更新pipeline
This commit is contained in:
41
readme.md
41
readme.md
@@ -1,11 +1,37 @@
|
||||
# B站关注清理工具(优化版)
|
||||
|
||||
> 一键命令运行全流程:`python source/run_pipeline.py`
|
||||
|
||||
本项目保留并聚焦一条可用功能链:
|
||||
|
||||
1. 抓取视频标题
|
||||
2. 分批AI分析
|
||||
3. 生成取关UID(支持按100拆分)
|
||||
4. 生成保留关注报告
|
||||
5. 按首字母排序
|
||||
6. 提取分组信息
|
||||
|
||||
## 快速开始
|
||||
|
||||
```powershell
|
||||
# 完整流程(推荐)
|
||||
python source/run_pipeline.py
|
||||
|
||||
# 速度优先
|
||||
python source/run_pipeline.py --workers 8 --batch-size 30 --sleep-seconds 0
|
||||
|
||||
# 试跑30个UP
|
||||
python source/run_pipeline.py --max-ups 30
|
||||
|
||||
# 跳过抓取,使用已有标题报告
|
||||
python source/run_pipeline.py --skip-fetch
|
||||
|
||||
# 跳过分析,仅生成产物
|
||||
python source/run_pipeline.py --skip-analyze
|
||||
|
||||
# 跳过排序/分组
|
||||
python source/run_pipeline.py --skip-sort --skip-group
|
||||
```
|
||||
|
||||
## 目录结构
|
||||
|
||||
@@ -46,21 +72,6 @@ VOLCENGINE_BASE_URL = "https://ark.cn-beijing.volces.com/api/v3"
|
||||
|
||||
`batch_ai_summary_from_report.py` 会自动读取该配置。
|
||||
|
||||
## 一键推荐用法
|
||||
|
||||
在项目根目录运行:
|
||||
|
||||
```powershell
|
||||
python source/run_pipeline.py
|
||||
```
|
||||
|
||||
默认会完成:
|
||||
|
||||
1. 从 [source/resources/export_uids.json](source/resources/export_uids.json) 抓取标题到 [source/output/reports/up_titles_report.md](source/output/reports/up_titles_report.md)
|
||||
2. 分批分析到 [source/output/reports/up_analysis_full_auto.md](source/output/reports/up_analysis_full_auto.md)
|
||||
3. 生成保留关注报告 [source/output/reports/up_keep_follow_only.md](source/output/reports/up_keep_follow_only.md)
|
||||
4. 生成取关UID [source/output/uids/unfollow_mids_list.txt](source/output/uids/unfollow_mids_list.txt) 并按100拆分
|
||||
|
||||
## 常用参数
|
||||
|
||||
```powershell
|
||||
|
||||
Reference in New Issue
Block a user