From 4c5edd3b901113e4c73cea04a7855a70be4b187f Mon Sep 17 00:00:00 2001
From: semiventurero <semi.venturero@bahcesehir.edu.tr>
Date: Thu, 9 Oct 2025 18:39:28 +0300
Subject: [PATCH 1/3] Add find_company_mail folder with placeholder

---
 task_examples/find_company_mail/.gitkeep | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 task_examples/find_company_mail/.gitkeep

diff --git a/task_examples/find_company_mail/.gitkeep b/task_examples/find_company_mail/.gitkeep
new file mode 100644
index 0000000..8d1c8b6
--- /dev/null
+++ b/task_examples/find_company_mail/.gitkeep
@@ -0,0 +1 @@
+ 

From 92a716b3a64751a2e468e23bcee985a325f6cf5a Mon Sep 17 00:00:00 2001
From: semiventurero <semi.venturero@bahcesehir.edu.tr>
Date: Thu, 9 Oct 2025 18:57:35 +0300
Subject: [PATCH 2/3] feat: add find-company-mail contribution folder

---
 task_examples/find_company_mail/README.md     |  24 ++++
 .../find_company_mail/email_utils.py          |  14 +++
 .../find_company_mail/find_company_mail.py    | 103 ++++++++++++++++++
 .../find_company_mail/serper_client.py        |  19 ++++
 4 files changed, 160 insertions(+)
 create mode 100644 task_examples/find_company_mail/README.md
 create mode 100644 task_examples/find_company_mail/email_utils.py
 create mode 100644 task_examples/find_company_mail/find_company_mail.py
 create mode 100644 task_examples/find_company_mail/serper_client.py

diff --git a/task_examples/find_company_mail/README.md b/task_examples/find_company_mail/README.md
new file mode 100644
index 0000000..df7d17c
--- /dev/null
+++ b/task_examples/find_company_mail/README.md
@@ -0,0 +1,24 @@
+# Find Company Mail
+
+Find a company's email by querying the web with the format `mail: {company}` and extracting emails from search results.
+
+## Usage
+
+```bash
+python task_examples/find_company_mail/find_company_mail.py --company "Linktera"
+```
+
+Example output:
+
+```json
+{
+  "company": "Linktera",
+  "email": "info@linktera.com"
+}
+```
+
+## Notes
+
+- Uses Serper (`SERPER_API_KEY` in your `.env`) to perform the query `mail: {company}`.
+- Extracts emails from result titles, snippets, and links.
+
diff --git a/task_examples/find_company_mail/email_utils.py b/task_examples/find_company_mail/email_utils.py
new file mode 100644
index 0000000..e248268
--- /dev/null
+++ b/task_examples/find_company_mail/email_utils.py
@@ -0,0 +1,14 @@
+import re
+from typing import List, Set
+
+
+EMAIL_REGEX = re.compile(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")
+
+
+def extract_emails_from_text(text: str) -> List[str]:
+    if not text:
+        return []
+    emails: Set[str] = set(re.findall(EMAIL_REGEX, text))
+    return sorted(emails)
+
+
diff --git a/task_examples/find_company_mail/find_company_mail.py b/task_examples/find_company_mail/find_company_mail.py
new file mode 100644
index 0000000..eedfa67
--- /dev/null
+++ b/task_examples/find_company_mail/find_company_mail.py
@@ -0,0 +1,103 @@
+import sys
+import os
+import argparse
+from typing import Optional
+from urllib.parse import urlparse
+
+# Allow running as a script
+sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+from pydantic import BaseModel
+
+try:
+    from task_examples.find_company_mail.serper_client import search_mail_query
+    from task_examples.find_company_mail.email_utils import extract_emails_from_text
+except ImportError:
+    from serper_client import search_mail_query
+    from email_utils import extract_emails_from_text
+
+
+class MailResponse(BaseModel):
+    company: str
+    email: Optional[str] = None
+    source: Optional[str] = None
+
+
+def _normalize_to_domain(company_or_url: str) -> str:
+    """Accepts a domain (e.g., linktera.com) or URL (https://linktera.com/) and returns the domain."""
+    text = company_or_url.strip()
+    if not text:
+        return text
+    has_scheme = text.startswith("http://") or text.startswith("https://")
+    to_parse = text if has_scheme else f"http://{text}"
+    parsed = urlparse(to_parse)
+    host = parsed.netloc or parsed.path
+    host = host.strip().lower()
+    if host.startswith("www."):
+        host = host[4:]
+    # Remove trailing slashes if any leaked into host
+    host = host.split("/")[0]
+    return host
+
+
+def find_company_mail(company: str) -> MailResponse:
+    domain = _normalize_to_domain(company)
+    query = f"mail: {domain}" if domain else f"mail: {company}"
+
+    try:
+        data = search_mail_query(query)
+    except Exception as e:
+        return MailResponse(company=company, email=None, source=None)
+
+    # Try to extract from organic results: titles, snippets, links
+    candidates = []
+    sources = []
+    for item in data.get("organic", []):
+        page_link = item.get("link")
+        for field in ("title", "snippet"):
+            val = item.get(field)
+            if val:
+                emails = extract_emails_from_text(val)
+                if emails:
+                    candidates.extend(emails)
+                    sources.extend([page_link] * len(emails))
+        link = item.get("link")
+        if link:
+            emails = extract_emails_from_text(link)
+            if emails:
+                candidates.extend(emails)
+                sources.extend([link] * len(emails))
+
+    # De-duplicate while preserving order
+    seen = set()
+    unique_candidates = []
+    unique_sources = []
+    for idx, c in enumerate(candidates):
+        if c not in seen:
+            seen.add(c)
+            unique_candidates.append(c)
+            # align the corresponding source if available
+            src = sources[idx] if idx < len(sources) else None
+            unique_sources.append(src)
+
+    # Prefer emails that match the provided domain
+    if domain:
+        for idx, email in enumerate(unique_candidates):
+            email_l = email.lower()
+            if email_l.endswith("@" + domain) or email_l.endswith("@www." + domain):
+                return MailResponse(company=company, email=email, source=unique_sources[idx])
+
+    if unique_candidates:
+        return MailResponse(company=company, email=unique_candidates[0], source=unique_sources[0])
+    return MailResponse(company=company, email=None, source=None)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Find a company's email via web search")
+    parser.add_argument("--company", required=True, help="Company name")
+    args = parser.parse_args()
+
+    result = find_company_mail(args.company)
+    print(result.model_dump_json(indent=2))
+
+
diff --git a/task_examples/find_company_mail/serper_client.py b/task_examples/find_company_mail/serper_client.py
new file mode 100644
index 0000000..645cf2b
--- /dev/null
+++ b/task_examples/find_company_mail/serper_client.py
@@ -0,0 +1,19 @@
+import os
+import requests
+from dotenv import load_dotenv
+
+load_dotenv()
+
+SERPER_API_KEY = os.getenv("SERPER_API_KEY")
+SERPER_URL = "https://google.serper.dev/search"
+
+
+def search_mail_query(query: str) -> dict:
+    if not SERPER_API_KEY:
+        raise ValueError("Missing SERPER_API_KEY in .env")
+    headers = {"X-API-KEY": SERPER_API_KEY, "Content-Type": "application/json"}
+    resp = requests.post(SERPER_URL, headers=headers, json={"q": query})
+    resp.raise_for_status()
+    return resp.json()
+
+

From e0c53d9f7e3abc029ad2cbc4d2a7c0456dee09a7 Mon Sep 17 00:00:00 2001
From: semiventurero <63498905+venturero@users.noreply.github.com>
Date: Thu, 9 Oct 2025 19:09:07 +0300
Subject: [PATCH 3/3] Delete task_examples/find_company_mail/.gitkeep

---
 task_examples/find_company_mail/.gitkeep | 1 -
 1 file changed, 1 deletion(-)
 delete mode 100644 task_examples/find_company_mail/.gitkeep

diff --git a/task_examples/find_company_mail/.gitkeep b/task_examples/find_company_mail/.gitkeep
deleted file mode 100644
index 8d1c8b6..0000000
--- a/task_examples/find_company_mail/.gitkeep
+++ /dev/null
@@ -1 +0,0 @@
-