feat: 🎸Add MKGMa source extraction for video downloads

Implements a new method to extract MKGMa encoded sources from HTML. This includes decoding, parsing, and fallback regex search for URLs. Enhances the ability to find direct video links, improving download capabilities.

Author: MPZ-00

dl.py

@@ -413,6 +413,66 @@ def download(URL):
                             print("[+] Found base64 encoded HLS (m3u8) URL.")
                 except Exception as e:
                     print(f"[!] Failed to decode a168c string: {e}")
+        
+        # Method 7: Look for MKGMa encoded sources
+        # https://github.com/p4ul17/voe-dl/issues/33#issuecomment-2807006973
+        if not source_json:
+            print("[*] Searching for MKGMa sources...")
+
+            MKGMa_pattern = r'MKGMa="(.*?)"'
+            match = re.search(MKGMa_pattern, html_page.text, re.DOTALL)
+
+            if match:
+                raw_MKGMa = match.group(1)
+
+                def rot13_decode(s: str) -> str:
+                    result = []
+                    for c in s:
+                        if 'A' <= c <= 'Z':
+                            result.append(chr((ord(c) - ord('A') + 13) % 26 + ord('A')))
+                        elif 'a' <= c <= 'z':
+                            result.append(chr((ord(c) - ord('a') + 13) % 26 + ord('a')))
+                        else:
+                            result.append(c)
+                    return ''.join(result)
+
+                def shift_characters(s: str, offset: int) -> str:
+                    return ''.join(chr(ord(c) - offset) for c in s)
+
+                try:
+                    step1 = rot13_decode(raw_MKGMa)
+                    step2 = step1.replace('_', '')
+                    step3 = base64.b64decode(step2).decode('utf-8')
+                    step4 = shift_characters(step3, 3)
+                    step5 = step4[::-1]
+
+                    decoded = base64.b64decode(step5).decode('utf-8')
+
+                    try:
+                        parsed_json = json.loads(decoded)
+
+                        if 'direct_access_url' in parsed_json:
+                            source_json = {"mp4": parsed_json['direct_access_url']}
+                            print("[+] Found direct .mp4 URL in JSON.")
+                        elif 'source' in parsed_json:
+                            source_json = {"hls": parsed_json['source']}
+                            print("[+] Found fallback .m3u8 URL in JSON.")
+
+                    except json.JSONDecodeError:
+                        print("[-] Decoded string is not valid JSON. Attempting fallback regex search...")
+
+                        mp4_match = re.search(r'(https?://[^\s"]+\.mp4[^\s"]*)', decoded)
+                        m3u8_match = re.search(r'(https?://[^\s"]+\.m3u8[^\s"]*)', decoded)
+
+                        if mp4_match:
+                            source_json = {"mp4": mp4_match.group(1)}
+                            print("[+] Found base64 encoded MP4 URL.")
+                        elif m3u8_match:
+                            source_json = {"hls": m3u8_match.group(1)}
+                            print("[+] Found base64 encoded HLS (m3u8) URL.")
+
+                except Exception as e:
+                    print(f"[-] Error while decoding MKGMa string: {e}")
 
         # If we still don't have sources, try to find any iframe that might contain the video
         if not source_json: