add sentry

src/green_classroom/apps/collector/crawler/xinhua.py

@@ -3,13 +3,27 @@ from bs4 import BeautifulSoup
 from urllib.parse import urljoin
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from datetime import datetime, timedelta
-import pytz  # 确保已安装 pytz 库，用于处理时区
+import pytz
+import logging
+import sys
+
+# 配置logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s [%(levelname)s] %(message)s',
+    handlers=[
+        logging.StreamHandler(sys.stdout)
+    ]
+)
+
+logger = logging.getLogger(__name__)
 
 BASE_URL = "https://www.news.cn/"
 HEADERS = {
     "User-Agent": "Mozilla/5.0"
 }
 
+
 def parse_xinhua_article(url: str, time_range_days: int = None):
     """
     解析新华网文章页，返回 dict 包含标题与正文。
@@ -19,7 +33,7 @@ def parse_xinhua_article(url: str, time_range_days: int = None):
         resp = requests.get(url, headers=HEADERS, timeout=10)
         resp.encoding = 'utf-8'
     except requests.RequestException as e:
-        print(f"❌ 请求失败：{e} URL: {url}")
+        logger.error(f"❌ 请求失败：{e} URL: {url}")
         return None
 
     soup = BeautifulSoup(resp.text, "html.parser")
@@ -29,14 +43,14 @@ def parse_xinhua_article(url: str, time_range_days: int = None):
 
     content_tag = soup.find("span", id="detailContent")
     if not content_tag:
-        print(f"❌ 没找到 detailContent: {url}")
+        logger.error(f"❌ 没找到 detailContent: {url}")
         return None
 
     paragraphs = content_tag.find_all("p")
     content = "\n".join(p.get_text(strip=True) for p in paragraphs)
 
     if len(content.strip()) < 50:
-        print(f"⚠️ 内容过短：{url}")
+        logger.warning(f"⚠️ 内容过短：{url}")
         return None
 
     # 提取发布时间（假设格式为 YYYY-MM-DD）
@@ -46,17 +60,18 @@ def parse_xinhua_article(url: str, time_range_days: int = None):
         try:
             publish_time = datetime.strptime(publish_time_str, "%Y-%m-%d").replace(tzinfo=pytz.utc)
         except ValueError:
-            print(f"❌ 无法解析时间：{publish_time_str} URL: {url}")
+            logger.error(f"❌ 无法解析时间：{publish_time_str} URL: {url}")
             return None
     else:
-        print(f"❌ 页面未找到发布时间：{url}")
+        logger.error(f"❌ 页面未找到发布时间：{url}")
         return None
 
-    # 检查时间范围
+    # 确保 title 和 content 为 UTF-8 编码的字符串
-    if time_range_days is not None:
+    try:
-        cutoff_time = datetime.now(pytz.utc) - timedelta(days=time_range_days)
+        title = title.encode('utf-8').decode('utf-8')
-        if publish_time < cutoff_time:
+        content = content.encode('utf-8').decode('utf-8')
-            print(f"⏰ 文章超出时间范围：{url}")
+    except UnicodeDecodeError:
+        logger.error(f"❌ 字符编码错误，无法正确解码标题或内容：{url}")
         return None
 
     return {
@@ -66,14 +81,15 @@ def parse_xinhua_article(url: str, time_range_days: int = None):
         "publish_time": publish_time
     }
 
+
 def crawl_xinhua_green(time_range_days: int = None):
     """
     爬取新华网所有频道及其文章，并保存到数据库（支持多线程）。
     可选参数：time_range_days（仅爬取最近指定天数内的文章）
     """
-    print("✅ 开始爬取新华网栏目列表...")
+    logger.info("✅ 开始爬取新华网栏目列表...")
     channels = get_channel_urls()
-    print(f"共找到 {len(channels)} 个频道")
+    logger.info(f"共找到 {len(channels)} 个频道")
 
     all_articles = []
 
@@ -88,8 +104,8 @@ def crawl_xinhua_green(time_range_days: int = None):
             ch_url = future_to_channel[future]
             try:
                 articles = future.result()
-                print(f"\n➡️ 抓取频道：{ch_url}")
+                logger.info(f"\n➡️ 抓取频道：{ch_url}")
-                print(f"  该频道找到 {len(articles)} 篇文章")
+                logger.info(f"  该频道找到 {len(articles)} 篇文章")
 
                 # 并发解析每篇文章
                 with ThreadPoolExecutor(max_workers=5) as article_executor:
@@ -101,7 +117,7 @@ def crawl_xinhua_green(time_range_days: int = None):
                     for article_future in as_completed(article_futures):
                         article = article_future.result()
                         if article:
-                            print(f"  ✔️ 文章：{article['title']}")
+                            logger.info(f"  ✔️ 文章：{article['title']}")
                             # 更新或创建文章，并标记 crawled=True
                             Article.objects.update_or_create(
                                 url=article['url'],
@@ -113,12 +129,44 @@ def crawl_xinhua_green(time_range_days: int = None):
                             )
                             all_articles.append(article)
                         else:
-                            print(f"  ❌ 文章解析失败：{article_futures[article_future]}")
+                            logger.error(f"  ❌ 文章解析失败：{article_futures[article_future]}")
             except Exception as exc:
-                print(f"❌ 频道 {ch_url} 抓取时发生异常：{exc}")
+                logger.error(f"❌ 频道 {ch_url} 抓取时发生异常：{exc}")
 
-    print(f"\n✅ 爬取结束，共抓取文章 {len(all_articles)} 篇")
+    logger.info(f"\n✅ 爬取结束，共抓取文章 {len(all_articles)} 篇")
     return all_articles
 
+
 if __name__ == "__main__":
+    logger.info("开始爬取...")
     crawl_xinhua_green(time_range_days=7)  # 示例：仅爬取最近 7 天的文章
+    logger.info("爬取完成")
+
+
+from django.http import JsonResponse
+
+
+def export_articles(request):
+    """
+    导出所有爬取的文章为 JSON 格式。
+    可通过访问 /export/xinhua-article/ 触发
+    """
+    time_range_days = request.GET.get('time_range_days', None)
+    if time_range_days is not None:
+        try:
+            time_range_days = int(time_range_days)
+        except ValueError:
+            logger.error("❌ 无效的时间范围参数")
+            return JsonResponse({"error": "无效的时间范围参数"}, status=400)
+
+    logger.info(f"开始导出文章，时间范围：{time_range_days} 天")
+    # 获取文章数据
+    articles = crawl_xinhua_green(time_range_days=time_range_days)
+
+    logger.info(f"成功导出 {len(articles)} 篇文章")
+    # 返回 JSON 响应，并确保中文不被转义
+    return JsonResponse(
+        articles,
+        safe=False,
+        json_dumps_params={'ensure_ascii': False, 'separators': (',', ':')}  # 减少空格，更兼容 Safari
+    )

src/green_classroom/apps/collector/migrations/0003_article_publish_time.py

@@ -0,0 +1,18 @@
+# Generated by Django 5.1 on 2025-07-22 07:53
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('collector', '0002_rename_is_verified_article_crawled_and_more'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='article',
+            name='publish_time',
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+    ]

src/green_classroom/apps/collector/models.py

@@ -14,6 +14,7 @@ class Article(models.Model):
     title = models.CharField(max_length=255)
     content = models.TextField()
     crawled = models.BooleanField(default=False)  # 确保此字段存在
+    publish_time = models.DateTimeField(null=True, blank=True)  # 添加 publish_time 字段
 
     def __str__(self):
         return self.title

src/green_classroom/apps/collector/templates/collector/article_list.html

@@ -20,5 +20,42 @@
         <li>暂无内容</li>
         {% endfor %}
     </ul>
+
+    <div>
+      <input type="number" id="timeRange" placeholder="时间范围（天）" />
+      <button onclick="exportArticles()">导出文章</button>
+    </div>
+
+    <script>
+    function exportArticles() {
+      const timeRange = document.getElementById('timeRange').value;
+      let exportUrl = '/collector/export/xinhua-article/';
+      
+      if (timeRange) {
+        exportUrl += `?time_range_days=${timeRange}`;
+      }
+
+      // 发起请求并触发下载
+      fetch(exportUrl)
+        .then(response => {
+          if (!response.ok) {
+            throw new Error('导出失败');
+          }
+          return response.blob();
+        })
+        .then(blob => {
+          const downloadUrl = window.URL.createObjectURL(blob);
+          const a = document.createElement('a');
+          a.href = downloadUrl;
+          a.download = 'articles.json';
+          document.body.appendChild(a);
+          a.click();
+          a.remove();
+        })
+        .catch(error => {
+          alert(error);
+        });
+    }
+    </script>
 </body>
 </html>

src/green_classroom/apps/collector/urls.py

@@ -1,10 +1,8 @@
-from django.urls import path
+app_name = 'collector'  # 添加 app_name 定义命名空间
-from green_classroom.apps.collector import views
 
-app_name = 'collector'  # 确保命名空间正确
+from django.urls import path
+from . import views
 
 urlpatterns = [
-    path('delete_all_articles/', views.delete_all_articles, name='delete_all_articles'),
+    path('article/<int:pk>/', views.article_detail, name='article_detail'),
-    path('article/<int:article_id>/', views.article_detail, name='article_detail'),
-    path('articles/', views.list_articles, name='article_list'),  # 添加这一行
 ]

src/green_classroom/apps/collector/views.py

@@ -1,3 +1,29 @@
+import logging
+import sys
+
+# 配置logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s [%(levelname)s] %(message)s',
+    handlers=[
+        logging.StreamHandler(sys.stdout)
+    ]
+)
+
+logger = logging.getLogger(__name__)
+
+
+from django.shortcuts import render
+from django.http import HttpResponse
+from django.http import JsonResponse
+from .models import Article  # 假设 Article 是你的模型
+
+def index(request):
+    """
+    主页视图，显示欢迎信息或文章列表。
+    """
+    return HttpResponse("欢迎来到绿色课堂资料库！")
+
 from django.shortcuts import render, get_object_or_404
 from django.core.management import call_command
 from green_classroom.apps.collector.models import Article
@@ -12,12 +38,25 @@ def list_articles(request):
     articles = Article.objects.all()
     return render(request, 'collector/article_list.html', {'articles': articles})
 
-def article_detail(request, article_id):
+def article_detail(request, pk):
     """
-    展示单篇文章的详细内容
+    根据主键 pk 获取文章详情。
     """
-    article = get_object_or_404(Article, id=article_id)
+    try:
-    return render(request, 'collector/article_detail.html', {'article': article})
+        article = Article.objects.get(pk=pk)
+        logger.info(f"返回文章标题: {article.title}")  # 添加日志确认标题是否正常
+        logger.info(f"返回文章内容: {article.content[:100]}...")  # 输出前100字符确认内容是否正常
+        data = {
+            'id': article.id,
+            'url': article.url,
+            'title': str(article.title),  # 强制转换为 str，避免潜在的编码问题
+            'content': str(article.content),  # 强制转换为 str
+            'publish_time': article.publish_time.isoformat() if article.publish_time else None,  # 格式化时间
+            'crawled': article.crawled
+        }
+        return JsonResponse(data, json_dumps_params={'ensure_ascii': False})
+    except Article.DoesNotExist:
+        return JsonResponse({'error': '文章不存在'}, status=404)
 
 def run_crawler(request):
     result = []

src/green_classroom/settings.py

@@ -25,8 +25,9 @@ SECRET_KEY = 'django-insecure-mi#9dyl0zwanl2=uziz3om_t**ovk08+pg127^+=5m=s6^+(@b
 
 # SECURITY WARNING: don't run with debug turned on in production!
 DEBUG = True
+#DEBUG = False
 
-ALLOWED_HOSTS = []
+ALLOWED_HOSTS = ['*',]
 
 
 # Application definition
@@ -126,3 +127,14 @@ DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
 
 # 增加最大字段数限制，适应 admin 页面大数据量展示
 DATA_UPLOAD_MAX_NUMBER_FIELDS = 10240
+
+
+import sentry_sdk
+
+sentry_sdk.init(
+    dsn="https://a976759c113a1e07050c61fb4dfe16bc@sentry.yuangyaa.com/2",
+    # Add data like request headers and IP for users,
+    # see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
+    send_default_pii=True,
+    environment="staging",  # 或其他你设置的环境名
+)

src/green_classroom/urls.py

@@ -7,3 +7,4 @@ urlpatterns = [
     path('articles/', views.list_articles, name='article_list'),
     path('admin/', admin.site.urls),  # 添加这一行以恢复 admin 页面访问
 ]
+