Upload 5 files

Dockerfile

@@ -0,0 +1,54 @@
+FROM docker.io/library/python:3.10@sha256:7118d485696a1eb1105ae30e3f55e5685117a9bc0c3ffbe3830a268911e0837d
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y fakeroot && \
+    mv /usr/bin/apt-get /usr/bin/.apt-get && \
+    echo '#!/usr/bin/env sh\nfakeroot /usr/bin/.apt-get $@' > /usr/bin/apt-get && \
+    chmod +x /usr/bin/apt-get && \
+    rm -rf /var/lib/apt/lists/* && \
+    useradd -m -u 1000 user
+
+COPY --chown=1000:1000 --from=root / /
+
+RUN pip install --no-cache-dir pip -U && \
+    pip install --no-cache-dir \
+    datasets \
+    "huggingface-hub>=0.19" \
+    "hf_xet>=1.0.0,<2.0.0" \
+    "hf-transfer>=0.1.4" \
+    "protobuf<4" \
+    "click<8.1" \
+    "pydantic~=1.0"
+
+WORKDIR /home/user/app
+
+RUN apt-get update && apt-get install -y \
+    git git-lfs ffmpeg libsm6 libxext6 cmake rsync libgl1-mesa-glx && \
+    rm -rf /var/lib/apt/lists/* && \
+    git lfs install
+
+RUN apt-get update && \
+    apt-get install -y curl && \
+    curl -fsSL https://deb.nodesource.com/setup_20.x | bash - && \
+    apt-get install -y nodejs && \
+    rm -rf /var/lib/apt/lists/* && apt-get clean
+
+# Assuming your requirements.txt is in the root of your repository
+COPY requirements.txt /tmp/requirements.txt
+
+# Install Python dependencies from requirements.txt
+RUN pip install --no-cache-dir -r /tmp/requirements.txt
+
+# Download the spaCy model and set the SPACY_DATA environment variable
+RUN python -m spacy download en_core_web_sm
+RUN python -c "import spacy; print(spacy.util.get_data_path())"
+ENV SPACY_DATA=$(python -c "import spacy; print(spacy.util.get_data_path())")
+
+# Copy your application code
+COPY . /home/user/app
+
+# Set the user context
+USER user
+
+# Define the command to run your application (adjust if your main file is named differently)
+CMD ["python", "app.py"]

README.md

@@ -1,13 +1,14 @@
----
-title: DarkTrawl
-emoji: 📈
-colorFrom: green
-colorTo: gray
-sdk: gradio
-sdk_version: 5.31.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: My Osint Tool
+emoji: 🦀
+colorFrom: purple
+colorTo: green
+sdk: gradio
+sdk_version: 5.31.0
+app_file: app.py
+pinned: false
+license: mit
+short_description: oshint_model_for_infromation_gathering
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,79 @@
+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()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,5 @@
+gradio==5.31.0
+spacy==3.8.0
+transformers==4.52.3
+torch==2.7.0
+sentencepiece==0.2.0