Add indexing for movies

almasmovie_indexer.py

@@ -1,46 +1,95 @@
 from glob import glob
 from urllib.parse import urlparse
+from pathlib import Path
 
+series_links_dict = {}
+movies_links_dict = {}
 
-links_dict = {}
+folder = Path("view/almasmovie")
 
-def parse_saymyname(link: str):
+def process_series(link: str):
     parsed = urlparse(link)
     splitted_path = parsed.path.split("/")
     first_letter = splitted_path[2]
 
-    first_letter_list = links_dict.get(first_letter)
-    if not first_letter_list: 
-        links_dict[first_letter] = list()
+    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])
+    joined_path = "/".join(splitted_path[:4])
     url = f"{parsed.scheme}://{parsed.hostname}{joined_path}"
 
-    if not url in links_dict[first_letter]:
-        links_dict[first_letter].append(url)
+    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:
-            if "saymyname" in link:
-                parse_saymyname(link)
+            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)
 
 
 
-text = "# آرشیو الماس‌مووی (فقط سریال) \n\n\n"
-text += "مرتب شده بر اساس حروف الفبا.\n\n"
-text += "جهت جستجو از قابلیت `find in page` مرورگر خود استفاده کنید.\n\n"
-text += "---\n"
-for k, v in links_dict.items():
-    print(f"{k}: {len(v)}")
-
+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]
-        text += f"- **{k}**: [{name}]({link.replace(' ', '%20')})\n\n"
+        series_text += f"- **{k}**: [{name}]({link.replace(' ', '%20')})\n\n"
 
-with open("view/almasmovie/series.md", "w") as fp:
-    fp.write(text)
+
+
+with open(folder / "series.md", "w") as fp:
+    fp.write(series_text)
+
+movies_text = "# آرشیو الماس‌مووی (فقط فیلم)"
+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]
+
+    movies_text += f"- **{first_letter}**: [{name}]({url})"
+
+    if year.isnumeric() and int(year) < 3000:
+        movies_text += f" ({year})"
+    
+    movies_text += "\n\n"
+
+with open(folder / "movies.md", "w") as fp:
+    fp.write(movies_text)