debugging for analysis tables

src/news_analysis.py

@@ -213,74 +213,74 @@ def tavily_search(query, days, max_results=10):
     return response.json()
 
 # === Smart News Search ===
-def fetch_deep_news(topic, days):
-    print(f"[DEBUG] Fetching mock articles for topic: {topic}")
-    return [
-        {
-            "title": "Startup raises $100M Series A funding",
-            "url": "https://example.com/funding",
-            "summary": "The startup raised $100M in Series A funding to expand operations.",
-            "date": "2025-07-20"
-        },
-        {
-            "title": "Company faces regulatory lawsuit",
-            "url": "https://example.com/lawsuit",
-            "summary": "The company is facing lawsuits due to environmental violations.",
-            "date": "2025-07-19"
-        }
-    ]
-
 # def fetch_deep_news(topic, days):
-#     all_results = []
-#     seen_urls = set()
-
-#     base_queries = [
-#         topic,
-#         f"{topic} AND startup",
-#         f"{topic} AND acquisition OR merger OR funding",
-#         f"{topic} AND CEO OR executive OR leadership",
-#         f"{topic} AND venture capital OR Series A OR Series B",
-#         f"{topic} AND government grant OR approval OR contract",
-#         f"{topic} AND underrated OR small-cap OR micro-cap"
+#     print(f"[DEBUG] Fetching mock articles for topic: {topic}")
+#     return [
+#         {
+#             "title": "Startup raises $100M Series A funding",
+#             "url": "https://example.com/funding",
+#             "summary": "The startup raised $100M in Series A funding to expand operations.",
+#             "date": "2025-07-20"
+#         },
+#         {
+#             "title": "Company faces regulatory lawsuit",
+#             "url": "https://example.com/lawsuit",
+#             "summary": "The company is facing lawsuits due to environmental violations.",
+#             "date": "2025-07-19"
+#         }
 #     ]
 
-#     investor_queries = [
-#         f"{topic} AND BlackRock OR Vanguard OR SoftBank",
-#         f"{topic} AND Elon Musk OR Sam Altman OR Peter Thiel",
-#         f"{topic} AND Berkshire Hathaway OR Warren Buffett",
-#         f"{topic} AND institutional investor OR hedge fund",
-#     ]
+def fetch_deep_news(topic, days):
+    all_results = []
+    seen_urls = set()
+
+    base_queries = [
+        topic,
+        f"{topic} AND startup",
+        f"{topic} AND acquisition OR merger OR funding",
+        f"{topic} AND CEO OR executive OR leadership",
+        f"{topic} AND venture capital OR Series A OR Series B",
+        f"{topic} AND government grant OR approval OR contract",
+        f"{topic} AND underrated OR small-cap OR micro-cap"
+    ]
 
-#     related_terms = get_related_terms(topic)
-#     synonym_queries = [f"{term} AND {kw}" for term in related_terms for kw in ["startup", "funding", "merger", "acquisition"]]
+    investor_queries = [
+        f"{topic} AND BlackRock OR Vanguard OR SoftBank",
+        f"{topic} AND Elon Musk OR Sam Altman OR Peter Thiel",
+        f"{topic} AND Berkshire Hathaway OR Warren Buffett",
+        f"{topic} AND institutional investor OR hedge fund",
+    ]
 
-#     all_queries = base_queries + investor_queries + synonym_queries
+    related_terms = get_related_terms(topic)
+    synonym_queries = [f"{term} AND {kw}" for term in related_terms for kw in ["startup", "funding", "merger", "acquisition"]]
 
-#     for query in all_queries:
-#         try:
-#             print(f"🔍 Tavily query: {query}")
-#             response = tavily_search(query, days)
+    all_queries = base_queries + investor_queries + synonym_queries
 
-#             if not isinstance(response, dict) or "results" not in response:
-#                 print(f"⚠️ Tavily API response issue: {response}")
-#                 continue
+    for query in all_queries:
+        try:
+            print(f"🔍 Tavily query: {query}")
+            response = tavily_search(query, days)
 
-#             for item in response.get("results", []):
-#                 url = item.get("url")
-#                 content = item.get("content", "") or item.get("summary", "") or item.get("title", "")
-#                 if url and url not in seen_urls and len(content) > 150:
-#                     all_results.append({
-#                         "title": item.get("title"),
-#                         "url": url,
-#                         "content": content
-#                     })
-#                     seen_urls.add(url)
+            if not isinstance(response, dict) or "results" not in response:
+                print(f"⚠️ Tavily API response issue: {response}")
+                continue
 
-#         except Exception as e:
-#             print(f"⚠️ Tavily request failed for query '{query}': {e}")
+            for item in response.get("results", []):
+                url = item.get("url")
+                content = item.get("content", "") or item.get("summary", "") or item.get("title", "")
+                if url and url not in seen_urls and len(content) > 150:
+                    all_results.append({
+                        "title": item.get("title"),
+                        "url": url,
+                        "content": content
+                    })
+                    seen_urls.add(url)
 
-#     print(f"📰 Total articles collected: {len(all_results)}")
-#     return all_results
+        except Exception as e:
+            print(f"⚠️ Tavily request failed for query '{query}': {e}")
+
+    print(f"📰 Total articles collected: {len(all_results)}")
+    return all_results
 
 # === Generate Markdown Report ===
 def generate_value_investor_report(topic, news_results, max_articles=20, max_chars_per_article=400):