Add modular TMDb-first movie pipeline and Discord bot

data_sources/tmdb_source.py

@@ -0,0 +1,118 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import json
+import urllib.parse
+import urllib.request
+from datetime import date
+
+TMDB_API_BASE = "https://api.themoviedb.org/3"
+TMDB_ANIME_KEYWORD_ID = "210024"
+
+
+def parse_release_date(value: str) -> date | None:
+    text = (value or "").strip()
+    if not text:
+        return None
+    try:
+        return date.fromisoformat(text[:10])
+    except ValueError:
+        return None
+
+
+def tmdb_get_json(path: str, params: dict, token: str) -> dict:
+    url = TMDB_API_BASE + path + "?" + urllib.parse.urlencode(params)
+    req = urllib.request.Request(
+        url,
+        headers={
+            "Accept": "application/json",
+            "Authorization": f"Bearer {token}",
+            "User-Agent": "anime-movies-script/1.0",
+        },
+    )
+    with urllib.request.urlopen(req, timeout=20) as resp:
+        return json.loads(resp.read().decode("utf-8"))
+
+
+def poster_url(path: str) -> str:
+    text = (path or "").strip()
+    if not text:
+        return ""
+    return "https://image.tmdb.org/t/p/w780" + text
+
+
+def fetch_genre_map(token: str, language: str = "de-DE") -> dict[int, str]:
+    payload = tmdb_get_json("/genre/movie/list", {"language": language}, token)
+    result = {}
+    for entry in payload.get("genres", []):
+        try:
+            gid = int(entry.get("id"))
+        except Exception:
+            continue
+        name = (entry.get("name") or "").strip()
+        if name:
+            result[gid] = name
+    return result
+
+
+def fetch_tmdb_anime_movies(start_date: date, end_date: date, token: str, language: str = "de-DE") -> list[dict]:
+    if not token:
+        return []
+
+    genre_map = fetch_genre_map(token, language=language)
+    page = 1
+    results = []
+    seen_ids = set()
+
+    while True:
+        params = {
+            "include_adult": "false",
+            "include_video": "false",
+            "language": language,
+            "sort_by": "primary_release_date.desc",
+            "primary_release_date.gte": start_date.isoformat(),
+            "primary_release_date.lte": end_date.isoformat(),
+            "with_keywords": TMDB_ANIME_KEYWORD_ID,
+            "page": str(page),
+        }
+        payload = tmdb_get_json("/discover/movie", params, token)
+        page_results = payload.get("results", [])
+        if not page_results:
+            break
+
+        for movie in page_results:
+            movie_id = movie.get("id")
+            if movie_id in seen_ids:
+                continue
+
+            release_date = parse_release_date(str(movie.get("release_date") or ""))
+            if not release_date:
+                continue
+
+            seen_ids.add(movie_id)
+            genre_names = [genre_map.get(gid, "") for gid in (movie.get("genre_ids") or [])]
+            genre_names = [name for name in genre_names if name]
+
+            results.append(
+                {
+                    "tmdb_id": movie_id,
+                    "title": (movie.get("title") or "").strip(),
+                    "original_title": (movie.get("original_title") or "").strip(),
+                    "overview": (movie.get("overview") or "").strip(),
+                    "release_date": release_date,
+                    "genres": genre_names,
+                    "genres_text": ", ".join(genre_names),
+                    "poster_url": poster_url(str(movie.get("poster_path") or "")),
+                    "popularity": movie.get("popularity"),
+                    "vote_average": movie.get("vote_average"),
+                    "vote_count": movie.get("vote_count"),
+                    "raw": movie,
+                }
+            )
+
+        total_pages = int(payload.get("total_pages") or page)
+        if page >= total_pages:
+            break
+        page += 1
+
+    return results