import requests from pathlib import Path import re import csv import sys # --------------------------- # Configuration # --------------------------- ACCESS_TOKEN = "YOUR_ACCESS_TOKEN_HERE" CRM_API_BASE = "https://www.zohoapis.com/crm/v2" CV_FOLDER = Path(r"D:\zohocv\batch") LOG_FILE = Path("upload_log.csv") # --------------------------- # Known email providers and common TLD tokens KNOWN_PROVIDERS = { "gmail", "yahoo", "hotmail", "outlook", "icloud", "live", "yandex", "protonmail", "msn", "aol" } KNOWN_TLDS = { "com", "net", "org", "co", "uk", "eg", "io", "dev", "edu", "gov", "info" } def extract_email_from_stem(stem: str): """Extract an email from the filename stem.""" if not stem: return None parts = stem.split("_") while parts and parts[-1].isdigit(): parts.pop() if not parts: return None for i, token in enumerate(parts): token_l = token.lower() if token_l in KNOWN_PROVIDERS: tld = None if i + 1 < len(parts) and parts[i+1].lower() in KNOWN_TLDS: tld = parts[i+1].lower() name_parts = parts[:i] if not name_parts: return None user = ".".join(name_parts) if tld: return f"{user}@{token_l}.{tld}" else: return f"{user}@{token_l}" if len(parts) >= 3 and parts[-2].lower() in KNOWN_PROVIDERS and parts[-1].lower() in KNOWN_TLDS: provider = parts[-2].lower() tld = parts[-1].lower() user = ".".join(parts[:-2]) if user: return f"{user}@{provider}.{tld}" for i in range(len(parts)-2): if parts[i].lower() in KNOWN_PROVIDERS and parts[i+1].lower() == "co" and parts[i+2].lower() in {"uk", "eg"}: provider = parts[i].lower() tld = f"co.{parts[i+2].lower()}" user = ".".join(parts[:i]) if user: return f"{user}@{provider}.{tld}" simple = stem.replace("_", "@", 1).replace("_", ".") if "@" in simple and "." in simple.split("@", 1)[1]: return simple return None def search_contact_by_email(access_token, email): """Search for a contact in Zoho CRM by email.""" if not email: return None headers = {"Authorization": f"Zoho-oauthtoken {access_token}"} url = f"{CRM_API_BASE}/Contacts/search?email={requests.utils.quote(email)}" try: r = requests.get(url, headers=headers, timeout=30) except Exception as e: print(f"[ERROR] search request failed for {email}: {e}") return None if r.status_code == 200: data = r.json().get("data") if data: return data[0].get("id") elif r.status_code == 204: return None else: print(f"[WARN] search API returned {r.status_code} for {email}: {r.text}") return None def create_contact(access_token, email): """Create a new contact in Zoho CRM with the given email.""" headers = { "Authorization": f"Zoho-oauthtoken {access_token}", "Content-Type": "application/json" } url = f"{CRM_API_BASE}/Contacts" payload = { "data": [ { "Last_Name": email.split("@")[0], # Last_Name is mandatory in Zoho CRM "Email": email } ] } r = requests.post(url, headers=headers, json=payload, timeout=30) return r def load_already_ok_entries(log_path: Path): """Load already processed OK emails from the log file.""" ok_emails = set() if not log_path.exists(): return ok_emails try: with open(log_path, newline="", encoding="utf-8") as f: reader = csv.DictReader(f) for row in reader: try: status = row.get("Status", "").strip().upper() email = row.get("Email", "").strip() if status == "CREATED" and email: ok_emails.add(email) except Exception: continue except Exception as e: print(f"[WARN] Could not read existing log file: {e}") return ok_emails def append_log_row(writer, log_file_obj, row): """Write a row to CSV and flush immediately.""" writer.writerow(row) log_file_obj.flush() def main(): access_token = ACCESS_TOKEN files = sorted([f for f in CV_FOLDER.iterdir() if f.is_file() and f.suffix.lower() in ['.pdf', '.doc', '.docx']]) if not files: print("[!] No CV files found in folder.") return already_ok = load_already_ok_entries(LOG_FILE) print(f"[INFO] Files found: {len(files)}. Already created contacts: {len(already_ok)}") file_exists = LOG_FILE.exists() with open(LOG_FILE, "a", newline="", encoding="utf-8") as log_file: fieldnames = ["Email", "FileName", "Status", "Message"] writer = csv.DictWriter(log_file, fieldnames=fieldnames) if not file_exists: writer.writeheader() log_file.flush() for f in files: stem = f.stem email = extract_email_from_stem(stem) if not email: msg = "PARSE_ERROR: could not extract email from filename" print(f"[ERROR] {f.name} -> {msg}") append_log_row(writer, log_file, {"Email": "", "FileName": f.name, "Status": "PARSE_ERROR", "Message": msg}) continue if email in already_ok: print(f"[SKIP] {email} already created previously.") append_log_row(writer, log_file, {"Email": email, "FileName": f.name, "Status": "SKIP", "Message": "Already created earlier"}) continue record_id = search_contact_by_email(access_token, email) if not record_id: resp = create_contact(access_token, email) if resp.status_code == 201: print(f"[OK] Created contact for {email}") append_log_row(writer, log_file, {"Email": email, "FileName": f.name, "Status": "CREATED", "Message": "Contact created"}) else: print(f"[ERROR] Failed to create contact {email}: {resp.text}") append_log_row(writer, log_file, {"Email": email, "FileName": f.name, "Status": "ERROR", "Message": resp.text}) else: print(f"[SKIP] Contact already exists: {email}") append_log_row(writer, log_file, {"Email": email, "FileName": f.name, "Status": "SKIP", "Message": "Contact already exists"}) print("[DONE] Processing completed. Check upload_log.csv for details.") if __name__ == "__main__": try: main() except KeyboardInterrupt: print("\n[ABORT] Interrupted by user.") sys.exit(1)