Better handling

main.py

@@ -5,11 +5,11 @@ import aiohttp
 from aiohttp import ClientError
 
 folder_hyperlink_pat: re.Pattern = re.compile(
-    r"\<a href=\"\/?([a-zA-Z0-9_ -]+\/)\"\>\s*\<code\>", re.IGNORECASE
+    r"\<a href=\"(\/?[a-zA-Z0-9_ \[\]-]+\/)+\"\>\s*\<code\>", re.IGNORECASE
 )
 
 movie_hyperlink_pat: re.Pattern = re.compile(
-    r"\<a href=\"\/?([a-zA-Z0-9_. -]+\.?(mp4|mkv|avi|mov|wmv|webm))\"\>\s*\<code\>",
+    r"\<a href=\"(\/?[a-zA-Z0-9_ \[\]-]+\/)*([a-zA-Z0-9_. -]+\.?(mp4|mkv|avi|mov|wmv|webm))\"\>\s*\<code\>",
     re.IGNORECASE,
 )
 
@@ -37,14 +37,19 @@ def join_url(a: str, b: str) -> str:
 
 async def traverse(pool: list[str], url: str, verbose=False) -> None:
     page = await fetch(url)
-    folders = re.findall(folder_hyperlink_pat, page)
-    files = re.findall(movie_hyperlink_pat, page)
+    folders = folder_hyperlink_pat.findall(page)
+    files = movie_hyperlink_pat.findall(page)
+
     for f in folders:
+        if f in url:
+            continue
+        if isinstance(f, tuple):
+            f = f[-1]
         if verbose:
             print(f" -> {join_url(url, f)}")
         await traverse(pool, join_url(url, f), verbose=verbose)
     for f in files:
-        file_name = f[0]
+        file_name = f[-2]
         if verbose:
             print(f"{join_url(url, file_name)} ({len(pool)})")
         pool.append(join_url(url, file_name))
@@ -78,11 +83,11 @@ async def main():
         )
         if not is_fancy:
             folder_hyperlink_pat = re.compile(
-                r"\<a href=\"\/?([a-zA-Z0-9_ -]+\/)\"\>", re.IGNORECASE
+                r"\<a href=\"(\/?[a-zA-Z0-9_ \[\]-]+\/)+\"\>", re.IGNORECASE
             )
 
             movie_hyperlink_pat = re.compile(
-                r"\<a href=\"\/?([a-zA-Z0-9_. -]+\.?(mp4|mkv|avi|mov|wmv|webm))\"\>",
+                r"\<a href=\"(\/?[a-zA-Z0-9_ \[\]-]+\/)*([a-zA-Z0-9_. -]+\.?(mp4|mkv|avi|mov|wmv|webm))\"\>",
                 re.IGNORECASE,
             )
         tasks.append(traverse(movies, url, is_verbose))