Add export into front

core/utils.py

@@ -1,4 +1,3 @@
-# core/utils.py
 import os
 import requests
 from bs4 import BeautifulSoup
@@ -42,6 +41,12 @@ def download_media(url, save_dir):
             filename += '.png'
         elif 'image/gif' in content_type:
             filename += '.gif'
+        elif 'video/mp4' in content_type:
+            filename += '.mp4'
+        elif 'video/avi' in content_type:
+            filename += '.avi'
+        elif 'video/quicktime' in content_type:
+            filename += '.mov'
         else:
             filename += '.bin'  # 默认二进制扩展名
 
@@ -61,6 +66,7 @@ def download_media(url, save_dir):
 
 
 def process_article(url, website):
+    # 检查文章是否已存在，如果存在则跳过
     if Article.objects.filter(url=url).exists():
         print(f"文章已存在，跳过: {url}")
         return
@@ -116,6 +122,8 @@ def process_article(url, website):
         return
 
     imgs = content_tag.find_all("img")
+    # 查找视频元素
+    videos = content_tag.find_all("video")
     media_files = []
 
     safe_title = "".join(c if c.isalnum() else "_" for c in title)[:50]
@@ -134,17 +142,51 @@ def process_article(url, website):
             img["src"] = settings.MEDIA_URL + rel_path.replace("\\", "/")
             media_files.append(rel_path.replace("\\", "/"))
 
+    # 处理视频文件
+    for video in videos:
+        src = video.get("src")
+        if not src:
+            # 检查<source>标签
+            source = video.find("source")
+            if source:
+                src = source.get("src")
+
+        if not src:
+            continue
+
+        if not src.startswith("http"):
+            src = urljoin(url, src)
+        local_path = download_media(src, save_dir)
+        if local_path:
+            rel_path = os.path.relpath(local_path, settings.MEDIA_ROOT)
+            # 更新视频src属性
+            if video.get("src"):
+                video["src"] = settings.MEDIA_URL + rel_path.replace("\\", "/")
+            else:
+                source = video.find("source")
+                if source:
+                    source["src"] = settings.MEDIA_URL + rel_path.replace("\\", "/")
+            media_files.append(rel_path.replace("\\", "/"))
+
     content_html = str(content_tag)
 
-    article = Article.objects.create(
-        website=website,
-        title=title,
-        url=url,
-        content=content_html,
-        pub_date=timezone.now(),
-        media_files=media_files
-    )
-    print(f"已保存文章及图片：{title}")
+    try:
+        # 使用try-except处理可能的数据库约束错误
+        article = Article.objects.create(
+            website=website,
+            title=title,
+            url=url,
+            content=content_html,
+            pub_date=timezone.now(),
+            media_files=media_files
+        )
+        print(f"已保存文章及图片：{title}")
+    except Exception as e:
+        # 处理重复URL或其他数据库错误
+        if "UNIQUE constraint failed" in str(e) and "core_article.url" in str(e):
+            print(f"文章URL重复，跳过保存: {url}")
+        else:
+            print(f"保存文章时出错: {url}，错误：{e}")
 
 
 def is_valid_url(url, base_netloc):