From c7ac1ea6a2ceff6c65c9ebdaaf53d7d79cef1fbf Mon Sep 17 00:00:00 2001
From: git <git@fredericofalcao.com>
Date: Sat, 22 Nov 2025 13:18:13 +0000
Subject: [PATCH] Add extract_email.py

---
 extract_email.py | 112 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 112 insertions(+)
 create mode 100644 extract_email.py

diff --git a/extract_email.py b/extract_email.py
new file mode 100644
index 0000000..465b444
--- /dev/null
+++ b/extract_email.py
@@ -0,0 +1,112 @@
+#!/usr/bin/env python3
+import sys
+import os
+import json
+import email
+from email import policy
+from email.parser import BytesParser
+from email.utils import getaddresses
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: extract_eml.py <file.eml>")
+        sys.exit(1)
+
+    eml_file = sys.argv[1]
+
+    if not os.path.isfile(eml_file):
+        print(f"Error: file not found: {eml_file}")
+        sys.exit(1)
+
+    base = os.path.splitext(eml_file)[0]
+
+    # Read the email
+    with open(eml_file, "rb") as f:
+        msg = BytesParser(policy=policy.default).parse(f)
+
+    # ---------------------------
+    # Extract Subject
+    # ---------------------------
+    subject = msg.get("subject", "").strip()
+
+    with open(f"{base}.subject.txt", "w", encoding="utf-8", errors="ignore") as f:
+        f.write(subject)
+
+    # ---------------------------
+    # Extract Text Body
+    # ---------------------------
+    body_text = None
+
+    if msg.is_multipart():
+        for part in msg.walk():
+            if part.get_content_type() == "text/plain":
+                try:
+                    body_text = part.get_payload(decode=True).decode(errors="ignore")
+                except:
+                    pass
+                break
+    else:
+        if msg.get_content_type() == "text/plain":
+            try:
+                body_text = msg.get_payload(decode=True).decode(errors="ignore")
+            except:
+                pass
+
+    if body_text is None:
+        body_text = "(No text/plain body found)"
+
+    with open(f"{base}.txt", "w", encoding="utf-8", errors="ignore") as f:
+        f.write(body_text)
+
+    # ---------------------------
+    # Extract Attachments
+    # ---------------------------
+    attachment_counter = 1
+
+    for part in msg.walk():
+        if part.get_content_disposition() == "attachment":
+            filename = part.get_filename()
+            if not filename:
+                filename = f"attachment{attachment_counter:02d}.bin"
+
+            _, ext = os.path.splitext(filename)
+            if ext:
+                outname = f"{base}.attachment{attachment_counter:02d}{ext}"
+            else:
+                outname = f"{base}.attachment{attachment_counter:02d}"
+
+            data = part.get_payload(decode=True)
+
+            with open(outname, "wb") as f:
+                f.write(data)
+
+            attachment_counter += 1
+
+    # ---------------------------
+    # Extract Addresses
+    # ---------------------------
+    from_addr = msg.get("from", "")
+    to_addr = msg.get_all("to", [])
+    cc_addr = msg.get_all("cc", [])
+    bcc_addr = msg.get_all("bcc", [])
+
+    # Normalize/parse multiple addresses
+    from_parsed = getaddresses([from_addr])
+    to_parsed = getaddresses(to_addr)
+    cc_parsed = getaddresses(cc_addr)
+    bcc_parsed = getaddresses(bcc_addr)
+
+    addresses_json = {
+        "fromAddress": from_parsed[0][1] if from_parsed else "",
+        "toAddresses": [a[1] for a in to_parsed],
+        "ccAddresses": [a[1] for a in cc_parsed],
+        "ccoAddresses": [a[1] for a in bcc_parsed]  # BCC
+    }
+
+    with open(f"{base}.addresses.json", "w", encoding="utf-8") as f:
+        json.dump(addresses_json, f, indent=4)
+
+    print("Done.")
+
+if __name__ == "__main__":
+    main()