Added function to get the airing schedule of a batch of animes and cache

.gitignore

@@ -220,5 +220,6 @@ __marimo__/
 .streamlit/secrets.toml
 
 # Anical
+airingdata.json
+listdata.json
 config.toml
-data.json

example.config.toml

@@ -2,5 +2,8 @@
 userId = 8283179
 mediaType = "ANIME"
 
+[anical]
+listNames = ["Completed", "Planning", "Watching", "Rewatching", "Paused"]
+
 [ical]
 # reserved for future use

main.py

@@ -16,7 +16,7 @@ def getMediaListCollection(
     mediaType=config["anilist"]["mediaType"],
     userId=config["anilist"]["userId"],
     *,
-    cachePath="data.json"
+    cachePath="listdata.json"
 ):
     """
     Returns a tuple of (entries, cached)
@@ -62,7 +62,7 @@ def getMediaListCollection(
 
             if not cacheExpired and not parametersChanged:
                 print("Cache is fresh, using cached data...")
-                return (entries["response"], True)
+                return (entries, True)
 
             if cacheExpired:
                 print("Cache has gone stale, refreshing...")
@@ -147,9 +147,193 @@ def getMediaListCollection(
 
     return (form, False)
 
+def getAiringScheduleBatch(
+    animeIds,
+    *,
+    ttl=TTL,
+    cachePath="airingdata.json",
+    maxRetries=5
+):
+    """
+    Returns a tuple of (entries, cached)
+
+    Entries is a dictionary of the values to be written to the cache file, such as:
+        - timestamp
+        - ttl
+        - params supplied
+        - response
+
+    response is a dictionary of mediaId (as a string) -> {"title": {"romaji", "english"}, "schedule": [upcoming airing schedule items]}
+
+    cached is a boolean indicating whether the cache file was used or not
+
+    Takes the following arguments:
+    - animeIds: list of AniList media ids to fetch airing schedules for
+    - ttl: seconds the cache stays fresh for. Only applied when the cache is refreshed;
+      an existing cache keeps the ttl it was written with (defaults to value from config.toml)
+    - cachePath: the path to the cache file (if not supplied, defaults to "airingdata.json")
+    - maxRetries: how many times in a row to retry after a 429 before giving up (defaults to 5)
+    """
+
+    if not animeIds:
+        raise RuntimeError("animeIds must not be empty")
+
+    animeIds = sorted(set(int(i) for i in animeIds))
+
+    if path.exists(cachePath):
+        with open(cachePath, "r") as f:
+            entries = json.load(f)
+
+        if (
+            "timestamp" in entries
+            and "ttl" in entries
+            and "response" in entries
+            and "params" in entries
+        ):
+            timestamp = float(entries["timestamp"])
+            cacheTtl = float(entries["ttl"])
+
+            cacheIds = entries["params"].get("animeIds")
+
+            cacheExpired = time.time() - timestamp > cacheTtl
+            parametersChanged = cacheIds != animeIds
+
+            if not cacheExpired and not parametersChanged:
+                print("Airing cache is fresh, using cached data...")
+                return (entries, True)
+
+            if cacheExpired:
+                print("Airing cache has gone stale, refreshing...")
+            elif parametersChanged:
+                print("Airing cache parameters changed, refreshing...")
+        else:
+            print("Airing cache is invalid, refreshing...")
+
+    query = """
+    query ($ids: [Int], $page: Int) {
+        Page(page: $page, perPage: 50) {
+            pageInfo {
+                hasNextPage
+                currentPage
+            }
+            airingSchedules(mediaId_in: $ids, notYetAired: true, sort: TIME) {
+                id
+                airingAt
+                timeUntilAiring
+                episode
+                mediaId
+                media {
+                    title {
+                        romaji
+                        english
+                    }
+                }
+            }
+        }
+    }
+    """
+
+    schedules = {}
+    page = 1
+    retries = 0
+
+    while True:
+        variables = {
+            "ids": animeIds,
+            "page": page,
+        }
+
+        resp = requests.post(
+            "https://graphql.anilist.co",
+            json={
+                "query": query,
+                "variables": variables,
+            },
+            timeout=30,
+        )
+
+        # retry if rate limited
+        if resp.status_code == 429:
+            retries += 1
+            if retries > maxRetries:
+                raise RuntimeError("Rate limited too many times, giving up")
+            wait = int(resp.headers.get("Retry-After", 60))
+            print(f"Rate limited, waiting {wait}s...")
+            time.sleep(wait)
+            continue
+
+        retries = 0
+        resp.raise_for_status()
+
+        data = resp.json()
+
+        if "errors" in data:
+            raise RuntimeError(data["errors"])
+
+        pageData = data["data"]["Page"]
+
+        for item in pageData["airingSchedules"]:
+            # media can be null, fall back to empty titles
+            media = item.pop("media", None) or {}
+            title = media.get("title") or {}
+
+            entry = schedules.setdefault(
+                str(item["mediaId"]),
+                {
+                    "title": {
+                        "romaji": title.get("romaji"),
+                        "english": title.get("english"),
+                    },
+                    "schedule": [],
+                },
+            )
+            entry["schedule"].append(item)
+
+        if not pageData["pageInfo"]["hasNextPage"]:
+            break
+
+        page += 1
+
+    form = {
+        "timestamp": str(time.time()),
+        "ttl": str(ttl),
+        "params": {
+            "animeIds": animeIds,
+        },
+        "response": schedules
+    }
+
+    return (form, False)
+
 if __name__ == "__main__":
     entries, cached = getMediaListCollection()
 
     if not cached:
-        with open("data.json", "w") as f:
+        with open("listdata.json", "w") as f:
             f.write(f"{json.dumps(entries, indent=2)}")
+
+    lists = entries["response"]
+
+    print("\nList Names updating for:")
+    for li in config["anical"]["listNames"]:
+        print(li)
+
+    # get a list of all the animes ids in these lists:
+    animeIds = []
+    for li in config["anical"]["listNames"]:
+        if li not in lists:
+            print(f"Warning: list '{li}' not found, skipping")
+            continue
+        for entry in lists[li]:
+            animeIds.append(entry["media"]["id"])
+
+    print(f"\nFound {len(animeIds)} anime ids")
+
+    airing, airingCached = getAiringScheduleBatch(animeIds)
+
+    if not airingCached:
+        with open("airingdata.json", "w") as f:
+            f.write(f"{json.dumps(airing, indent=2)}")
+
+    schedules = airing["response"]
+    print(f"\nGot upcoming episodes for {len(schedules)} anime")