return
for content_item in contents:
await update_zhihu_content(content_item)
async def update_zhihu_content(content_item: ZhihuContent):
"""
Update Zhihu content
Args:
content_item:
Returns:
"""
content_item.source_keyword = source_keyword_var.get()
local_db_item = content_item.model_dump()
local_db_item.update({"last_modify_ts": utils.get_current_timestamp()})
utils.logger.info(f"[store.zhihu.update_zhihu_content] zhihu content: {local_db_item}")
await ZhihuStoreFactory.create_store().store_content(local_db_item)
async def batch_update_zhihu_note_comments(comments: List[ZhihuComment]):
"""
Batch update Zhihu content comments
Args:
comments:
Returns:
"""
if not comments:
return
for comment_item in comments:
await update_zhihu_content_comment(comment_item)
async def update_zhihu_content_comment(comment_item: ZhihuComment):
"""
Update Zhihu content comment
Args:
comment_item:
Returns:
"""
local_db_item = comment_item.model_dump()
local_db_item.update({"last_modify_ts": utils.get_current_timestamp()})
utils.logger.info(f"[store.zhihu.update_zhihu_note_comment] zhihu content comment:{local_db_item}")
await ZhihuStoreFactory.create_store().store_comment(local_db_item)
async def save_creator(creator: ZhihuCreator):
"""
Save Zhihu creator information
Args:
creator:
Returns:
"""
if not creator:
return
local_db_item = creator.model_dump()
local_db_item.update({"last_modify_ts": utils.get_current_timestamp()})
await ZhihuStoreFactory.create_store().store_creator(local_db_item)