# Basic — get text description
python3 scripts/caption.py /mnt/data/image.png
 
# Custom prompt — guide what to extract
python3 scripts/caption.py /mnt/data/chart.png --prompt "提取所有数值，Markdown 表格格式"
 
# JSON output — includes detected type, usage stats, cache info
python3 scripts/caption.py /mnt/data/image.png --json
 
# Batch — process all images in a directory
python3 scripts/caption.py /mnt/data/images/ --batch --output /mnt/data/captions.json
 
# Override model (optional)
python3 scripts/caption.py /mnt/data/image.png --model gemini-3.1-flash-lite-preview

{
  "file": "/mnt/data/image.png",
  "type": "chart",
  "description": "这是一张柱状图...",
  "usage": {"prompt_tokens": 1100, "completion_tokens": 400},
  "cached": false
}

import subprocess, json
CAPTION = "/path/to/skills/sn-da-image-caption/scripts/caption.py"
# Single image
result = subprocess.run(
    ["python3", CAPTION, "/mnt/data/chart.png", "--json",
     "--prompt", "提取图表数据，Markdown 表格输出"],
    capture_output=True, text=True, timeout=60
)
data = json.loads(result.stdout)
description = data["description"]
# Batch
result = subprocess.run(
    ["python3", CAPTION, "/mnt/data/images/", "--batch",
     "--output", "/mnt/data/captions.json"],
    capture_output=True, text=True, timeout=300
)
with open("/mnt/data/captions.json") as f:
    all_captions = json.load(f)

import pandas as pd
def parse_markdown_table(text):
    lines = text.strip().split('\n')
    table_lines = []
    in_table = False
    for line in lines:
        stripped = line.strip()
        if '|' in stripped:
            in_table = True
            table_lines.append(stripped)
        elif in_table:
            break
    data_lines = []
    for l in table_lines:
        cells = [c.strip() for c in l.split('|') if c.strip()]
        if cells and not all(set(c) <= set('-: ') for c in cells):
            data_lines.append(cells)
    if len(data_lines) < 2:
        return None
    header = data_lines[0]
    rows = [r for r in data_lines[1:] if len(r) == len(header)]
    df = pd.DataFrame(rows, columns=header)
    # Auto numeric conversion
    for col in df.columns:
        try:
            cleaned = df[col].str.replace(',', '').str.strip()
            if cleaned.str.endswith('%').any():
                df[col] = pd.to_numeric(cleaned.str.rstrip('%'), errors='coerce')
            else:
                converted = pd.to_numeric(cleaned, errors='coerce')
                if converted.notna().sum() > len(df) * 0.5:
                    df[col] = converted
        except Exception:
            pass
    return df

import matplotlib.pyplot as plt
import matplotlib
import os
font_path = '/usr/share/fonts/truetype/wqy/wqy-zenhei.ttc'
if os.path.exists(font_path):
    matplotlib.rcParams['font.family'] = 'WenQuanYi Zen Hei'
matplotlib.rcParams['axes.unicode_minus'] = False

COLORS = ['#4C72B0', '#55A868', '#C44E52', '#8172B2', '#CCB974', '#64B5CD']

plt.savefig('/mnt/data/chart.png', dpi=150, bbox_inches='tight')
plt.show()
print("![图表](sandbox:/mnt/data/chart.png)")

from openpyxl.styles import Font, PatternFill, Alignment
output_path = "/mnt/data/result.xlsx"
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
    df.to_excel(writer, index=False, sheet_name='提取数据')
    ws = writer.sheets['提取数据']
    fill = PatternFill(start_color='4472C4', end_color='4472C4', fill_type='solid')
    for cell in ws[1]:
        cell.font = Font(bold=True, color='FFFFFF')
        cell.fill = fill
        cell.alignment = Alignment(horizontal='center')
    for i, col in enumerate(df.columns, 1):
        w = max(df[col].astype(str).str.len().max(), len(str(col))) + 2
        ws.column_dimensions[chr(64 + i)].width = min(w * 1.2, 40)
print(f"[下载](sandbox:{output_path})")

import glob
image_files = sorted(glob.glob("/mnt/data/*.png"))
all_dfs = []
for img in image_files:
    r = subprocess.run(
        ["python3", CAPTION, img, "--json", "--prompt", "提取数据，Markdown 表格"],
        capture_output=True, text=True, timeout=60
    )
    desc = json.loads(r.stdout)["description"]
    df = parse_markdown_table(desc)
    if df is not None:
        all_dfs.append(df)
combined = pd.concat(all_dfs, ignore_index=True) if all_dfs else None

python3 scripts/caption.py /mnt/data/images/ --batch --output /mnt/data/captions.json