152 lines
5.2 KiB
Python
152 lines
5.2 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Analyze PPT and PDF materials to extract main content structure
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
from pathlib import Path
|
|
from pptx import Presentation
|
|
import fitz # PyMuPDF
|
|
|
|
class MaterialAnalyzer:
|
|
def __init__(self):
|
|
self.project_root = Path(__file__).parent.parent
|
|
|
|
def analyze_ppt(self):
|
|
"""Analyze PPT structure and content"""
|
|
print("=" * 80)
|
|
print("📊 PPT分析结果")
|
|
print("=" * 80)
|
|
|
|
ppt_path = self.project_root / "assets/0_input/ライフプラン情報.pptx"
|
|
prs = Presentation(str(ppt_path))
|
|
|
|
print(f"\n总页数: {len(prs.slides)}页\n")
|
|
|
|
for idx, slide in enumerate(prs.slides):
|
|
print(f"\n【第{idx + 1}页】")
|
|
print("-" * 60)
|
|
|
|
# Extract title
|
|
if slide.shapes.title:
|
|
print(f"标题: {slide.shapes.title.text}")
|
|
|
|
# Extract text content
|
|
text_content = []
|
|
for shape in slide.shapes:
|
|
if hasattr(shape, "text") and shape.text.strip():
|
|
if shape != slide.shapes.title:
|
|
text_content.append(shape.text.strip())
|
|
|
|
if text_content:
|
|
print(f"\n内容摘要:")
|
|
for i, text in enumerate(text_content[:5], 1): # Show first 5 items
|
|
preview = text[:100] + "..." if len(text) > 100 else text
|
|
print(f" {i}. {preview}")
|
|
|
|
if len(text_content) > 5:
|
|
print(f" ... (还有{len(text_content) - 5}项内容)")
|
|
|
|
print(f"\n文本框数量: {len(text_content)}")
|
|
|
|
def analyze_pdf(self):
|
|
"""Analyze PDF structure and content"""
|
|
print("\n\n" + "=" * 80)
|
|
print("📄 PDF分析结果")
|
|
print("=" * 80)
|
|
|
|
pdf_path = self.project_root / "assets/0_input/帳票（お客様向け）.pdf"
|
|
doc = fitz.open(str(pdf_path))
|
|
|
|
print(f"\n总页数: {len(doc)}页\n")
|
|
|
|
for page_num in range(min(10, len(doc))): # Analyze first 10 pages
|
|
page = doc[page_num]
|
|
text = page.get_text()
|
|
|
|
print(f"\n【第{page_num + 1}页】")
|
|
print("-" * 60)
|
|
|
|
# Extract key information
|
|
lines = [line.strip() for line in text.split('\n') if line.strip()]
|
|
|
|
if lines:
|
|
print(f"页面内容预览:")
|
|
for i, line in enumerate(lines[:15], 1): # Show first 15 lines
|
|
preview = line[:80] + "..." if len(line) > 80 else line
|
|
print(f" {i}. {preview}")
|
|
|
|
if len(lines) > 15:
|
|
print(f" ... (还有{len(lines) - 15}行内容)")
|
|
else:
|
|
print(" (此页可能为图像或表格)")
|
|
|
|
print(f"\n文本行数: {len(lines)}")
|
|
|
|
if len(doc) > 10:
|
|
print(f"\n... (还有{len(doc) - 10}页未显示)")
|
|
|
|
doc.close()
|
|
|
|
def find_family_info_pages(self):
|
|
"""Find pages containing family information"""
|
|
print("\n\n" + "=" * 80)
|
|
print("🔍 家庭信息页面定位")
|
|
print("=" * 80)
|
|
|
|
pdf_path = self.project_root / "assets/0_input/帳票（お客様向け）.pdf"
|
|
doc = fitz.open(str(pdf_path))
|
|
|
|
keywords = ["テスト太郎", "家族", "年齢", "年収", "生年月日", "基本情報", "家族構成"]
|
|
|
|
print(f"\n搜索关键词: {', '.join(keywords)}\n")
|
|
|
|
matches = []
|
|
for page_num in range(len(doc)):
|
|
page = doc[page_num]
|
|
text = page.get_text()
|
|
|
|
found_keywords = [kw for kw in keywords if kw in text]
|
|
if found_keywords:
|
|
matches.append((page_num, found_keywords, text))
|
|
|
|
if matches:
|
|
print(f"找到{len(matches)}个包含家庭信息的页面:\n")
|
|
for page_num, keywords_found, text in matches[:5]: # Show first 5
|
|
print(f"【PDF第{page_num + 1}页】(pdfPageIndex={page_num})")
|
|
print(f" 匹配关键词: {', '.join(keywords_found)}")
|
|
|
|
# Show excerpt
|
|
lines = [line.strip() for line in text.split('\n') if line.strip()]
|
|
print(f" 内容片段:")
|
|
for line in lines[:8]:
|
|
preview = line[:70] + "..." if len(line) > 70 else line
|
|
print(f" {preview}")
|
|
print()
|
|
else:
|
|
print("未找到包含家庭信息的页面")
|
|
|
|
doc.close()
|
|
|
|
def run(self):
|
|
"""Execute full analysis"""
|
|
try:
|
|
self.analyze_ppt()
|
|
self.analyze_pdf()
|
|
self.find_family_info_pages()
|
|
|
|
print("\n" + "=" * 80)
|
|
print("✅ 分析完成")
|
|
print("=" * 80)
|
|
|
|
except Exception as e:
|
|
print(f"\n❌ 分析失败: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
|
|
if __name__ == "__main__":
|
|
analyzer = MaterialAnalyzer()
|
|
analyzer.run()
|