fixing date issues

src/news_analysis.py

@@ -217,7 +217,6 @@ from datetime import datetime, timedelta  # Ensure this is at the top
 def fetch_deep_news(topic, days):
     all_results = []
     seen_urls = set()
-    cutoff_date = datetime.now() - timedelta(days=days)
 
     base_queries = [
         topic,
@@ -253,28 +252,13 @@ def fetch_deep_news(topic, days):
             for item in response.get("results", []):
                 url = item.get("url")
                 content = item.get("content", "") or item.get("summary", "") or item.get("title", "")
-                if not url or url in seen_urls or len(content) <= 150:
-                    continue
-
-                pub_date_str = item.get("published_date")
-                if pub_date_str:
-                    try:
-                        pub_date = datetime.fromisoformat(pub_date_str.rstrip("Z"))
-                        if pub_date < cutoff_date:
-                            continue  # Skip articles too old
-                        date_str = pub_date.strftime("%Y-%m-%d")
-                    except Exception:
-                        date_str = "Unknown"
-                else:
-                    date_str = "Unknown"
-
-                all_results.append({
-                    "title": item.get("title"),
-                    "url": url,
-                    "content": content,
-                    "date": date_str
-                })
-                seen_urls.add(url)
+                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)
 
         except Exception as e:
             print(f"⚠️ Tavily request failed for query '{query}': {e}")
@@ -282,59 +266,9 @@ def fetch_deep_news(topic, days):
     print(f"📰 Total articles collected: {len(all_results)}")
     return all_results
 
-# 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"
-#     ]
-
-#     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",
-#     ]
-
-#     related_terms = get_related_terms(topic)
-#     synonym_queries = [f"{term} AND {kw}" for term in related_terms for kw in ["startup", "funding", "merger", "acquisition"]]
-
-#     all_queries = base_queries + investor_queries + synonym_queries
-
-#     for query in all_queries:
-#         try:
-#             print(f"🔍 Tavily query: {query}")
-#             response = tavily_search(query, days)
-
-#             if not isinstance(response, dict) or "results" not in response:
-#                 print(f"⚠️ Tavily API response issue: {response}")
-#                 continue
-
-#             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)
-
-#         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 ===
+from datetime import datetime
+
 def generate_value_investor_report(topic, news_results, max_articles=20, max_chars_per_article=400):
     news_results = news_results[:max_articles]
 
@@ -353,7 +287,7 @@ def generate_value_investor_report(topic, news_results, max_articles=20, max_cha
     )
 
     prompt = PromptTemplate.from_template("""
-You're a highly focused value investor. Analyze this week's news on "{Topic}".
+You're a highly focused value investor. Today is {Today}. Analyze this week's news on "{Topic}".
 
 Your goal is to uncover:
 - Meaningful events (e.g., CEO joining a startup, insider buys, big-name partnerships)
@@ -403,9 +337,85 @@ Include context and macroeconomic/regulatory angles. Add an intro on sentiment a
     ])
     prompt_value = chat_prompt.format_prompt(
         Topic=topic,
-        ArticleSummaries=article_summary
+        ArticleSummaries=article_summary,
+        Today=datetime.now().strftime("%B %d, %Y")
     ).to_messages()
 
     llm = get_llm()
     result = llm.invoke(prompt_value)
     return result.content
+
+# def generate_value_investor_report(topic, news_results, max_articles=20, max_chars_per_article=400):
+#     news_results = news_results[:max_articles]
+
+#     for item in news_results:
+#         text = item.get("summary") or item.get("content", "")
+#         result = analyze_article(text)
+#         item["fin_sentiment"] = result.get("sentiment", "neutral")
+#         item["fin_confidence"] = result.get("confidence", 0.0)
+#         item["investment_decision"] = result.get("investment_decision", "Watch")
+
+#     article_summary = "".join(
+#         f"- **{item['title']}**: { (item.get('content') or item.get('summary', ''))[:max_chars_per_article]}... "
+#         f"(Sentiment: {item['fin_sentiment'].title()}, Confidence: {item['fin_confidence']:.2f}, "
+#         f"Decision: {item['investment_decision']}) [link]({item['url']})\n"
+#         for item in news_results
+#     )
+
+#     prompt = PromptTemplate.from_template("""
+# You're a highly focused value investor. Analyze this week's news on "{Topic}".
+
+# Your goal is to uncover:
+# - Meaningful events (e.g., CEO joining a startup, insider buys, big-name partnerships)
+# - Startups or small caps that may signal undervalued opportunity
+# - Connections to key individuals or institutions (e.g., Elon Musk investing, Sam Altman joining)
+# - Companies with strong fundamentals: low P/E, low P/B, high ROE, recent IPOs, moats, or high free cash flow - THEY MUST INCLUDE THE LINK AS WELL and this is very important
+
+                                          
+# ### News
+# {ArticleSummaries}
+
+# Write a markdown memo with:
+# 1. **Key Value Signals**
+# 2. **Stocks or Startups to Watch** -- MUST: Explanation of each or why they are interesting AND ALSO MUST: the Add on each of the stocks the Price-to-Earnings Ratio · Price-to-Book Ratio · Debt-to-Equity Ratio · Free Cash Flow · PEG Ratio ·  fore each, this is very important
+# 3. **What Smart Money Might Be Acting On**
+# 4. **References**
+# 5. **Investment Hypothesis**
+
+#                                           ### 📌 Executive Summary
+
+# Summarize the topic's current investment environment in 3–4 bullet points. Include sentiment, risks, and catalysts.
+
+# ---
+
+# ### 📊 Signals and Analysis (Include Sources)
+
+# For each important news item, write a short paragraph with:
+# - What happened
+# - Why it matters (financially)
+# - Embedded source as `[source title](url)`
+# - Bold any key financial terms (e.g., **Series A**, **merger**, **valuation**)
+
+# ---
+
+# ### 🧠 Investment Thesis
+
+# Give a reasoned conclusion:
+# - Is this a buy/sell/watch opportunity?
+# - What’s the risk/reward?
+# - What signals or themes matter most?
+
+# Include context and macroeconomic/regulatory angles. Add an intro on sentiment and market trends for the week.
+# """)
+
+#     chat_prompt = ChatPromptTemplate.from_messages([
+#         SystemMessagePromptTemplate(prompt=prompt)
+#     ])
+#     prompt_value = chat_prompt.format_prompt(
+#         Topic=topic,
+#         ArticleSummaries=article_summary
+#     ).to_messages()
+
+#     llm = get_llm()
+#     result = llm.invoke(prompt_value)
+#     return result.content