Update app.py

app.py

@@ -1,79 +1,81 @@
-import spacy
-import re
-from transformers import pipeline
-import gradio as gr
-
-print("Loading models...")
-try:
-    nlp = spacy.load("en_core_web_sm")
-    print("SpaCy model loaded successfully!")
-except OSError as e:
-    print(f"Error loading SpaCy model: {e}")
-    nlp = None
-
-summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-print("Models loaded successfully!")
-
-def analyze_osint(text):
-    if not text:
-        return "Please enter some text to analyze.", {}
-    summary = ""
-    if len(text.split()) > 50:
-        try:
-            summary_result = summarizer(text, max_length=150, min_length=30, do_sample=False)
-            summary = summary_result[0]['summary_text']
-        except Exception as e:
-            summary = f"Summarization error: {str(e)}"
-    else:
-        summary = "Text is too short to summarize."
-
-    doc = nlp(text) if nlp else None
-    names = []
-    orgs = []
-    locations = []
-    if doc:
-        names = list(set([ent.text for ent in doc.ents if ent.label_ == 'PERSON']))
-        orgs = list(set([ent.text for ent in doc.ents if ent.label_ == 'ORG']))
-        locations = list(set([ent.text for ent in doc.ents if ent.label_ == 'GPE']))
-
-    emails = list(set(re.findall(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', text)))
-    ips = list(set(re.findall(r'\b\d{1,3}(?:\.\d{1,3}){3}\b', text)))
-    socials = list(set(re.findall(r'@(\w{4,15})\b', text)))
-
-    highlighted_entities = []
-    def add_to_highlight(entities_list, label):
-        for item in entities_list:
-            for match in re.finditer(re.escape(item), text):
-                highlighted_entities.append((match.start(), match.end(), label))
-
-    add_to_highlight(names, "NAME")
-    add_to_highlight(orgs, "ORG")
-    add_to_highlight(locations, "LOCATION")
-    add_to_highlight(emails, "EMAIL")
-    add_to_highlight(ips, "IP")
-    add_to_highlight(socials, "SOCIAL")
-
-    return summary, (text, highlighted_entities)
-
-iface = gr.Interface(
-    fn=analyze_osint,
-    inputs=gr.Textbox(lines=10, label="OSINT Text", placeholder="Paste your OSINT data here..."),
-    outputs=[
-        gr.Textbox(label="Executive Summary"),
-        gr.HighlightedText(label="Extracted Entities", color_map={
-            "NAME": "red",
-            "ORG": "blue",
-            "LOCATION": "green",
-            "EMAIL": "orange",
-            "IP": "purple",
-            "SOCIAL": "teal"
-        })
-    ],
-    title="OSINT Analysis Tool",
-    description="Enter any unstructured text to extract key entities and generate a summary.",
-    allow_flagging="never"
-)
-
-if __name__ == "__main__":
-    print("===== Application Startup =====")
-    iface.launch()
+import spacy
+import re
+from transformers import pipeline
+import gradio as gr
+
+print("Loading models...")
+try:
+    nlp = spacy.load("en_core_web_sm")
+    print("SpaCy model loaded successfully!")
+except OSError as e:
+    print(f"Error loading SpaCy model: {e}")
+    nlp = None
+
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+print("Models loaded successfully!")
+
+def analyze_osint(text):
+    if not text:
+        return "Please enter some text to analyze.", []
+
+    summary = ""
+    if len(text.split()) > 50:
+        try:
+            summary_result = summarizer(text, max_length=150, min_length=30, do_sample=False)
+            summary = summary_result[0]['summary_text']
+        except Exception as e:
+            summary = f"Summarization error: {str(e)}"
+    else:
+        summary = "Text is too short to summarize."
+
+    doc = nlp(text) if nlp else None
+    names = []
+    orgs = []
+    locations = []
+    if doc:
+        names = list(set([ent.text for ent in doc.ents if ent.label_ == 'PERSON']))
+        orgs = list(set([ent.text for ent in doc.ents if ent.label_ == 'ORG']))
+        locations = list(set([ent.text for ent in doc.ents if ent.label_ == 'GPE']))
+
+    emails = list(set(re.findall(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', text)))
+    ips = list(set(re.findall(r'\b\d{1,3}(?:\.\d{1,3}){3}\b', text)))
+    socials = list(set(re.findall(r'@(\w{4,15})\b', text)))
+
+    highlighted_entities = []
+
+    def add_to_highlight(entities_list, label):
+        for item in entities_list:
+            highlighted_entities.append((item, label))
+
+    add_to_highlight(names, "NAME")
+    add_to_highlight(orgs, "ORG")
+    add_to_highlight(locations, "LOCATION")
+    add_to_highlight(emails, "EMAIL")
+    add_to_highlight(ips, "IP")
+    add_to_highlight(socials, "SOCIAL")
+
+    return summary, highlighted_entities
+
+iface = gr.Interface(
+    fn=analyze_osint,
+    inputs=gr.Textbox(lines=10, label="OSINT Text", placeholder="Paste your OSINT data here..."),
+    outputs=[
+        gr.Textbox(label="Executive Summary"),
+        gr.HighlightedText(label="Extracted Entities", color_map={
+            "NAME": "red",
+            "ORG": "blue",
+            "LOCATION": "green",
+            "EMAIL": "orange",
+            "IP": "purple",
+            "SOCIAL": "teal"
+        })
+    ],
+    title="OSINT Analysis Tool",
+    description="Enter any unstructured text to extract key entities and generate a summary.",
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    print("===== Application Startup =====")
+    iface.launch()
+