Overview
- Skill Key
- alfredxia-ai/feishu-document-reader
- Author
- alfredxia-ai
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/alfredxia-ai/feishu-document-reader
- Latest Commit SHA
- 729425df188fe3eb461658c5594af26a9e9b4f93
Read and extract content from all Feishu (Lark) document types using the official Feishu Open API
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 feishu-doc-reader 技能。 若已安装,则直接安装 feishu-doc-reader 技能。
# Feishu Document Reader
This skill enables reading and extracting content from all Feishu (Lark) document types using the official Feishu Open API.
## Configuration
### Set Up the Skill
1. Create the configuration file at `./reference/feishu_config.json` with your Feishu app credentials:
```json
{
"app_id": "your_feishu_app_id_here",
"app_secret": "your_feishu_app_secret_here"
}
```
2. Make sure the scripts are executable:
```bash
chmod +x scripts/read_doc.sh
chmod +x scripts/read_feishu.sh
chmod +x scripts/get_blocks.sh
```
**Security Note**: The configuration file should be kept secure and not committed to version control. Consider using proper file permissions (`chmod 600 ./reference/feishu_config.json`).
## Usage
### Unified Document Reader (推荐)
使用统一文档读取器可以自动识别并读取所有支持的文档类型:
```bash
# 自动识别文档类型并读取
./scripts/read_feishu.sh "docx_xxxxxxxxxxxxxx"
./scripts/read_feishu.sh "sheet_xxxxxxxxxxxxx"
./scripts/read_feishu.sh "basexxxxxxxxxxxxxx"
./scripts/read_feishu.sh "wikcnxxxxxxxxxxxxx"
# 从URL直接读取
./scripts/read_feishu.sh "https://xxx.feishu.cn/docx/xxxxx"
# 指定文档类型
./scripts/read_feishu.sh "token" --type bitable
# 格式化JSON输出
./scripts/read_feishu.sh "token" --pretty
# 只输出文本内容
./scripts/read_feishu.sh "docx_token" --output text
```
### Wiki Knowledge Base (知识库)
读取飞书知识库节点和内容:
```bash
# 读取单个Wiki节点
./scripts/read_feishu.sh "wikcnxxxxxxxxxxxxxx" --type wiki
# 读取整个知识空间
./scripts/read_feishu.sh --wiki-space "SPACE_ID"
# 递归读取所有子节点内容
./scripts/read_feishu.sh --wiki-space "SPACE_ID" --recursive
```
### Bitable (多维表格)
读取飞书多维表格数据:
```bash
# 读取多维表格(包含所有数据表和记录)
./scripts/read_feishu.sh "basexxxxxxxxxxxxxx" --type bitable
```
### Basic Document Reading
```bash
# 读取新版文档
./scripts/read_doc.sh "docx_xxxxxxxxxxxxxx"
# 读取电子表格
./scripts/read_doc.sh "sheet_xxxxxxxxxxxxx" sheet
# 读取多维表格
./scripts/read_doc.sh "...
# Feishu Document Reader - 飞书文档统一读取器
全面支持飞书(Lark)各类在线文档的读取,包括文档、表格、知识库等。
## Features
- **多文档类型支持**:
- ✅ Docx (新版文档) - 完整blocks结构和内容
- ✅ Doc (旧版文档) - 基本支持
- ✅ Sheet (电子表格) - 完整数据读取
- ✅ Bitable (多维表格) - 字段和记录完整提取
- ✅ Wiki (知识库) - 节点信息和内容读取
- **自动类型识别**: 根据token或URL自动识别文档类型
- **统一接口**: 一个命令读取所有类型
- **安全认证**: 自动令牌管理和刷新
- **完善的错误处理**: 详细的错误信息和诊断
## Quick Start
### 1. Configuration
Create `./reference/feishu_config.json`:
```json
{
"app_id": "your_feishu_app_id",
"app_secret": "your_feishu_app_secret"
}
```
Set proper permissions:
```bash
chmod 600 ./reference/feishu_config.json
chmod +x scripts/*.sh
```
### 2. Usage
#### 统一读取器(推荐):
```bash
# 自动识别文档类型
./scripts/read_feishu.sh "docx_your_document_token"
./scripts/read_feishu.sh "sheet_xxxxxxxxxxxxx"
./scripts/read_feishu.sh "basexxxxxxxxxxxxxx"
./scripts/read_feishu.sh "wikcnxxxxxxxxxxxxx"
# 从URL读取
./scripts/read_feishu.sh "https://xxx.feishu.cn/docx/xxxxx"
# 格式化输出
./scripts/read_feishu.sh "docx_token" --pretty
```
#### 读取知识库:
```bash
# 读取单个节点
./scripts/read_feishu.sh "wikcn_token" --type wiki
# 读取整个知识空间
./scripts/read_feishu.sh --wiki-space "SPACE_ID" --recursive
```
#### 读取多维表格:
```bash
./scripts/read_feishu.sh "base_token" --type bitable --pretty
```
#### Python直接调用:
```bash
python scripts/feishu_reader.py "docx_token" --pretty
python scripts/feishu_reader.py "base_token" --type bitable
python scripts/feishu_reader.py --wiki-space "SPACE_ID"
```
### 3. Output Format
输出包含以下内容(根据文档类型有所不同):
**文档 (docx/doc)**:
- `document`: 文档元信息
- `blocks`: 完整的blocks结构
- `text_content`: 提取的纯文本
**电子表格 (sheet)**:
- `spreadsheet`: 表格元信息
- `sheets`: 各工作表数据
**多维表格 (bitable)**:
- `app`: 多维表格元信息
- `tables`: 数据表列表(含字段和记录)...
openstockdata
OpenClaw Skill for stock data analysis
romeosy
OpenClaw Chinese AI-enhanced knowledge management skill
capt-marbles
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.
cccat6
Ensure real-time accurate scheduling and planning across UTC, server time, NTP-sourced time, user local time, and arbitrary time zones. Use for timers, reminders, cron planning, in X minutes or months or years calculations, absolute timestamp conversion, Chinese lunar date awareness, and cross-timezone coordination. Enforce exact duration fidelity so user values are never replaced by example values, compute target times in UTC first, and verify deltas before execution.
cassh100k
SoulKeeper
capt-marbles
Control PhantomBuster automation agents via API. List agents, launch automations, get output/results, check status, and abort running agents. Use when the user needs to run LinkedIn scraping, Twitter automation, lead generation phantoms, or any PhantomBuster workflow.