nanan/green_classroom
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Search button

Browse Source
This commit is contained in:
yuangyaa
2025-08-11 23:42:14 +08:00
parent b6bbb90703
commit 958b087f54
8 changed files with 330 additions and 187 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
core/admin.py
View File

@@ -9,33 +9,39 @@ import csv
from django.http import HttpResponse from django.http import HttpResponse
import json import json
# 创建自定义管理站点 # 创建自定义管理站点
class NewsCnAdminSite(AdminSite): class NewsCnAdminSite(AdminSite):
site_header = "新华网管理后台" site_header = "新华网管理后台"
site_title = "新华网管理" site_title = "新华网管理"
index_title = "新华网内容管理" index_title = "新华网内容管理"
class DongfangyancaoAdminSite(AdminSite): class DongfangyancaoAdminSite(AdminSite):
site_header = "东方烟草报管理后台" site_header = "东方烟草报管理后台"
site_title = "东方烟草报管理" site_title = "东方烟草报管理"
index_title = "东方烟草报内容管理" index_title = "东方烟草报内容管理"
# 实例化管理站点 # 实例化管理站点
news_cn_admin = NewsCnAdminSite(name='news_cn_admin') news_cn_admin = NewsCnAdminSite(name='news_cn_admin')
dongfangyancao_admin = DongfangyancaoAdminSite(name='dongfangyancao_admin') dongfangyancao_admin = DongfangyancaoAdminSite(name='dongfangyancao_admin')
@admin.register(Website) @admin.register(Website)
class WebsiteAdmin(admin.ModelAdmin): class WebsiteAdmin(admin.ModelAdmin):
list_display = ('name', 'base_url', 'enabled') list_display = ('name', 'base_url', 'enabled')
# 为ArticleAdmin添加自定义动作 # 为ArticleAdmin添加自定义动作
@admin.register(Article) @admin.register(Article)
class ArticleAdmin(admin.ModelAdmin): class ArticleAdmin(admin.ModelAdmin):
list_display = ('title', 'website', 'pub_date') list_display = ('title', 'website', 'pub_date')
search_fields = ('title', 'content') search_fields = ('title', 'content')
# 添加动作选项 # 添加动作选项
actions = ['delete_selected_articles', 'delete_dongfangyancao_articles', 'export_as_csv', 'export_as_json', 'export_as_word'] actions = ['delete_selected_articles', 'delete_dongfangyancao_articles', 'export_as_csv', 'export_as_json',
'export_as_word']
def delete_dongfangyancao_articles(self, request, queryset): def delete_dongfangyancao_articles(self, request, queryset):
"""一键删除东方烟草报的所有文章""" """一键删除东方烟草报的所有文章"""
# 获取东方烟草报网站对象 # 获取东方烟草报网站对象
@@ -46,33 +52,34 @@ class ArticleAdmin(admin.ModelAdmin):
self.message_user(request, f"成功删除 {deleted_count} 篇东方烟草报文章", messages.SUCCESS) self.message_user(request, f"成功删除 {deleted_count} 篇东方烟草报文章", messages.SUCCESS)
except Website.DoesNotExist: except Website.DoesNotExist:
self.message_user(request, "未找到东方烟草报网站配置", messages.ERROR) self.message_user(request, "未找到东方烟草报网站配置", messages.ERROR)
# 设置动作的显示名称 # 设置动作的显示名称
delete_dongfangyancao_articles.short_description = "删除所有东方烟草报文章" delete_dongfangyancao_articles.short_description = "删除所有东方烟草报文章"
def export_as_csv(self, request, queryset): def export_as_csv(self, request, queryset):
"""导出选中的文章为CSV格式""" """导出选中的文章为CSV格式"""
meta = self.model._meta meta = self.model._meta
field_names = [field.name for field in meta.fields] field_names = [field.name for field in meta.fields]
response = HttpResponse(content_type='text/csv') response = HttpResponse(content_type='text/csv')
response['Content-Disposition'] = 'attachment; filename={}.csv'.format(meta) response['Content-Disposition'] = 'attachment; filename={}.csv'.format(meta)
writer = csv.writer(response) writer = csv.writer(response)
writer.writerow(field_names) writer.writerow(field_names)
for obj in queryset: for obj in queryset:
row = [getattr(obj, field)() if callable(getattr(obj, field)) else getattr(obj, field) for field in field_names] row = [getattr(obj, field)() if callable(getattr(obj, field)) else getattr(obj, field) for field in
field_names]
writer.writerow(row) writer.writerow(row)
return response return response
export_as_csv.short_description = "导出选中文章为CSV格式" export_as_csv.short_description = "导出选中文章为CSV格式"
def export_as_json(self, request, queryset): def export_as_json(self, request, queryset):
"""导出选中的文章为JSON格式""" """导出选中的文章为JSON格式"""
response = HttpResponse(content_type='application/json') response = HttpResponse(content_type='application/json')
response['Content-Disposition'] = 'attachment; filename=articles.json' response['Content-Disposition'] = 'attachment; filename=articles.json'
# 构造要导出的数据 # 构造要导出的数据
articles_data = [] articles_data = []
for article in queryset: for article in queryset:
@@ -86,11 +93,11 @@ class ArticleAdmin(admin.ModelAdmin):
'created_at': article.created_at.strftime('%Y-%m-%d %H:%M:%S'), 'created_at': article.created_at.strftime('%Y-%m-%d %H:%M:%S'),
'media_files': article.media_files 'media_files': article.media_files
}) })
# 写入JSON数据 # 写入JSON数据
response.write(json.dumps(articles_data, ensure_ascii=False, indent=2)) response.write(json.dumps(articles_data, ensure_ascii=False, indent=2))
return response return response
export_as_json.short_description = "导出选中文章为JSON格式" export_as_json.short_description = "导出选中文章为JSON格式"
def export_as_word(self, request, queryset): def export_as_word(self, request, queryset):
@@ -110,19 +117,20 @@ class ArticleAdmin(admin.ModelAdmin):
for article in queryset: for article in queryset:
# 添加文章标题 # 添加文章标题
doc.add_heading(article.title, level=1) doc.add_heading(article.title, level=1)
# 添加文章元数据 # 添加文章元数据
doc.add_paragraph(f"网站: {article.website.name}") doc.add_paragraph(f"网站: {article.website.name}")
doc.add_paragraph(f"URL: {article.url}") doc.add_paragraph(f"URL: {article.url}")
doc.add_paragraph(f"发布时间: {article.pub_date.strftime('%Y-%m-%d %H:%M:%S') if article.pub_date else 'N/A'}") doc.add_paragraph(
f"发布时间: {article.pub_date.strftime('%Y-%m-%d %H:%M:%S') if article.pub_date else 'N/A'}")
doc.add_paragraph(f"创建时间: {article.created_at.strftime('%Y-%m-%d %H:%M:%S')}") doc.add_paragraph(f"创建时间: {article.created_at.strftime('%Y-%m-%d %H:%M:%S')}")
# 添加文章内容 # 添加文章内容
doc.add_heading('内容', level=2) doc.add_heading('内容', level=2)
# 简单处理HTML内容，移除标签并处理图片 # 简单处理HTML内容，移除标签并处理图片
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
soup = BeautifulSoup(article.content, 'html.parser') soup = BeautifulSoup(article.content, 'html.parser')
# 处理内容中的图片 # 处理内容中的图片
for img in soup.find_all('img'): for img in soup.find_all('img'):
src = img.get('src', '') src = img.get('src', '')
@@ -133,7 +141,7 @@ class ArticleAdmin(admin.ModelAdmin):
from django.conf import settings from django.conf import settings
import requests import requests
from io import BytesIO from io import BytesIO
# 构建完整的图片路径 # 构建完整的图片路径
if src.startswith('http'): if src.startswith('http'):
# 网络图片 # 网络图片
@@ -148,13 +156,13 @@ class ArticleAdmin(admin.ModelAdmin):
except Exception as e: except Exception as e:
# 如果添加图片失败，添加图片URL作为文本 # 如果添加图片失败，添加图片URL作为文本
doc.add_paragraph(f"[图片: {src}]") doc.add_paragraph(f"[图片: {src}]")
# 移除原始img标签 # 移除原始img标签
img.decompose() img.decompose()
content_text = soup.get_text() content_text = soup.get_text()
doc.add_paragraph(content_text) doc.add_paragraph(content_text)
# 添加媒体文件信息 # 添加媒体文件信息
if article.media_files: if article.media_files:
doc.add_heading('媒体文件', level=2) doc.add_heading('媒体文件', level=2)
@@ -164,7 +172,7 @@ class ArticleAdmin(admin.ModelAdmin):
from django.conf import settings from django.conf import settings
from io import BytesIO from io import BytesIO
import requests import requests
full_path = os.path.join(settings.MEDIA_ROOT, media_file) full_path = os.path.join(settings.MEDIA_ROOT, media_file)
if os.path.exists(full_path): if os.path.exists(full_path):
# 添加图片到文档 # 添加图片到文档
@@ -179,44 +187,46 @@ class ArticleAdmin(admin.ModelAdmin):
doc.add_paragraph(media_file) doc.add_paragraph(media_file)
except Exception as e: except Exception as e:
doc.add_paragraph(media_file) doc.add_paragraph(media_file)
# 添加分页符 # 添加分页符
doc.add_page_break() doc.add_page_break()
# 保存到内存 # 保存到内存
buffer = BytesIO() buffer = BytesIO()
doc.save(buffer) doc.save(buffer)
buffer.seek(0) buffer.seek(0)
# 创建HttpResponse # 创建HttpResponse
from django.http import HttpResponse from django.http import HttpResponse
response = HttpResponse(buffer.getvalue(), content_type='application/vnd.openxmlformats-officedocument.wordprocessingml.document') response = HttpResponse(buffer.getvalue(),
content_type='application/vnd.openxmlformats-officedocument.wordprocessingml.document')
response['Content-Disposition'] = 'attachment; filename=articles.docx' response['Content-Disposition'] = 'attachment; filename=articles.docx'
return response return response
export_as_word.short_description = "导出选中文章为Word格式" export_as_word.short_description = "导出选中文章为Word格式"
# 为不同网站创建专门的文章管理类 # 为不同网站创建专门的文章管理类
class NewsCnArticleAdmin(admin.ModelAdmin): class NewsCnArticleAdmin(admin.ModelAdmin):
list_display = ('title', 'pub_date') list_display = ('title', 'pub_date')
search_fields = ('title', 'content') search_fields = ('title', 'content')
list_filter = ('pub_date',) list_filter = ('pub_date',)
actions = ['export_as_csv', 'export_as_json'] actions = ['export_as_csv', 'export_as_json']
def get_queryset(self, request): def get_queryset(self, request):
qs = super().get_queryset(request) qs = super().get_queryset(request)
# 只显示新华网的文章 # 只显示新华网的文章
return qs.filter(website__name='www.news.cn') return qs.filter(website__name='www.news.cn')
def export_as_csv(self, request, queryset): def export_as_csv(self, request, queryset):
"""导出选中的文章为CSV格式""" """导出选中的文章为CSV格式"""
meta = self.model._meta meta = self.model._meta
field_names = [field.name for field in meta.fields if field.name != 'content'] # 排除content字段以减小CSV大小 field_names = [field.name for field in meta.fields if field.name != 'content'] # 排除content字段以减小CSV大小
response = HttpResponse(content_type='text/csv') response = HttpResponse(content_type='text/csv')
response['Content-Disposition'] = 'attachment; filename=news_cn_articles.csv' response['Content-Disposition'] = 'attachment; filename=news_cn_articles.csv'
writer = csv.writer(response) writer = csv.writer(response)
writer.writerow(field_names) writer.writerow(field_names)
for obj in queryset: for obj in queryset:
row = [] row = []
@@ -228,16 +238,16 @@ class NewsCnArticleAdmin(admin.ModelAdmin):
value = value.name value = value.name
row.append(value) row.append(value)
writer.writerow(row) writer.writerow(row)
return response return response
export_as_csv.short_description = "导出选中文章为CSV格式" export_as_csv.short_description = "导出选中文章为CSV格式"
def export_as_json(self, request, queryset): def export_as_json(self, request, queryset):
"""导出选中的文章为JSON格式""" """导出选中的文章为JSON格式"""
response = HttpResponse(content_type='application/json') response = HttpResponse(content_type='application/json')
response['Content-Disposition'] = 'attachment; filename=news_cn_articles.json' response['Content-Disposition'] = 'attachment; filename=news_cn_articles.json'
# 构造要导出的数据 # 构造要导出的数据
articles_data = [] articles_data = []
for article in queryset: for article in queryset:
@@ -251,43 +261,44 @@ class NewsCnArticleAdmin(admin.ModelAdmin):
'created_at': article.created_at.strftime('%Y-%m-%d %H:%M:%S'), 'created_at': article.created_at.strftime('%Y-%m-%d %H:%M:%S'),
'media_files': article.media_files 'media_files': article.media_files
}) })
# 写入JSON数据 # 写入JSON数据
response.write(json.dumps(articles_data, ensure_ascii=False, indent=2)) response.write(json.dumps(articles_data, ensure_ascii=False, indent=2))
return response return response
export_as_json.short_description = "导出选中文章为JSON格式" export_as_json.short_description = "导出选中文章为JSON格式"
class DongfangyancaoArticleAdmin(admin.ModelAdmin): class DongfangyancaoArticleAdmin(admin.ModelAdmin):
list_display = ('title', 'pub_date') list_display = ('title', 'pub_date')
search_fields = ('title', 'content') search_fields = ('title', 'content')
list_filter = ('pub_date',) list_filter = ('pub_date',)
# 添加动作选项 # 添加动作选项
actions = ['delete_selected_articles', 'delete_all_articles', 'export_as_csv', 'export_as_json'] actions = ['delete_selected_articles', 'delete_all_articles', 'export_as_csv', 'export_as_json']
def get_queryset(self, request): def get_queryset(self, request):
qs = super().get_queryset(request) qs = super().get_queryset(request)
# 只显示东方烟草报的文章 # 只显示东方烟草报的文章
return qs.filter(website__name='东方烟草报') return qs.filter(website__name='东方烟草报')
def delete_all_articles(self, request, queryset): def delete_all_articles(self, request, queryset):
"""删除当前筛选的所有文章（东方烟草报的所有文章）""" """删除当前筛选的所有文章（东方烟草报的所有文章）"""
# 删除所有东方烟草报的文章 # 删除所有东方烟草报的文章
deleted_count = self.get_queryset(request).delete()[0] deleted_count = self.get_queryset(request).delete()[0]
self.message_user(request, f"成功删除 {deleted_count} 篇文章", messages.SUCCESS) self.message_user(request, f"成功删除 {deleted_count} 篇文章", messages.SUCCESS)
# 设置动作的显示名称 # 设置动作的显示名称
delete_all_articles.short_description = "删除所有当前筛选的文章" delete_all_articles.short_description = "删除所有当前筛选的文章"
def export_as_csv(self, request, queryset): def export_as_csv(self, request, queryset):
"""导出选中的文章为CSV格式""" """导出选中的文章为CSV格式"""
meta = self.model._meta meta = self.model._meta
field_names = [field.name for field in meta.fields if field.name != 'content'] # 排除content字段以减小CSV大小 field_names = [field.name for field in meta.fields if field.name != 'content'] # 排除content字段以减小CSV大小
response = HttpResponse(content_type='text/csv') response = HttpResponse(content_type='text/csv')
response['Content-Disposition'] = 'attachment; filename=dongfangyancao_articles.csv' response['Content-Disposition'] = 'attachment; filename=dongfangyancao_articles.csv'
writer = csv.writer(response) writer = csv.writer(response)
writer.writerow(field_names) writer.writerow(field_names)
for obj in queryset: for obj in queryset:
row = [] row = []
@@ -299,16 +310,16 @@ class DongfangyancaoArticleAdmin(admin.ModelAdmin):
value = value.name value = value.name
row.append(value) row.append(value)
writer.writerow(row) writer.writerow(row)
return response return response
export_as_csv.short_description = "导出选中文章为CSV格式" export_as_csv.short_description = "导出选中文章为CSV格式"
def export_as_json(self, request, queryset): def export_as_json(self, request, queryset):
"""导出选中的文章为JSON格式""" """导出选中的文章为JSON格式"""
response = HttpResponse(content_type='application/json') response = HttpResponse(content_type='application/json')
response['Content-Disposition'] = 'attachment; filename=dongfangyancao_articles.json' response['Content-Disposition'] = 'attachment; filename=dongfangyancao_articles.json'
# 构造要导出的数据 # 构造要导出的数据
articles_data = [] articles_data = []
for article in queryset: for article in queryset:
@@ -322,16 +333,17 @@ class DongfangyancaoArticleAdmin(admin.ModelAdmin):
'created_at': article.created_at.strftime('%Y-%m-%d %H:%M:%S'), 'created_at': article.created_at.strftime('%Y-%m-%d %H:%M:%S'),
'media_files': article.media_files 'media_files': article.media_files
}) })
# 写入JSON数据 # 写入JSON数据
response.write(json.dumps(articles_data, ensure_ascii=False, indent=2)) response.write(json.dumps(articles_data, ensure_ascii=False, indent=2))
return response return response
export_as_json.short_description = "导出选中文章为JSON格式" export_as_json.short_description = "导出选中文章为JSON格式"
# 在各自的管理站点中注册模型 # 在各自的管理站点中注册模型
news_cn_admin.register(Website, WebsiteAdmin) news_cn_admin.register(Website, WebsiteAdmin)
news_cn_admin.register(Article, NewsCnArticleAdmin) news_cn_admin.register(Article, NewsCnArticleAdmin)
dongfangyancao_admin.register(Website, WebsiteAdmin) dongfangyancao_admin.register(Website, WebsiteAdmin)
dongfangyancao_admin.register(Article, DongfangyancaoArticleAdmin) dongfangyancao_admin.register(Article, DongfangyancaoArticleAdmin)

3
core/management/commands/crawl_dongfangyancao.py
View File

@@ -1,4 +1,3 @@
# core/management/commands/crawl_dongfangyancao.py
from django.core.management.base import BaseCommand from django.core.management.base import BaseCommand
from core.models import Website from core.models import Website
from core.utils import full_site_crawler from core.utils import full_site_crawler
@@ -18,4 +17,4 @@ class Command(BaseCommand):
start_url = "https://www.eastobacco.com/" start_url = "https://www.eastobacco.com/"
self.stdout.write(f"开始全站爬取: {start_url}") self.stdout.write(f"开始全站爬取: {start_url}")
full_site_crawler(start_url, website, max_pages=500) full_site_crawler(start_url, website, max_pages=500)
self.stdout.write("爬取完成") self.stdout.write("爬取完成")

1
core/management/commands/crawl_xinhua.py
View File

@@ -1,4 +1,3 @@
# core/management/commands/crawl_xinhua.py
from django.core.management.base import BaseCommand from django.core.management.base import BaseCommand
from core.models import Website from core.models import Website
from core.utils import full_site_crawler from core.utils import full_site_crawler

70
core/management/commands/export_articles.py
View File

@@ -23,7 +23,7 @@ class Command(BaseCommand):
website_name = options['website'] website_name = options['website']
output_path = options['output'] output_path = options['output']
include_media = options['include_media'] include_media = options['include_media']
# 获取文章查询集 # 获取文章查询集
articles = Article.objects.all() articles = Article.objects.all()
if website_name: if website_name:
@@ -33,15 +33,15 @@ class Command(BaseCommand):
except Website.DoesNotExist: except Website.DoesNotExist:
self.stdout.write(self.style.ERROR(f'网站 "{website_name}" 不存在')) self.stdout.write(self.style.ERROR(f'网站 "{website_name}" 不存在'))
return return
if not articles.exists(): if not articles.exists():
self.stdout.write(self.style.WARNING('没有找到文章')) self.stdout.write(self.style.WARNING('没有找到文章'))
return return
# 准备导出数据 # 准备导出数据
articles_data = [] articles_data = []
media_files = [] media_files = []
for article in articles: for article in articles:
article_data = { article_data = {
'id': article.id, 'id': article.id,
@@ -54,14 +54,14 @@ class Command(BaseCommand):
'media_files': article.media_files 'media_files': article.media_files
} }
articles_data.append(article_data) articles_data.append(article_data)
# 收集媒体文件路径 # 收集媒体文件路径
if include_media: if include_media:
for media_path in article.media_files: for media_path in article.media_files:
full_path = os.path.join(settings.MEDIA_ROOT, media_path) full_path = os.path.join(settings.MEDIA_ROOT, media_path)
if os.path.exists(full_path): if os.path.exists(full_path):
media_files.append(full_path) media_files.append(full_path)
# 确定输出路径 # 确定输出路径
if not output_path: if not output_path:
timestamp = timezone.now().strftime('%Y%m%d_%H%M%S') timestamp = timezone.now().strftime('%Y%m%d_%H%M%S')
@@ -69,7 +69,7 @@ class Command(BaseCommand):
output_path = f'articles_export_{timestamp}.zip' output_path = f'articles_export_{timestamp}.zip'
else: else:
output_path = f'articles_export_{timestamp}.{format_type}' output_path = f'articles_export_{timestamp}.{format_type}'
# 执行导出 # 执行导出
if include_media: if include_media:
self.export_with_media(articles_data, media_files, output_path, format_type) self.export_with_media(articles_data, media_files, output_path, format_type)
@@ -84,7 +84,7 @@ class Command(BaseCommand):
else: else:
self.stdout.write(self.style.ERROR('不支持的格式，仅支持 json、csv 或 docx')) self.stdout.write(self.style.ERROR('不支持的格式，仅支持 json、csv 或 docx'))
return return
self.stdout.write(self.style.SUCCESS(f'成功导出 {len(articles_data)} 篇文章到 {output_path}')) self.stdout.write(self.style.SUCCESS(f'成功导出 {len(articles_data)} 篇文章到 {output_path}'))
def export_as_json(self, articles_data, output_path): def export_as_json(self, articles_data, output_path):
@@ -94,16 +94,17 @@ class Command(BaseCommand):
def export_as_csv(self, articles_data, output_path): def export_as_csv(self, articles_data, output_path):
if not articles_data: if not articles_data:
return return
# 打开CSV文件 # 打开CSV文件
with open(output_path, 'w', newline='', encoding='utf-8') as csvfile: with open(output_path, 'w', newline='', encoding='utf-8') as csvfile:
fieldnames = ['id', 'title', 'website', 'url', 'pub_date', 'content', 'created_at', 'media_files'] fieldnames = ['id', 'title', 'website', 'url', 'pub_date', 'content', 'created_at', 'media_files']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames) writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader() writer.writeheader()
for article_data in articles_data: for article_data in articles_data:
# 将列表转换为字符串以便在CSV中存储 # 将列表转换为字符串以便在CSV中存储
article_data['media_files'] = ';'.join(article_data['media_files']) if article_data['media_files'] else '' article_data['media_files'] = ';'.join(article_data['media_files']) if article_data[
'media_files'] else ''
writer.writerow(article_data) writer.writerow(article_data)
# 添加Word格式导出方法 # 添加Word格式导出方法
@@ -122,19 +123,19 @@ class Command(BaseCommand):
for article_data in articles_data: for article_data in articles_data:
# 添加文章标题 # 添加文章标题
doc.add_heading(article_data['title'], level=1) doc.add_heading(article_data['title'], level=1)
# 添加文章元数据 # 添加文章元数据
doc.add_paragraph(f"网站: {article_data['website']}") doc.add_paragraph(f"网站: {article_data['website']}")
doc.add_paragraph(f"URL: {article_data['url']}") doc.add_paragraph(f"URL: {article_data['url']}")
doc.add_paragraph(f"发布时间: {article_data['pub_date']}") doc.add_paragraph(f"发布时间: {article_data['pub_date']}")
doc.add_paragraph(f"创建时间: {article_data['created_at']}") doc.add_paragraph(f"创建时间: {article_data['created_at']}")
# 添加文章内容 # 添加文章内容
doc.add_heading('内容', level=2) doc.add_heading('内容', level=2)
# 简单处理HTML内容，移除标签 # 简单处理HTML内容，移除标签
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
soup = BeautifulSoup(article_data['content'], 'html.parser') soup = BeautifulSoup(article_data['content'], 'html.parser')
# 处理内容中的图片 # 处理内容中的图片
for img in soup.find_all('img'): for img in soup.find_all('img'):
src = img.get('src', '') src = img.get('src', '')
@@ -145,7 +146,7 @@ class Command(BaseCommand):
from django.conf import settings from django.conf import settings
import requests import requests
from io import BytesIO from io import BytesIO
# 构建完整的图片路径 # 构建完整的图片路径
if src.startswith('http'): if src.startswith('http'):
# 网络图片 # 网络图片
@@ -160,13 +161,13 @@ class Command(BaseCommand):
except Exception as e: except Exception as e:
# 如果添加图片失败，添加图片URL作为文本 # 如果添加图片失败，添加图片URL作为文本
doc.add_paragraph(f"[图片: {src}]") doc.add_paragraph(f"[图片: {src}]")
# 移除原始img标签 # 移除原始img标签
img.decompose() img.decompose()
content_text = soup.get_text() content_text = soup.get_text()
doc.add_paragraph(content_text) doc.add_paragraph(content_text)
# 添加媒体文件信息 # 添加媒体文件信息
if article_data['media_files']: if article_data['media_files']:
doc.add_heading('媒体文件', level=2) doc.add_heading('媒体文件', level=2)
@@ -176,7 +177,7 @@ class Command(BaseCommand):
from django.conf import settings from django.conf import settings
from io import BytesIO from io import BytesIO
import requests import requests
full_path = os.path.join(settings.MEDIA_ROOT, media_file) full_path = os.path.join(settings.MEDIA_ROOT, media_file)
if os.path.exists(full_path): if os.path.exists(full_path):
# 添加图片到文档 # 添加图片到文档
@@ -191,10 +192,10 @@ class Command(BaseCommand):
doc.add_paragraph(media_file) doc.add_paragraph(media_file)
except Exception as e: except Exception as e:
doc.add_paragraph(media_file) doc.add_paragraph(media_file)
# 添加分页符 # 添加分页符
doc.add_page_break() doc.add_page_break()
# 保存文档 # 保存文档
doc.save(output_path) doc.save(output_path)
@@ -215,7 +216,8 @@ class Command(BaseCommand):
writer = csv.DictWriter(csv_buffer, fieldnames=fieldnames) writer = csv.DictWriter(csv_buffer, fieldnames=fieldnames)
writer.writeheader() writer.writeheader()
for article_data in articles_data: for article_data in articles_data:
article_data['media_files'] = ';'.join(article_data['media_files']) if article_data['media_files'] else '' article_data['media_files'] = ';'.join(article_data['media_files']) if article_data[
'media_files'] else ''
writer.writerow(article_data) writer.writerow(article_data)
zipf.writestr(data_filename, csv_buffer.getvalue()) zipf.writestr(data_filename, csv_buffer.getvalue())
# 添加Word格式支持 # 添加Word格式支持
@@ -225,7 +227,7 @@ class Command(BaseCommand):
from docx import Document from docx import Document
from docx.shared import Inches from docx.shared import Inches
from io import BytesIO from io import BytesIO
doc = Document() doc = Document()
doc.add_heading('文章导出', 0) doc.add_heading('文章导出', 0)
@@ -235,11 +237,11 @@ class Command(BaseCommand):
doc.add_paragraph(f"URL: {article_data['url']}") doc.add_paragraph(f"URL: {article_data['url']}")
doc.add_paragraph(f"发布时间: {article_data['pub_date']}") doc.add_paragraph(f"发布时间: {article_data['pub_date']}")
doc.add_paragraph(f"创建时间: {article_data['created_at']}") doc.add_paragraph(f"创建时间: {article_data['created_at']}")
doc.add_heading('内容', level=2) doc.add_heading('内容', level=2)
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
soup = BeautifulSoup(article_data['content'], 'html.parser') soup = BeautifulSoup(article_data['content'], 'html.parser')
# 处理内容中的图片 # 处理内容中的图片
for img in soup.find_all('img'): for img in soup.find_all('img'):
src = img.get('src', '') src = img.get('src', '')
@@ -249,7 +251,7 @@ class Command(BaseCommand):
import os import os
from django.conf import settings from django.conf import settings
import requests import requests
# 构建完整的图片路径 # 构建完整的图片路径
if src.startswith('http'): if src.startswith('http'):
# 网络图片 # 网络图片
@@ -264,20 +266,20 @@ class Command(BaseCommand):
except Exception as e: except Exception as e:
# 如果添加图片失败，添加图片URL作为文本 # 如果添加图片失败，添加图片URL作为文本
doc.add_paragraph(f"[图片: {src}]") doc.add_paragraph(f"[图片: {src}]")
# 移除原始img标签 # 移除原始img标签
img.decompose() img.decompose()
content_text = soup.get_text() content_text = soup.get_text()
doc.add_paragraph(content_text) doc.add_paragraph(content_text)
if article_data['media_files']: if article_data['media_files']:
doc.add_heading('媒体文件', level=2) doc.add_heading('媒体文件', level=2)
for media_file in article_data['media_files']: for media_file in article_data['media_files']:
try: try:
import os import os
from django.conf import settings from django.conf import settings
full_path = os.path.join(settings.MEDIA_ROOT, media_file) full_path = os.path.join(settings.MEDIA_ROOT, media_file)
if os.path.exists(full_path): if os.path.exists(full_path):
# 添加图片到文档 # 添加图片到文档
@@ -292,9 +294,9 @@ class Command(BaseCommand):
doc.add_paragraph(media_file) doc.add_paragraph(media_file)
except Exception as e: except Exception as e:
doc.add_paragraph(media_file) doc.add_paragraph(media_file)
doc.add_page_break() doc.add_page_break()
# 将文档保存到内存中再写入ZIP # 将文档保存到内存中再写入ZIP
doc_buffer = BytesIO() doc_buffer = BytesIO()
doc.save(doc_buffer) doc.save(doc_buffer)
@@ -302,8 +304,8 @@ class Command(BaseCommand):
zipf.writestr(data_filename, doc_buffer.read()) zipf.writestr(data_filename, doc_buffer.read())
except ImportError: except ImportError:
zipf.writestr(data_filename, "错误：缺少python-docx库，无法生成Word文档") zipf.writestr(data_filename, "错误：缺少python-docx库，无法生成Word文档")
# 添加媒体文件 # 添加媒体文件
for media_path in media_files: for media_path in media_files:
arcname = os.path.join('media', os.path.relpath(media_path, settings.MEDIA_ROOT)) arcname = os.path.join('media', os.path.relpath(media_path, settings.MEDIA_ROOT))
zipf.write(media_path, arcname) zipf.write(media_path, arcname)

32
core/templates/core/article_detail.html
View File

@@ -13,39 +13,46 @@
padding: 20px; padding: 20px;
background-color: #f8f9fa; background-color: #f8f9fa;
} }
.article-container { .article-container {
background: white; background: white;
border-radius: 8px; border-radius: 8px;
box-shadow: 0 2px 10px rgba(0,0,0,0.1); box-shadow: 0 2px 10px rgba(0, 0, 0, 0.1);
padding: 30px; padding: 30px;
margin-bottom: 20px; margin-bottom: 20px;
} }
h1 { h1 {
color: #2c3e50; color: #2c3e50;
border-bottom: 2px solid #3498db; border-bottom: 2px solid #3498db;
padding-bottom: 10px; padding-bottom: 10px;
margin-top: 0; margin-top: 0;
} }
.meta { .meta {
color: #7f8c8d; color: #7f8c8d;
font-size: 0.9em; font-size: 0.9em;
margin-bottom: 20px; margin-bottom: 20px;
} }
hr { hr {
border: 0; border: 0;
height: 1px; height: 1px;
background: #ecf0f1; background: #ecf0f1;
margin: 20px 0; margin: 20px 0;
} }
.content { .content {
font-size: 16px; font-size: 16px;
} }
.content img { .content img {
max-width: 100%; max-width: 100%;
height: auto; height: auto;
border-radius: 4px; border-radius: 4px;
margin: 10px 0; margin: 10px 0;
} }
.back-link { .back-link {
display: inline-block; display: inline-block;
padding: 10px 20px; padding: 10px 20px;
@@ -55,23 +62,24 @@
border-radius: 4px; border-radius: 4px;
transition: background-color 0.3s; transition: background-color 0.3s;
} }
.back-link:hover { .back-link:hover {
background-color: #2980b9; background-color: #2980b9;
} }
</style> </style>
</head> </head>
<body> <body>
<div class="article-container"> <div class="article-container">
<h1>{{ article.title }}</h1> <h1>{{ article.title }}</h1>
<div class="meta"> <div class="meta">
<p>发布时间: {{ article.pub_date|date:"Y-m-d H:i" }}</p> <p>发布时间: {{ article.pub_date|date:"Y-m-d H:i" }}</p>
</div>
<hr/>
<div class="content">
{{ article.content|safe }}
</div>
<hr/>
<p><a href="{% url 'article_list' %}" class="back-link">← 返回列表</a></p>
</div> </div>
<hr/>
<div class="content">
{{ article.content|safe }}
</div>
<hr/>
<p><a href="{% url 'article_list' %}" class="back-link">← 返回列表</a></p>
</div>
</body> </body>
</html> </html>

214
core/templates/core/article_list.html
View File

@@ -13,25 +13,29 @@
padding: 20px; padding: 20px;
background-color: #f8f9fa; background-color: #f8f9fa;
} }
.container { .container {
background: white; background: white;
border-radius: 8px; border-radius: 8px;
box-shadow: 0 2px 10px rgba(0,0,0,0.1); box-shadow: 0 2px 10px rgba(0, 0, 0, 0.1);
padding: 30px; padding: 30px;
margin-bottom: 20px; margin-bottom: 20px;
} }
h1 { h1 {
color: #2c3e50; color: #2c3e50;
border-bottom: 2px solid #3498db; border-bottom: 2px solid #3498db;
padding-bottom: 10px; padding-bottom: 10px;
margin-top: 0; margin-top: 0;
} }
.filters { .filters {
margin-bottom: 20px; margin-bottom: 20px;
padding: 15px; padding: 15px;
background-color: #f1f8ff; background-color: #f1f8ff;
border-radius: 5px; border-radius: 5px;
} }
.filters a { .filters a {
display: inline-block; display: inline-block;
padding: 5px 10px; padding: 5px 10px;
@@ -41,38 +45,47 @@
text-decoration: none; text-decoration: none;
border-radius: 3px; border-radius: 3px;
} }
.filters a.active { .filters a.active {
background-color: #3498db; background-color: #3498db;
color: white; color: white;
} }
ul { ul {
list-style: none; list-style: none;
padding: 0; padding: 0;
} }
li { li {
padding: 10px 0; padding: 10px 0;
border-bottom: 1px solid #ecf0f1; border-bottom: 1px solid #ecf0f1;
} }
li:last-child { li:last-child {
border-bottom: none; border-bottom: none;
} }
a { a {
color: #3498db; color: #3498db;
text-decoration: none; text-decoration: none;
} }
a:hover { a:hover {
color: #2980b9; color: #2980b9;
text-decoration: underline; text-decoration: underline;
} }
.meta { .meta {
color: #7f8c8d; color: #7f8c8d;
font-size: 0.9em; font-size: 0.9em;
} }
.pagination { .pagination {
margin-top: 30px; margin-top: 30px;
text-align: center; text-align: center;
padding: 20px 0; padding: 20px 0;
} }
.pagination a { .pagination a {
display: inline-block; display: inline-block;
padding: 8px 16px; padding: 8px 16px;
@@ -82,95 +95,158 @@
border-radius: 4px; border-radius: 4px;
margin: 0 2px; /* 修改:调整页码间距 */ margin: 0 2px; /* 修改:调整页码间距 */
} }
.pagination a:hover { .pagination a:hover {
background-color: #2980b9; background-color: #2980b9;
} }
.pagination span { .pagination span {
margin: 0 10px; margin: 0 10px;
color: #7f8c8d; color: #7f8c8d;
} }
/* 新增:当前页码样式 */ /* 新增:当前页码样式 */
.pagination .current { .pagination .current {
background-color: #2980b9; background-color: #2980b9;
cursor: default; cursor: default;
} }
/* 新增:省略号样式 */ /* 新增:省略号样式 */
.pagination .ellipsis { .pagination .ellipsis {
display: inline-block; display: inline-block;
padding: 8px 4px; padding: 8px 4px;
color: #7f8c8d; color: #7f8c8d;
} }
/* 新增:搜索框样式 */
.search-form {
margin-bottom: 20px;
padding: 15px;
background-color: #f1f8ff;
border-radius: 5px;
}
.search-form input[type="text"] {
padding: 8px 12px;
border: 1px solid #ddd;
border-radius: 4px;
width: 300px;
margin-right: 10px;
}
.search-form input[type="submit"] {
padding: 8px 16px;
background-color: #3498db;
color: white;
border: none;
border-radius: 4px;
cursor: pointer;
}
.search-form input[type="submit"]:hover {
background-color: #2980b9;
}
.search-info {
color: #7f8c8d;
font-size: 0.9em;
margin-bottom: 10px;
}
</style> </style>
</head> </head>
<body> <body>
<div class="container"> <div class="container">
<h1>绿色课堂文章列表</h1> <h1>绿色课堂文章列表</h1>
<div class="filters"> <!-- 新增:返回首页链接 -->
<strong>按网站筛选：</strong> <div style="margin-bottom: 20px;">
<a href="{% url 'article_list' %}" {% if not selected_website %}class="active"{% endif %}>全部</a> <a href="{% url 'article_list' %}" style="color: #3498db; text-decoration: none;">&larr; 返回首页</a>
{% for website in websites %}
<a href="?website={{ website.id }}" {% if selected_website.id == website.id %}class="active"{% endif %}>{{ website.name }}</a>
{% endfor %}
</div>
<ul>
{% for article in page_obj %}
<li>
<a href="{% url 'article_detail' article.id %}">{{ article.title }}</a>
<div class="meta">({{ article.website.name }} - {{ article.created_at|date:"Y-m-d" }})</div>
</li>
{% empty %}
<li>暂无文章</li>
{% endfor %}
</ul>
<div class="pagination">
{% if page_obj.has_previous %}
{% if selected_website %}
<a href="?website={{ selected_website.id }}&page=1">&laquo; 首页</a>
<a href="?website={{ selected_website.id }}&page={{ page_obj.previous_page_number }}">上一页</a>
{% else %}
<a href="?page=1">&laquo; 首页</a>
<a href="?page={{ page_obj.previous_page_number }}">上一页</a>
{% endif %}
{% endif %}
<span>第 {{ page_obj.number }} 页，共 {{ page_obj.paginator.num_pages }} 页</span>
<!-- 修改:优化页码显示逻辑 -->
{% with page_obj.paginator as paginator %}
{% for num in paginator.page_range %}
{% if page_obj.number == num %}
<a href="#" class="current">{{ num }}</a>
{% elif num > page_obj.number|add:'-3' and num < page_obj.number|add:'3' %}
{% if selected_website %}
<a href="?website={{ selected_website.id }}&page={{ num }}">{{ num }}</a>
{% else %}
<a href="?page={{ num }}">{{ num }}</a>
{% endif %}
{% elif num == 1 or num == paginator.num_pages %}
{% if selected_website %}
<a href="?website={{ selected_website.id }}&page={{ num }}">{{ num }}</a>
{% else %}
<a href="?page={{ num }}">{{ num }}</a>
{% endif %}
{% elif num == page_obj.number|add:'-3' or num == page_obj.number|add:'3' %}
<span class="ellipsis">...</span>
{% endif %}
{% endfor %}
{% endwith %}
{% if page_obj.has_next %}
{% if selected_website %}
<a href="?website={{ selected_website.id }}&page={{ page_obj.next_page_number }}">下一页</a>
<a href="?website={{ selected_website.id }}&page={{ page_obj.paginator.num_pages }}">末页 &raquo;</a>
{% else %}
<a href="?page={{ page_obj.next_page_number }}">下一页</a>
<a href="?page={{ page_obj.paginator.num_pages }}">末页 &raquo;</a>
{% endif %}
{% endif %}
</div>
</div> </div>
<!-- 新增:搜索表单 -->
<div class="search-form">
<form method="get">
<input type="text" name="q" placeholder="输入关键词搜索文章..." value="{{ search_query }}">
{% if selected_website %}
<input type="hidden" name="website" value="{{ selected_website.id }}">
{% endif %}
<input type="submit" value="搜索">
</form>
</div>
<div class="filters">
<strong>按网站筛选：</strong>
<a href="{% url 'article_list' %}{% if search_query %}?q={{ search_query }}{% endif %}" {% if not selected_website %}class="active" {% endif %}>全部</a>
{% for website in websites %}
<a href="?website={{ website.id }}{% if search_query %}&q={{ search_query }}{% endif %}" {% if selected_website and selected_website.id == website.id %}class="active" {% endif %}>{{ website.name }}</a>
{% endfor %}
</div>
<!-- 新增:搜索结果信息 -->
{% if search_query %}
<div class="search-info">
搜索 "{{ search_query }}" 找到 {{ page_obj.paginator.count }} 篇文章
<a href="{% if selected_website %}?website={{ selected_website.id }}{% else %}{% url 'article_list' %}{% endif %}">清除搜索</a>
</div>
{% endif %}
<ul>
{% for article in page_obj %}
<li>
<a href="{% url 'article_detail' article.id %}">{{ article.title }}</a>
<div class="meta">({{ article.website.name }} - {{ article.created_at|date:"Y-m-d" }})</div>
</li>
{% empty %}
<li>暂无文章</li>
{% endfor %}
</ul>
<div class="pagination">
{% if page_obj.has_previous %}
{% if selected_website %}
<a href="?website={{ selected_website.id }}{% if search_query %}&q={{ search_query }}{% endif %}&page=1">&laquo; 首页</a>
<a href="?website={{ selected_website.id }}{% if search_query %}&q={{ search_query }}{% endif %}&page={{ page_obj.previous_page_number }}">上一页</a>
{% else %}
<a href="?{% if search_query %}q={{ search_query }}&{% endif %}page=1">&laquo; 首页</a>
<a href="?{% if search_query %}q={{ search_query }}&{% endif %}page={{ page_obj.previous_page_number }}">上一页</a>
{% endif %}
{% endif %}
<span>第 {{ page_obj.number }} 页，共 {{ page_obj.paginator.num_pages }} 页</span>
<!-- 修改:优化页码显示逻辑 -->
{% with page_obj.paginator as paginator %}
{% for num in paginator.page_range %}
{% if page_obj.number == num %}
<a href="#" class="current">{{ num }}</a>
{% elif num > page_obj.number|add:'-3' and num < page_obj.number|add:'3' %}
{% if selected_website %}
<a href="?website={{ selected_website.id }}{% if search_query %}&q={{ search_query }}{% endif %}&page={{ num }}">{{ num }}</a>
{% else %}
<a href="?{% if search_query %}q={{ search_query }}&{% endif %}page={{ num }}">{{ num }}</a>
{% endif %}
{% elif num == 1 or num == paginator.num_pages %}
{% if selected_website %}
<a href="?website={{ selected_website.id }}{% if search_query %}&q={{ search_query }}{% endif %}&page={{ num }}">{{ num }}</a>
{% else %}
<a href="?{% if search_query %}q={{ search_query }}&{% endif %}page={{ num }}">{{ num }}</a>
{% endif %}
{% elif num == page_obj.number|add:'-3' or num == page_obj.number|add:'3' %}
<span class="ellipsis">...</span>
{% endif %}
{% endfor %}
{% endwith %}
{% if page_obj.has_next %}
{% if selected_website %}
<a href="?website={{ selected_website.id }}{% if search_query %}&q={{ search_query }}{% endif %}&page={{ page_obj.next_page_number }}">下一页</a>
<a href="?website={{ selected_website.id }}{% if search_query %}&q={{ search_query }}{% endif %}&page={{ page_obj.paginator.num_pages }}">末页 &raquo;</a>
{% else %}
<a href="?{% if search_query %}q={{ search_query }}&{% endif %}page={{ page_obj.next_page_number }}">下一页</a>
<a href="?{% if search_query %}q={{ search_query }}&{% endif %}page={{ page_obj.paginator.num_pages }}">末页 &raquo;</a>
{% endif %}
{% endif %}
</div>
</div>
</body> </body>
</html> </html>

54
core/views.py
View File

@@ -1,28 +1,44 @@
from django.shortcuts import render, get_object_or_404 from django.shortcuts import render
from django.core.paginator import Paginator from django.core.paginator import Paginator
from .models import Article from .models import Article, Website
def article_list(request): def article_list(request):
""" # 获取所有启用的网站
显示文章列表的视图函数 websites = Website.objects.filter(enabled=True)
"""
articles = Article.objects.all().order_by('-created_at') # 获取筛选网站
paginator = Paginator(articles, 20) # 每页显示10篇文章 selected_website = None
articles = Article.objects.all()
website_id = request.GET.get('website')
if website_id:
try:
selected_website = Website.objects.get(id=website_id)
articles = articles.filter(website=selected_website)
except Website.DoesNotExist:
pass
# 新增:处理关键词搜索
search_query = request.GET.get('q')
if search_query:
articles = articles.filter(title__icontains=search_query)
# 按创建时间倒序排列
articles = articles.order_by('-created_at')
# 分页
paginator = Paginator(articles, 10) # 每页显示10篇文章
page_number = request.GET.get('page') page_number = request.GET.get('page')
page_obj = paginator.get_page(page_number) page_obj = paginator.get_page(page_number)
return render(request, 'core/article_list.html', { return render(request, 'core/article_list.html', {
'page_obj': page_obj 'page_obj': page_obj,
'websites': websites,
'selected_website': selected_website,
# 新增:传递搜索关键词到模板
'search_query': search_query
}) })
def article_detail(request, article_id): def article_detail(request, article_id):
""" article = Article.objects.get(id=article_id)
显示文章详情的视图函数 return render(request, 'core/article_detail.html', {'article': article})
"""
article = get_object_or_404(Article, id=article_id)
return render(request, 'core/article_detail.html', {
'article': article
})

31
requirements.txt Normal file
View File

@@ -0,0 +1,31 @@
asgiref==3.9.1
asttokens==3.0.0
beautifulsoup4==4.13.4
bs4==0.0.2
certifi==2025.8.3
charset-normalizer==3.4.3
decorator==5.2.1
Django==5.1
executing==2.2.0
idna==3.10
ipython==9.4.0
ipython_pygments_lexers==1.1.1
jedi==0.19.2
lxml==6.0.0
matplotlib-inline==0.1.7
parso==0.8.4
pexpect==4.9.0
prompt_toolkit==3.0.51
ptyprocess==0.7.0
pure_eval==0.2.3
Pygments==2.19.2
python-docx==1.2.0
requests==2.32.4
soupsieve==2.7
sqlparse==0.5.3
stack-data==0.6.3
traitlets==5.14.3
typing_extensions==4.14.1
urllib3==2.5.0
uv==0.8.8
wcwidth==0.2.13