CoPAW 银登公告与结果爬取 Skill
这是一个用于 CoPAW (Copilot Automation Workflow) 的标准 Skill，支持自动爬取银登网不良贷款转让公告及转让结果，并利用大模型（LLM）提取关键数据。
Best use case
CoPAW 银登公告与结果爬取 Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
这是一个用于 CoPAW (Copilot Automation Workflow) 的标准 Skill，支持自动爬取银登网不良贷款转让公告及转让结果，并利用大模型（LLM）提取关键数据。
Teams using CoPAW 银登公告与结果爬取 Skill should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/yindenganalyse/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How CoPAW 银登公告与结果爬取 Skill Compares
| Feature / Agent | CoPAW 银登公告与结果爬取 Skill | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
这是一个用于 CoPAW (Copilot Automation Workflow) 的标准 Skill，支持自动爬取银登网不良贷款转让公告及转让结果，并利用大模型（LLM）提取关键数据。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Top AI Agents for Productivity
See the top AI agent skills for productivity, workflow automation, operational systems, documentation, and everyday task execution.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# CoPAW 银登公告与结果爬取 Skill 这是一个用于 CoPAW (Copilot Automation Workflow) 的标准 Skill，支持自动爬取银登网不良贷款转让公告及转让结果，并利用大模型（LLM）提取关键数据。 ## 目录结构 ``` yindeng_skill/ ├── skill.py # 标准 Skill 接口 (Agent/Tool Use) ├── skill.json # Skill 元数据定义 ├── main.py # CLI 入口脚本 ├── crawler.py # 核心爬虫逻辑 ├── ocr_utils.py # OCR 与数据汇总工具 ├── requirements.txt # 依赖清单 └── SKILL.md # 说明文档 ``` ## Agent 集成 (CoPaw / Tool Use) 本 Skill 提供了标准的 Python 函数接口和 JSON Schema 定义，可供 AI Agent 直接调用。 ### Python 接口 ```python from skill import run_yindeng_crawler # 爬取并分析 result = run_yindeng_crawler(source="result", analyze=True) print(result) ``` ### Skill 定义 (skill.json) 包含完整的工具描述和参数定义，符合 OpenAI/Anthropics Tool Schema 标准。 ## 功能特性 1. **多任务支持**：可同时爬取“转让公告”和“转让结果公告”。 2. **自动爬取**：根据日期（自动计算或指定）爬取银登网公告并下载 PDF。 3. **智能分析**：支持多模型（DeepSeek、千问、硅基流动等）提取 PDF 中的关键金融数据。 4. **数据导出**： - 爬取记录 Excel - 债权转让证明信息汇总（仅结果公告，含 OCR 数据） - LLM 分析结果报表 (`analysis_result.xlsx`) ## 部署与使用 ### 1. 安装依赖 在运行环境或 Docker 容器中安装 Python 依赖（需提前安装 Tesseract-OCR 和 Poppler）： ```bash pip install -r requirements.txt ``` ### 2. 环境变量配置 (LLM) 设置以下环境变量以启用 LLM 分析功能。本 Skill 支持多种 LLM 提供商。 #### 通用配置 - `LLM_API_KEY`: **(必须)** 您的 API Key。 - `LLM_PROVIDER`: (可选) 指定服务商，如 `deepseek`, `siliconflow`, `qwen`。默认为 `deepseek`。 - `LLM_API_BASE`: (可选) API 基础地址。 - `LLM_MODEL`: (可选) 模型名称。 #### 常用服务商配置示例 **DeepSeek (默认)** ```bash export LLM_API_KEY="sk-..." export LLM_PROVIDER="deepseek" # 默认 BASE: https://api.deepseek.com/v1 # 默认 MODEL: deepseek-chat ``` **硅基流动 (SiliconFlow)** ```bash export LLM_API_KEY="sk-..." export LLM_PROVIDER="siliconflow" # 默认 BASE: https://api.siliconflow.cn/v1 # 默认 MODEL: deepseek-ai/DeepSeek-V3 ``` **通义千问 (DashScope/Aliyun)** ```bash export LLM_API_KEY="sk-..." export LLM_PROVIDER="qwen" # 默认 BASE: https://dashscope.aliyuncs.com/compatible-mode/v1 # 默认 MODEL: qwen-plus ``` ### 3. 调用方式 **默认运行（爬取公告 + 结果）：** ```bash python main.py ``` **仅爬取转让结果：** ```bash python main.py --source result ``` **爬取并启用 LLM 分析：** ```bash python main.py --analyze ``` **指定日期运行：** ```bash python main.py 2026-03-03 ``` ## 输出结果 - **转让公告**: `YYYY-MM-DD银登公告/` - **转让结果**: `YYYY-MM-DD银登公告结果/` - `*债权转让证明信息汇总.xlsx`: 包含 OCR 识别后的结构化数据。 - `analysis_result.xlsx`: 包含 LLM 提取的深度分析数据。 ## 退出码说明 - `0`: 成功且有新数据。 - `2`: 成功但**暂无更新**（所有任务均无新增数据）。 - `1`: 运行出错。
Related Skills
copaw-ai-assistant
Personal AI assistant framework supporting multiple chat channels (DingTalk, Feishu, QQ, Discord, etc.) with extensible skills, local/cloud deployment, and cron scheduling.
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成（播客、视频、幻灯片、测验、思维导图等）、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。