Update app.py

app.py

@@ -8,13 +8,15 @@ from textblob import TextBlob
 from transformers import pipeline
 import textstat
 import trafilatura
+import requests
+from bs4 import BeautifulSoup
 
 # constants
 MAX_TEXT_LENGTH = 1500
 
-ARTICLE_A = """Global leaders achieved a historic breakthrough today, signing a comprehensive climate accord aimed at drastically slashing carbon emissions by 2030. Environmental advocates are celebrating the mandate, which forces heavy-polluting industries to finally take accountability for their ecological damage. While corporations warn of transition costs, scientists emphasize that failing to act now would result in catastrophic, irreversible damage to our planet's fragile ecosystems."""
+ARTICLE_A = """In a long-overdue victory for working-class families, lawmakers unveiled a bold new wealth tax targeting the nation's ultra-rich. For decades, billionaires have exploited gaping loopholes to hoard unprecedented wealth while paying a fraction of what ordinary citizens pay in taxes. This progressive legislation finally forces the top 0.1% to pay their fair share. Advocates argue the trillions generated will revitalize crumbling public schools, expand healthcare access, and begin to heal the gaping wounds of systemic economic inequality that have ravaged our communities."""
 
-ARTICLE_B = """A sweeping new climate agreement signed today is drawing fierce criticism from industry leaders, who warn the aggressive emission targets will cripple economic growth. The heavy-handed regulations impose massive compliance costs on the manufacturing and energy sectors, inevitably leading to significant job losses and higher prices for consumers. Critics argue the rushed accord prioritizes bureaucratic posturing over practical, market-driven solutions to environmental concerns."""
+ARTICLE_B = """A radical new wealth tax proposed today has sent shockwaves through the financial sector, with economists warning the punitive measure will severely cripple investment and drive capital overseas. The heavy-handed legislation directly penalizes success and job creators, fundamentally undermining the free-market principles that drive innovation. Analysts caution that this bureaucratic overreach will inevitably backfire, stifling economic growth, destroying millions of private-sector jobs, and ultimately passing the financial burden down to the everyday consumer."""
 
 
 @st.cache_resource
@@ -41,6 +43,10 @@ def _load_nlp_models() -> typing.Dict[str, typing.Any]:
         "text-classification", 
         model="roberta-large-mnli" 
     )
+    theme_classifier = pipeline(
+        "zero-shot-classification",
+        model="typeform/distilbert-base-uncased-mnli"
+    )
 
     return {
         "sentiment": sentiment_analyzer,
@@ -50,13 +56,6 @@ def _load_nlp_models() -> typing.Dict[str, typing.Any]:
         "nli": nli_classifier,
     }
 
-    return {
-        "sentiment": sentiment_analyzer,
-        "emotion": emotion_classifier,
-        "ner": ner_extractor,
-        "keyword": keyword_extractor,
-    }
-
 
 def analyze_article(text: str) -> dict:
     """Analyzes framing using semantic keyphrases, sentiment, emotion, readability and NER."""
@@ -94,6 +93,16 @@ def analyze_article(text: str) -> dict:
     )
     extracted_keywords = [kw[0] for kw in keyword_results]
 
+    # Thematic Framing
+    framing_dimensions = [
+        "economic consequences", 
+        "moral and ethical fairness", 
+        "legal and bureaucratic", 
+        "public safety and health"
+    ]
+    theme_result = models["theme"](safe_text, framing_dimensions)
+    primary_theme = theme_result["labels"][0]
+
     # Named Entity Recognition 
     ner_results = models["ner"](safe_text)
     extracted_entities = list(set([ent["word"] for ent in ner_results if ent["score"] > 0.6]))
@@ -179,12 +188,34 @@ def _highlight_keywords(text: str, keywords: typing.List[str]) -> str:
 
 
 def fetch_article_text(url: str) -> str:
-    """Scrapes clean article text from a given URL."""
+    """Scrapes article text."""
     downloaded = trafilatura.fetch_url(url)
     if downloaded:
         text = trafilatura.extract(downloaded)
-        return text if text else "Error: Could not extract text."
-    return "Error: Could not fetch URL. It might be protected."
+        if text and len(text) > 200:
+            return text
+
+    try:
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
+            'Accept-Language': 'en-US,en;q=0.9',
+        }
+        response = requests.get(url, headers=headers, timeout=10)
+        soup = BeautifulSoup(response.content, 'html.parser')
+        
+        for script in soup(["script", "style"]):
+            script.extract()
+            
+        paragraphs = soup.find_all('p')
+        text = ' '.join([p.get_text() for p in paragraphs])
+        
+        if text and len(text) > 200:
+            return text.strip()
+            
+    except Exception as e:
+        return f"Error: Could not fetch URL. Connection failed."
+
+    return "Error: Could not extract text. The site may be protected by hard paywalls."
 
 
 def check_contradiction(text_a: str, text_b: str) -> dict:
@@ -199,14 +230,16 @@ def check_contradiction(text_a: str, text_b: str) -> dict:
     return {"relationship": result["label"], "confidence": result["score"]}
     
 
+# USER INTERFACE (Must be the first Streamlit command)
+st.set_page_config(page_title="FrameVis | Media Framing", layout="wide")
+
 # STATE MANAGEMENT
 if "results_a" not in st.session_state:
     st.session_state.results_a = None
 if "results_b" not in st.session_state:
     st.session_state.results_b = None
-
-# USER INTERFACE
-st.set_page_config(page_title="FrameVis | Media Framing", layout="wide")
+if "nli_result" not in st.session_state:
+    st.session_state.nli_result = None
 
 st.title("FrameVis")
 st.markdown("##### Media bias and framing effects across global news sources.")
@@ -235,11 +268,12 @@ with col2:
 
 st.write("")
 
-# Single unified execution button
-if st.button("Analyze & Compare Sources", use_container_width=True, type="primary"):
-    with st.spinner("Analyzing framing semantics for both sources."):
+# Execution button
+if st.button("Analyze and Compare Sources", use_container_width=True, type="primary"):
+    with st.spinner("Analyzing framing semantics for both sources..."):
         st.session_state.results_a = analyze_article(user_article_a)
         st.session_state.results_b = analyze_article(user_article_b)
+        st.session_state.nli_result = check_contradiction(user_article_a, user_article_b)
 
 # Analysis Display
 if st.session_state.results_a and st.session_state.results_b:
@@ -247,14 +281,15 @@ if st.session_state.results_a and st.session_state.results_b:
     st.markdown("### Framing Analytics & Comparison")
     
     # Display Contradictions
-    nli_result = check_contradiction(user_article_a, user_article_b)
-    if nli_result["relationship"] == "CONTRADICTION":
-        st.error(f"**NARRATIVE CONTRADICTION** (Confidence: {nli_result['confidence']:.2f}) - These sources are actively disputing each other's foundational facts.")
-    elif nli_result["relationship"] == "ENTAILMENT":
-        st.success(f"**NARRATIVE ALIGNMENT** (Confidence: {nli_result['confidence']:.2f}) - These sources agree on the core premise.")
-    else:
-        st.info(f"**NEUTRAL RELATIONSHIP** - These sources are discussing the topic without direct contradiction or alignment.")
-    
+    nli_result = st.session_state.nli_result
+    if nli_result:
+        if nli_result["relationship"] == "CONTRADICTION":
+            st.error(f"**NARRATIVE CONTRADICTION** (Confidence: {nli_result['confidence']:.2f}) - These sources are disputing each other's facts.")
+        elif nli_result["relationship"] == "ENTAILMENT":
+            st.success(f"**NARRATIVE ALIGNMENT** (Confidence: {nli_result['confidence']:.2f}) - These sources agree on the core premise.")
+        else:
+            st.info(f"**NEUTRAL RELATIONSHIP** - These sources are discussing the topic without direct contradiction or alignment.")
+            
     st.plotly_chart(_create_comparison_radar_chart(st.session_state.results_a, st.session_state.results_b), use_container_width=True)
 
     res_col1, res_col2 = st.columns(2)
@@ -263,10 +298,12 @@ if st.session_state.results_a and st.session_state.results_b:
     with res_col1:
         r_a = st.session_state.results_a
         st.markdown("#### Source A Breakdown")
-        m1, m2, m3 = st.columns(3)
+        m1, m2 = st.columns(2)
+        m3, m4 = st.columns(2)
         m1.metric("Subjectivity", f"{r_a['subjectivity_score']:.2f}")
         m2.metric("Primary Emotion", r_a['primary_tone'].title())
-        m3.metric("Reading Ease", f"{r_a['reading_ease']:.1f}")
+        m3.metric("Framing Lens", r_a['primary_theme'].title())
+        m4.metric("Reading Ease", f"{r_a['reading_ease']:.1f}")
 
         st.plotly_chart(_create_sentiment_gauge(r_a["sentiment_score"], "Sentiment Bias"), use_container_width=True)
         
@@ -281,10 +318,12 @@ if st.session_state.results_a and st.session_state.results_b:
     with res_col2:
         r_b = st.session_state.results_b
         st.markdown("#### Source B Breakdown")
-        m1, m2, m3 = st.columns(3)
+        m1, m2 = st.columns(2)
+        m3, m4 = st.columns(2)
         m1.metric("Subjectivity", f"{r_b['subjectivity_score']:.2f}")
         m2.metric("Primary Emotion", r_b['primary_tone'].title())
-        m3.metric("Reading Ease", f"{r_b['reading_ease']:.1f}")
+        m3.metric("Framing Lens", r_b['primary_theme'].title())
+        m4.metric("Reading Ease", f"{r_b['reading_ease']:.1f}")
 
         st.plotly_chart(_create_sentiment_gauge(r_b["sentiment_score"], "Sentiment Bias"), use_container_width=True)