Evilom
ab2ca1d836
Reusable 6-step pipeline for collecting DingTalk group messages, extracting Feishu doc links, fetching content, and generating summaries. Skills structure: - SKILL.md: trigger rules, workflow, config reference - config.yaml: group IDs, collection settings - scripts/paths.py: shared path resolution - scripts/step1-6: modular pipeline steps - scripts/run_all.py: one-click runner
38 lines
982 B
YAML
38 lines
982 B
YAML
# 钉钉飞书采集器配置
|
|
# 修改此文件即可适配其他群组/项目
|
|
|
|
groups:
|
|
dc战略问题研究院: "cidoUneRB4Db8TAXaTrKxkQAw=="
|
|
创新组: "cidMuM+itt5PeY7xNSWsv3M0g=="
|
|
|
|
collection:
|
|
# 首次全量拉取的起始时间
|
|
start_date: "2026-05-01 00:00:00"
|
|
# 增量模式：拉取最近N天
|
|
days_back: 3
|
|
# 每次API返回上限
|
|
limit: 200
|
|
# 分段拉取的时间节点（用于全量拉取时的分页）
|
|
segments:
|
|
- "2026-05-01 00:00:00"
|
|
- "2026-05-19 00:00:00"
|
|
- "2026-05-24 00:00:00"
|
|
|
|
# dws CLI 路径查找优先级
|
|
# auto: 环境变量 DWS_PATH > tools/dws.exe > 悟空内置 > PATH
|
|
dws_path: auto
|
|
|
|
# lark-cli 路径（默认从 PATH 查找）
|
|
lark_cli_path: auto
|
|
|
|
# 输出目录（相对于项目根目录）
|
|
output_dir: "./output"
|
|
data_dir: "./data"
|
|
|
|
# 飞书域名映射（可选，用于识别不同租户）
|
|
feishu_domains:
|
|
- "dianchukeji.feishu.cn"
|
|
- "fcnlycv6dd0w.feishu.cn"
|
|
- "ocnmca6f1o0p.feishu.cn"
|
|
- "my.feishu.cn"
|