Improved docker handling, introduced GitHub registry and smoother setup

.dockerignore

@@ -0,0 +1,19 @@
+# Git
+.git
+.gitignore
+.github
+
+# Documentation
+README.md
+CHANGELOG.md
+LICENSE.md
+
+# Docker
+Dockerfile
+.dockerignore
+__pycache__
+data
+
+# IDE
+.vscode
+.idea

.github/workflows/docker-build.yml

@@ -0,0 +1,56 @@
+name: Build and Push Docker Image
+
+on:
+  push:
+    branches: [ main, master ]
+    tags: [ 'v*' ]
+  pull_request:
+    branches: [ main, master ]
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Log in to Container Registry
+      if: github.event_name != 'pull_request'
+      uses: docker/login-action@v3
+      with:
+        registry: ${{ env.REGISTRY }}
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Extract metadata
+      id: meta
+      uses: docker/metadata-action@v5
+      with:
+        images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+        tags: |
+          type=ref,event=branch
+          type=ref,event=pr
+          type=semver,pattern={{version}}
+          type=semver,pattern={{major}}.{{minor}}
+          type=sha,prefix=sha-
+
+    - name: Build and push Docker image
+      uses: docker/build-push-action@v5
+      with:
+        context: .
+        push: ${{ github.event_name != 'pull_request' }}
+        tags: ${{ steps.meta.outputs.tags }}
+        labels: ${{ steps.meta.outputs.labels }}
+        cache-from: type=gha
+        cache-to: type=gha,mode=max 

.gitignore

@@ -1,2 +1,3 @@
 
 *.pyc
+data/

Dockerfile

@@ -1,16 +1,14 @@
 FROM python:3-alpine
 
-LABEL name photon
-LABEL src "https://github.com/s0md3v/Photon"
-LABEL creator s0md3v
-LABEL dockerfile_maintenance khast3x
-LABEL desc "Incredibly fast crawler designed for reconnaissance."
+LABEL name=photon
+LABEL src="https://github.com/s0md3v/Photon"
+LABEL desc="Incredibly fast crawler designed for OSINT."
 
-RUN apk add git && git clone https://github.com/s0md3v/Photon.git Photon
-WORKDIR Photon
-RUN pip install -r requirements.txt
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+COPY . .
+VOLUME [ "/app/data" ]
 
-VOLUME [ "/Photon" ]
-# ENTRYPOINT ["sh"]
 ENTRYPOINT [ "python", "photon.py" ]
 CMD ["--help"]

README.md

@@ -20,9 +20,6 @@
   <a href="https://github.com/s0md3v/Photon/issues?q=is%3Aissue+is%3Aclosed">
       <img src="https://img.shields.io/github/issues-closed-raw/s0md3v/Photon.svg">
   </a>
-  <a href="https://travis-ci.com/s0md3v/Photon">
-    <img src="https://img.shields.io/travis/com/s0md3v/Photon.svg">
-  </a>
 </p>
 
 ![demo](https://image.ibb.co/kQSUcz/demo.png)
@@ -70,19 +67,21 @@ Still, crawling can be resource intensive but Photon has some tricks up it's sle
 
 #### Docker
 
-Photon can be launched using a lightweight Python-Alpine (103 MB) Docker image.
+Photon can be launched using a lightweight Docker image.
+To view results, you should open the created folder named `data`.
+
 
+**Use the prebuild Docker image:**
 ```bash
-$ git clone https://github.com/s0md3v/Photon.git
-$ cd Photon
-$ docker build -t photon .
-$ docker run -it --name photon photon:latest -u google.com
+docker run -it -v "$PWD/data:/app/data" ghcr.io/s0md3v/photon:master -u google.com
 ```
 
-To view results, you can either head over to the local docker volume, which you can find by running `docker inspect photon` or by mounting the target loot folder:
-
+**Or build the docker image on your computer:**
 ```bash
-$ docker run -it --name photon -v "$PWD:/Photon/google.com" photon:latest -u google.com
+git clone https://github.com/s0md3v/Photon.git
+cd Photon
+docker build -t photon .
+docker run -it -v "$PWD/data:/app/data" photon:latest -u google.com
 ```
 
 #### Frequent & Seamless Updates

photon.py

@@ -15,11 +15,12 @@
 from core.colors import good, info, run, green, red, white, end, bad
 
 # Just a fancy ass banner
-print('''%s      ____  __          __
+print(r'''%s      ____  __          __
      / %s__%s \/ /_  ____  / /_____  ____
     / %s/_/%s / __ \/ %s__%s \/ __/ %s__%s \/ __ \\
    / ____/ / / / %s/_/%s / /_/ %s/_/%s / / / /
-  /_/   /_/ /_/\____/\__/\____/_/ /_/ %sv1.3.2%s\n''' %
+  /_/   /_/ /_/\____/\__/\____/_/ /_/ %sv1.3.2%s
+  ''' %
       (red, white, red, white, red, white, red, white, red, white, red, white,
        red, white, end))
 
@@ -189,7 +190,11 @@
 # Extracts host out of the URL
 host = urlparse(main_url).netloc
 
-output_dir = args.output or host
+# Always use data/** format for Docker compatibility
+if args.output:
+    output_dir = args.output
+else:
+    output_dir = f"data/{host}"
 
 try:
     domain = top_level(main_url)
@@ -374,8 +379,13 @@ def jscanner(url):
 minutes, seconds, time_per_request = timer(diff, processed)
 
 # Step 4. Save the results
+# Ensure the data directory exists for Docker compatibility
+if not args.output:  # Only create data directory structure when using default output
+    data_dir = "data"
+    if not os.path.exists(data_dir):
+        os.makedirs(data_dir)
 if not os.path.exists(output_dir): # if the directory doesn't exist
-    os.mkdir(output_dir) # create a new directory
+    os.makedirs(output_dir) # create a new directory (use makedirs for nested dirs)
 
 datasets = [files, intel, robots, custom, failed, internal, scripts,
             external, fuzzable, endpoints, keys]