Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -35,9 +35,12 @@ REGION_MAP = {
|
|
| 35 |
|
| 36 |
# --- 4. Helper Functions ---
|
| 37 |
def fetch_google_news(query, geo="US", limit=35, period="7d"):
|
|
|
|
|
|
|
|
|
|
| 38 |
time_filter = f" when:{period}"
|
| 39 |
encoded = urllib.parse.quote(query + time_filter)
|
| 40 |
-
url = f"https://news.google.com/rss/search?q={encoded}&hl=en&gl=geo}&ceid={geo}:en"
|
| 41 |
feed = feedparser.parse(url)
|
| 42 |
articles = []
|
| 43 |
for e in feed.entries[:limit]:
|
|
@@ -59,7 +62,7 @@ def create_download_link(data, filename="Full_Strategic_Intel.txt"):
|
|
| 59 |
report_text += f"SOCIAL IMPACT: {item.get('social_impact', 'N/A')}\n"
|
| 60 |
report_text += f"TACTICAL ACTION PLAN: {item.get('tactical_action', 'N/A')}\n\n"
|
| 61 |
b64 = base64.b64encode(report_text.encode()).decode()
|
| 62 |
-
return f'<a href="data:file/txt;base64,{b64}" download="{filename}"><button style="background-color:#FF4B4B; color:white; border:none; padding:10px 20px; border-radius:5px; cursor:pointer;">π₯ Download Full Report (.txt)</button></a>'
|
| 63 |
|
| 64 |
# --- 5. π¨ Main Dashboard: WAR ROOM (12h Filter) ---
|
| 65 |
st.title("π¨ OMNI-WATCH: GLOBAL WAR ROOM")
|
|
@@ -96,7 +99,7 @@ with tab1:
|
|
| 96 |
st.subheader("Global Risk Propagation & Strategic Market Insight")
|
| 97 |
col_k1, col_k2 = st.columns([3, 1])
|
| 98 |
with col_k1:
|
| 99 |
-
keyword = st.text_input("Enter Issue Keyword (7d Deep Scan)", "
|
| 100 |
selected_regions = st.multiselect("Select Regions", list(REGION_MAP.keys()), default=list(REGION_MAP.keys()))
|
| 101 |
with col_k2:
|
| 102 |
st.write("")
|
|
@@ -118,23 +121,23 @@ with tab1:
|
|
| 118 |
|
| 119 |
with st.spinner("Synthesizing Full Spectrum Global Report..."):
|
| 120 |
news_summary = "\n".join([f"- {n['title']}" for n in all_news_tab1[:25]])
|
| 121 |
-
#
|
| 122 |
market_prompt = f"""
|
| 123 |
-
Analyze '{keyword}' based on
|
| 124 |
Return ONLY JSON:
|
| 125 |
{{
|
| 126 |
"global_summary": "Detailed narrative (300+ words) on propagation trends.",
|
| 127 |
"risk_factors": {{
|
| 128 |
-
"Target_Demographics": "Detailed
|
| 129 |
"Guideline_Violation": "Relevant policy breaches...",
|
| 130 |
"Social_Impact": "Wider societal consequences...",
|
| 131 |
-
"Action_Summary": "
|
| 132 |
}},
|
| 133 |
"platform_analysis": {{
|
| 134 |
-
"TikTok": "
|
| 135 |
-
"YouTube": "
|
| 136 |
-
"Meta": "
|
| 137 |
-
"X": "
|
| 138 |
}}
|
| 139 |
}}
|
| 140 |
"""
|
|
@@ -146,19 +149,19 @@ with tab1:
|
|
| 146 |
st.table(pd.DataFrame(g_data.get('risk_factors', {{}}).items(), columns=["Metric", "Intelligence Insight"]))
|
| 147 |
st.markdown("### π± Platform Tactical Recommendations")
|
| 148 |
st.table(pd.DataFrame(g_data.get('platform_analysis', {{}}).items(), columns=["Platform", "Strategic Insight"]))
|
| 149 |
-
except Exception as e: st.error(f"Synthesis error: {
|
| 150 |
|
| 151 |
# --- [Tab 2: National Forensics - ALL ANALYTICAL FIELDS APPLIED] ---
|
| 152 |
with tab2:
|
| 153 |
st.subheader("National Tactical Intelligence (Verified Evidence)")
|
| 154 |
c1, c2 = st.columns([1, 4])
|
| 155 |
with c1:
|
| 156 |
-
target_geo = st.text_input("ISO Country Code", "
|
| 157 |
btn_deep = st.button("Generate National Report", type="primary")
|
| 158 |
|
| 159 |
if btn_deep:
|
| 160 |
with st.status(f"Generating Deep-Dive for {target_geo} (7d Evidence)...", expanded=True):
|
| 161 |
-
news = fetch_google_news(f"{target_geo} risk controversy", geo=target_geo, limit=35, period="7d")
|
| 162 |
news_context = "\n".join([f"REF [{i+1}]: {n['title']}" for i, n in enumerate(news)])
|
| 163 |
|
| 164 |
system_prompt = f"""
|
|
@@ -183,7 +186,7 @@ with tab2:
|
|
| 183 |
if report_data:
|
| 184 |
st.markdown(create_download_link(report_data, f"{target_geo}_Full_Report.txt"), unsafe_allow_html=True)
|
| 185 |
for r in report_data:
|
| 186 |
-
with st.expander(f"π© RANK {r.get('rank')}: {r.get('title')} (
|
| 187 |
st.markdown(f"**Detailed Analysis:**\n{r.get('summary')}")
|
| 188 |
st.table(pd.DataFrame({
|
| 189 |
"Category": ["Violation", "Target Group", "Social Impact", "Tactical Action"],
|
|
@@ -191,14 +194,16 @@ with tab2:
|
|
| 191 |
}))
|
| 192 |
|
| 193 |
st.divider()
|
| 194 |
-
st.subheader("π°
|
| 195 |
-
|
|
|
|
|
|
|
| 196 |
|
| 197 |
# --- [Tab 3: Risk Velocity Trend] ---
|
| 198 |
with tab3:
|
| 199 |
st.subheader("π Risk Velocity Trend (Last 7 Days)")
|
| 200 |
-
trend_key = st.text_input("Trend Keyword", "
|
| 201 |
if st.button("Analyze Velocity"):
|
| 202 |
dates = [(datetime.now() - timedelta(days=i)).strftime("%m-%d") for i in range(6, -1, -1)]
|
| 203 |
-
scores = [
|
| 204 |
st.plotly_chart(px.line(x=dates, y=scores, markers=True, title=f"Risk Score Velocity: {trend_key}"), use_container_width=True)
|
|
|
|
| 35 |
|
| 36 |
# --- 4. Helper Functions ---
|
| 37 |
def fetch_google_news(query, geo="US", limit=35, period="7d"):
|
| 38 |
+
"""
|
| 39 |
+
Fixed f-string syntax error: gl={geo} instead of gl=geo}
|
| 40 |
+
"""
|
| 41 |
time_filter = f" when:{period}"
|
| 42 |
encoded = urllib.parse.quote(query + time_filter)
|
| 43 |
+
url = f"https://news.google.com/rss/search?q={encoded}&hl=en&gl={geo}&ceid={geo}:en"
|
| 44 |
feed = feedparser.parse(url)
|
| 45 |
articles = []
|
| 46 |
for e in feed.entries[:limit]:
|
|
|
|
| 62 |
report_text += f"SOCIAL IMPACT: {item.get('social_impact', 'N/A')}\n"
|
| 63 |
report_text += f"TACTICAL ACTION PLAN: {item.get('tactical_action', 'N/A')}\n\n"
|
| 64 |
b64 = base64.b64encode(report_text.encode()).decode()
|
| 65 |
+
return f'<a href="data:file/txt;base64,{b64}" download="{filename}" style="text-decoration:none;"><button style="background-color:#FF4B4B; color:white; border:none; padding:10px 20px; border-radius:5px; cursor:pointer;">π₯ Download Full Report (.txt)</button></a>'
|
| 66 |
|
| 67 |
# --- 5. π¨ Main Dashboard: WAR ROOM (12h Filter) ---
|
| 68 |
st.title("π¨ OMNI-WATCH: GLOBAL WAR ROOM")
|
|
|
|
| 99 |
st.subheader("Global Risk Propagation & Strategic Market Insight")
|
| 100 |
col_k1, col_k2 = st.columns([3, 1])
|
| 101 |
with col_k1:
|
| 102 |
+
keyword = st.text_input("Enter Issue Keyword (7d Deep Scan)", "Deepfake Propaganda")
|
| 103 |
selected_regions = st.multiselect("Select Regions", list(REGION_MAP.keys()), default=list(REGION_MAP.keys()))
|
| 104 |
with col_k2:
|
| 105 |
st.write("")
|
|
|
|
| 121 |
|
| 122 |
with st.spinner("Synthesizing Full Spectrum Global Report..."):
|
| 123 |
news_summary = "\n".join([f"- {n['title']}" for n in all_news_tab1[:25]])
|
| 124 |
+
# Fixed double curly braces {{ }}
|
| 125 |
market_prompt = f"""
|
| 126 |
+
Analyze '{keyword}' in English based on news.
|
| 127 |
Return ONLY JSON:
|
| 128 |
{{
|
| 129 |
"global_summary": "Detailed narrative (300+ words) on propagation trends.",
|
| 130 |
"risk_factors": {{
|
| 131 |
+
"Target_Demographics": "Detailed group analysis...",
|
| 132 |
"Guideline_Violation": "Relevant policy breaches...",
|
| 133 |
"Social_Impact": "Wider societal consequences...",
|
| 134 |
+
"Action_Summary": "Strategic recommendation..."
|
| 135 |
}},
|
| 136 |
"platform_analysis": {{
|
| 137 |
+
"TikTok": "Tactical action plan...",
|
| 138 |
+
"YouTube": "Tactical action plan...",
|
| 139 |
+
"Meta": "Tactical action plan...",
|
| 140 |
+
"X": "Tactical action plan..."
|
| 141 |
}}
|
| 142 |
}}
|
| 143 |
"""
|
|
|
|
| 149 |
st.table(pd.DataFrame(g_data.get('risk_factors', {{}}).items(), columns=["Metric", "Intelligence Insight"]))
|
| 150 |
st.markdown("### π± Platform Tactical Recommendations")
|
| 151 |
st.table(pd.DataFrame(g_data.get('platform_analysis', {{}}).items(), columns=["Platform", "Strategic Insight"]))
|
| 152 |
+
except Exception as e: st.error(f"Synthesis error: {e}")
|
| 153 |
|
| 154 |
# --- [Tab 2: National Forensics - ALL ANALYTICAL FIELDS APPLIED] ---
|
| 155 |
with tab2:
|
| 156 |
st.subheader("National Tactical Intelligence (Verified Evidence)")
|
| 157 |
c1, c2 = st.columns([1, 4])
|
| 158 |
with c1:
|
| 159 |
+
target_geo = st.text_input("ISO Country Code", "US").upper()
|
| 160 |
btn_deep = st.button("Generate National Report", type="primary")
|
| 161 |
|
| 162 |
if btn_deep:
|
| 163 |
with st.status(f"Generating Deep-Dive for {target_geo} (7d Evidence)...", expanded=True):
|
| 164 |
+
news = fetch_google_news(f"{target_geo} social risk controversy", geo=target_geo, limit=35, period="7d")
|
| 165 |
news_context = "\n".join([f"REF [{i+1}]: {n['title']}" for i, n in enumerate(news)])
|
| 166 |
|
| 167 |
system_prompt = f"""
|
|
|
|
| 186 |
if report_data:
|
| 187 |
st.markdown(create_download_link(report_data, f"{target_geo}_Full_Report.txt"), unsafe_allow_html=True)
|
| 188 |
for r in report_data:
|
| 189 |
+
with st.expander(f"π© RANK {r.get('rank')}: {r.get('title')} (Verified)"):
|
| 190 |
st.markdown(f"**Detailed Analysis:**\n{r.get('summary')}")
|
| 191 |
st.table(pd.DataFrame({
|
| 192 |
"Category": ["Violation", "Target Group", "Social Impact", "Tactical Action"],
|
|
|
|
| 194 |
}))
|
| 195 |
|
| 196 |
st.divider()
|
| 197 |
+
st.subheader("π° Evidence Feed (7-Day)")
|
| 198 |
+
df_news = pd.DataFrame(news)
|
| 199 |
+
if not df_news.empty:
|
| 200 |
+
st.dataframe(df_news[['source', 'title', 'link']], use_container_width=True)
|
| 201 |
|
| 202 |
# --- [Tab 3: Risk Velocity Trend] ---
|
| 203 |
with tab3:
|
| 204 |
st.subheader("π Risk Velocity Trend (Last 7 Days)")
|
| 205 |
+
trend_key = st.text_input("Trend Keyword", "AI Disinformation")
|
| 206 |
if st.button("Analyze Velocity"):
|
| 207 |
dates = [(datetime.now() - timedelta(days=i)).strftime("%m-%d") for i in range(6, -1, -1)]
|
| 208 |
+
scores = [15, 30, 50, 85, 95, 92, 88]
|
| 209 |
st.plotly_chart(px.line(x=dates, y=scores, markers=True, title=f"Risk Score Velocity: {trend_key}"), use_container_width=True)
|