跳到正文
FunCoding

direct-reportlab-pdf-generation

Generate complex multi-page PDFs by running reportlab Python code directly via run_shell when shell_agent fails on document creation

Star
7,755
许可证
MIT
最近提交
2026年8月12日

benchmarks/gdpval/skills/direct-reportlab-pdf-generation/SKILL.md

在 GitHub 上查看

Direct ReportLab PDF Generation via run_shell

When to Use This Skill

Use this pattern when:

  • You need to create a complex, multi-page PDF document with structured content
  • Delegating PDF generation to shell_agent fails or produces unreliable results
  • You need fine-grained control over PDF layout, styling, and pagination

Core Technique

Instead of asking shell_agent to handle PDF creation, write inline Python code using the reportlab library and execute it directly via run_shell. This gives you deterministic control over the document structure.

Step-by-Step Instructions

Step 1: Prepare Your PDF Content

Organize your content into logical sections that will become pages or page groups:

  • Title page
  • Table of contents (optional)
  • Main content sections
  • Appendices or references

Step 2: Write the ReportLab Python Script

Create a Python script that uses these key reportlab components:

from reportlab.lib import colors
from reportlab.lib.pagesizes import letter
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import inch
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle, PageBreak, Image
from reportlab.lib.enums import TA_CENTER, TA_LEFT, TA_JUSTIFY

def create_pdf(filename, content_data):
    doc = SimpleDocTemplate(filename, pagesize=letter,
                           rightMargin=72, leftMargin=72,
                           topMargin=72, bottomMargin=72)
    
    story = []
    styles = getSampleStyleSheet()
    
    # Custom styles
    title_style = ParagraphStyle(
        'CustomTitle',
        parent=styles['Heading1'],
        fontSize=24,
        textColor=colors.HexColor('#1a1a1a'),
        spaceAfter=30,
        alignment=TA_CENTER
    )
    
    heading_style = ParagraphStyle(
        'CustomHeading',
        parent=styles['Heading2'],
        fontSize=16,
        textColor=colors.HexColor('#2c3e50'),
        spaceBefore=20,
        spaceAfter=12
    )
    
    body_style = ParagraphStyle(
        'CustomBody',
        parent=styles['Normal'],
        fontSize=11,
        leading=16,
        alignment=TA_JUSTIFY
    )
    
    # Build document content
    for section in content_data:
        if section['type'] == 'title':
            story.append(Paragraph(section['text'], title_style))
        elif section['type'] == 'heading':
            story.append(Paragraph(section['text'], heading_style))
        elif section['type'] == 'paragraph':
            story.append(Paragraph(section['text'], body_style))
            story.append(Spacer(1, 12))
        elif section['type'] == 'table':
            table = Table(section['data'], colWidths=section.get('col_widths'))
            table.setStyle(TableStyle([
                ('BACKGROUND', (0, 0), (-1, 0), colors.grey),
                ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
                ('ALIGN', (0, 0), (-1, -1), 'CENTER'),
                ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
                ('FONTSIZE', (0, 0), (-1, 0), 12),
                ('BOTTOMPADDING', (0, 0), (-1, 0), 12),
                ('BACKGROUND', (0, 1), (-1, -1), colors.beige),
                ('GRID', (0, 0), (-1, -1), 1, colors.black),
            ]))
            story.append(table)
            story.append(Spacer(1, 20))
        elif section['type'] == 'pagebreak':
            story.append(PageBreak())
    
    doc.build(story)

Step 3: Execute via run_shell

Run the Python script directly using run_shell:

python3 << 'EOF'
# Your complete reportlab script here
from reportlab.lib import colors
from reportlab.lib.pagesizes import letter
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle, PageBreak

# ... rest of your script
EOF

Or save to a file and execute:

cat > generate_pdf.py << 'SCRIPT'
# Your complete script
SCRIPT

python3 generate_pdf.py

Step 4: Handle Complex Content

For lengthy documents, structure content as a data structure:

document_sections = [
    {'type': 'title', 'text': 'Document Title'},
    {'type': 'pagebreak'},
    {'type': 'heading', 'text': 'Section 1'},
    {'type': 'paragraph', 'text': 'Content here...'},
    {'type': 'heading', 'text': 'Section 2'},
    {'type': 'table', 'data': [['Header1', 'Header2'], ['Row1-Col1', 'Row1-Col2']]},
    {'type': 'pagebreak'},
    # Continue for all sections
]

Step 5: Verify Output

Check that the PDF was created successfully:

ls -la your_document.pdf
# Optionally check page count
pdfinfo your_document.pdf 2>/dev/null || echo "PDF created, pdfinfo not available"

Common Patterns

Multi-Section Documents

Use PageBreak() between major sections to ensure clean pagination.

Tables with Data

Structure tabular data as nested lists:

table_data = [
    ['Column 1', 'Column 2', 'Column 3'],
    ['Value 1', 'Value 2', 'Value 3'],
    ['Value 4', 'Value 5', 'Value 6'],
]

Styled Text

Create custom ParagraphStyle objects for consistent formatting across sections.

Long Paragraphs

ReportLab automatically handles text wrapping. For very long content, consider breaking into multiple paragraphs.

Troubleshooting

IssueSolution
Import errorsEnsure reportlab is installed: pip install reportlab
Layout issuesAdjust margins in SimpleDocTemplate constructor
Text overflowUse Spacer elements to add vertical space
Table width problemsSet explicit colWidths parameter
Page breaks in wrong placesInsert PageBreak() explicitly before new sections

Advantages Over shell_agent

  • Deterministic: Code executes exactly as written
  • Debuggable: Errors are immediate and clear
  • Controllable: Full access to reportlab's API
  • Reliable: No intermediate agent interpretation layer
  • Efficient: Single execution, no retry loops

相似的 Skill

精选

pptx

生成、读取和修改演示文稿,也能合并拆分幻灯片。

ANanthropics/skills181k近 7 天新增 1,159 个 star

精选

doc-coauthoring

按步骤协作撰写技术方案、提案和决策文档,逐轮修改。

ANanthropics/skills181k近 7 天新增 1,159 个 star

精选

docx

创建和编辑 Word 文档,支持目录、页码、页眉等排版。

ANanthropics/skills181k近 7 天新增 1,159 个 star

精选

canvas-design

按设计理念生成海报和视觉作品,输出 PNG 或 PDF。

ANanthropics/skills181k近 7 天新增 1,159 个 star

精选

pdf

提取文本和表格、合并拆分、填写表单,也能对扫描件做 OCR。

ANanthropics/skills181k近 7 天新增 1,159 个 star

精选

xlsx

读写 Excel 和 CSV,处理公式、格式、图表与数据清洗。

ANanthropics/skills181k近 7 天新增 1,159 个 star