feat: add Motherless email and username scan modules

user_scanner/email_scan/adult/motherless.py

@@ -0,0 +1,46 @@
+import httpx
+from user_scanner.core.result import Result
+
+
+async def _check(email: str) -> Result:
+    show_url = "https://motherless.xxx"
+    url = "https://motherless.xxx/register/checkemail"
+
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Mobile Safari/537.36",
+        "X-Requested-With": "XMLHttpRequest",
+        "Origin": show_url,
+        "Referer": show_url + "/register",
+        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
+    }
+
+    try:
+        async with httpx.AsyncClient(http2=True, timeout=15.0) as client:
+            response = await client.post(url, data={"email": email}, headers=headers)
+
+            if response.status_code == 429:
+                return Result.error("Rate limited, wait for a few minutes")
+
+            if response.status_code != 200:
+                return Result.error(f"HTTP Error: {response.status_code}")
+
+            body = response.text
+
+            # The field check reuses "not-available" for both existing accounts
+            # and rejected input (e.g. "Invalid Host.").
+            if 'class="not-available"' in body:
+                if "invalid" in body.lower():
+                    return Result.error("Email address rejected by Motherless")
+                return Result.taken(url=show_url)
+
+            if 'class="available"' in body:
+                return Result.available(url=show_url)
+
+            return Result.error("Unexpected response body, report it via GitHub issues")
+
+    except Exception as e:
+        return Result.error(e)
+
+
+async def validate_motherless(email: str) -> Result:
+    return await _check(email)

user_scanner/user_scan/adult/motherless.py

@@ -0,0 +1,75 @@
+import re
+from user_scanner.core.orchestrator import generic_validate, make_request, Result
+
+CHECK_URL = "https://motherless.xxx/register/checkusername"
+HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Mobile Safari/537.36",
+    "X-Requested-With": "XMLHttpRequest",
+    "Origin": "https://motherless.xxx",
+    "Referer": "https://motherless.xxx/register",
+}
+
+
+def validate_motherless(user):
+    show_url = f"https://motherless.xxx/m/{user}"
+
+    def process(response):
+        if response.status_code != 200:
+            return Result.error(f"Unexpected status: {response.status_code}", url=show_url)
+
+        body = response.text
+
+        # The field check reuses "not-available" for both taken names and
+        # rejected input (e.g. "Username is invalid.").
+        if 'class="not-available"' in body:
+            if "invalid" in body.lower():
+                return Result.error("Username rejected by Motherless", url=show_url)
+            return Result.taken(extra=_fetch_profile(show_url), url=show_url)
+
+        if 'class="available"' in body:
+            return Result.available(url=show_url)
+
+        return Result.error("Unexpected response body, report it via GitHub issues", url=show_url)
+
+    return generic_validate(
+        CHECK_URL, process, show_url=show_url, method="POST", data={"username": user}, headers=HEADERS
+    )
+
+
+def _fetch_profile(profile_url: str) -> dict:
+    """The checkusername endpoint only reports availability, so pull the public
+    member page for metadata. Best-effort: a failed fetch yields no extra."""
+    try:
+        response = make_request(profile_url)
+        if response.status_code != 200:
+            return {}
+        return _extract_profile(response.text)
+    except Exception:
+        return {}
+
+
+def _extract_profile(html_text: str) -> dict:
+    extra = {}
+
+    # The public member page renders two field blocks: "profile-stats" rows
+    # (<span>Label:</span> value) and "profile-member-info" rows
+    # (<strong>Label</strong> <span>value</span>). Pull every row rather than a
+    # fixed subset so whatever the member fills in is captured. Zero counts are
+    # dropped as noise.
+    for row in re.finditer(r'<div class="profile-stats">\s*<span>([^<]+?):\s*</span>\s*(.*?)\s*</div>', html_text, re.DOTALL):
+        label = re.sub(r"\s+", " ", row.group(1)).strip()
+        value = re.sub(r"\s+", " ", re.sub(r"<[^>]+>", " ", row.group(2))).strip()
+        if value and value != "0":
+            extra[label] = value
+
+    for row in re.finditer(r'<div class="profile-member-info[^"]*">\s*<strong>([^<]+?)</strong>\s*<span>\s*(.*?)\s*</span>', html_text, re.DOTALL):
+        label = re.sub(r"\s+", " ", row.group(1)).strip()
+        value = re.sub(r"\s+", " ", re.sub(r"<[^>]+>", " ", row.group(2))).strip()
+        if value:
+            extra[label] = value
+
+    avatar = re.search(r'og:image"\s+content="([^"]+)"', html_text, re.IGNORECASE)
+    if avatar:
+        extra["avatar"] = avatar.group(1)
+
+    return extra