175 lines
6.6 KiB
Python
175 lines
6.6 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
"""
|
|||
|
|
验证所有图片链接是否有效
|
|||
|
|
"""
|
|||
|
|
import re
|
|||
|
|
from pathlib import Path
|
|||
|
|
from urllib.parse import unquote
|
|||
|
|
from collections import defaultdict
|
|||
|
|
|
|||
|
|
class ImageValidator:
|
|||
|
|
def __init__(self):
|
|||
|
|
self.data_path = Path(__file__).parent.parent / "data" / "订单班文档资料"
|
|||
|
|
self.broken_links = defaultdict(list)
|
|||
|
|
self.valid_links = 0
|
|||
|
|
self.total_links = 0
|
|||
|
|
|
|||
|
|
def extract_image_refs(self, content: str) -> list:
|
|||
|
|
"""提取Markdown中的图片引用"""
|
|||
|
|
# 匹配  格式
|
|||
|
|
pattern1 = r'!\[([^\]]*)\]\(([^)]+)\)'
|
|||
|
|
# 匹配 <img> 标签
|
|||
|
|
pattern2 = r'<img[^>]+src=["\']((?!http)[^"\']+)["\'][^>]*>'
|
|||
|
|
|
|||
|
|
refs = []
|
|||
|
|
for match in re.finditer(pattern1, content):
|
|||
|
|
refs.append(match.group(2))
|
|||
|
|
for match in re.finditer(pattern2, content):
|
|||
|
|
refs.append(match.group(1))
|
|||
|
|
|
|||
|
|
return refs
|
|||
|
|
|
|||
|
|
def normalize_path(self, path: str) -> str:
|
|||
|
|
"""标准化路径"""
|
|||
|
|
path = unquote(path) # URL解码
|
|||
|
|
if path.startswith('./'):
|
|||
|
|
path = path[2:]
|
|||
|
|
if path.startswith('image/'):
|
|||
|
|
return path
|
|||
|
|
return f"image/{path}" if '/' not in path else path
|
|||
|
|
|
|||
|
|
def validate_order_class(self, order_dir: Path) -> dict:
|
|||
|
|
"""验证单个订单班的图片链接"""
|
|||
|
|
notion_dir = order_dir / "notion文稿"
|
|||
|
|
image_dir = notion_dir / "image"
|
|||
|
|
|
|||
|
|
stats = {
|
|||
|
|
"name": order_dir.name,
|
|||
|
|
"total": 0,
|
|||
|
|
"valid": 0,
|
|||
|
|
"broken": 0,
|
|||
|
|
"broken_files": []
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
if not notion_dir.exists():
|
|||
|
|
return stats
|
|||
|
|
|
|||
|
|
# 收集所有实际图片
|
|||
|
|
actual_images = set()
|
|||
|
|
if image_dir.exists():
|
|||
|
|
for img_file in image_dir.glob("*"):
|
|||
|
|
if img_file.is_file() and img_file.suffix.lower() in ['.jpg', '.jpeg', '.png', '.gif', '.webp']:
|
|||
|
|
actual_images.add(img_file.name)
|
|||
|
|
|
|||
|
|
# 检查所有Markdown文件
|
|||
|
|
for md_file in notion_dir.glob("*.md"):
|
|||
|
|
if md_file.name.endswith('.bak') or md_file.name == "图片索引.md":
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
try:
|
|||
|
|
content = md_file.read_text(encoding='utf-8')
|
|||
|
|
refs = self.extract_image_refs(content)
|
|||
|
|
|
|||
|
|
for ref in refs:
|
|||
|
|
stats["total"] += 1
|
|||
|
|
self.total_links += 1
|
|||
|
|
|
|||
|
|
# 规范化路径
|
|||
|
|
normalized = self.normalize_path(ref)
|
|||
|
|
if normalized.startswith('image/'):
|
|||
|
|
img_name = normalized.split('/')[-1]
|
|||
|
|
else:
|
|||
|
|
img_name = normalized
|
|||
|
|
|
|||
|
|
# 检查文件是否存在
|
|||
|
|
if img_name in actual_images:
|
|||
|
|
stats["valid"] += 1
|
|||
|
|
self.valid_links += 1
|
|||
|
|
else:
|
|||
|
|
stats["broken"] += 1
|
|||
|
|
stats["broken_files"].append({
|
|||
|
|
"file": md_file.name,
|
|||
|
|
"ref": ref,
|
|||
|
|
"expected": img_name
|
|||
|
|
})
|
|||
|
|
self.broken_links[order_dir.name].append({
|
|||
|
|
"file": md_file.name,
|
|||
|
|
"ref": ref,
|
|||
|
|
"expected": img_name
|
|||
|
|
})
|
|||
|
|
except Exception as e:
|
|||
|
|
print(f" ⚠️ 无法读取 {md_file.name}: {e}")
|
|||
|
|
|
|||
|
|
return stats
|
|||
|
|
|
|||
|
|
def run(self):
|
|||
|
|
"""验证所有订单班"""
|
|||
|
|
print("\n" + "="*60)
|
|||
|
|
print("🔍 图片链接验证工具")
|
|||
|
|
print("="*60)
|
|||
|
|
|
|||
|
|
# 获取所有订单班
|
|||
|
|
order_classes = sorted([d for d in self.data_path.iterdir() if d.is_dir()])
|
|||
|
|
|
|||
|
|
all_stats = []
|
|||
|
|
|
|||
|
|
for order_dir in order_classes:
|
|||
|
|
stats = self.validate_order_class(order_dir)
|
|||
|
|
all_stats.append(stats)
|
|||
|
|
|
|||
|
|
# 显示结果
|
|||
|
|
if stats["total"] > 0:
|
|||
|
|
if stats["broken"] == 0:
|
|||
|
|
print(f"✅ {stats['name']}: 所有 {stats['total']} 个链接有效")
|
|||
|
|
else:
|
|||
|
|
print(f"❌ {stats['name']}: {stats['broken']}/{stats['total']} 个链接损坏")
|
|||
|
|
for broken in stats["broken_files"][:3]:
|
|||
|
|
print(f" - {broken['file']}: {broken['ref']}")
|
|||
|
|
if len(stats["broken_files"]) > 3:
|
|||
|
|
print(f" ... 还有 {len(stats['broken_files']) - 3} 个")
|
|||
|
|
else:
|
|||
|
|
print(f"ℹ️ {stats['name']}: 无图片引用")
|
|||
|
|
|
|||
|
|
# 显示总结
|
|||
|
|
print("\n" + "="*60)
|
|||
|
|
print("📊 总结")
|
|||
|
|
print("="*60)
|
|||
|
|
print(f" 检查订单班: {len(order_classes)} 个")
|
|||
|
|
print(f" 总链接数: {self.total_links}")
|
|||
|
|
print(f" 有效链接: {self.valid_links}")
|
|||
|
|
print(f" 损坏链接: {self.total_links - self.valid_links}")
|
|||
|
|
|
|||
|
|
if self.valid_links == self.total_links:
|
|||
|
|
print(f"\n🎉 所有图片链接都有效！")
|
|||
|
|
else:
|
|||
|
|
broken_percentage = ((self.total_links - self.valid_links) / self.total_links) * 100
|
|||
|
|
print(f"\n⚠️ {broken_percentage:.1f}% 的链接需要修复")
|
|||
|
|
|
|||
|
|
# 显示需要修复的订单班
|
|||
|
|
print("\n需要修复的订单班:")
|
|||
|
|
for order_name, broken_refs in self.broken_links.items():
|
|||
|
|
print(f" • {order_name}: {len(broken_refs)} 个损坏链接")
|
|||
|
|
|
|||
|
|
# 保存验证报告
|
|||
|
|
report_file = Path(__file__).parent.parent / "image_validation_report.txt"
|
|||
|
|
with open(report_file, 'w', encoding='utf-8') as f:
|
|||
|
|
f.write("图片链接验证报告\n")
|
|||
|
|
f.write("="*60 + "\n\n")
|
|||
|
|
|
|||
|
|
for stats in all_stats:
|
|||
|
|
f.write(f"{stats['name']}:\n")
|
|||
|
|
f.write(f" 总链接: {stats['total']}\n")
|
|||
|
|
f.write(f" 有效: {stats['valid']}\n")
|
|||
|
|
f.write(f" 损坏: {stats['broken']}\n")
|
|||
|
|
|
|||
|
|
if stats['broken_files']:
|
|||
|
|
f.write(" 损坏详情:\n")
|
|||
|
|
for broken in stats['broken_files']:
|
|||
|
|
f.write(f" - {broken['file']}: {broken['ref']} -> {broken['expected']}\n")
|
|||
|
|
f.write("\n")
|
|||
|
|
|
|||
|
|
print(f"\n📄 详细报告已保存到: {report_file}")
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
validator = ImageValidator()
|
|||
|
|
validator.run()
|