From c26140d6ce5ef0474ca2d1f616af138560f158ed Mon Sep 17 00:00:00 2001
From: g0ldyy <153996346+g0ldyy@users.noreply.github.com>
Date: Sun, 4 Jan 2026 20:38:55 +0100
Subject: [PATCH] feat: add TorrentsDB scraper and remove redundant `pass`
 statements in other scrapers

---
 .env-sample                   |  2 ++
 comet/core/logger.py          |  5 ++++
 comet/core/models.py          |  1 +
 comet/scrapers/comet.py       |  1 -
 comet/scrapers/mediafusion.py |  1 -
 comet/scrapers/torrentsdb.py  | 54 +++++++++++++++++++++++++++++++++++
 6 files changed, 62 insertions(+), 2 deletions(-)
 create mode 100644 comet/scrapers/torrentsdb.py

diff --git a/.env-sample b/.env-sample
index 5d7a055..177b4ee 100644
--- a/.env-sample
+++ b/.env-sample
@@ -216,6 +216,8 @@ DEBRIDIO_PROVIDER_KEY=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 SCRAPE_TORBOX=False
 TORBOX_API_KEY=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 
+SCRAPE_TORRENTSDB=False
+
 # ============================== #
 # Debrid Stream Proxy Settings   #
 # ============================== #
diff --git a/comet/core/logger.py b/comet/core/logger.py
index fc3e343..0bbca1e 100644
--- a/comet/core/logger.py
+++ b/comet/core/logger.py
@@ -370,6 +370,11 @@ def log_startup_info(settings):
         f"TorBox Scraper: {settings.format_scraper_mode(settings.SCRAPE_TORBOX)}{torbox_api_key}",
     )
 
+    logger.log(
+        "COMET",
+        f"TorrentsDB Scraper: {settings.format_scraper_mode(settings.SCRAPE_TORRENTSDB)}",
+    )
+
     debrid_stream_proxy_display = (
         f" - Password: {settings.PROXY_DEBRID_STREAM_PASSWORD} - Max Connections: {settings.PROXY_DEBRID_STREAM_MAX_CONNECTIONS} - Inactivity Threshold: {settings.PROXY_DEBRID_STREAM_INACTIVITY_THRESHOLD}s - Default Debrid Service: {settings.PROXY_DEBRID_STREAM_DEBRID_DEFAULT_SERVICE} - Default Debrid API Key: {settings.PROXY_DEBRID_STREAM_DEBRID_DEFAULT_APIKEY}"
         if settings.PROXY_DEBRID_STREAM
diff --git a/comet/core/models.py b/comet/core/models.py
index 70492a3..cdd5cf6 100644
--- a/comet/core/models.py
+++ b/comet/core/models.py
@@ -100,6 +100,7 @@ class AppSettings(BaseSettings):
     DEBRIDIO_PROVIDER_KEY: Optional[str] = None
     SCRAPE_TORBOX: Union[bool, str] = False
     TORBOX_API_KEY: Optional[str] = None
+    SCRAPE_TORRENTSDB: Union[bool, str] = False
     CUSTOM_HEADER_HTML: Optional[str] = None
     PROXY_DEBRID_STREAM: Optional[bool] = False
     PROXY_DEBRID_STREAM_PASSWORD: Optional[str] = "".join(
diff --git a/comet/scrapers/comet.py b/comet/scrapers/comet.py
index f4401fe..48d8dfd 100644
--- a/comet/scrapers/comet.py
+++ b/comet/scrapers/comet.py
@@ -39,6 +39,5 @@ class CometScraper(BaseScraper):
                 )
         except Exception as e:
             log_scraper_error("Comet", self.url, request.media_id, e)
-            pass
 
         return torrents
diff --git a/comet/scrapers/mediafusion.py b/comet/scrapers/mediafusion.py
index 2cf9a57..aa29586 100644
--- a/comet/scrapers/mediafusion.py
+++ b/comet/scrapers/mediafusion.py
@@ -53,6 +53,5 @@ class MediaFusionScraper(BaseScraper):
                 )
         except Exception as e:
             log_scraper_error("MediaFusion", self.url, request.media_id, e)
-            pass
 
         return torrents
diff --git a/comet/scrapers/torrentsdb.py b/comet/scrapers/torrentsdb.py
new file mode 100644
index 0000000..57338b9
--- /dev/null
+++ b/comet/scrapers/torrentsdb.py
@@ -0,0 +1,54 @@
+import re
+
+from comet.core.logger import log_scraper_error
+from comet.scrapers.base import BaseScraper
+from comet.scrapers.models import ScrapeRequest
+from comet.utils.formatting import size_to_bytes
+
+METADATA_PATTERN = re.compile(
+    r"(?:📅 S\d+E\d+ )?(?:👤 (\d+) )?💾 ([\d.]+ [KMGT]?B)(?: ⚙️ (.+))?", re.IGNORECASE
+)
+
+
+class TorrentsDBScraper(BaseScraper):
+    def __init__(self, manager, session):
+        super().__init__(manager, session)
+
+    async def scrape(self, request: ScrapeRequest):
+        torrents = []
+        try:
+            async with self.session.get(
+                f"https://torrentsdb.com/stream/{request.media_type}/{request.media_id}.json",
+            ) as response:
+                results = await response.json()
+
+            for torrent in results["streams"]:
+                description = torrent["title"]
+
+                lines = description.split("\n")
+                title = lines[0]
+                metadata_line = lines[-1]
+
+                match = METADATA_PATTERN.search(metadata_line)
+
+                seeders = int(match.group(1)) if match and match.group(1) else None
+                size = size_to_bytes(match.group(2)) if match and match.group(2) else 0
+                tracker = match.group(3) if match and match.group(3) else None
+
+                torrents.append(
+                    {
+                        "title": title,
+                        "infoHash": torrent["infoHash"].lower(),
+                        "fileIndex": torrent.get("fileIdx", None),
+                        "seeders": seeders,
+                        "size": size,
+                        "tracker": f"TorrentsDB|{tracker}" if tracker else "TorrentsDB",
+                        "sources": torrent.get("sources", []),
+                    }
+                )
+        except Exception as e:
+            log_scraper_error(
+                "TorrentsDB", "https://torrentsdb.com", request.media_id, e
+            )
+
+        return torrents