内容刷新自动化
掌握内容刷新流程的自动化方法，建立持续监控、自动识别、批量刷新的高效工作流

# 内容刷新信号自动检测脚本
import json, requests, re
from datetime import datetime, timedelta
from urllib.parse import urljoin

class ContentRefreshDetector:
    def __init__(self, sitemap_url):
        self.sitemap_url = sitemap_url
        self.urls = []
        self.results = []
    
    def load_urls_from_sitemap(self):
        """从Sitemap加载所有URL"""
        resp = requests.get(self.sitemap_url)
        urls = re.findall(r'<loc>(.*?)</loc>', resp.text)
        self.urls = urls
        print(f"Loaded {len(urls)} URLs")
    
    def check_url(self, url):
        """检查单个URL的刷新信号"""
        signals = []
        score = 0
        
        try:
            resp = requests.get(url, timeout=10)
            html = resp.text
            
            # 信号1: dateModified检查
            mod_match = re.search(r'"dateModified":\s*"([^"]+)"', html)
            if mod_match:
                mod_date = datetime.fromisoformat(mod_match.group(1).replace('Z', '+00:00'))
                days_since = (datetime.now(mod_date.tzinfo) - mod_date).days
                if days_since > 180:
                    signals.append(f"内容超过{days_since}天未更新")
                    score += 30
            else:
                signals.append("缺少dateModified标记")
                score += 20
            
            # 信号2: Schema检查
            has_article = 'NewsArticle' in html or 'Article' in html
            has_faq = 'FAQPage' in html
            if not has_faq:
                signals.append("缺少FAQ Schema")
                score += 10
            
            # 信号3: 内容长度检查
            body_text = re.sub(r'<[^>]+>', '', html)
            if len(body_text) < 1000:
                signals.append(f"内容过短({len(body_text)}字)")
                score += 15
            
            # 信号4: 失效链接检查
            links = re.findall(r'href="([^"]+)"', html)
            # 可扩展为实际链接检查
            
        except Exception as e:
            signals.append(f"检查失败: {str(e)}")
            score += 50
        
        return {'url': url, 'score': score, 'signals': signals}
    
    def run_audit(self):
        """执行全站审计"""
        self.load_urls_from_sitemap()
        for url in self.urls:
            result = self.check_url(url)
            self.results.append(result)
        
        # 按分数排序
        self.results.sort(key=lambda x: x['score'], reverse=True)
        
        # 输出报告
        print(f"\n{'='*60}")
        print(f"内容刷新审计报告")
        print(f"{'='*60}")
        print(f"总页面数: {len(self.results)}")
        print(f"需要紧急刷新(>50分): {len([r for r in self.results if r['score']>=50])}")
        print(f"建议刷新(30-49分): {len([r for r in self.results if 30<=r['score']<50])}")
        print(f"保持监控(<30分): {len([r for r in self.results if r['score']<30])}")
        
        # 输出TOP10
        print(f"\nTOP 10 需刷新页面:")
        for r in self.results[:10]:
            print(f"  [{r['score']}分] {r['url']}")
            for s in r['signals']:
                print(f"    - {s}")