Merge pull request #124 from kaifcodec/feat/email-osint

refactor: reorganize username checks to prepare for email OSINT support

Author: kaifcodec

.github/workflows/lint-pr.yml

@@ -0,0 +1,35 @@
+name: Lint & Type Checks
+
+on:
+  pull_request:
+
+permissions:
+  contents: read
+
+jobs:
+  lint:
+    name: Lint & types (ruff + mypy)
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.11]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install linters
+        run: |
+          python -m pip install --upgrade pip
+          pip install httpx colorama types-colorama
+          pip install ruff mypy
+
+      - name: Run ruff
+        run: ruff check .
+
+      - name: Run mypy
+        run: mypy user_scanner

.github/workflows/lint.yml .github/workflows/lint-push.yml.github/workflows/lint.yml renamed to .github/workflows/lint-push.yml

@@ -2,7 +2,6 @@ name: Lint & Type Checks
 
 on:
   push:
-  pull_request:
     branches: [ main ]
 
 permissions:
@@ -30,18 +29,8 @@ jobs:
           pip install httpx colorama types-colorama
           pip install ruff mypy
 
-      - name: Show installed linters
-        run: |
-          ruff --version || true
-          mypy --version || true
-          pip freeze | sed -n '1,200p'
-
-      - name: Run ruff (style/lint)
-        run: |
-          echo "==== Running ruff ===="
-          ruff check . || { echo "Ruff failed"; exit 1; }
+      - name: Run ruff
+        run: ruff check .
 
-      - name: Run mypy (type checks)
-        run: |
-          echo "==== Running mypy ===="
-          mypy user_scanner || { echo "Mypy found issues"; exit 1; }
+      - name: Run mypy
+        run: mypy user_scanner

.github/workflows/tests-pr.yml

@@ -0,0 +1,63 @@
+name: Tests (pytest + coverage)
+
+on:
+  pull_request:
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    name: Test (pytest + coverage) — ${{ matrix.python-version }}
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Show Python info
+        run: |
+          python --version
+          which python
+          python -m pip --version
+
+      - name: Cache pip
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/pyproject.toml', '**/requirements*.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+
+      - name: Install package & test deps
+        run: |
+          python -m pip install --upgrade pip
+          pip install .
+          pip install pytest pytest-cov
+
+      - name: Show installed packages
+        run: pip freeze | sed -n '1,200p'
+
+      - name: Run pytest with coverage
+        run: |
+          mkdir -p test-output
+          pytest -vv --maxfail=1 --disable-warnings \
+            --junitxml=test-output/report.xml \
+            --cov=user_scanner \
+            --cov-report=xml:test-output/coverage.xml \
+            --cov-report=term
+
+      - name: Upload test artifacts
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-reports-${{ matrix.python-version }}
+          path: test-output

.github/workflows/ci.yml .github/workflows/tests-push.yml.github/workflows/ci.yml renamed to .github/workflows/tests-push.yml

@@ -2,7 +2,6 @@ name: Tests (pytest + coverage)
 
 on:
   push:
-  pull_request:
     branches: [ main ]
 
 permissions:
@@ -15,6 +14,7 @@ jobs:
     strategy:
       matrix:
         python-version: ["3.10"]
+
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -44,43 +44,21 @@ jobs:
           pip install .
           pip install pytest pytest-cov
 
-      - name: Show installed packages (top)
-        run: |
-          pip freeze | sed -n '1,200p'
+      - name: Show installed packages
+        run: pip freeze | sed -n '1,200p'
 
-      - name: Run pytest (verbose) with coverage and generate JUnit XML
+      - name: Run pytest with coverage
         run: |
           mkdir -p test-output
           pytest -vv --maxfail=1 --disable-warnings \
             --junitxml=test-output/report.xml \
-            --cov=user_scanner --cov-report=xml:test-output/coverage.xml --cov-report=term
-
-      - name: Show pytest junit xml (head)
-        if: always()
-        run: |
-          echo "==== JUnit report (head) ===="
-          sed -n '1,200p' test-output/report.xml || true
-          echo "==== JUnit report (tail) ===="
-          sed -n '200,400p' test-output/report.xml || true
+            --cov=user_scanner \
+            --cov-report=xml:test-output/coverage.xml \
+            --cov-report=term
 
-      - name: Show coverage xml (head)
-        if: always()
-        run: |
-          echo "==== Coverage XML (head) ===="
-          sed -n '1,200p' test-output/coverage.xml || true
-
-      - name: Upload test & coverage artifacts
+      - name: Upload test artifacts
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-reports-${{ matrix.python-version }}
           path: test-output
-
-      - name: (Optional) Upload coverage to Codecov
-        if: success() && env.CODECOV_TOKEN != ''
-        uses: codecov/codecov-action@v4
-        with:
-          files: test-output/coverage.xml
-          token: ${{ secrets.CODECOV_TOKEN }}
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

user_scanner/cli/printer.py

@@ -47,7 +47,7 @@ def get_end(self, json_char: str = "]") -> str:
         return indentate(json_char, self.indent)
 
     def get_result_output(self, result: Result) -> str:
-        #In principle result should always have this
+        # In principle result should always have this
         site_name = result.site_name
         username = result.username
 

user_scanner/core/orchestrator.py

@@ -27,7 +27,7 @@ def load_modules(category_path: Path):
 
 
 def load_categories() -> Dict[str, Path]:
-    root = Path(__file__).resolve().parent.parent  # Should be user_scanner
+    root = Path(__file__).resolve().parent.parent / "user_scan"
     categories = {}
 
     for subfolder in root.iterdir():

user_scanner/user_scan/community/__init__.py

@@ -0,0 +1 @@
+# community

user_scanner/user_scan/community/coderlegion.py

@@ -0,0 +1,19 @@
+from user_scanner.core.orchestrator import status_validate
+
+
+def validate_coderlegion(user):
+    url = f"https://coderlegion.com/user/{user}"
+
+    return status_validate(url, 404, 200, timeout=15.0)
+
+
+if __name__ == "__main__":
+    user = input("Username?: ").strip()
+    result = validate_coderlegion(user)
+
+    if result == 1:
+        print("Available!")
+    elif result == 0:
+        print("Unavailable!")
+    else:
+        print("Error occured!")

user_scanner/user_scan/community/hackernews.py

@@ -0,0 +1,33 @@
+import re
+from user_scanner.core.orchestrator import generic_validate, Result
+
+
+def validate_hackernews(user: str) -> Result:
+    if not (2 <= len(user) <= 15):
+        return Result.error("Length must be 2-15 characters")
+
+    if not re.match(r'^[a-zA-Z0-9_-]+$', user):
+        return Result.error("Only use letters, numbers, underscores, and hyphens")
+
+    url = f"https://news.ycombinator.com/user?id={user}"
+
+    def process(response):
+        if "No such user." in response.text:
+            return Result.available()
+        if f"profile: {user}" in response.text.lower() or "created:" in response.text:
+            return Result.taken()
+        return Result.error("Unexpected response structure")
+
+    return generic_validate(url, process, timeout=3.0, follow_redirects=True)
+
+
+if __name__ == "__main__":
+    user = input("Username?: ").strip()
+    result = validate_hackernews(user)
+
+    if result == 1:
+        print("Available!")
+    elif result == 0:
+        print("Unavailable!")
+    else:
+        print(f"Error occurred! Reason: {result.get_reason()}")

user_scanner/user_scan/community/stackoverflow.py

@@ -0,0 +1,35 @@
+from user_scanner.core.orchestrator import generic_validate
+from user_scanner.core.result import Result
+
+def validate_stackoverflow(user: str) -> Result:
+    url = f"https://stackoverflow.com/users/filter?search={user}"
+
+    def process(response):
+        if response.status_code == 200:
+            text = response.text
+
+            if "No users matched your search." in text:
+                return Result.available()
+
+            pattern = f'>{user}<'
+            if pattern in text:
+                return Result.taken()
+
+            return Result.available()
+
+        return Result.error("Unexpected status code from Stack Overflow")
+
+    return generic_validate(url, process)
+
+
+if __name__ == "__main__":
+    user = input("Username?: ").strip()
+    result = validate_stackoverflow(user)
+
+    if result == Result.available():
+        print("Available!")
+    elif result == Result.taken():
+        print("Unavailable!")
+    else:
+        msg = result.get_reason()
+        print("Error occurred!" + msg)