feat(user_scan): add hackerone, wix, tradingview, and unsplash modules with unique string verification and data extraction

user_scanner/user_scan/creator/unsplash.py

@@ -0,0 +1,39 @@
+import re
+import html
+import httpx
+from user_scanner.core.result import Result
+from user_scanner.core.orchestrator import make_request
+
+def validate_unsplash(username: str) -> Result:
+    """Validate a username on Unsplash."""
+    url = f"https://unsplash.com/@{username}"
+    show_url = f"https://unsplash.com/@{username}"
+
+    try:
+        # We pass headers={} to use httpx's default user-agent, 
+        # as Unsplash blocks/redirects the default browser user-agent.
+        response = make_request(url, headers={}, follow_redirects=True)
+        response_text = response.text
+
+        # Verify status code 200 AND check unique Unsplash strings in the response body to prevent false positives
+        if response.status_code == 200 and "unsplash" in response_text.lower() and "page not found" not in response_text.lower():
+            extra = {}
+            title_match = re.search(r"<title>(.*?)</title>", response_text, re.IGNORECASE)
+            if title_match:
+                title = html.unescape(title_match.group(1).strip())
+                title_clean = title.split(" | ")[0]
+                match = re.search(r"^(.*?)\s*\((?:@" + re.escape(username) + r")\)", title_clean, re.IGNORECASE)
+                if match:
+                    name = match.group(1).strip()
+                    name = re.sub(r"'\s*s (?:Collections|Photos|Likes|Stats)$", "", name, flags=re.IGNORECASE)
+                    name = re.sub(r"'\''s (?:Collections|Photos|Likes|Stats)$", "", name, flags=re.IGNORECASE)
+                    extra["name"] = name
+            return Result.taken(extra=extra, url=show_url)
+        elif response.status_code == 404 or "page not found" in response_text.lower():
+            return Result.available(url=show_url)
+        else:
+            return Result.error(f"Unexpected status: {response.status_code}", url=show_url)
+    except httpx.TimeoutException:
+        return Result.skipped("Connection timed out")
+    except Exception as e:
+        return Result.error(e, url=show_url)

user_scanner/user_scan/dev/hackerone.py

@@ -0,0 +1,33 @@
+import re
+import html
+import httpx
+from user_scanner.core.result import Result
+from user_scanner.core import orchestrator
+
+def validate_hackerone(username: str) -> Result:
+    """Validate a username on HackerOne."""
+    url = f"https://hackerone.com/{username}"
+    show_url = f"https://hackerone.com/{username}"
+    try:
+        response = orchestrator.make_request(url, follow_redirects=True)
+        response_text = response.text
+
+        # Verify status code 200 AND check unique HackerOne strings in the response body to prevent false positives
+        if response.status_code == 200 and "hackerone" in response_text.lower() and f"hackerone.com/{username}" in response_text.lower():
+            extra = {}
+            # Extract user bio/description from OpenGraph metadata
+            bio_match = re.search(r'property="og:description"\s+content="([^"]+)"', response_text, re.IGNORECASE)
+            if not bio_match:
+                bio_match = re.search(r'content="([^"]+)"\s+property="og:description"', response_text, re.IGNORECASE)
+            if bio_match:
+                bio = html.unescape(bio_match.group(1).strip())
+                if bio and bio != "-":
+                    extra["bio"] = bio
+            return Result.taken(extra=extra, url=show_url)
+        elif response.status_code == 404 or "page not found" in response_text.lower():
+            return Result.available(url=show_url)
+        return Result.error(f"Unexpected status: {response.status_code}", url=show_url)
+    except httpx.TimeoutException:
+        return Result.skipped("Connection timed out")
+    except Exception as e:
+        return Result.error(e, url=show_url)

user_scanner/user_scan/dev/wix.py

@@ -0,0 +1,31 @@
+import re
+import html
+import httpx
+from user_scanner.core.result import Result
+from user_scanner.core import orchestrator
+
+def validate_wix(username: str) -> Result:
+    """Validate a username on Wix."""
+    url = f"https://{username}.wix.com"
+    show_url = f"https://{username}.wix.com"
+    try:
+        response = orchestrator.make_request(url, follow_redirects=True)
+        response_text = response.text
+
+        # Verify status code 200 AND check unique Wix strings in the response body to prevent false positives
+        if response.status_code == 200 and "wix" in response_text.lower():
+            extra = {}
+            title_match = re.search(r"<title>(.*?)</title>", response_text, re.IGNORECASE)
+            if title_match:
+                extra["title"] = html.unescape(title_match.group(1).strip())
+            return Result.taken(extra=extra, url=show_url)
+        elif response.status_code == 404:
+            return Result.available(url=show_url)
+        return Result.error(f"Unexpected status: {response.status_code}", url=show_url)
+    except httpx.ConnectError:
+        # If the domain doesn't resolve at all, it usually means the username/subdomain is available
+        return Result.available(url=show_url)
+    except httpx.TimeoutException:
+        return Result.skipped("Connection timed out")
+    except Exception as e:
+        return Result.error(e, url=show_url)

user_scanner/user_scan/finance/tradingview.py

@@ -0,0 +1,35 @@
+import re
+import html
+import httpx
+from user_scanner.core.result import Result
+from user_scanner.core import orchestrator
+
+def validate_tradingview(username: str) -> Result:
+    """Validate a username on TradingView."""
+    url = f"https://www.tradingview.com/u/{username}/"
+    show_url = f"https://www.tradingview.com/u/{username}/"
+    try:
+        response = orchestrator.make_request(url, follow_redirects=True)
+        response_text = response.text
+
+        # Verify status code 200 AND check unique TradingView strings in the response body to prevent false positives
+        if response.status_code == 200 and "tradingview" in response_text.lower() and "page not found" not in response_text.lower():
+            extra = {}
+            title_match = re.search(r"<title>(.*?)</title>", response_text, re.IGNORECASE)
+            if title_match:
+                title = html.unescape(title_match.group(1).strip())
+                # TradingView format: {Name} — Trading Ideas and Scripts — TradingView
+                # or {Username} — Trading Ideas and Scripts — TradingView
+                title_parts = title.split(" — ")
+                if len(title_parts) > 0:
+                    name = title_parts[0].strip()
+                    if name.lower() != username.lower():
+                        extra["name"] = name
+            return Result.taken(extra=extra, url=show_url)
+        elif response.status_code == 404 or "page not found" in response_text.lower():
+            return Result.available(url=show_url)
+        return Result.error(f"Unexpected status: {response.status_code}", url=show_url)
+    except httpx.TimeoutException:
+        return Result.skipped("Connection timed out")
+    except Exception as e:
+        return Result.error(e, url=show_url)