Fix DMM parser and a couple of other minor issues. (#226)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

.github/ISSUE_TEMPLATE/bug_report.md

@@ -12,6 +12,9 @@ A clear and concise description of what the bug is.
 
 **To Reproduce**
 Steps to reproduce the behavior:
+1.
+2.
+3.
 
 **Expected behavior**
 A clear and concise description of what you expected to happen.
@@ -23,6 +26,7 @@ If the logs are short, make sure to triple backtick them, or use https://pastebi
 **Hardware:**
  - OS and distro: [e.g. Raspberry Pi OS, Ubuntu, Rocky]
  - Server: [e.g. VM, Baremetal, Pi]
+ - Knightcrawler Version: [2.0.xx]
 
 **Additional context**
 Add any other context about the problem here.

.github/workflows/git_cliff.yml

@@ -0,0 +1,39 @@
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  changelog:
+    name: Generate changelog
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Generate a changelog
+        uses: orhun/git-cliff-action@v3
+        with:
+          config: cliff.toml
+          args: --verbose
+        env:
+          OUTPUT: CHANGELOG.md
+          GITHUB_REPO: ${{ github.repository }}
+
+      - name: Commit
+        run: |
+          git config user.name 'github-actions[bot]'
+          git config user.email 'github-actions[bot]@users.noreply.github.com'
+          set +e
+          git checkout -b feat/changelog_$(date +"%d_%m")
+          git add CHANGELOG.md
+          git commit -m "[skip ci] Update changelog"
+          git push https://${{ secrets.GITHUB_TOKEN }}@github.com/${{ github.repository }}.git feat/changelog_$(date +"%d_%m")
+
+      - name: create pull request
+        run: gh pr create -B main -H feat/changelog_$(date +"%d_%m") --title '[skip ci] Update changelog' --body 'Changelog update by git-cliff'
+        env:
+            GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

CHANGELOG.md

@@ -0,0 +1,22 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [1.0.0] - 2024-03-25
+### Details
+#### Changed
+- Change POSTGRES_USERNAME to POSTGRES_USER. Oops by @purple-emily
+- Change POSTGRES_DATABASE to POSTGRES_DB by @purple-emily
+- Two movie commands instead of movie and tv by @purple-emily
+- Cleanup RabbitMQ env vars, and Github Pat by @iPromKnight
+
+#### Fixed
+- HRD -> HDR by @mplewis
+
+## New Contributors
+* @mplewis made their first contribution
+
+<!-- generated by git-cliff -->

CONTRIBUTING.md

@@ -0,0 +1,34 @@
+We use [Meaningful commit messages](https://reflectoring.io/meaningful-commit-messages/)
+
+Tl;dr:
+1. It should answer the question: “What happens if the changes are applied?".
+2. Use the imperative, present tense. It is easier to read and scan quickly:
+```
+Right: Add feature to alert admin for new user registration
+Wrong: Added feature ... (past tense)
+```
+3. The summary should always be able to complete the following sentence:
+`If applied, this commit will… `
+
+We use [git-cliff] for our changelog.
+
+The breaking flag is set to true when the commit has an exclamation mark after the commit type and scope, e.g.:
+`feat(scope)!: this is a breaking change`
+
+Keywords (Commit messages should start with these):
+```
+# Added
+add
+support
+# Removed
+remove
+delete
+# Fixed
+test
+fix
+```
+
+Any other commits will fall under the `Changed` category
+
+
+This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html)

README.md

@@ -67,30 +67,6 @@ Then set any of the values you wouldd like to customize.
 
 By default, Knight Crawler is configured to be *relatively* conservative in its resource usage. If running on a decent machine (16GB RAM, i5+ or equivalent), you can increase some settings to increase consumer throughput. This is especially helpful if you have a large backlog from [importing databases](#importing-external-dumps).
 
-### DebridMediaManager setup (optional)
-
-There are some optional steps you should take to maximise the number of movies/tv shows we can find.
-
-We can search DebridMediaManager hash lists which are hosted on GitHub. This allows us to add hundreds of thousands of movies and tv shows, but it requires a Personal Access Token to be generated. The software only needs read access and only for public repositories. To generate one, please follow these steps:
-
-1. Navigate to GitHub settings -> Developer Settings -> Personal access tokens -> Fine-grained tokens (click [here](https://github.com/settings/tokens?type=beta) for a direct link)
-2. Press `Generate new token`
-3. Fill out the form (example data below):
-   ```
-    Token name:
-        KnightCrawler
-    Expiration:
-        90 days
-    Description:
-        <blank>
-    Repository access
-        (checked) Public Repositories (read-only)
-   ```
-4. Click `Generate token`
-5. Take the new token and add it to the bottom of the [stack.env](deployment/docker/stack.env) file
-   ```
-   GITHUB_PAT=<YOUR TOKEN HERE>
-   ```
 ### Configure external access
 
 Please choose which applies to you:

cliff.toml

@@ -0,0 +1,112 @@
+# git-cliff ~ configuration file
+# https://git-cliff.org/docs/configuration
+
+[changelog]
+# changelog header
+header = """
+# Changelog\n
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).\n
+"""
+# template for the changelog body
+# https://keats.github.io/tera/docs/#introduction
+body = """
+{%- macro remote_url() -%}
+  https://github.com/{{ remote.github.owner }}/{{ remote.github.repo }}
+{%- endmacro -%}
+
+{% if version -%}
+    ## [{{ version | trim_start_matches(pat="v") }}] - {{ timestamp | date(format="%Y-%m-%d") }}
+{% else -%}
+    ## [Unreleased]
+{% endif -%}
+
+### Details\
+
+{% for group, commits in commits | group_by(attribute="group") %}
+    #### {{ group | upper_first }}
+    {%- for commit in commits %}
+        - {{ commit.message | upper_first | trim }}\
+            {% if commit.github.username %} by @{{ commit.github.username }}{%- endif -%}
+            {% if commit.github.pr_number %} in \
+              [#{{ commit.github.pr_number }}]({{ self::remote_url() }}/pull/{{ commit.github.pr_number }}) \
+            {%- endif -%}
+    {% endfor %}
+{% endfor %}
+
+{%- if github.contributors | filter(attribute="is_first_time", value=true) | length != 0 %}
+  ## New Contributors
+{%- endif -%}
+
+{% for contributor in github.contributors | filter(attribute="is_first_time", value=true) %}
+  * @{{ contributor.username }} made their first contribution
+    {%- if contributor.pr_number %} in \
+      [#{{ contributor.pr_number }}]({{ self::remote_url() }}/pull/{{ contributor.pr_number }}) \
+    {%- endif %}
+{%- endfor %}\n
+"""
+# template for the changelog footer
+footer = """
+{%- macro remote_url() -%}
+  https://github.com/{{ remote.github.owner }}/{{ remote.github.repo }}
+{%- endmacro -%}
+
+{% for release in releases -%}
+    {% if release.version -%}
+        {% if release.previous.version -%}
+            [{{ release.version | trim_start_matches(pat="v") }}]: \
+                {{ self::remote_url() }}/compare/{{ release.previous.version }}..{{ release.version }}
+        {% endif -%}
+    {% else -%}
+        [unreleased]: {{ self::remote_url() }}/compare/{{ release.previous.version }}..HEAD
+    {% endif -%}
+{% endfor %}
+<!-- generated by git-cliff -->
+"""
+# remove the leading and trailing whitespace from the templates
+trim = true
+
+[git]
+# parse the commits based on https://www.conventionalcommits.org
+conventional_commits = true
+# filter out the commits that are not conventional
+filter_unconventional = true
+# process each line of a commit as an individual commit
+split_commits = false
+# regex for preprocessing the commit messages
+commit_preprocessors = [
+    # remove issue numbers from commits
+    { pattern = '\((\w+\s)?#([0-9]+)\)', replace = "" },
+]
+# regex for parsing and grouping commits
+commit_parsers = [
+    { message = "^.*: add", group = "Added" },
+    { message = "^add", group = "Added" },
+    { message = "^.*: support", group = "Added" },
+    { message = "^support", group = "Added" },
+    { message = "^.*: remove", group = "Removed" },
+    { message = "^remove", group = "Removed" },
+    { message = "^.*: delete", group = "Removed" },
+    { message = "^delete", group = "Removed" },
+    { message = "^.*: test", group = "Fixed" },
+    { message = "^test", group = "Fixed" },
+    { message = "^.*: fix", group = "Fixed" },
+    { message = "^fix", group = "Fixed" },
+    { message = "^.*", group = "Changed" },
+]
+# protect breaking changes from being skipped due to matching a skipping commit_parser
+protect_breaking_commits = false
+# filter out the commits that are not matched by commit parsers
+filter_commits = true
+# regex for matching git tags
+tag_pattern = "v[0-9].*"
+# regex for skipping tags
+skip_tags = "v0.1.0-beta.1"
+# regex for ignoring tags
+ignore_tags = ""
+# sort the tags topologically
+topo_order = false
+# sort the commits inside sections by oldest/newest order
+sort_commits = "oldest"

deployment/docker/config/qbit/qbittorrent.conf

@@ -14,12 +14,14 @@ program=
 [BitTorrent]
 Session\AnonymousModeEnabled=true
 Session\BTProtocol=TCP
+Session\ConnectionSpeed=150
 Session\DefaultSavePath=/downloads/
 Session\ExcludedFileNames=
-Session\MaxActiveCheckingTorrents=5
+Session\MaxActiveCheckingTorrents=20
-Session\MaxActiveDownloads=10
+Session\MaxActiveDownloads=20
 Session\MaxActiveTorrents=50
 Session\MaxActiveUploads=50
+Session\MaxConcurrentHTTPAnnounces=1000
 Session\MaxConnections=2000
 Session\Port=6881
 Session\QueueingSystemEnabled=true

deployment/docker/docker-compose.yaml

@@ -94,7 +94,7 @@ services:
         condition: service_healthy
     env_file: stack.env
     hostname: knightcrawler-addon
-    image: gabisonfire/knightcrawler-addon:2.0.20
+    image: gabisonfire/knightcrawler-addon:2.0.26
     labels:
       logging: promtail
     networks:
@@ -117,7 +117,7 @@ services:
       redis:
         condition: service_healthy
     env_file: stack.env
-    image: gabisonfire/knightcrawler-consumer:2.0.20
+    image: gabisonfire/knightcrawler-consumer:2.0.26
     labels:
       logging: promtail
     networks:
@@ -138,7 +138,7 @@ services:
       redis:
         condition: service_healthy
     env_file: stack.env
-    image: gabisonfire/knightcrawler-debrid-collector:2.0.20
+    image: gabisonfire/knightcrawler-debrid-collector:2.0.26
     labels:
       logging: promtail
     networks:
@@ -152,7 +152,7 @@ services:
       migrator:
         condition: service_completed_successfully
     env_file: stack.env
-    image: gabisonfire/knightcrawler-metadata:2.0.20
+    image: gabisonfire/knightcrawler-metadata:2.0.26
     networks:
       - knightcrawler-network
     restart: "no"
@@ -163,7 +163,7 @@ services:
       postgres:
         condition: service_healthy
     env_file: stack.env
-    image: gabisonfire/knightcrawler-migrator:2.0.20
+    image: gabisonfire/knightcrawler-migrator:2.0.26
     networks:
       - knightcrawler-network
     restart: "no"
@@ -182,7 +182,7 @@ services:
       redis:
         condition: service_healthy
     env_file: stack.env
-    image: gabisonfire/knightcrawler-producer:2.0.20
+    image: gabisonfire/knightcrawler-producer:2.0.26
     labels:
       logging: promtail
     networks:
@@ -207,7 +207,7 @@ services:
     deploy:
       replicas: ${QBIT_REPLICAS:-0}
     env_file: stack.env
-    image: gabisonfire/knightcrawler-qbit-collector:2.0.20
+    image: gabisonfire/knightcrawler-qbit-collector:2.0.26
     labels:
       logging: promtail
     networks:

deployment/docker/src/components/knightcrawler.yaml

@@ -20,7 +20,7 @@ x-depends: &knightcrawler-app-depends
 
 services:
   metadata:
-    image: gabisonfire/knightcrawler-metadata:2.0.20
+    image: gabisonfire/knightcrawler-metadata:2.0.26
     env_file: ../../.env
     networks:
       - knightcrawler-network
@@ -30,7 +30,7 @@ services:
         condition: service_completed_successfully
 
   migrator:
-    image: gabisonfire/knightcrawler-migrator:2.0.20
+    image: gabisonfire/knightcrawler-migrator:2.0.26
     env_file: ../../.env
     networks:
       - knightcrawler-network
@@ -40,7 +40,7 @@ services:
         condition: service_healthy
 
   addon:
-    image: gabisonfire/knightcrawler-addon:2.0.20
+    image: gabisonfire/knightcrawler-addon:2.0.26
     <<: [*knightcrawler-app, *knightcrawler-app-depends]
     restart: unless-stopped
     hostname: knightcrawler-addon
@@ -48,22 +48,22 @@ services:
       - "7000:7000"
 
   consumer:
-    image: gabisonfire/knightcrawler-consumer:2.0.20
+    image: gabisonfire/knightcrawler-consumer:2.0.26
     <<: [*knightcrawler-app, *knightcrawler-app-depends]
     restart: unless-stopped
 
   debridcollector:
-    image: gabisonfire/knightcrawler-debrid-collector:2.0.20
+    image: gabisonfire/knightcrawler-debrid-collector:2.0.26
     <<: [*knightcrawler-app, *knightcrawler-app-depends]
     restart: unless-stopped
         
   producer:
-    image: gabisonfire/knightcrawler-producer:2.0.20
+    image: gabisonfire/knightcrawler-producer:2.0.26
     <<: [*knightcrawler-app, *knightcrawler-app-depends]
     restart: unless-stopped
 
   qbitcollector:
-    image: gabisonfire/knightcrawler-qbit-collector:2.0.20
+    image: gabisonfire/knightcrawler-qbit-collector:2.0.26
     <<: [*knightcrawler-app, *knightcrawler-app-depends]
     restart: unless-stopped
     depends_on:

deployment/docker/stack.env

@@ -32,6 +32,7 @@ COLLECTOR_DEBRID_ENABLED=true
 COLLECTOR_REAL_DEBRID_API_KEY=
 QBIT_HOST=http://qbittorrent:8080
 QBIT_TRACKERS_URL=https://raw.githubusercontent.com/ngosang/trackerslist/master/trackers_all_http.txt
+QBIT_CONCURRENCY=8
 
 # Number of replicas for the qBittorrent collector and qBitTorrent client. Should be 0 or 1.
 QBIT_REPLICAS=0

src/addon/package-lock.json

@@ -12,7 +12,7 @@
         "@redis/client": "^1.5.14",
         "@redis/json": "^1.0.6",
         "@redis/search": "^1.1.6",
-        "all-debrid-api": "^1.1.0",
+        "all-debrid-api": "^1.2.0",
         "axios": "^1.6.1",
         "bottleneck": "^2.19.5",
         "cache-manager": "^3.4.4",

src/addon/package.json

@@ -10,7 +10,7 @@
   },
   "dependencies": {
     "@putdotio/api-client": "^8.42.0",
-    "all-debrid-api": "^1.1.0",
+    "all-debrid-api": "^1.2.0",
     "axios": "^1.6.1",
     "bottleneck": "^2.19.5",
     "cache-manager": "^3.4.4",

src/addon/src/addon.js

@@ -3,6 +3,7 @@ import { addonBuilder } from 'stremio-addon-sdk';
 import { cacheWrapStream } from './lib/cache.js';
 import { dummyManifest } from './lib/manifest.js';
 import * as repository from './lib/repository.js';
+import applyFilters from "./lib/filter.js";
 import applySorting from './lib/sort.js';
 import { toStreamInfo, applyStaticInfo } from './lib/streamInfo.js';
 import { Type } from './lib/types.js';
@@ -32,6 +33,7 @@ builder.defineStreamHandler((args) => {
       .then(records => records
           .sort((a, b) => b.torrent.seeders - a.torrent.seeders || b.torrent.uploadDate - a.torrent.uploadDate)
           .map(record => toStreamInfo(record)))))
+      .then(streams => applyFilters(streams, args.extra))
       .then(streams => applySorting(streams, args.extra))
       .then(streams => applyStaticInfo(streams))
       .then(streams => applyMochs(streams, args.extra))

src/addon/src/lib/repository.js

@@ -84,7 +84,7 @@ export function getImdbIdMovieEntries(imdbId) {
         where: {
             imdbId: { [Op.eq]: imdbId }
         },
-        include: [Torrent],
+        include: { model: Torrent, required: true },
         limit: 500,
         order: [
             [Torrent, 'size', 'DESC']
@@ -99,7 +99,7 @@ export function getImdbIdSeriesEntries(imdbId, season, episode) {
             imdbSeason: { [Op.eq]: season },
             imdbEpisode: { [Op.eq]: episode }
         },
-        include: [Torrent],
+        include: { model: Torrent, required: true },
         limit: 500,
         order: [
             [Torrent, 'size', 'DESC']
@@ -112,7 +112,7 @@ export function getKitsuIdMovieEntries(kitsuId) {
         where: {
             kitsuId: { [Op.eq]: kitsuId }
         },
-        include: [Torrent],
+        include: { model: Torrent, required: true },
         limit: 500,
         order: [
             [Torrent, 'size', 'DESC']
@@ -126,7 +126,7 @@ export function getKitsuIdSeriesEntries(kitsuId, episode) {
             kitsuId: { [Op.eq]: kitsuId },
             kitsuEpisode: { [Op.eq]: episode }
         },
-        include: [Torrent],
+        include: { model: Torrent, required: true },
         limit: 500,
         order: [
             [Torrent, 'size', 'DESC']

src/addon/src/lib/streamInfo.js

@@ -20,7 +20,7 @@ export function toStreamInfo(record) {
   const title = joinDetailParts(
       [
         joinDetailParts([record.torrent.title.replace(/[, ]+/g, ' ')]),
-        joinDetailParts([!sameInfo && record.title || undefined]),
+        joinDetailParts([record.title || undefined]),
         joinDetailParts([
           joinDetailParts([formatSize(record.size)], '💾 ')
         ]),

src/debrid-collector/Dockerfile

@@ -15,7 +15,7 @@ WORKDIR /app
 
 ENV PYTHONUNBUFFERED=1
 
-RUN apk add --update --no-cache python3=~3.11.8-r0 py3-pip && ln -sf python3 /usr/bin/python
+RUN apk add --update --no-cache python3=~3.11 py3-pip && ln -sf python3 /usr/bin/python
 
 COPY --from=build /src/out .
 

src/metadata/Features/Configuration/PostgresConfiguration.cs

@@ -8,12 +8,14 @@ public class PostgresConfiguration
     private const string PasswordVariable = "PASSWORD";
     private const string DatabaseVariable = "DB";
     private const string PortVariable = "PORT";
+    private const string CommandTimeoutVariable = "COMMAND_TIMEOUT_SEC"; // Seconds
 
     private string Host { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(HostVariable);
     private string Username { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(UsernameVariable);
     private string Password { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(PasswordVariable);
     private string Database { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(DatabaseVariable);
     private int PORT { get; init; } = Prefix.GetEnvironmentVariableAsInt(PortVariable, 5432);
+    private int CommandTimeout { get; init; } = Prefix.GetEnvironmentVariableAsInt(CommandTimeoutVariable, 300);
 
-    public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};";
+    public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};CommandTimeout={CommandTimeout}";
 }

src/metadata/Features/ImportImdbData/ImdbDbService.cs

@@ -134,7 +134,7 @@ public class ImdbDbService(PostgresConfiguration configuration, ILogger<ImdbDbSe
     {
         try
         {
-            await using var connection = CreateNpgsqlConnection();
+            await using var connection = new NpgsqlConnection(configuration.StorageConnectionString);
             await connection.OpenAsync();
 
             await operation(connection);
@@ -145,16 +145,6 @@ public class ImdbDbService(PostgresConfiguration configuration, ILogger<ImdbDbSe
         }
     }
 
-    private NpgsqlConnection CreateNpgsqlConnection()
-    {
-        var connectionStringBuilder = new NpgsqlConnectionStringBuilder(configuration.StorageConnectionString)
-        {
-            CommandTimeout = 3000,
-        };
-
-        return new(connectionStringBuilder.ConnectionString);
-    }
-
     private async Task ExecuteCommandWithTransactionAsync(Func<NpgsqlConnection, NpgsqlTransaction, Task> operation, NpgsqlTransaction transaction, string errorMessage)
     {
         try

src/metadata/Metadata.csproj

@@ -13,7 +13,7 @@
       <PackageReference Include="Dapper" Version="2.1.35" />
       <PackageReference Include="Microsoft.Extensions.Hosting" Version="8.0.0" />
       <PackageReference Include="Microsoft.Extensions.Http" Version="8.0.0" />
-      <PackageReference Include="Npgsql" Version="8.0.2" />
+      <PackageReference Include="Npgsql" Version="8.0.3" />
       <PackageReference Include="Serilog" Version="3.1.1" />
       <PackageReference Include="Serilog.AspNetCore" Version="8.0.1" />
       <PackageReference Include="Serilog.Sinks.Console" Version="5.0.1" />

src/migrator/migrations/014_file_subtitle_infohash_fileidx_index.sql

@@ -0,0 +1,43 @@
+-- Drop Duplicate Files in Files Table
+DELETE FROM public.files
+WHERE id NOT IN (
+    SELECT MAX(id)
+    FROM public.files
+    GROUP BY "infoHash", "fileIndex"
+);
+
+-- Add Index to files table
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT 1
+        FROM pg_constraint
+        WHERE conname = 'files_unique_infohash_fileindex'
+    ) THEN
+        ALTER TABLE public.files
+            ADD CONSTRAINT files_unique_infohash_fileindex UNIQUE ("infoHash", "fileIndex");
+    END IF;
+END $$;
+
+
+-- Drop Duplicate subtitles in Subtitles Table
+DELETE FROM public.subtitles
+WHERE id NOT IN (
+    SELECT MAX(id)
+    FROM public.subtitles
+    GROUP BY "infoHash", "fileIndex"
+);
+
+-- Add Index to subtitles table
+DO $$
+    BEGIN
+        IF NOT EXISTS (
+            SELECT 1
+            FROM pg_constraint
+            WHERE conname = 'subtitles_unique_infohash_fileindex'
+        ) THEN
+            ALTER TABLE public.subtitles
+                ADD CONSTRAINT subtitles_unique_infohash_fileindex UNIQUE ("infoHash", "fileIndex");
+        END IF;
+    END $$;
+

src/producer/src/Configuration/scrapers.json

@@ -4,27 +4,34 @@
       {
         "Name": "SyncEzTvJob",
         "IntervalSeconds": 60,
-        "Enabled": true
+        "Enabled": true,
+        "Url": "https://eztvx.to/ezrss.xml",
+        "XmlNamespace": "http://xmlns.ezrss.it/0.1/"
       },
       {
         "Name": "SyncNyaaJob",
         "IntervalSeconds": 60,
-        "Enabled": true
+        "Enabled": true,
+        "Url": "https://nyaa.si/?page=rss&c=1_2&f=0",
+        "XmlNamespace": "https://nyaa.si/xmlns/nyaa"
       },
       {
         "Name": "SyncTpbJob",
         "IntervalSeconds": 60,
-        "Enabled": true
+        "Enabled": true,
+        "Url": "https://apibay.org/precompiled/data_top100_recent.json"
       },
       {
         "Name": "SyncYtsJob",
         "IntervalSeconds": 60,
-        "Enabled": true
+        "Enabled": true,
+        "Url": "https://yts.am/rss"
       },
       {
         "Name": "SyncTgxJob",
         "IntervalSeconds": 60,
-        "Enabled": true
+        "Enabled": true,
+        "Url": "https://tgx.rs/rss"
       },
       {
         "Name": "SyncDmmJob",

src/producer/src/Dockerfile

@@ -14,7 +14,7 @@ WORKDIR /app
 
 ENV PYTHONUNBUFFERED=1
 
-RUN apk add --update --no-cache python3=~3.11.8-r0 py3-pip && ln -sf python3 /usr/bin/python
+RUN apk add --update --no-cache python3=~3.11 py3-pip && ln -sf python3 /usr/bin/python
 
 COPY --from=build /src/out .
 

src/producer/src/Features/CrawlerSupport/BaseJsonCrawler.cs

@@ -6,6 +6,12 @@ public abstract class BaseJsonCrawler(IHttpClientFactory httpClientFactory, ILog
 
     protected virtual async Task Execute(string collectionName)
     {
+        if (string.IsNullOrWhiteSpace(Url))
+        {
+            logger.LogWarning("No URL provided for {Source} crawl", Source);
+            return;
+        }
+        
         logger.LogInformation("Starting {Source} crawl", Source);
 
         using var client = httpClientFactory.CreateClient("Scraper");

src/producer/src/Features/CrawlerSupport/BaseXmlCrawler.cs

@@ -4,6 +4,12 @@ public abstract class BaseXmlCrawler(IHttpClientFactory httpClientFactory, ILogg
 {
     public override async Task Execute()
     {
+        if (string.IsNullOrWhiteSpace(Url))
+        {
+            logger.LogWarning("No URL provided for {Source} crawl", Source);
+            return;
+        }
+        
         logger.LogInformation("Starting {Source} crawl", Source);
 
         using var client = httpClientFactory.CreateClient(Literals.CrawlerClient);

src/producer/src/Features/CrawlerSupport/Scraper.cs

@@ -7,4 +7,8 @@ public class Scraper
     public int IntervalSeconds { get; set; } = 60;
 
     public bool Enabled { get; set; } = true;
+    
+    public string? Url { get; set; }
+    
+    public string? XmlNamespace { get; set; }
 }

src/producer/src/Features/Crawlers/Dmm/DebridMediaManagerCrawler.cs

@@ -69,7 +69,7 @@ public partial class DebridMediaManagerCrawler(
             if (page.TryGetValue(infoHash, out var dmmContent) &&
                 successfulResponses.TryGetValue(dmmContent.Filename, out var parsedResponse))
             {
-                page[infoHash] = dmmContent with {ParseResponse = parsedResponse};
+                page[infoHash] = dmmContent with { ParseResponse = parsedResponse };
             }
 
             return ValueTask.CompletedTask;
@@ -106,9 +106,34 @@ public partial class DebridMediaManagerCrawler(
 
         var decodedJson = LZString.DecompressFromEncodedURIComponent(encodedJson.Value);
 
-        var json = JsonDocument.Parse(decodedJson);
+        JsonElement arrayToProcess;
+        try
+        {
+            var json = JsonDocument.Parse(decodedJson);
 
-        var torrents = await json.RootElement.EnumerateArray()
+            if (json.RootElement.ValueKind == JsonValueKind.Object &&
+                json.RootElement.TryGetProperty("torrents", out var torrentsProperty) &&
+                torrentsProperty.ValueKind == JsonValueKind.Array)
+            {
+                arrayToProcess = torrentsProperty;
+            }
+            else if (json.RootElement.ValueKind == JsonValueKind.Array)
+            {
+                arrayToProcess = json.RootElement;
+            }
+            else
+            {
+                logger.LogWarning("Unexpected JSON format in {Name}", name);
+                return [];
+            }
+        }
+        catch (Exception ex)
+        {
+            logger.LogError("Failed to parse JSON {decodedJson} for {Name}: {Exception}", decodedJson, name, ex);
+            return [];
+        }
+
+        var torrents = await arrayToProcess.EnumerateArray()
             .ToAsyncEnumerable()
             .Select(ParsePageContent)
             .Where(t => t is not null)
@@ -141,7 +166,7 @@ public partial class DebridMediaManagerCrawler(
         {
             var (infoHash, dmmContent) = kvp;
             var parsedTorrent = dmmContent.ParseResponse;
-            if (parsedTorrent is not {Success: true})
+            if (parsedTorrent is not { Success: true })
             {
                 return;
             }

src/producer/src/Features/Crawlers/Dmm/ServiceCollectionExtensions.cs

@@ -9,6 +9,7 @@ public static class ServiceCollectionExtensions
             client.BaseAddress = new("https://github.com/debridmediamanager/hashlists/zipball/main/");
             client.DefaultRequestHeaders.Add("Accept-Encoding", "gzip");
             client.DefaultRequestHeaders.UserAgent.ParseAdd("curl");
+            client.Timeout = TimeSpan.FromMinutes(10); // 10 minute timeout, #217
         });
 
         return services;

src/producer/src/Features/Crawlers/EzTv/EzTvCrawler.cs

@@ -1,11 +1,10 @@
 namespace Producer.Features.Crawlers.EzTv;
 
-public class EzTvCrawler(IHttpClientFactory httpClientFactory, ILogger<EzTvCrawler> logger, IDataStorage storage) : BaseXmlCrawler(httpClientFactory, logger, storage)
+public class EzTvCrawler(IHttpClientFactory httpClientFactory, ILogger<EzTvCrawler> logger, IDataStorage storage, ScrapeConfiguration scrapeConfiguration) : BaseXmlCrawler(httpClientFactory, logger, storage)
 {
-    protected override string Url => "https://eztv1.xyz/ezrss.xml";
+    protected override string Url => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncEzTvJob", StringComparison.OrdinalIgnoreCase))?.Url ?? string.Empty;
     protected override string Source => "EZTV";
-
+    private XNamespace XmlNamespace => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncEzTvJob", StringComparison.OrdinalIgnoreCase))?.XmlNamespace ?? string.Empty;
-    private static readonly XNamespace XmlNamespace = "http://xmlns.ezrss.it/0.1/";
 
     protected override IReadOnlyDictionary<string, string> Mappings =>
         new Dictionary<string, string>

src/producer/src/Features/Crawlers/Nyaa/NyaaCrawler.cs

@@ -1,11 +1,10 @@
 namespace Producer.Features.Crawlers.Nyaa;
 
-public class NyaaCrawler(IHttpClientFactory httpClientFactory, ILogger<NyaaCrawler> logger, IDataStorage storage) : BaseXmlCrawler(httpClientFactory, logger, storage)
+public class NyaaCrawler(IHttpClientFactory httpClientFactory, ILogger<NyaaCrawler> logger, IDataStorage storage, ScrapeConfiguration scrapeConfiguration) : BaseXmlCrawler(httpClientFactory, logger, storage)
 {
-    protected override string Url => "https://nyaa.si/?page=rss&c=1_2&f=0";
+    protected override string Url => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncNyaaJob", StringComparison.OrdinalIgnoreCase))?.Url ?? string.Empty;
     protected override string Source => "Nyaa";
-
+    private XNamespace XmlNamespace => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncNyaaJob", StringComparison.OrdinalIgnoreCase))?.XmlNamespace ?? string.Empty;
-    private static readonly XNamespace XmlNamespace = "https://nyaa.si/xmlns/nyaa";
 
     protected override IReadOnlyDictionary<string, string> Mappings =>
         new Dictionary<string, string>

src/producer/src/Features/Crawlers/Tgx/TgxCrawler.cs

@@ -1,13 +1,13 @@
 namespace Producer.Features.Crawlers.Tgx;
 
-public partial class TgxCrawler(IHttpClientFactory httpClientFactory, ILogger<TgxCrawler> logger, IDataStorage storage) : BaseXmlCrawler(httpClientFactory, logger, storage)
+public partial class TgxCrawler(IHttpClientFactory httpClientFactory, ILogger<TgxCrawler> logger, IDataStorage storage, ScrapeConfiguration scrapeConfiguration) : BaseXmlCrawler(httpClientFactory, logger, storage)
 {
     [GeneratedRegex(@"Size:\s+(.+?)\s+Added")]
     private static partial Regex SizeStringExtractor();
     [GeneratedRegex(@"(?i)\b(\d+(\.\d+)?)\s*([KMGT]?B)\b", RegexOptions.None, "en-GB")]
     private static partial Regex SizeStringParser();
 
-    protected override string Url => "https://tgx.rs/rss";
+    protected override string Url => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncTgxJob", StringComparison.OrdinalIgnoreCase))?.Url ?? string.Empty;
 
     protected override string Source => "TorrentGalaxy";
     protected override IReadOnlyDictionary<string, string> Mappings

src/producer/src/Features/Crawlers/Tpb/TpbCrawler.cs

@@ -1,8 +1,8 @@
 namespace Producer.Features.Crawlers.Tpb;
 
-public class TpbCrawler(IHttpClientFactory httpClientFactory, ILogger<TpbCrawler> logger, IDataStorage storage) : BaseJsonCrawler(httpClientFactory, logger, storage)
+public class TpbCrawler(IHttpClientFactory httpClientFactory, ILogger<TpbCrawler> logger, IDataStorage storage, ScrapeConfiguration scrapeConfiguration) : BaseJsonCrawler(httpClientFactory, logger, storage)
 {
-    protected override string Url => "https://apibay.org/precompiled/data_top100_recent.json";
+    protected override string Url => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncTpbJob", StringComparison.OrdinalIgnoreCase))?.Url ?? string.Empty;
 
     protected override string Source => "TPB";
     

src/producer/src/Features/Crawlers/Yts/YtsCrawler.cs

@@ -1,9 +1,8 @@
 namespace Producer.Features.Crawlers.Yts;
 
-public class YtsCrawler(IHttpClientFactory httpClientFactory, ILogger<YtsCrawler> logger, IDataStorage storage) : BaseXmlCrawler(httpClientFactory, logger, storage)
+public class YtsCrawler(IHttpClientFactory httpClientFactory, ILogger<YtsCrawler> logger, IDataStorage storage, ScrapeConfiguration scrapeConfiguration) : BaseXmlCrawler(httpClientFactory, logger, storage)
 {
-    protected override string Url => "https://yts.am/rss";
+    protected override string Url => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncYtsJob", StringComparison.OrdinalIgnoreCase))?.Url ?? string.Empty;
-
     protected override string Source => "YTS";
     protected override IReadOnlyDictionary<string, string> Mappings
         => new Dictionary<string, string>

src/qbit-collector/Dockerfile

@@ -15,7 +15,7 @@ WORKDIR /app
 
 ENV PYTHONUNBUFFERED=1
 
-RUN apk add --update --no-cache python3=~3.11.8-r0 py3-pip && ln -sf python3 /usr/bin/python
+RUN apk add --update --no-cache python3=~3.11 py3-pip && ln -sf python3 /usr/bin/python
 
 COPY --from=build /src/out .
 

src/qbit-collector/Extensions/ServiceCollectionExtensions.cs

@@ -44,6 +44,7 @@ public static class ServiceCollectionExtensions
     {
         var rabbitConfiguration = services.LoadConfigurationFromEnv<RabbitMqConfiguration>();
         var redisConfiguration = services.LoadConfigurationFromEnv<RedisConfiguration>();
+        var qbitConfiguration = services.LoadConfigurationFromEnv<QbitConfiguration>();
 
         services.AddStackExchangeRedisCache(
             option =>
@@ -80,8 +81,8 @@ public static class ServiceCollectionExtensions
                     e.ConfigureConsumer<WriteQbitMetadataConsumer>(context);
                     e.ConfigureConsumer<PerformQbitMetadataRequestConsumer>(context);
                     e.ConfigureSaga<QbitMetadataSagaState>(context);
-                    e.ConcurrentMessageLimit = 5;
+                    e.ConcurrentMessageLimit = qbitConfiguration.Concurrency;
-                    e.PrefetchCount = 5;
+                    e.PrefetchCount = qbitConfiguration.Concurrency;
                 });
             });
         });
@@ -98,7 +99,7 @@ public static class ServiceCollectionExtensions
                     cfg.UseTimeout(
                         timeout =>
                         {
-                            timeout.Timeout = TimeSpan.FromMinutes(1);
+                            timeout.Timeout = TimeSpan.FromMinutes(3);
                         });
                 })
             .RedisRepository(redisConfiguration.ConnectionString, options =>
@@ -110,7 +111,7 @@ public static class ServiceCollectionExtensions
     {
         var qbitConfiguration = services.LoadConfigurationFromEnv<QbitConfiguration>();
         var client = new QBittorrentClient(new(qbitConfiguration.Host));
-        client.Timeout = TimeSpan.FromSeconds(10);
+        client.Timeout = TimeSpan.FromSeconds(20);
 
         services.AddSingleton<IQBittorrentClient>(client);
     }

src/qbit-collector/Features/Qbit/QBitRequestProcessor.cs

@@ -1,6 +1,6 @@
 namespace QBitCollector.Features.Qbit;
 
-public class QbitRequestProcessor(IQBittorrentClient client, ITrackersService trackersService, ILogger<QbitRequestProcessor> logger)
+public class QbitRequestProcessor(IQBittorrentClient client, ITrackersService trackersService, ILogger<QbitRequestProcessor> logger, QbitConfiguration configuration)
 {
     public async Task<IReadOnlyList<TorrentContent>?> ProcessAsync(string infoHash, CancellationToken cancellationToken = default)
     {
@@ -14,7 +14,7 @@ public class QbitRequestProcessor(IQBittorrentClient client, ITrackersService tr
 
         using var timeoutCts = CancellationTokenSource.CreateLinkedTokenSource(cancellationToken);
 
-        timeoutCts.CancelAfter(TimeSpan.FromSeconds(30));
+        timeoutCts.CancelAfter(TimeSpan.FromSeconds(60));
 
         try
         {
@@ -30,7 +30,7 @@ public class QbitRequestProcessor(IQBittorrentClient client, ITrackersService tr
                     break;
                 }
 
-                await Task.Delay(TimeSpan.FromSeconds(1), timeoutCts.Token);
+                await Task.Delay(TimeSpan.FromMilliseconds(200), timeoutCts.Token);
             }
         }
         catch (OperationCanceledException) when (timeoutCts.IsCancellationRequested)

src/qbit-collector/Features/Qbit/QbitConfiguration.cs

@@ -5,7 +5,10 @@ public class QbitConfiguration
     private const string Prefix = "QBIT";
     private const string HOST_VARIABLE = "HOST";
     private const string TRACKERS_URL_VARIABLE = "TRACKERS_URL";
+    private const string CONCURRENCY_VARIABLE = "CONCURRENCY";
     
     public string? Host { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(HOST_VARIABLE);
     public string? TrackersUrl { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(TRACKERS_URL_VARIABLE);
+    
+    public int Concurrency { get; init; } = Prefix.GetEnvironmentVariableAsInt(CONCURRENCY_VARIABLE, 8);
 }

src/qbit-collector/Features/Worker/WriteQbitMetadataConsumer.cs

@@ -6,6 +6,12 @@ public class WriteQbitMetadataConsumer(IRankTorrentName rankTorrentName, IDataSt
     {
         var request = context.Message;
         
+        if (request.Metadata.Metadata.Count == 0)
+        {
+            await context.Publish(new QbitMetadataWritten(request.Metadata, false));
+            return;
+        }
+
         var torrentFiles = QbitMetaToTorrentMeta.MapMetadataToFilesCollection(
             rankTorrentName, request.Torrent, request.ImdbId, request.Metadata.Metadata, logger);
 

src/shared/Configuration/PostgresConfiguration.cs

@@ -8,12 +8,14 @@ public class PostgresConfiguration
     private const string PasswordVariable = "PASSWORD";
     private const string DatabaseVariable = "DB";
     private const string PortVariable = "PORT";
+    private const string CommandTimeoutVariable = "COMMAND_TIMEOUT_SEC"; // Seconds
 
     private string Host { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(HostVariable);
     private string Username { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(UsernameVariable);
     private string Password { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(PasswordVariable);
     private string Database { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(DatabaseVariable);
     private int PORT { get; init; } = Prefix.GetEnvironmentVariableAsInt(PortVariable, 5432);
+    private int CommandTimeout { get; init; } = Prefix.GetEnvironmentVariableAsInt(CommandTimeoutVariable, 300);
 
-    public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};";
+    public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};CommandTimeout={CommandTimeout}";
 }

src/shared/Dapper/DapperDataStorage.cs

@@ -152,7 +152,8 @@ public class DapperDataStorage(PostgresConfiguration configuration, RabbitMqConf
                     INSERT INTO files
                         ("infoHash", "fileIndex", title, "size", "imdbId", "imdbSeason", "imdbEpisode", "kitsuId", "kitsuEpisode", "createdAt", "updatedAt")
                     VALUES
-                        (@InfoHash, @FileIndex, @Title, @Size, @ImdbId, @ImdbSeason, @ImdbEpisode, @KitsuId, @KitsuEpisode, Now(), Now());
+                        (@InfoHash, @FileIndex, @Title, @Size, @ImdbId, @ImdbSeason, @ImdbEpisode, @KitsuId, @KitsuEpisode, Now(), Now())
+                    ON CONFLICT ("infoHash", "fileIndex") DO NOTHING;
                     """;
                 
                 await connection.ExecuteAsync(query, files);
@@ -167,7 +168,8 @@ public class DapperDataStorage(PostgresConfiguration configuration, RabbitMqConf
                     INSERT INTO subtitles
                         ("infoHash", "fileIndex", "fileId", "title")
                     VALUES
-                        (@InfoHash, @FileIndex, @FileId, @Title);
+                        (@InfoHash, @FileIndex, @FileId, @Title)
+                    ON CONFLICT ("infoHash", "fileIndex") DO NOTHING;
                     """;
                 
                 await connection.ExecuteAsync(query, subtitles);

src/shared/SharedContracts.csproj

@@ -15,7 +15,7 @@
   <PackageReference Include="Dapper" Version="2.1.35" />
   <PackageReference Include="MassTransit.Abstractions" Version="8.2.0" />
   <PackageReference Include="MassTransit.RabbitMQ" Version="8.2.0" />
-  <PackageReference Include="Npgsql" Version="8.0.2" />
+  <PackageReference Include="Npgsql" Version="8.0.3" />
   <PackageReference Include="pythonnet" Version="3.0.3" />
   <PackageReference Include="Serilog" Version="3.1.1" />
   <PackageReference Include="Serilog.Extensions.Hosting" Version="8.0.0" />

src/tissue/Features/DataProcessing/PostgresConfiguration.cs

@@ -8,12 +8,14 @@ public class PostgresConfiguration
     private const string PasswordVariable = "PASSWORD";
     private const string DatabaseVariable = "DB";
     private const string PortVariable = "PORT";
+    private const string CommandTimeoutVariable = "COMMAND_TIMEOUT_SEC"; // Seconds
 
     private string Host { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(HostVariable);
     private string Username { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(UsernameVariable);
     private string Password { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(PasswordVariable);
     private string Database { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(DatabaseVariable);
     private int PORT { get; init; } = Prefix.GetEnvironmentVariableAsInt(PortVariable, 5432);
+    private int CommandTimeout { get; init; } = Prefix.GetEnvironmentVariableAsInt(CommandTimeoutVariable, 300);
 
-    public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};";
+    public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};CommandTimeout={CommandTimeout}";
 }

src/tissue/Tissue.csproj

@@ -12,7 +12,7 @@
       <PackageReference Include="Dapper" Version="2.1.28" />
       <PackageReference Include="Microsoft.Extensions.Hosting" Version="8.0.0" />
       <PackageReference Include="Microsoft.Extensions.Http" Version="8.0.0" />
-      <PackageReference Include="Npgsql" Version="8.0.1" />
+      <PackageReference Include="Npgsql" Version="8.0.3" />
       <PackageReference Include="Serilog" Version="3.1.1" />
       <PackageReference Include="Serilog.AspNetCore" Version="8.0.1" />
       <PackageReference Include="Serilog.Sinks.Console" Version="5.0.1" />