add sentry

.idea/.gitignore

@@ -0,0 +1,8 @@
+# 默认忽略的文件
+/shelf/
+/workspace.xml
+# 基于编辑器的 HTTP 客户端请求
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/green_classroom.iml

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="FacetManager">
+    <facet type="django" name="Django">
+      <configuration>
+        <option name="rootFolder" value="$MODULE_DIR$/src" />
+        <option name="settingsModule" value="green_classroom/settings.py" />
+        <option name="manageScript" value="$MODULE_DIR$/src/manage.py" />
+        <option name="environment" value="&lt;map/&gt;" />
+        <option name="doNotUseTestRunner" value="false" />
+        <option name="trackFilePattern" value="migrations" />
+      </configuration>
+    </facet>
+  </component>
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <sourceFolder url="file://$MODULE_DIR$/src" isTestSource="false" />
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.12 (green_classroom)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.12 (green_classroom)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (green_classroom)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/green_classroom.iml" filepath="$PROJECT_DIR$/.idea/green_classroom.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

README.md

@@ -1,3 +1,4 @@
 # green_classroom
 
 行政办 绿色课堂
+# init projects 

develop.txt

@@ -0,0 +1 @@
+# 開發分支

init.txt

@@ -0,0 +1 @@
+0.1 初始內容

requirements.in

@@ -0,0 +1,6 @@
+uv==0.7.22
+django==5.1 
+psycopg2-binary 
+requests 
+beautifulsoup4
+ipython

requirements.txt

@@ -0,0 +1,70 @@
+#
+# This file is autogenerated by pip-compile with Python 3.12
+# by the following command:
+#
+#    pip-compile requirements.in
+#
+--index-url https://pypi.nicestudio.com.tw/root/pypi
+
+asgiref==3.9.1
+    # via django
+asttokens==3.0.0
+    # via stack-data
+beautifulsoup4==4.13.4
+    # via -r requirements.in
+certifi==2025.7.14
+    # via requests
+charset-normalizer==3.4.2
+    # via requests
+decorator==5.2.1
+    # via ipython
+django==5.1
+    # via -r requirements.in
+executing==2.2.0
+    # via stack-data
+idna==3.10
+    # via requests
+ipython==9.4.0
+    # via -r requirements.in
+ipython-pygments-lexers==1.1.1
+    # via ipython
+jedi==0.19.2
+    # via ipython
+matplotlib-inline==0.1.7
+    # via ipython
+parso==0.8.4
+    # via jedi
+pexpect==4.9.0
+    # via ipython
+prompt-toolkit==3.0.51
+    # via ipython
+psycopg2-binary==2.9.10
+    # via -r requirements.in
+ptyprocess==0.7.0
+    # via pexpect
+pure-eval==0.2.3
+    # via stack-data
+pygments==2.19.2
+    # via
+    #   ipython
+    #   ipython-pygments-lexers
+requests==2.32.4
+    # via -r requirements.in
+soupsieve==2.7
+    # via beautifulsoup4
+sqlparse==0.5.3
+    # via django
+stack-data==0.6.3
+    # via ipython
+traitlets==5.14.3
+    # via
+    #   ipython
+    #   matplotlib-inline
+typing-extensions==4.14.1
+    # via beautifulsoup4
+urllib3==2.5.0
+    # via requests
+uv==0.7.22
+    # via -r requirements.in
+wcwidth==0.2.13
+    # via prompt-toolkit

src/green_classroom/apps/collector/admin.py

@@ -0,0 +1,7 @@
+from django.contrib import admin
+from .models import Article
+
+@admin.register(Article)
+class ArticleAdmin(admin.ModelAdmin):
+    list_display = ('title', 'url', 'crawled')
+    search_fields = ('title',)

src/green_classroom/apps/collector/apps.py

@@ -0,0 +1,6 @@
+from django.apps import AppConfig
+
+
+class CollectorConfig(AppConfig):
+    default_auto_field = 'django.db.models.BigAutoField'
+    name = 'green_classroom.apps.collector'  # 修改为完整路径

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

@@ -0,0 +1,172 @@
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from datetime import datetime, timedelta
+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。
+    如果指定了 time_range_days，则只保留该时间范围内的文章。
+    """
+    try:
+        resp = requests.get(url, headers=HEADERS, timeout=10)
+        resp.encoding = 'utf-8'
+    except requests.RequestException as e:
+        logger.error(f"❌ 请求失败：{e} URL: {url}")
+        return None
+
+    soup = BeautifulSoup(resp.text, "html.parser")
+
+    title_tag = soup.find("span", class_="title")
+    title = title_tag.get_text(strip=True) if title_tag else "无标题"
+
+    content_tag = soup.find("span", id="detailContent")
+    if not content_tag:
+        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:
+        logger.warning(f"⚠️ 内容过短：{url}")
+        return None
+
+    # 提取发布时间（假设格式为 YYYY-MM-DD）
+    publish_time_tag = soup.find("span", class_="publish-time")
+    if publish_time_tag:
+        publish_time_str = publish_time_tag.get_text(strip=True)
+        try:
+            publish_time = datetime.strptime(publish_time_str, "%Y-%m-%d").replace(tzinfo=pytz.utc)
+        except ValueError:
+            logger.error(f"❌ 无法解析时间：{publish_time_str} URL: {url}")
+            return None
+    else:
+        logger.error(f"❌ 页面未找到发布时间：{url}")
+        return None
+
+    # 确保 title 和 content 为 UTF-8 编码的字符串
+    try:
+        title = title.encode('utf-8').decode('utf-8')
+        content = content.encode('utf-8').decode('utf-8')
+    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 {
+        "url": url,
+        "title": title,
+        "content": content,
+        "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）
+    """
+    logger.info("✅ 开始爬取新华网栏目列表...")
+    channels = get_channel_urls()
+    logger.info(f"共找到 {len(channels)} 个频道")
+
+    all_articles = []
+
+    # 并发抓取每个频道的文章链接
+    with ThreadPoolExecutor(max_workers=5) as executor:
+        future_to_channel = {
+            executor.submit(get_article_urls_from_channel, ch_url): ch_url
+            for ch_url in channels
+        }
+
+        for future in as_completed(future_to_channel):
+            ch_url = future_to_channel[future]
+            try:
+                articles = future.result()
+                logger.info(f"\n➡️ 抓取频道：{ch_url}")
+                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:
+                    article_futures = {
+                        article_executor.submit(parse_xinhua_article, art_url, time_range_days): art_url
+                        for art_url in articles
+                    }
+
+                    for article_future in as_completed(article_futures):
+                        article = article_future.result()
+                        if article:
+                            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'],
+                                defaults={
+                                    'title': article['title'],
+                                    'content': article['content'],
+                                    'crawled': True  # 标记为已爬取
+                                }
+                            )
+                            all_articles.append(article)
+                        else:
+                            logger.error(f"  ❌ 文章解析失败：{article_futures[article_future]}")
+            except Exception as exc:
+                logger.error(f"❌ 频道 {ch_url} 抓取时发生异常：{exc}")
+
+    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/management/commands/crawl_xinhua.py

@@ -0,0 +1,10 @@
+from django.core.management.base import BaseCommand
+from green_classroom.apps.collector.crawler.xinhua import crawl_xinhua_green
+
+class Command(BaseCommand):
+    help = '爬取新华网文章并保存到数据库'
+
+    def handle(self, *args, **kwargs):
+        self.stdout.write("开始爬取...")
+        articles = crawl_xinhua_green()
+        self.stdout.write(f"爬取完成，共抓取 {len(articles)} 篇文章")

src/green_classroom/apps/collector/migrations/0001_initial.py

@@ -0,0 +1,39 @@
+# Generated by Django 5.1 on 2025-07-21 12:00
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='SourceSite',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('name', models.CharField(max_length=100)),
+                ('url', models.URLField()),
+                ('is_active', models.BooleanField(default=True)),
+                ('remarks', models.TextField(blank=True)),
+            ],
+        ),
+        migrations.CreateModel(
+            name='Article',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('title', models.CharField(max_length=300)),
+                ('url', models.URLField(unique=True)),
+                ('publish_date', models.DateField(blank=True, null=True)),
+                ('content', models.TextField()),
+                ('category', models.CharField(choices=[('政策', '政策'), ('案例', '案例'), ('新闻', '新闻'), ('科研', '科研')], max_length=100)),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+                ('is_verified', models.BooleanField(default=False)),
+                ('source', models.ForeignKey(null=True, on_delete=django.db.models.deletion.SET_NULL, to='collector.sourcesite')),
+            ],
+        ),
+    ]

src/green_classroom/apps/collector/migrations/0002_rename_is_verified_article_crawled_and_more.py

@@ -0,0 +1,39 @@
+# Generated by Django 5.1 on 2025-07-21 12:52
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('collector', '0001_initial'),
+    ]
+
+    operations = [
+        migrations.RenameField(
+            model_name='article',
+            old_name='is_verified',
+            new_name='crawled',
+        ),
+        migrations.RemoveField(
+            model_name='article',
+            name='category',
+        ),
+        migrations.RemoveField(
+            model_name='article',
+            name='created_at',
+        ),
+        migrations.RemoveField(
+            model_name='article',
+            name='publish_date',
+        ),
+        migrations.RemoveField(
+            model_name='article',
+            name='source',
+        ),
+        migrations.AlterField(
+            model_name='article',
+            name='title',
+            field=models.CharField(max_length=255),
+        ),
+    ]

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

@@ -0,0 +1,20 @@
+from django.db import models
+
+class SourceSite(models.Model):
+    name = models.CharField(max_length=100)
+    url = models.URLField()
+    is_active = models.BooleanField(default=True)
+    remarks = models.TextField(blank=True)
+
+    def __str__(self):
+        return self.name
+
+class Article(models.Model):
+    url = models.URLField(unique=True)
+    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_detail.html

@@ -0,0 +1,16 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>{{ article.title }}</title>
+</head>
+<body>
+    <h1>{{ article.title }}</h1>
+    <p><strong>来源：</strong>{{ article.source.name }}</p>
+    <p><strong>分类：</strong>{{ article.category }}</p>
+    <p><strong>发布时间：</strong>{{ article.publish_date }}</p>
+    <div>
+        {{ article.content|linebreaks }}
+    </div>
+    <p><a href="{% url 'collector:article_list' %}">返回列表</a></p>
+</body>
+</html>

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

@@ -0,0 +1,61 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>绿色课堂资料库</title>
+</head>
+<body>
+    <h1>绿色课堂资料库</h1>
+    <form method="get">
+        <input type="text" name="q" placeholder="关键词搜索..." value="{{ request.GET.q }}">
+        <button type="submit">搜索</button>
+    </form>
+
+    <ul>
+        {% for article in articles %}
+        <li>
+            <a href="{% url 'collector:article_detail' article.id %}">{{ article.title }}</a>
+            （{{ article.category }} | {{ article.publish_date }}）
+        </li>
+        {% empty %}
+        <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/tests.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

src/green_classroom/apps/collector/urls.py

@@ -0,0 +1,8 @@
+app_name = 'collector'  # 添加 app_name 定义命名空间
+
+from django.urls import path
+from . import views
+
+urlpatterns = [
+    path('article/<int:pk>/', views.article_detail, name='article_detail'),
+]

src/green_classroom/apps/collector/views.py

@@ -0,0 +1,90 @@
+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
+import os
+from django.conf import settings
+from django.template import TemplateDoesNotExist
+
+def list_articles(request):
+    """
+    展示所有文章的视图
+    """
+    articles = Article.objects.all()
+    return render(request, 'collector/article_list.html', {'articles': articles})
+
+def article_detail(request, pk):
+    """
+    根据主键 pk 获取文章详情。
+    """
+    try:
+        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 = []
+    if request.method == 'POST':
+        # 调用爬虫命令并获取输出
+        from io import StringIO
+        output = StringIO()
+        call_command('crawl_xinhua', stdout=output)
+        result.append(output.getvalue())
+    
+    # 调试：打印模板路径
+    template_path = os.path.join(settings.BASE_DIR, 'templates', 'collector', 'run_crawler.html')
+    print(f"🔍 正在查找模板文件：{template_path}")
+    
+    # 调试：检查模板是否存在
+    try:
+        with open(template_path, 'r', encoding='utf-8') as f:
+            print("✅ 模板文件存在")
+    except FileNotFoundError:
+        print("❌ 模板文件不存在，请检查路径")
+    
+    return render(request, 'collector/run_crawler.html', {'output': result})
+
+def delete_all_articles(request):
+    """
+    删除所有文章的视图
+    """
+    if request.method == 'POST':
+        Article.objects.all().delete()
+        return redirect('collector:article_list')
+    return render(request, 'collector/delete_all_articles.html')

src/green_classroom/asgi.py

@@ -0,0 +1,16 @@
+"""
+ASGI config for green_classroom project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'green_classroom.settings')
+
+application = get_asgi_application()

src/green_classroom/settings.py

@@ -0,0 +1,140 @@
+"""
+Django settings for green_classroom project.
+
+Generated by 'django-admin startproject' using Django 5.1.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/5.1/ref/settings/
+"""
+
+from pathlib import Path
+import os
+
+# Build paths inside the project like this: BASE_DIR / 'subdir'.
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/5.1/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+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 = ['*',]
+
+
+# Application definition
+
+INSTALLED_APPS = [
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+    'green_classroom.apps.collector.apps.CollectorConfig',
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'green_classroom.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [os.path.join(BASE_DIR, 'templates')],  # ✅ 确保此行存在
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'green_classroom.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/5.1/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.sqlite3',
+        'NAME': BASE_DIR / 'db.sqlite3',
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/5.1/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/5.1/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/5.1/howto/static-files/
+
+STATIC_URL = 'static/'
+
+# Default primary key field type
+# https://docs.djangoproject.com/en/5.1/ref/settings/#default-auto-field
+
+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/templates/collector/article_detail.html

@@ -0,0 +1,11 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>{{ article.title }}</title>
+</head>
+<body>
+    <h1>{{ article.title }}</h1>
+    <p>{{ article.content }}</p>
+    <a href="{% url 'collector:article_list' %}">返回文章列表</a>
+</body>
+</html>

src/green_classroom/templates/collector/article_list.html

@@ -0,0 +1,19 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>文章列表</title>
+</head>
+<body>
+    <h1>所有文章</h1>
+    <ul>
+        {% for article in articles %}
+            <li>
+                <a href="{% url 'collector:article_detail' article_id=article.id %}">
+                    <strong>{{ article.title }}</strong>
+                </a><br>
+                {{ article.content|truncatewords:50 }}
+            </li>
+        {% endfor %}
+    </ul>
+</body>
+</html>

src/green_classroom/templates/collector/delete_all_articles.html

@@ -0,0 +1,15 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>删除所有文章</title>
+</head>
+<body>
+    <h1>确认删除所有文章</h1>
+    <p>您确定要删除所有文章吗？此操作不可撤销。</p>
+    <form method="post">
+        {% csrf_token %}
+        <button type="submit">删除所有文章</button>
+    </form>
+    <a href="{% url 'collector:article_list' %}">取消</a>
+</body>
+</html>

src/green_classroom/templates/collector/run_crawler.html

@@ -0,0 +1,17 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>运行爬虫</title>
+</head>
+<body>
+    <h1>运行爬虫</h1>
+    <form method="post">
+        {% csrf_token %}
+        <button type="submit">开始爬取</button>
+    </form>
+    {% if output %}
+        <h2>输出：</h2>
+        <pre>{{ output }}</pre>
+    {% endif %}
+</body>
+</html>

src/green_classroom/urls.py

@@ -0,0 +1,10 @@
+from django.urls import path, include
+from django.contrib import admin  # 新增导入
+from green_classroom.apps.collector import views
+
+urlpatterns = [
+    path('collector/', include('green_classroom.apps.collector.urls', namespace='collector')),
+    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
+]
+

src/green_classroom/wsgi.py

@@ -0,0 +1,16 @@
+"""
+WSGI config for green_classroom project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'green_classroom.settings')
+
+application = get_wsgi_application()

src/manage.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+import os
+import sys
+
+
+def main():
+    """Run administrative tasks."""
+    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'green_classroom.settings')
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError as exc:
+        raise ImportError(
+            "Couldn't import Django. Are you sure it's installed and "
+            "available on your PYTHONPATH environment variable? Did you "
+            "forget to activate a virtual environment?"
+        ) from exc
+    execute_from_command_line(sys.argv)
+
+
+if __name__ == '__main__':
+    main()

src/test_xinhua_article.py

@@ -0,0 +1,10 @@
+from green_classroom.apps.collector.crawler.xinhua import parse_xinhua_article
+
+url = "https://www.news.cn/legal/20250721/f340f7be3d5b4b938cbd6b9889b6fbdc/c.html"
+article = parse_xinhua_article(url)
+
+if article:
+    print("✅ 成功抓取文章：", article["title"])
+    print("📄 正文预览：\n", article["content"][:500])
+else:
+    print("❌ 抓取失败")