xinhua_base

core/admin.py

@@ -0,0 +1,11 @@
+from django.contrib import admin
+from .models import Website, Article
+
+@admin.register(Website)
+class WebsiteAdmin(admin.ModelAdmin):
+    list_display = ('name', 'base_url', 'enabled')
+
+@admin.register(Article)
+class ArticleAdmin(admin.ModelAdmin):
+    list_display = ('title', 'website', 'pub_date')
+    search_fields = ('title', 'content')

core/apps.py

@@ -0,0 +1,6 @@
+from django.apps import AppConfig
+
+
+class CoreConfig(AppConfig):
+    default_auto_field = 'django.db.models.BigAutoField'
+    name = 'core'

core/management/commands/crawl_xinhua.py

@@ -0,0 +1,23 @@
+from django.core.management.base import BaseCommand
+from core.models import Website
+from core.utils import crawl_xinhua_article
+
+class Command(BaseCommand):
+    help = '爬取新华网文章示例'
+
+    def handle(self, *args, **options):
+        # 假设你事先在后台建了“新华网”这个Website实例
+        website_name = "新华网"
+        try:
+            website = Website.objects.get(name=website_name)
+        except Website.DoesNotExist:
+            self.stdout.write(self.style.ERROR(f"网站 '{website_name}' 不存在，请先后台创建"))
+            return
+
+        # 这里写你想爬取的文章URL列表，可以循环多篇
+        urls = [
+            "https://www.news.cn/legal/20250721/f340f7be3d5b4b938cbd6b9889b6fbdc/c.html",
+        ]
+
+        for url in urls:
+            crawl_xinhua_article(url, website)

core/migrations/0001_initial.py

@@ -0,0 +1,41 @@
+# Generated by Django 5.1 on 2025-08-11 04:53
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='Website',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('name', models.CharField(max_length=100, unique=True)),
+                ('base_url', models.URLField()),
+                ('description', models.TextField(blank=True, null=True)),
+                ('article_list_url', models.URLField(blank=True, null=True)),
+                ('article_selector', models.CharField(blank=True, max_length=255, null=True)),
+                ('content_selector', models.CharField(blank=True, max_length=255, null=True)),
+                ('enabled', models.BooleanField(default=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)),
+                ('pub_date', models.DateTimeField(blank=True, null=True)),
+                ('content', models.TextField()),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+                ('media_files', models.JSONField(blank=True, default=list)),
+                ('website', models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, to='core.website')),
+            ],
+        ),
+    ]

core/models.py

@@ -0,0 +1,26 @@
+from django.db import models
+
+class Website(models.Model):
+    name = models.CharField(max_length=100, unique=True)
+    base_url = models.URLField()
+    description = models.TextField(blank=True, null=True)
+    article_list_url = models.URLField(blank=True, null=True)
+    article_selector = models.CharField(max_length=255, blank=True, null=True)
+    content_selector = models.CharField(max_length=255, blank=True, null=True)
+    enabled = models.BooleanField(default=True)
+
+    def __str__(self):
+        return self.name
+
+
+class Article(models.Model):
+    website = models.ForeignKey(Website, on_delete=models.CASCADE)
+    title = models.CharField(max_length=300)
+    url = models.URLField(unique=True)
+    pub_date = models.DateTimeField(null=True, blank=True)
+    content = models.TextField()  # html内容
+    created_at = models.DateTimeField(auto_now_add=True)
+    media_files = models.JSONField(default=list, blank=True)
+
+    def __str__(self):
+        return self.title

core/templates/core/article_detail.html

@@ -0,0 +1,17 @@
+<!DOCTYPE html>
+<html lang="zh">
+<head>
+    <meta charset="UTF-8" />
+    <title>{{ article.title }}</title>
+</head>
+<body>
+    <h1>{{ article.title }}</h1>
+    <p>发布时间: {{ article.pub_date|date:"Y-m-d H:i" }}</p>
+    <hr />
+    <div>
+        {{ article.content|safe }}
+    </div>
+    <hr />
+    <p><a href="{% url 'article_list' %}">返回列表</a></p>
+</body>
+</html>

core/templates/core/article_list.html

@@ -0,0 +1,33 @@
+<!DOCTYPE html>
+<html lang="zh">
+<head>
+    <meta charset="UTF-8" />
+    <title>绿色课堂文章列表</title>
+</head>
+<body>
+    <h1>绿色课堂文章列表</h1>
+
+    <ul>
+        {% for article in page_obj %}
+            <li>
+                <a href="{% url 'article_detail' article.id %}">{{ article.title }}</a>
+                ({{ article.created_at|date:"Y-m-d" }})
+            </li>
+        {% empty %}
+            <li>暂无文章</li>
+        {% endfor %}
+    </ul>
+
+    <div class="pagination">
+        {% if page_obj.has_previous %}
+            <a href="?page={{ page_obj.previous_page_number }}">上一页</a>
+        {% endif %}
+
+        <span>第 {{ page_obj.number }} 页，共 {{ page_obj.paginator.num_pages }} 页</span>
+
+        {% if page_obj.has_next %}
+            <a href="?page={{ page_obj.next_page_number }}">下一页</a>
+        {% endif %}
+    </div>
+</body>
+</html>

core/tests.py

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

core/urls.py

@@ -0,0 +1,10 @@
+from django.urls import path
+from . import views
+
+urlpatterns = [
+    # 主页，文章列表
+    path('', views.article_list, name='article_list'),
+    # 文章详情
+    path('article/<int:article_id>/', views.article_detail, name='article_detail'),
+    # 后续可以加更多路径
+]

core/utils.py

@@ -0,0 +1,35 @@
+import requests
+from bs4 import BeautifulSoup
+from django.utils import timezone
+from core.models import Website, Article
+
+def crawl_xinhua_article(url, website):
+    headers = {
+        "User-Agent": "Mozilla/5.0"
+    }
+    resp = requests.get(url, headers=headers)
+    resp.encoding = 'utf-8'
+    soup = BeautifulSoup(resp.text, "html.parser")
+
+    # 提取标题
+    title_tag = soup.find("span", class_="title")
+    title = title_tag.get_text(strip=True) if title_tag else "无标题"
+
+    # 提取正文
+    content_tag = soup.find("span", id="detailContent")
+    paragraphs = content_tag.find_all("p") if content_tag else []
+    content_html = "".join(str(p) for p in paragraphs)  # 保留p标签的html结构
+
+    # 如果文章已存在，则不重复插入
+    if Article.objects.filter(url=url).exists():
+        print(f"文章已存在，跳过: {url}")
+        return
+
+    article = Article.objects.create(
+        website=website,
+        title=title,
+        url=url,
+        content=content_html,
+        pub_date=timezone.now(),
+    )
+    print(f"已保存文章：{title}")

core/views.py

@@ -0,0 +1,28 @@
+from django.shortcuts import render, get_object_or_404
+from django.core.paginator import Paginator
+from .models import Article
+
+def article_list(request):
+    """
+    显示文章列表的视图函数
+    """
+    articles = Article.objects.all().order_by('-created_at')
+    paginator = Paginator(articles, 10)  # 每页显示10篇文章
+    
+    page_number = request.GET.get('page')
+    page_obj = paginator.get_page(page_number)
+    
+    return render(request, 'core/article_list.html', {
+        'page_obj': page_obj
+    })
+
+def article_detail(request, article_id):
+    """
+    显示文章详情的视图函数
+    """
+    article = get_object_or_404(Article, id=article_id)
+    return render(request, 'core/article_detail.html', {
+        'article': article
+    })
+
+# Create your views here.