Include . (dot) in regex pattern for directories

Reviewed-on: #1

README.md

@@ -1,3 +1,35 @@
-# movies
+# movies - مجموعه آرشیو های مرتب شده فیلم
 
-Some movies
+بهتر است برای جستجو در آرشیو ها از قابلیت `find in page` مرورگر خود استفاده کنید.
+## آرشیو های موجود فعلی: 
+
+### 🍿 Donyaye Serial 
+
+- *Dubbed* and *SoftSob* 
+- Links: 
+    - **All links**: [Open](https://dls2.iran-gamecenter-host.com/DonyayeSerial/donyaye_serial_all_archive.html)
+    - **Top 1000 Series**: [Open](https://dls2.iran-gamecenter-host.com/DonyayeSerial/top_1000_series.html)
+    - **Top 5000 Movies**: [Open](https://dls2.iran-gamecenter-host.com/DonyayeSerial/top_5000_movies.html)
+
+### 💎 Almas Movie
+
+- Links: 
+    - **Series**: [Open](http://chai.bokhary.ir/logique/movies/src/branch/master/view/almasmovie/series.md)
+    - **Movies**: [Open](http://chai.bokhary.ir/logique/movies/src/branch/master/view/almasmovie/movies.md)
+    - **All Links**: [Open](http://chai.bokhary.ir/logique/movies/src/branch/master/view/almasmovie/all.md)
+
+## استخراج کننده لینک
+
+لینک های آرشیو های بالا با استفاده از یک اسکریپت جستجو و لینک های آن ها استخراج شده است. در صورت تمایل می‌توانید از اسکریپت مذکور روی هر آرشیو مشابهی استفاده کنید.
+
+### آموزش نصب پیش نیاز ها و استفاده از اسکریپت:
+
+**کلون کردن و دریافت فایل با استفاده از گیت:**
+```bash
+git clone http://chai.bokhary.ir/logique/movies.git
+```
+
+**نصب بسته ها با استفاده از:**
+```bash
+pip install -i https://mirror-pypi.runflare.com/simple -r requirements.txt 
+```

almasmovie_indexer.py

@@ -0,0 +1,115 @@
+from glob import glob
+from urllib.parse import urlparse
+from pathlib import Path
+
+series_links_dict = {}
+movies_links_dict = {}
+all_links = []
+
+folder = Path("view/almasmovie")
+
+def process_series(link: str):
+    parsed = urlparse(link)
+    splitted_path = parsed.path.split("/")
+    first_letter = splitted_path[2]
+
+    first_letter_list = series_links_dict.get(first_letter)
+    if not first_letter_list:
+        series_links_dict[first_letter] = list()
+
+    joined_path = "/".join(splitted_path[:4])
+    url = f"{parsed.scheme}://{parsed.hostname}{joined_path}"
+
+    if not url in series_links_dict[first_letter]:
+        series_links_dict[first_letter].append(url)
+
+
+def process_movies(link: str):
+    parsed = urlparse(link)
+    splitted_path = parsed.path.split("/")
+
+    folder_name = splitted_path[-2]
+
+    if not movies_links_dict.get(folder_name):
+        year = splitted_path[-3]
+        name = splitted_path[-1].replace("_", " ").replace(".", " ")
+        joined_path = "/".join(splitted_path[: len(splitted_path) - 1])
+        movies_links_dict[folder_name] = (
+            name,
+            f"{parsed.scheme}://{parsed.hostname}{joined_path}",
+            year,
+            folder_name,
+        )
+
+
+# Iterating series
+for file in glob("data/*.saymyname.website-series.txt"):
+    with open(file, "r") as fp:
+        links = fp.readlines()
+
+        for link in links:
+            process_series(link)
+
+for file in glob("data/*.saymyname.website-movies.txt"):
+    with open(file, "r") as fp:
+        links = fp.readlines()
+
+        for link in links:
+            process_movies(link)
+
+
+
+series_text = "# آرشیو الماس‌مووی (فقط سریال) \n\n\n"
+series_text += "مرتب شده بر اساس حروف الفبا.\n\n"
+series_text += "جهت جستجو از قابلیت `find in page` مرورگر خود استفاده کنید.\n\n"
+series_text += "---\n"
+for k, v in series_links_dict.items():
+    for link in v:
+        parsed_link = urlparse(link)
+        name = parsed_link.path.split("/")[-1]
+        line = f"- **{k}**: [{name}]({link.replace(' ', '%20')})\n\n"
+        all_links.append((name, line))
+        series_text += line
+
+
+
+with open(folder / "series.md", "w") as fp:
+    fp.write(series_text)
+
+movies_text = "# آرشیو الماس‌مووی (فقط فیلم) \n\n\n"
+movies_text += "مرتب شده بر اساس حروف الفبا.\n\n"
+movies_text += "جهت جستجو از قابلیت `find in page` مرورگر خود استفاده کنید.\n\n"
+movies_text += "---\n"
+
+for v in sorted(movies_links_dict.values(), key=lambda x: x[0]):
+    name = v[0]
+    first_letter = "0-9" if name[0].isnumeric() else name[0]
+    url = v[1].replace(" ", "%20")
+    year = v[2]
+
+    line = f"- **{first_letter}**: [{name}]({url})"
+
+    if year.isnumeric() and int(year) < 3000:
+        line += f" ({year})"
+    
+    line += "\n\n"
+
+    all_links.append((name, line))
+    movies_text += line
+
+
+with open(folder / "movies.md", "w") as fp:
+    fp.write(movies_text)
+
+all_links.sort(key=lambda x: x[0])
+
+all_text = "# آرشیو الماس‌مووی \n\n\n"
+all_text += "مرتب شده بر اساس حروف الفبا.\n\n"
+all_text += "جهت جستجو از قابلیت `find in page` مرورگر خود استفاده کنید.\n\n"
+all_text += "---\n"
+
+for v in all_links:
+    all_text += v[1]
+
+with open(folder / "all.md", "w") as fp:
+    fp.write(all_text)

archives.txt

@@ -0,0 +1,8 @@
+https://dls2.iran-gamecenter-host.com/DonyayeSerial/donyaye_serial_all_archive.html
+https://berlin.saymyname.website/Movies
+https://tokyo.saymyname.website/Movies
+https://nairobi.saymyname.website/Movies
+https://tokyo.saymyname.website/Series
+https://nairobi.saymyname.website/Series
+https://dl1.ehsansub.sbs/
+https://dl2.ehsansub.sbs/

main.py

@@ -0,0 +1,100 @@
+import asyncio
+import re
+
+import aiohttp
+from aiohttp import ClientError
+
+folder_hyperlink_pat: re.Pattern = re.compile(
+    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_ \[\].-]+\/)*([a-zA-Z0-9_. -]+\.?(mp4|mkv|avi|mov|wmv|webm))\"\>\s*\<code\>",
+    re.IGNORECASE,
+)
+
+
+async def fetch(url, tries=0):
+    try:
+        async with aiohttp.ClientSession() as session:
+            async with session.get(url) as response:
+                return await response.text()
+    except ClientError:
+        print(f"Failed ({tries + 1})...", end="")
+        if tries >= 5:
+            raise RuntimeError(f"Failed to fetch URL {url} after 6 tries")
+        return await fetch(url, tries + 1)
+    except Exception as e:
+        print(f"Unexpected error: {e}")
+        return None
+
+
+def join_url(a: str, b: str) -> str:
+    if b.startswith("/"):
+        return a[: a.rfind(".") + a[a.rfind(".") :].find("/")] + b
+    return a.rstrip("/") + "/" + b
+
+
+async def traverse(pool: list[str], url: str, verbose=False) -> None:
+    page = await fetch(url)
+    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[-2]
+        if verbose:
+            print(f"{join_url(url, file_name)} ({len(pool)})")
+        pool.append(join_url(url, file_name))
+
+
+URLS: list[str] = ["https://dl1.ehsansub.sbs/"]
+
+movies: list[str] = []
+
+
+def ask(q: str, default=True) -> bool:
+    y = "Y" if default else "y"
+    n = "n" if default else "N"
+    while True:
+        a = input(f"{q} [{y}|{n}]: ").lower()
+        if not a:
+            return default
+        if a == "y" or a == "n":
+            return a == "y"
+
+
+is_verbose = ask("Verbose?")
+
+
+async def main():
+    global folder_hyperlink_pat, movie_hyperlink_pat
+    tasks = []
+    for url in URLS:
+        is_fancy = ask(
+            f"Is {url[url.find('/') + 2 : url.rfind('.') + url[url.rfind('.') :].find('/')]} fancy?"
+        )
+        if not is_fancy:
+            folder_hyperlink_pat = re.compile(
+                r"\<a href=\"(\/?[a-zA-Z0-9_ \[\].-]+\/)+\"\>", re.IGNORECASE
+            )
+
+            movie_hyperlink_pat = re.compile(
+                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))
+    await asyncio.gather(*tasks)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
+
+open("movies.txt", mode="w", encoding="utf-8").write("\n".join(movies))

requirements.txt

@@ -0,0 +1,10 @@
+aiohappyeyeballs==2.6.1
+aiohttp==3.13.3
+aiosignal==1.4.0
+attrs==25.4.0
+frozenlist==1.8.0
+idna==3.11
+multidict==6.7.0
+propcache==0.4.1
+typing_extensions==4.15.0
+yarl==1.22.0