pdf-extractor
使用Python脚本提取和转换PDF文档
📖 中文导读:使用Python脚本提取和转换PDF文档 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。
name: pdf-extractor description: Extract and convert PDF documents using Python scripts version: 1.0.0 allowed-tools: - Bash - Read - Write
PDF Extractor Skill
This skill provides tools for extracting text and metadata from PDF documents and converting them to different formats.
Available Scripts
extract.py
Extracts text and metadata from PDF files.
Input:
{
"file_path": "/path/to/document.pdf",
"pages": "all" | [1, 2, 3]
}
Output:
{
"text": "Extracted text content...",
"metadata": {
"title": "Document Title",
"author": "Author Name",
"pages": 10
}
}
convert.sh
Converts PDF files to different formats (text, markdown, etc.).
Input:
{
"input_file": "/path/to/input.pdf",
"output_format": "txt" | "md" | "html"
}
parse.py
Parses structured data from PDF forms and tables.
Input:
{
"file_path": "/path/to/form.pdf",
"extract_tables": true,
"extract_forms": true
}
Usage Example
from skillkit import SkillManager
manager = SkillManager()
result = manager.execute_skill_script(
skill_name="pdf-extractor",
script_name="extract",
arguments={"file_path": "document.pdf", "pages": "all"}
)
if result.success:
print(result.stdout)