Initial commit: 百家号文章采集系统

test_html.py

@@ -0,0 +1,23 @@
+from app import BaijiahaoScraper
+
+app_id = "1700253559210167"
+
+print(f"测试app_id: {app_id}\n")
+
+uk, cookies = BaijiahaoScraper.get_uk_from_app_id(app_id)
+print(f"UK: {uk}\n")
+
+scraper = BaijiahaoScraper(uk, cookies)
+
+# 测试HTML解析方式
+print("使用HTML解析方式:")
+articles = scraper.get_articles_from_html(app_id=app_id)
+
+if articles:
+    print(f"\n成功! 获取到 {len(articles)} 篇文章")
+    print("\n前3篇:")
+    for i, article in enumerate(articles[:3], 1):
+        print(f"{i}. {article['标题']}")
+        print(f"   {article['链接'][:80]}...")
+else:
+    print("未获取到文章")