1 Commits

Author SHA1 Message Date
iPromKnight
f56f205bbe helm chart [wip] 2024-03-30 23:54:34 +00:00
102 changed files with 1112 additions and 988 deletions

View File

@@ -12,9 +12,6 @@ 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.
@@ -26,7 +23,6 @@ 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.

View File

@@ -1,39 +0,0 @@
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 }}

4
.gitignore vendored
View File

@@ -612,7 +612,3 @@ fabric.properties
# Mac directory indexes
.DS_Store
deployment/docker/stack.env
src/producer/src/python/
src/debrid-collector/python/
src/qbit-collector/python/

View File

@@ -1,22 +0,0 @@
# 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 -->

View File

@@ -1,34 +0,0 @@
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)

View File

@@ -67,6 +67,30 @@ 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:

View File

@@ -1,112 +0,0 @@
# 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"

View File

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

View File

@@ -94,7 +94,7 @@ services:
condition: service_healthy
env_file: stack.env
hostname: knightcrawler-addon
image: gabisonfire/knightcrawler-addon:2.0.26
image: gabisonfire/knightcrawler-addon:2.0.17
labels:
logging: promtail
networks:
@@ -117,7 +117,7 @@ services:
redis:
condition: service_healthy
env_file: stack.env
image: gabisonfire/knightcrawler-consumer:2.0.26
image: gabisonfire/knightcrawler-consumer:2.0.17
labels:
logging: promtail
networks:
@@ -138,7 +138,7 @@ services:
redis:
condition: service_healthy
env_file: stack.env
image: gabisonfire/knightcrawler-debrid-collector:2.0.26
image: gabisonfire/knightcrawler-debrid-collector:2.0.17
labels:
logging: promtail
networks:
@@ -152,7 +152,7 @@ services:
migrator:
condition: service_completed_successfully
env_file: stack.env
image: gabisonfire/knightcrawler-metadata:2.0.26
image: gabisonfire/knightcrawler-metadata:2.0.17
networks:
- knightcrawler-network
restart: "no"
@@ -163,7 +163,7 @@ services:
postgres:
condition: service_healthy
env_file: stack.env
image: gabisonfire/knightcrawler-migrator:2.0.26
image: gabisonfire/knightcrawler-migrator:2.0.17
networks:
- knightcrawler-network
restart: "no"
@@ -182,7 +182,7 @@ services:
redis:
condition: service_healthy
env_file: stack.env
image: gabisonfire/knightcrawler-producer:2.0.26
image: gabisonfire/knightcrawler-producer:2.0.17
labels:
logging: promtail
networks:
@@ -207,7 +207,7 @@ services:
deploy:
replicas: ${QBIT_REPLICAS:-0}
env_file: stack.env
image: gabisonfire/knightcrawler-qbit-collector:2.0.26
image: gabisonfire/knightcrawler-qbit-collector:2.0.17
labels:
logging: promtail
networks:

View File

@@ -20,7 +20,7 @@ x-depends: &knightcrawler-app-depends
services:
metadata:
image: gabisonfire/knightcrawler-metadata:2.0.26
image: gabisonfire/knightcrawler-metadata:2.0.17
env_file: ../../.env
networks:
- knightcrawler-network
@@ -30,7 +30,7 @@ services:
condition: service_completed_successfully
migrator:
image: gabisonfire/knightcrawler-migrator:2.0.26
image: gabisonfire/knightcrawler-migrator:2.0.17
env_file: ../../.env
networks:
- knightcrawler-network
@@ -40,7 +40,7 @@ services:
condition: service_healthy
addon:
image: gabisonfire/knightcrawler-addon:2.0.26
image: gabisonfire/knightcrawler-addon:2.0.17
<<: [*knightcrawler-app, *knightcrawler-app-depends]
restart: unless-stopped
hostname: knightcrawler-addon
@@ -48,22 +48,22 @@ services:
- "7000:7000"
consumer:
image: gabisonfire/knightcrawler-consumer:2.0.26
image: gabisonfire/knightcrawler-consumer:2.0.17
<<: [*knightcrawler-app, *knightcrawler-app-depends]
restart: unless-stopped
debridcollector:
image: gabisonfire/knightcrawler-debrid-collector:2.0.26
image: gabisonfire/knightcrawler-debrid-collector:2.0.17
<<: [*knightcrawler-app, *knightcrawler-app-depends]
restart: unless-stopped
producer:
image: gabisonfire/knightcrawler-producer:2.0.26
image: gabisonfire/knightcrawler-producer:2.0.17
<<: [*knightcrawler-app, *knightcrawler-app-depends]
restart: unless-stopped
qbitcollector:
image: gabisonfire/knightcrawler-qbit-collector:2.0.26
image: gabisonfire/knightcrawler-qbit-collector:2.0.17
<<: [*knightcrawler-app, *knightcrawler-app-depends]
restart: unless-stopped
depends_on:

View File

@@ -32,10 +32,12 @@ 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
# Addon
DEBUG_MODE=false
# Producer
GITHUB_PAT=

View File

@@ -0,0 +1,6 @@
apiVersion: v2
appVersion: 2.0.17
description: A helm chart for Knightcrawler
name: knightcrawler
type: application
version: 0.1.0

View File

@@ -0,0 +1,6 @@
Congratulations,
Knightcrawler is now deployed. This may take a while to be up and responding.

View File

@@ -0,0 +1,27 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: '{{ .Release.Name }}-config'
labels:
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
data:
COLLECTOR_DEBRID_ENABLED: '{{ .Values.knightcrawler.debridcollector.enabled }}'
COLLECTOR_QBIT_ENABLED: '{{ .Values.knightcrawler.qbitcollector.enabled }}'
DEBUG_MODE: '{{ .Values.knightcrawler.debug }}'
METADATA_INSERT_BATCH_SIZE: '{{ .Values.environment.metadata.insertBatchSize }}'
POSTGRES_DB: '{{ .Values.environment.postgres.dbName }}'
POSTGRES_HOST: '{{ if .Values.environment.postgres.external }}{{ .Values.environment.postgres.host }}{{ else }}{{ .Release.Name }}-postgres{{ end }}'
POSTGRES_PORT: '{{ .Values.environment.postgres.port }}'
QBIT_HOST: '{{ .Values.environment.qbitcollector.qbitHost }}'
QBIT_TRACKERS_URL: '{{ .Values.environment.qbitcollector.trackersUrl }}'
RABBITMQ_CONSUMER_QUEUE_NAME: '{{ .Values.environment.producer.queueName }}'
RABBITMQ_DURABLE: '{{ .Values.environment.producer.durable }}'
RABBITMQ_HOST: '{{ if .Values.environment.lavinmq.external }}{{ .Values.environment.lavinmq.host }}{{ else }}{{ .Release.Name }}-lavinmq{{ end }}'
RABBITMQ_MAX_PUBLISH_BATCH_SIZE: '{{ .Values.environment.producer.maxPublishBatchSize }}'
RABBITMQ_MAX_QUEUE_SIZE: '{{ .Values.environment.producer.maxQueueSize }}'
RABBITMQ_PUBLISH_INTERVAL_IN_SECONDS: '{{ .Values.environment.producer.publishIntervalSeconds }}'
REDIS_EXTRA: '{{ .Values.environment.redis.extra }}'
REDIS_HOST: '{{ if .Values.environment.redis.external }}{{ .Values.environment.redis.host }}{{ else }}{{ .Release.Name }}-redis{{ end }}'
REDIS_PORT: '{{ .Values.environment.redis.port }}'
TZ: '{{ .Values.shared.timezone }}'

View File

@@ -0,0 +1,15 @@
apiVersion: v1
kind: Secret
metadata:
name: '{{ .Release.Name }}-secrets'
labels:
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
type: Opaque
data:
GITHUB_PAT: '{{ .Values.environment.producer.githubPat | b64enc }}'
COLLECTOR_REAL_DEBRID_API_KEY: '{{ .Values.environment.debridcollector.realDebridApiKey | b64enc }}'
POSTGRES_USER: '{{ .Values.environment.postgres.user | b64enc }}'
POSTGRES_PASSWORD: '{{ .Values.environment.postgres.password | b64enc }}'
RABBITMQ_PASSWORD: '{{ .Values.environment.lavinmq.password | b64enc }}'
RABBITMQ_USER: '{{ .Values.environment.lavinmq.user | b64enc }}'

View File

@@ -0,0 +1,25 @@
{{ if .Values.infrastructure.lavinmq.enabled }}
apiVersion: v1
kind: Service
metadata:
name: '{{ .Release.Name }}-lavinmq'
labels:
component: lavinmq
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
spec:
selector:
component: lavinmq
release: '{{ .Release.Name }}'
type: ClusterIP
ports:
- protocol: TCP
port: 5672
targetPort: 5672
- protocol: TCP
port: 15672
targetPort: 15672
- protocol: TCP
port: 15692
targetPort: 15692
{{- end -}}

View File

@@ -0,0 +1,60 @@
{{ if .Values.infrastructure.lavinmq.enabled }}
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: '{{ .Release.Name }}-lavinmq'
labels:
component: lavinmq
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "0"
spec:
serviceName: '{{ .Release.Name }}-lavinmq'
replicas: 1
selector:
matchLabels:
component: lavinmq
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: lavinmq
release: '{{ .Release.Name }}'
spec:
containers:
- name: lavinmq
image: '{{ .Values.infrastructure.lavinmq.image }}:{{ .Values.infrastructure.lavinmq.tag }}'
ports:
- name: lavinmq
containerPort: 5672
- name: lavinmq-15672
containerPort: 15672
- name: lavinmq-15692
containerPort: 15692
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'
volumeMounts:
- mountPath: /var/lib/lavinmq
name: lavinmq
livenessProbe:
exec:
command:
- lavinmqctl status
periodSeconds: 10
initialDelaySeconds: 10
successThreshold: 1
failureThreshold: 3
volumeClaimTemplates:
- metadata:
name: lavinmq
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: '{{ .Values.persistence.lavinmq.capacity }}'
{{- end -}}

View File

@@ -0,0 +1,19 @@
{{ if .Values.infrastructure.postgres.enabled }}
apiVersion: v1
kind: Service
metadata:
name: '{{ .Release.Name }}-postgres'
labels:
component: postgres
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
spec:
selector:
component: postgres
release: '{{ .Release.Name }}'
type: ClusterIP
ports:
- protocol: TCP
port: 5432
targetPort: 5432
{{- end -}}

View File

@@ -0,0 +1,58 @@
{{ if .Values.infrastructure.postgres.enabled }}
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: '{{ .Release.Name }}-postgres'
labels:
component: postgres
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "0"
spec:
serviceName: '{{ .Release.Name }}-postgres'
replicas: 1
selector:
matchLabels:
component: postgres
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: postgres
release: '{{ .Release.Name }}'
spec:
containers:
- name: postgres
image: '{{ .Values.infrastructure.postgres.image }}:{{ .Values.infrastructure.postgres.tag }}'
ports:
- name: postgres
containerPort: 5432
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'
volumeMounts:
- mountPath: /var/lib/postgresql/data
name: postgres
livenessProbe:
exec:
command:
- sh
- -c
- pg_isready -h localhost -U $POSTGRES_USER
periodSeconds: 10
initialDelaySeconds: 10
successThreshold: 1
failureThreshold: 3
volumeClaimTemplates:
- metadata:
name: postgres
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: '{{ .Values.persistence.postgres.capacity }}'
{{- end -}}

View File

@@ -0,0 +1,57 @@
{{ if .Values.knightcrawler.qbitcollector.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: '{{ .Release.Name }}-qbittorrent'
labels:
component: qbittorrent
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "0"
spec:
replicas: 1
selector:
matchLabels:
component: qbittorrent
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: qbittorrent
release: '{{ .Release.Name }}'
spec:
containers:
- name: qbittorrent
image: '{{ .Values.infrastructure.qbittorrent.image }}:{{ .Values.infrastructure.qbittorrent.tag }}'
ports:
- name: qbittorrent
containerPort: 6881
- name: qbittorrent-6881
containerPort: 6881
- name: qbittorrent-8080
containerPort: 8080
env:
- name: PUID
value: '{{ .Values.environment.qbittorrent.puid }}'
- name: PGID
value: '{{ .Values.environment.qbittorrent.pgid }}'
- name: TORRENTING_PORT
value: '{{ .Values.environment.qbittorrent.torrentingPort }}'
- name: WEBUI_PORT
value: '{{ .Values.environment.qbittorrent.webuiPort }}'
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'
livenessProbe:
exec:
command:
- curl --fail http://localhost:8080
periodSeconds: 10
initialDelaySeconds: 10
successThreshold: 1
failureThreshold: 3
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{ if .Values.knightcrawler.qbitcollector.enabled }}
apiVersion: v1
kind: Service
metadata:
name: '{{ .Release.Name }}-qbittorrent'
labels:
component: qbittorrent
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
spec:
selector:
component: qbittorrent
release: '{{ .Release.Name }}'
type: ClusterIP
ports:
- protocol: TCP
port: 6881
targetPort: 6881
- protocol: TCP
port: 6881
targetPort: 6881
- protocol: TCP
port: 8080
targetPort: 8080
{{- end -}}

View File

@@ -0,0 +1,19 @@
{{ if .Values.infrastructure.redis.enabled }}
apiVersion: v1
kind: Service
metadata:
name: '{{ .Release.Name }}-redis'
labels:
component: redis
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
spec:
selector:
component: redis
release: '{{ .Release.Name }}'
type: ClusterIP
ports:
- protocol: TCP
port: 6379
targetPort: 6379
{{- end -}}

View File

@@ -0,0 +1,56 @@
{{ if .Values.infrastructure.redis.enabled }}
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: '{{ .Release.Name }}-redis'
labels:
component: redis
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "0"
spec:
serviceName: '{{ .Release.Name }}-redis'
replicas: 1
selector:
matchLabels:
component: redis
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: redis
release: '{{ .Release.Name }}'
spec:
containers:
- name: redis
image: '{{ .Values.infrastructure.redis.image }}:{{ .Values.infrastructure.redis.tag }}'
ports:
- name: redis
containerPort: 6379
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'
volumeMounts:
- mountPath: /data
name: redis
livenessProbe:
exec:
command:
- redis-cli ping
periodSeconds: 10
initialDelaySeconds: 10
successThreshold: 1
failureThreshold: 3
volumeClaimTemplates:
- metadata:
name: redis
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: '{{ .Values.persistence.redis.capacity }}'
{{- end -}}

View File

@@ -0,0 +1,28 @@
apiVersion: batch/v1
kind: Job
metadata:
name: '{{ .Release.Name }}-metadata'
labels:
component: metadata
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "2"
"helm.sh/hook-delete-policy": hook-succeeded
spec:
template:
metadata:
labels:
component: metadata
release: '{{ .Release.Name }}'
spec:
restartPolicy: OnFailure
containers:
- name: metadata
image: '{{ .Values.knightcrawler.metadata.image }}{{ if ne .Values.knightcrawler.globalImageTagOverride "" }}:{{ .Values.knightcrawler.globalImageTagOverride }}{{else}}:{{ .Values.knightcrawler.metadata.tag}}{{ end }}'
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'

View File

@@ -0,0 +1,28 @@
apiVersion: batch/v1
kind: Job
metadata:
name: '{{ .Release.Name }}-migrator'
labels:
component: migrator
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "1"
"helm.sh/hook-delete-policy": hook-succeeded
spec:
template:
metadata:
labels:
component: migrator
release: '{{ .Release.Name }}'
spec:
restartPolicy: OnFailure
containers:
- name: migrator
image: '{{ .Values.knightcrawler.migrator.image }}{{ if ne .Values.knightcrawler.globalImageTagOverride "" }}:{{ .Values.knightcrawler.globalImageTagOverride }}{{else}}:{{ .Values.knightcrawler.migrator.tag}}{{ end }}'
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'

View File

@@ -0,0 +1,35 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: '{{ .Release.Name }}-addon'
labels:
component: addon
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "4"
spec:
replicas: {{ .Values.knightcrawler.addon.replicas }}
selector:
matchLabels:
component: addon
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: addon
release: '{{ .Release.Name }}'
spec:
containers:
- name: addon
image: '{{ .Values.knightcrawler.addon.image }}{{ if ne .Values.knightcrawler.globalImageTagOverride "" }}:{{ .Values.knightcrawler.globalImageTagOverride }}{{else}}:{{ .Values.knightcrawler.addon.tag}}{{ end }}'
ports:
- name: addon
containerPort: 7000
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'

View File

@@ -0,0 +1,32 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: '{{ .Release.Name }}-consumer'
labels:
component: consumer
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "4"
spec:
replicas: {{ .Values.knightcrawler.consumer.replicas }}
selector:
matchLabels:
component: consumer
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: consumer
release: '{{ .Release.Name }}'
spec:
containers:
- name: consumer
image: '{{ .Values.knightcrawler.consumer.image }}{{ if ne .Values.knightcrawler.globalImageTagOverride "" }}:{{ .Values.knightcrawler.globalImageTagOverride }}{{else}}:{{ .Values.knightcrawler.consumer.tag}}{{ end }}'
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'

View File

@@ -0,0 +1,31 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: '{{ .Release.Name }}-debridcollector'
labels:
component: debridcollector
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "4"
spec:
replicas: {{ .Values.knightcrawler.debridcollector.replicas }}
selector:
matchLabels:
component: debridcollector
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: debridcollector
release: '{{ .Release.Name }}'
spec:
containers:
- name: debridcollector
image: '{{ .Values.knightcrawler.debridcollector.image }}{{ if ne .Values.knightcrawler.globalImageTagOverride "" }}:{{ .Values.knightcrawler.globalImageTagOverride }}{{else}}:{{ .Values.knightcrawler.debridcollector.tag}}{{ end }}'
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'

View File

@@ -0,0 +1,31 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: '{{ .Release.Name }}-producer'
labels:
component: producer
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "4"
spec:
replicas: {{ .Values.knightcrawler.producer.replicas }}
selector:
matchLabels:
component: producer
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: producer
release: '{{ .Release.Name }}'
spec:
containers:
- name: producer
image: '{{ .Values.knightcrawler.producer.image }}{{ if ne .Values.knightcrawler.globalImageTagOverride "" }}:{{ .Values.knightcrawler.globalImageTagOverride }}{{else}}:{{ .Values.knightcrawler.producer.tag}}{{ end }}'
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'

View File

@@ -0,0 +1,33 @@
{{ if .Values.knightcrawler.qbitcollector.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: '{{ .Release.Name }}-qbitcollector'
labels:
component: qbitcollector
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-weight": "4"
spec:
replicas: {{ .Values.knightcrawler.qbitcollector.replicas }}
selector:
matchLabels:
component: qbitcollector
release: '{{ .Release.Name }}'
template:
metadata:
labels:
component: qbitcollector
release: '{{ .Release.Name }}'
spec:
containers:
- name: qbitcollector
image: '{{ .Values.knightcrawler.qbitcollector.image }}{{ if ne .Values.knightcrawler.globalImageTagOverride "" }}:{{ .Values.knightcrawler.globalImageTagOverride }}{{else}}:{{ .Values.knightcrawler.qbitcollector.tag}}{{ end }}'
envFrom:
- configMapRef:
name: '{{ .Release.Name }}-config'
- secretRef:
name: '{{ .Release.Name }}-secrets'
{{- end -}}

View File

@@ -0,0 +1,17 @@
apiVersion: v1
kind: Service
metadata:
name: '{{ .Release.Name }}-addon'
labels:
component: addon
project: '{{ .Chart.Name }}'
release: '{{ .Release.Name }}'
spec:
selector:
component: addon
release: '{{ .Release.Name }}'
type: ClusterIP
ports:
- protocol: TCP
port: 7000
targetPort: 7000

100
deployment/k8s/values.yaml Normal file
View File

@@ -0,0 +1,100 @@
knightcrawler:
debug: false
globalImageTagOverride: ""
addon:
image: "gabisonfire/knightcrawler-addon"
tag: "2.0.17"
replicas: 1
consumer:
image: "gabisonfire/knightcrawler-consumer"
tag: "2.0.17"
replicas: 1
metadata:
image: "gabisonfire/knightcrawler-metadata"
tag: "2.0.17"
replicas: 1
migrator:
image: "gabisonfire/knightcrawler-migrator"
tag: "2.0.17"
replicas: 1
debridcollector:
image: "gabisonfire/knightcrawler-debrid-collector"
tag: "2.0.17"
enabled: true
replicas: 1
qbitcollector:
image: "gabisonfire/knightcrawler-qbit-collector"
tag: "2.0.17"
enabled: false
replicas: 1
producer:
image: "gabisonfire/knightcrawler-producer"
tag: "2.0.17"
replicas: 1
infrastructure:
lavinmq:
image: "cloudamqp/lavinmq"
tag: "latest"
enabled: true
postgres:
image: "postgres"
tag: "latest"
enabled: true
redis:
image: "redis/redis-stack-server"
tag: "latest"
enabled: true
qbittorrent:
image: "lscr.io/linuxserver/qbittorrent"
tag: "latest"
environment:
redis:
external: false
host: ""
port: "6379"
extra: "abortConnect=false,allowAdmin=true"
postgres:
external: false
host: ""
port: "5432"
dbName: "knightcrawler"
user: "postgres"
password: "postgres"
lavinmq:
external: false
host: ""
user: "guest"
password: "guest"
qbitcollector:
qbitHost: "http://qbittorrent:8080"
trackersUrl: "https://raw.githubusercontent.com/ngosang/trackerslist/master/trackers_all_http.txt"
debridcollector:
realDebridApiKey: ""
producer:
githubPat: ""
queueName: "ingested"
durable: true
maxPublishBatchSize: 500
maxQueueSize: 0
publishIntervalSeconds: 10
metadata:
insertBatchSize: 50000
qbittorrent:
pgid: "1000"
puid: "1000"
torrentingPort: "6881"
webuiPort: "8080"
persistence:
storageClassName: ""
redis:
capacity: 1Gi
postgres:
capacity: 1Gi
lavinmq:
capacity: 1Gi
shared:
timezone: "London/Europe"

View File

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

View File

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

View File

@@ -3,7 +3,6 @@ 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';
@@ -33,7 +32,6 @@ 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))

View File

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

View File

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

View File

@@ -17,6 +17,7 @@
<PackageReference Include="Microsoft.Extensions.Http" Version="8.0.0" />
<PackageReference Include="Microsoft.Extensions.Http.Polly" Version="8.0.3" />
<PackageReference Include="Polly" Version="8.3.1" />
<PackageReference Include="PromKnight.ParseTorrentTitle" Version="1.0.4" />
<PackageReference Include="Serilog" Version="3.1.1" />
<PackageReference Include="Serilog.AspNetCore" Version="8.0.1" />
<PackageReference Include="Serilog.Sinks.Console" Version="5.0.1" />
@@ -28,30 +29,10 @@
<None Include="Configuration\logging.json">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
<None Update="requirements.txt">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
<Content Remove="eng\**" />
<None Remove="eng\**" />
</ItemGroup>
<ItemGroup Condition="'$(Configuration)' == 'Debug'">
<Content Remove="python\**" />
<None Include="python\**">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\shared\SharedContracts.csproj" />
</ItemGroup>
<ItemGroup>
<Compile Remove="eng\**" />
</ItemGroup>
<ItemGroup>
<EmbeddedResource Remove="eng\**" />
</ItemGroup>
</Project>

View File

@@ -6,12 +6,6 @@ Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "SharedContracts", "..\share
EndProject
Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "shared", "shared", "{2C0A0F53-28E6-404F-9EFE-DADFBEF8338B}"
EndProject
Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "eng", "eng", "{72A042C3-B4F3-45C5-AC20-041FE8F41EFC}"
ProjectSection(SolutionItems) = preProject
eng\install-python-reqs.ps1 = eng\install-python-reqs.ps1
eng\install-python-reqs.sh = eng\install-python-reqs.sh
EndProjectSection
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|Any CPU = Debug|Any CPU

View File

@@ -9,23 +9,12 @@ RUN dotnet restore -a $TARGETARCH
RUN dotnet publish -c Release --no-restore -o /src/out -a $TARGETARCH
FROM mcr.microsoft.com/dotnet/aspnet:8.0-alpine3.19
FROM mcr.microsoft.com/dotnet/aspnet:8.0-alpine
WORKDIR /app
ENV PYTHONUNBUFFERED=1
RUN apk add --update --no-cache python3=~3.11 py3-pip && ln -sf python3 /usr/bin/python
COPY --from=build /src/out .
RUN rm -rf /app/python && mkdir -p /app/python
RUN pip3 install -r /app/requirements.txt -t /app/python
RUN addgroup -S debrid && adduser -S -G debrid debrid
USER debrid
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
CMD pgrep -f dotnet || exit 1
ENV PYTHONNET_PYDLL=/usr/lib/libpython3.11.so.1.0
ENTRYPOINT ["dotnet", "DebridCollector.dll"]

View File

@@ -1,3 +1,5 @@
using DebridCollector.Features.Configuration;
namespace DebridCollector.Extensions;
public static class ServiceCollectionExtensions
@@ -15,8 +17,7 @@ public static class ServiceCollectionExtensions
var serviceConfiguration = services.LoadConfigurationFromEnv<DebridCollectorConfiguration>();
services.AddRealDebridClient(serviceConfiguration);
services.RegisterPythonEngine();
services.AddSingleton<IRankTorrentName, RankTorrentName>();
services.AddSingleton<IParseTorrentTitle, ParseTorrentTitle>();
services.AddHostedService<DebridRequestProcessor>();
return services;

View File

@@ -1,4 +1,6 @@
namespace DebridCollector.Features.Debrid;
using DebridCollector.Features.Configuration;
namespace DebridCollector.Features.Debrid;
public static class ServiceCollectionExtensions
{

View File

@@ -3,11 +3,10 @@ namespace DebridCollector.Features.Worker;
public static class DebridMetaToTorrentMeta
{
public static IReadOnlyList<TorrentFile> MapMetadataToFilesCollection(
IRankTorrentName rankTorrentName,
IParseTorrentTitle torrentTitle,
Torrent torrent,
string ImdbId,
FileDataDictionary Metadata,
ILogger<WriteMetadataConsumer> logger)
FileDataDictionary Metadata)
{
try
{
@@ -16,42 +15,34 @@ public static class DebridMetaToTorrentMeta
foreach (var metadataEntry in Metadata.Where(m => Filetypes.VideoFileExtensions.Any(ext => m.Value.Filename.EndsWith(ext))))
{
var validFileIndex = int.TryParse(metadataEntry.Key, out var fileIndex);
var fileIndexMinusOne = Math.Max(0, fileIndex - 1);
var file = new TorrentFile
{
ImdbId = ImdbId,
KitsuId = 0,
InfoHash = torrent.InfoHash,
FileIndex = validFileIndex ? fileIndexMinusOne : 0,
FileIndex = validFileIndex ? fileIndex : 0,
Title = metadataEntry.Value.Filename,
Size = metadataEntry.Value.Filesize.GetValueOrDefault(),
};
var parsedTitle = rankTorrentName.Parse(file.Title, false);
var parsedTitle = torrentTitle.Parse(file.Title);
if (!parsedTitle.Success)
{
logger.LogWarning("Failed to parse title {Title} for metadata mapping", file.Title);
continue;
}
file.ImdbSeason = parsedTitle.Response?.Season?.FirstOrDefault() ?? 0;
file.ImdbEpisode = parsedTitle.Response?.Episode?.FirstOrDefault() ?? 0;
file.ImdbSeason = parsedTitle.Seasons.FirstOrDefault();
file.ImdbEpisode = parsedTitle.Episodes.FirstOrDefault();
files.Add(file);
}
return files;
}
catch (Exception ex)
catch (Exception)
{
logger.LogWarning("Failed to map metadata to files collection: {Exception}", ex.Message);
return [];
}
}
public static async Task<IReadOnlyList<SubtitleFile>> MapMetadataToSubtitlesCollection(IDataStorage storage, string InfoHash, FileDataDictionary Metadata, ILogger<WriteMetadataConsumer> logger)
public static async Task<IReadOnlyList<SubtitleFile>> MapMetadataToSubtitlesCollection(IDataStorage storage, string InfoHash, FileDataDictionary Metadata)
{
try
{
@@ -67,14 +58,13 @@ public static class DebridMetaToTorrentMeta
foreach (var metadataEntry in Metadata.Where(m => Filetypes.SubtitleFileExtensions.Any(ext => m.Value.Filename.EndsWith(ext))))
{
var validFileIndex = int.TryParse(metadataEntry.Key, out var fileIndex);
var fileIndexMinusOne = Math.Max(0, fileIndex - 1);
var fileId = torrentFiles.FirstOrDefault(
t => Path.GetFileNameWithoutExtension(t.Title) == Path.GetFileNameWithoutExtension(metadataEntry.Value.Filename))?.Id ?? 0;
var file = new SubtitleFile
{
InfoHash = InfoHash,
FileIndex = validFileIndex ? fileIndexMinusOne : 0,
FileIndex = validFileIndex ? fileIndex : 0,
FileId = fileId,
Title = metadataEntry.Value.Filename,
};
@@ -84,9 +74,8 @@ public static class DebridMetaToTorrentMeta
return files;
}
catch (Exception ex)
catch (Exception)
{
logger.LogWarning("Failed to map metadata to subtitles collection: {Exception}", ex.Message);
return [];
}
}

View File

@@ -53,12 +53,6 @@ public class InfohashMetadataSagaStateMachine : MassTransitStateMachine<Infohash
.Then(
context =>
{
if (!context.Message.WithFiles)
{
logger.LogInformation("No files written for torrent {InfoHash} in Saga {SagaId}", context.Saga.Torrent.InfoHash, context.Saga.CorrelationId);
return;
}
logger.LogInformation("Metadata Written for torrent {InfoHash} in Saga {SagaId}", context.Saga.Torrent.InfoHash, context.Saga.CorrelationId);
})
.TransitionTo(Completed)

View File

@@ -16,7 +16,7 @@ public record WriteMetadata(Torrent Torrent, TorrentMetadataResponse Metadata, s
}
[EntityName("metadata-written-debrid-colloctor")]
public record MetadataWritten(TorrentMetadataResponse Metadata, bool WithFiles) : CorrelatedBy<Guid>
public record MetadataWritten(TorrentMetadataResponse Metadata) : CorrelatedBy<Guid>
{
public Guid CorrelationId { get; init; } = Metadata.CorrelationId;
}

View File

@@ -1,28 +1,25 @@
namespace DebridCollector.Features.Worker;
public class WriteMetadataConsumer(IRankTorrentName rankTorrentName, IDataStorage dataStorage, ILogger<WriteMetadataConsumer> logger) : IConsumer<WriteMetadata>
public class WriteMetadataConsumer(IParseTorrentTitle parseTorrentTitle, IDataStorage dataStorage) : IConsumer<WriteMetadata>
{
public async Task Consume(ConsumeContext<WriteMetadata> context)
{
var request = context.Message;
var torrentFiles = DebridMetaToTorrentMeta.MapMetadataToFilesCollection(rankTorrentName, request.Torrent, request.ImdbId, request.Metadata.Metadata, logger);
var torrentFiles = DebridMetaToTorrentMeta.MapMetadataToFilesCollection(parseTorrentTitle, request.Torrent, request.ImdbId, request.Metadata.Metadata);
if (!torrentFiles.Any())
if (torrentFiles.Any())
{
await context.Publish(new MetadataWritten(request.Metadata, false));
return;
await dataStorage.InsertFiles(torrentFiles);
var subtitles = await DebridMetaToTorrentMeta.MapMetadataToSubtitlesCollection(dataStorage, request.Torrent.InfoHash, request.Metadata.Metadata);
if (subtitles.Any())
{
await dataStorage.InsertSubtitles(subtitles);
}
}
await dataStorage.InsertFiles(torrentFiles);
var subtitles = await DebridMetaToTorrentMeta.MapMetadataToSubtitlesCollection(dataStorage, request.Torrent.InfoHash, request.Metadata.Metadata, logger);
if (subtitles.Any())
{
await dataStorage.InsertSubtitles(subtitles);
}
await context.Publish(new MetadataWritten(request.Metadata, true));
await context.Publish(new MetadataWritten(request.Metadata));
}
}

View File

@@ -4,18 +4,17 @@ global using System.Text.Json;
global using System.Text.Json.Serialization;
global using System.Threading.Channels;
global using DebridCollector.Extensions;
global using DebridCollector.Features.Configuration;
global using DebridCollector.Features.Debrid;
global using DebridCollector.Features.Worker;
global using MassTransit;
global using MassTransit.Mediator;
global using Microsoft.AspNetCore.Builder;
global using Microsoft.Extensions.DependencyInjection;
global using Polly;
global using Polly.Extensions.Http;
global using PromKnight.ParseTorrentTitle;
global using SharedContracts.Configuration;
global using SharedContracts.Dapper;
global using SharedContracts.Extensions;
global using SharedContracts.Models;
global using SharedContracts.Python;
global using SharedContracts.Python.RTN;
global using SharedContracts.Requests;

View File

@@ -1,2 +0,0 @@
mkdir -p ../python
python -m pip install -r ../requirements.txt -t ../python/

View File

@@ -1,5 +0,0 @@
#!/bin/bash
rm -rf ../python
mkdir -p ../python
python3 -m pip install -r ../requirements.txt -t ../python/

View File

@@ -1 +0,0 @@
rank-torrent-name==0.2.13

View File

@@ -8,14 +8,12 @@ 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};CommandTimeout={CommandTimeout}";
public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};";
}

View File

@@ -134,7 +134,7 @@ public class ImdbDbService(PostgresConfiguration configuration, ILogger<ImdbDbSe
{
try
{
await using var connection = new NpgsqlConnection(configuration.StorageConnectionString);
await using var connection = CreateNpgsqlConnection();
await connection.OpenAsync();
await operation(connection);
@@ -145,6 +145,16 @@ 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

View File

@@ -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="8.0.3" />
<PackageReference Include="Npgsql" Version="8.0.2" />
<PackageReference Include="Serilog" Version="3.1.1" />
<PackageReference Include="Serilog.AspNetCore" Version="8.0.1" />
<PackageReference Include="Serilog.Sinks.Console" Version="5.0.1" />

View File

@@ -1,43 +0,0 @@
-- 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 $$
BEGIN
IF NOT EXISTS (
SELECT 1
FROM pg_constraint
WHERE conname = 'subtitles_unique_infohash_fileindex'
) THEN
ALTER TABLE public.subtitles
ADD CONSTRAINT subtitles_unique_infohash_fileindex UNIQUE ("infoHash", "fileIndex");
END IF;
END $$;

View File

@@ -4,38 +4,31 @@
{
"Name": "SyncEzTvJob",
"IntervalSeconds": 60,
"Enabled": true,
"Url": "https://eztvx.to/ezrss.xml",
"XmlNamespace": "http://xmlns.ezrss.it/0.1/"
"Enabled": true
},
{
"Name": "SyncNyaaJob",
"IntervalSeconds": 60,
"Enabled": true,
"Url": "https://nyaa.si/?page=rss&c=1_2&f=0",
"XmlNamespace": "https://nyaa.si/xmlns/nyaa"
"Enabled": true
},
{
"Name": "SyncTpbJob",
"IntervalSeconds": 60,
"Enabled": true,
"Url": "https://apibay.org/precompiled/data_top100_recent.json"
"Enabled": true
},
{
"Name": "SyncYtsJob",
"IntervalSeconds": 60,
"Enabled": true,
"Url": "https://yts.am/rss"
"Enabled": true
},
{
"Name": "SyncTgxJob",
"IntervalSeconds": 60,
"Enabled": true,
"Url": "https://tgx.rs/rss"
"Enabled": true
},
{
"Name": "SyncDmmJob",
"IntervalSeconds": 10800,
"IntervalSeconds": 1800,
"Enabled": true
},
{

View File

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

View File

@@ -6,12 +6,6 @@ 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");

View File

@@ -4,12 +4,6 @@ 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);

View File

@@ -7,8 +7,4 @@ 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; }
}

View File

@@ -1,70 +0,0 @@
namespace Producer.Features.Crawlers.Dmm;
public class DMMFileDownloader(HttpClient client, ILogger<DMMFileDownloader> logger) : IDMMFileDownloader
{
private const string Filename = "main.zip";
private readonly IReadOnlyCollection<string> _filesToIgnore = [
"index.html",
"404.html",
"dedupe.sh",
"CNAME",
];
public const string ClientName = "DmmFileDownloader";
public async Task<string> DownloadFileToTempPath(CancellationToken cancellationToken)
{
logger.LogInformation("Downloading DMM Hashlists");
var response = await client.GetAsync(Filename, cancellationToken);
var tempDirectory = Path.Combine(Path.GetTempPath(), "DMMHashlists");
EnsureDirectoryIsClean(tempDirectory);
response.EnsureSuccessStatusCode();
await using var stream = await response.Content.ReadAsStreamAsync(cancellationToken);
using var archive = new ZipArchive(stream);
logger.LogInformation("Extracting DMM Hashlists to {TempDirectory}", tempDirectory);
foreach (var entry in archive.Entries)
{
var entryPath = Path.Combine(tempDirectory, Path.GetFileName(entry.FullName));
if (!entry.FullName.EndsWith('/')) // It's a file
{
entry.ExtractToFile(entryPath, true);
}
}
foreach (var file in _filesToIgnore)
{
CleanRepoExtras(tempDirectory, file);
}
logger.LogInformation("Downloaded and extracted Repository to {TempDirectory}", tempDirectory);
return tempDirectory;
}
private static void CleanRepoExtras(string tempDirectory, string fileName)
{
var repoIndex = Path.Combine(tempDirectory, fileName);
if (File.Exists(repoIndex))
{
File.Delete(repoIndex);
}
}
private static void EnsureDirectoryIsClean(string tempDirectory)
{
if (Directory.Exists(tempDirectory))
{
Directory.Delete(tempDirectory, true);
}
Directory.CreateDirectory(tempDirectory);
}
}

View File

@@ -1,6 +0,0 @@
namespace Producer.Features.Crawlers.Dmm;
public class DMMHttpClient
{
}

View File

@@ -1,99 +1,64 @@
namespace Producer.Features.Crawlers.Dmm;
public partial class DebridMediaManagerCrawler(
IDMMFileDownloader dmmFileDownloader,
IHttpClientFactory httpClientFactory,
ILogger<DebridMediaManagerCrawler> logger,
IDataStorage storage,
GithubConfiguration githubConfiguration,
IRankTorrentName rankTorrentName,
IDistributedCache cache) : BaseCrawler(logger, storage)
{
[GeneratedRegex("""<iframe src="https:\/\/debridmediamanager.com\/hashlist#(.*)"></iframe>""")]
private static partial Regex HashCollectionMatcher();
protected override string Url => "";
private const string DownloadBaseUrl = "https://raw.githubusercontent.com/debridmediamanager/hashlists/main";
protected override IReadOnlyDictionary<string, string> Mappings => new Dictionary<string, string>();
protected override string Url => "https://api.github.com/repos/debridmediamanager/hashlists/git/trees/main?recursive=1";
protected override string Source => "DMM";
private const int ParallelismCount = 4;
public override async Task Execute()
{
var tempDirectory = await dmmFileDownloader.DownloadFileToTempPath(CancellationToken.None);
var client = httpClientFactory.CreateClient("Scraper");
client.DefaultRequestHeaders.Authorization = new("Bearer", githubConfiguration.PAT);
client.DefaultRequestHeaders.UserAgent.ParseAdd("curl");
var files = Directory.GetFiles(tempDirectory, "*.html", SearchOption.AllDirectories);
var jsonBody = await client.GetStringAsync(Url);
logger.LogInformation("Found {Files} files to parse", files.Length);
var json = JsonDocument.Parse(jsonBody);
var options = new ParallelOptions { MaxDegreeOfParallelism = ParallelismCount };
var entriesArray = json.RootElement.GetProperty("tree");
await Parallel.ForEachAsync(files, options, async (file, token) =>
logger.LogInformation("Found {Entries} total DMM pages", entriesArray.GetArrayLength());
foreach (var entry in entriesArray.EnumerateArray())
{
var fileName = Path.GetFileName(file);
var torrentDictionary = await ExtractPageContents(file, fileName);
if (torrentDictionary == null)
{
return;
}
await ParseTitlesWithRtn(fileName, torrentDictionary);
var results = await ParseTorrents(torrentDictionary);
if (results.Count <= 0)
{
return;
}
await InsertTorrents(results);
await Storage.MarkPageAsIngested(fileName, token);
});
await ParsePage(entry, client);
}
}
private async Task ParseTitlesWithRtn(string fileName, IDictionary<string, DmmContent> page)
private async Task ParsePage(JsonElement entry, HttpClient client)
{
logger.LogInformation("Parsing titles for {Page}", fileName);
var (pageIngested, name) = await IsAlreadyIngested(entry);
var batchProcessables = page.Select(value => new RtnBatchProcessable(value.Key, value.Value.Filename)).ToList();
var parsedResponses = rankTorrentName.BatchParse(
batchProcessables.Select<RtnBatchProcessable, string>(bp => bp.Filename).ToList(), trashGarbage: false);
// Filter out unsuccessful responses and match RawTitle to requesting title
var successfulResponses = parsedResponses
.Where(response => response != null && response.Success)
.GroupBy(response => response.Response.RawTitle!)
.ToDictionary(group => group.Key, group => group.First());
var options = new ParallelOptions { MaxDegreeOfParallelism = ParallelismCount };
await Parallel.ForEachAsync(batchProcessables.Select(t => t.InfoHash), options, (infoHash, _) =>
if (string.IsNullOrEmpty(name) || pageIngested)
{
if (page.TryGetValue(infoHash, out var dmmContent) &&
successfulResponses.TryGetValue(dmmContent.Filename, out var parsedResponse))
{
page[infoHash] = dmmContent with { ParseResponse = parsedResponse };
}
return ValueTask.CompletedTask;
});
}
private async Task<ConcurrentDictionary<string, DmmContent>?> ExtractPageContents(string filePath, string filenameOnly)
{
var (pageIngested, name) = await IsAlreadyIngested(filenameOnly);
if (pageIngested)
{
return [];
return;
}
var pageSource = await File.ReadAllTextAsync(filePath);
var pageSource = await client.GetStringAsync($"{DownloadBaseUrl}/{name}");
await ExtractPageContents(pageSource, name);
}
private async Task ExtractPageContents(string pageSource, string name)
{
var match = HashCollectionMatcher().Match(pageSource);
if (!match.Success)
{
logger.LogWarning("Failed to match hash collection for {Name}", name);
await Storage.MarkPageAsIngested(filenameOnly);
return [];
await Storage.MarkPageAsIngested(name);
return;
}
var encodedJson = match.Groups.Values.ElementAtOrDefault(1);
@@ -101,165 +66,34 @@ public partial class DebridMediaManagerCrawler(
if (string.IsNullOrEmpty(encodedJson?.Value))
{
logger.LogWarning("Failed to extract encoded json for {Name}", name);
return [];
return;
}
var decodedJson = LZString.DecompressFromEncodedURIComponent(encodedJson.Value);
await ProcessExtractedContentsAsTorrentCollection(encodedJson.Value, name);
}
JsonElement arrayToProcess;
try
{
var json = JsonDocument.Parse(decodedJson);
private async Task ProcessExtractedContentsAsTorrentCollection(string encodedJson, string name)
{
var decodedJson = LZString.DecompressFromEncodedURIComponent(encodedJson);
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)
var json = JsonDocument.Parse(decodedJson);
await InsertTorrentsForPage(json);
var result = await Storage.MarkPageAsIngested(name);
if (!result.IsSuccess)
{
logger.LogError("Failed to parse JSON {decodedJson} for {Name}: {Exception}", decodedJson, name, ex);
return [];
logger.LogWarning("Failed to mark page as ingested: [{Error}]", result.Failure.ErrorMessage);
return;
}
var torrents = await arrayToProcess.EnumerateArray()
.ToAsyncEnumerable()
.Select(ParsePageContent)
.Where(t => t is not null)
.ToListAsync();
if (torrents.Count == 0)
{
logger.LogWarning("No torrents found in {Name}", name);
await Storage.MarkPageAsIngested(filenameOnly);
return [];
}
var torrentDictionary = torrents
.Where(x => x is not null)
.GroupBy(x => x.InfoHash)
.ToConcurrentDictionary(g => g.Key, g => new DmmContent(g.First().Filename, g.First().Bytes, null));
logger.LogInformation("Parsed {Torrents} torrents for {Name}", torrentDictionary.Count, name);
return torrentDictionary;
logger.LogInformation("Successfully marked page as ingested");
}
private async Task<List<IngestedTorrent>> ParseTorrents(IDictionary<string, DmmContent> page)
private async Task<IngestedTorrent?> ParseTorrent(JsonElement item)
{
var ingestedTorrents = new List<IngestedTorrent>();
var options = new ParallelOptions { MaxDegreeOfParallelism = ParallelismCount };
await Parallel.ForEachAsync(page, options, async (kvp, ct) =>
{
var (infoHash, dmmContent) = kvp;
var parsedTorrent = dmmContent.ParseResponse;
if (parsedTorrent is not { Success: true })
{
return;
}
var torrentType = parsedTorrent.Response.IsMovie ? "movie" : "tvSeries";
var cacheKey = GetCacheKey(torrentType, parsedTorrent.Response.ParsedTitle, parsedTorrent.Response.Year);
var (cached, cachedResult) = await CheckIfInCacheAndReturn(cacheKey);
if (cached)
{
logger.LogInformation("[{ImdbId}] Found cached imdb result for {Title}", cachedResult.ImdbId, parsedTorrent.Response.ParsedTitle);
lock (ingestedTorrents)
{
ingestedTorrents.Add(MapToTorrent(cachedResult, dmmContent.Bytes, infoHash, parsedTorrent));
}
return;
}
int? year = parsedTorrent.Response.Year != 0 ? parsedTorrent.Response.Year : null;
var imdbEntry = await Storage.FindImdbMetadata(parsedTorrent.Response.ParsedTitle, torrentType, year, ct);
if (imdbEntry is null)
{
return;
}
await AddToCache(cacheKey, imdbEntry);
logger.LogInformation("[{ImdbId}] Found best match for {Title}: {BestMatch} with score {Score}", imdbEntry.ImdbId, parsedTorrent.Response.ParsedTitle, imdbEntry.Title, imdbEntry.Score);
lock (ingestedTorrents)
{
ingestedTorrents.Add(MapToTorrent(imdbEntry, dmmContent.Bytes, infoHash, parsedTorrent));
}
});
return ingestedTorrents;
}
private IngestedTorrent MapToTorrent(ImdbEntry result, long size, string infoHash, ParseTorrentTitleResponse parsedTorrent) =>
new()
{
Source = Source,
Name = result.Title,
Imdb = result.ImdbId,
Size = size.ToString(),
InfoHash = infoHash,
Seeders = 0,
Leechers = 0,
Category = AssignCategory(result),
RtnResponse = parsedTorrent.Response.ToJson(),
};
private Task AddToCache(string cacheKey, ImdbEntry best)
{
var cacheOptions = new DistributedCacheEntryOptions
{
AbsoluteExpirationRelativeToNow = TimeSpan.FromDays(1),
};
return cache.SetStringAsync(cacheKey, JsonSerializer.Serialize(best), cacheOptions);
}
private async Task<(bool Success, ImdbEntry? Entry)> CheckIfInCacheAndReturn(string cacheKey)
{
var cachedImdbId = await cache.GetStringAsync(cacheKey);
if (!string.IsNullOrEmpty(cachedImdbId))
{
return (true, JsonSerializer.Deserialize<ImdbEntry>(cachedImdbId));
}
return (false, null);
}
private async Task<(bool Success, string? Name)> IsAlreadyIngested(string filename)
{
var pageIngested = await Storage.PageIngested(filename);
return (pageIngested, filename);
}
private static string AssignCategory(ImdbEntry entry) =>
entry.Category.ToLower() switch
{
var category when string.Equals(category, "movie", StringComparison.OrdinalIgnoreCase) => "movies",
var category when string.Equals(category, "tvSeries", StringComparison.OrdinalIgnoreCase) => "tv",
_ => "unknown",
};
private static string GetCacheKey(string category, string title, int year) => $"{category.ToLowerInvariant()}:{year}:{title.ToLowerInvariant()}";
private static ExtractedDMMContent? ParsePageContent(JsonElement item)
{
if (!item.TryGetProperty("filename", out var filenameElement) ||
!item.TryGetProperty("bytes", out var bytesElement) ||
!item.TryGetProperty("hash", out var hashElement))
@@ -267,10 +101,122 @@ public partial class DebridMediaManagerCrawler(
return null;
}
return new(filenameElement.GetString(), bytesElement.GetInt64(), hashElement.GetString());
var torrentTitle = filenameElement.GetString();
if (torrentTitle.IsNullOrEmpty())
{
return null;
}
var parsedTorrent = rankTorrentName.Parse(torrentTitle);
if (!parsedTorrent.Success)
{
return null;
}
var torrentType = parsedTorrent.Response.IsMovie ? "movie" : "tvSeries";
var cacheKey = GetCacheKey(torrentType, parsedTorrent.Response.ParsedTitle, parsedTorrent.Response.Year);
var (cached, cachedResult) = await CheckIfInCacheAndReturn(cacheKey);
if (cached)
{
logger.LogInformation("[{ImdbId}] Found cached imdb result for {Title}", cachedResult.ImdbId, parsedTorrent.Response.ParsedTitle);
return MapToTorrent(cachedResult, bytesElement, hashElement, parsedTorrent);
}
int? year = parsedTorrent.Response.Year != 0 ? parsedTorrent.Response.Year : null;
var imdbEntry = await Storage.FindImdbMetadata(parsedTorrent.Response.ParsedTitle, torrentType, year);
if (imdbEntry is null)
{
return null;
}
await AddToCache(cacheKey, imdbEntry);
logger.LogInformation("[{ImdbId}] Found best match for {Title}: {BestMatch} with score {Score}", imdbEntry.ImdbId, parsedTorrent.Response.ParsedTitle, imdbEntry.Title, imdbEntry.Score);
return MapToTorrent(imdbEntry, bytesElement, hashElement, parsedTorrent);
}
private record DmmContent(string Filename, long Bytes, ParseTorrentTitleResponse? ParseResponse);
private record ExtractedDMMContent(string Filename, long Bytes, string InfoHash);
private record RtnBatchProcessable(string InfoHash, string Filename);
private IngestedTorrent MapToTorrent(ImdbEntry result, JsonElement bytesElement, JsonElement hashElement, ParseTorrentTitleResponse parsedTorrent) =>
new()
{
Source = Source,
Name = result.Title,
Imdb = result.ImdbId,
Size = bytesElement.GetInt64().ToString(),
InfoHash = hashElement.ToString(),
Seeders = 0,
Leechers = 0,
Category = AssignCategory(result),
RtnResponse = parsedTorrent.Response.ToJson(),
};
private Task AddToCache(string cacheKey, ImdbEntry best)
{
var cacheOptions = new DistributedCacheEntryOptions
{
AbsoluteExpirationRelativeToNow = TimeSpan.FromDays(1),
};
return cache.SetStringAsync(cacheKey, JsonSerializer.Serialize(best), cacheOptions);
}
private async Task<(bool Success, ImdbEntry? Entry)> CheckIfInCacheAndReturn(string cacheKey)
{
var cachedImdbId = await cache.GetStringAsync(cacheKey);
if (!string.IsNullOrEmpty(cachedImdbId))
{
return (true, JsonSerializer.Deserialize<ImdbEntry>(cachedImdbId));
}
return (false, null);
}
private async Task InsertTorrentsForPage(JsonDocument json)
{
var torrents = await json.RootElement.EnumerateArray()
.ToAsyncEnumerable()
.SelectAwait(async x => await ParseTorrent(x))
.Where(t => t is not null)
.ToListAsync();
if (torrents.Count == 0)
{
logger.LogWarning("No torrents found in {Source} response", Source);
return;
}
await InsertTorrents(torrents!);
}
private async Task<(bool Success, string? Name)> IsAlreadyIngested(JsonElement entry)
{
var name = entry.GetProperty("path").GetString();
if (string.IsNullOrEmpty(name))
{
return (false, null);
}
var pageIngested = await Storage.PageIngested(name);
return (pageIngested, name);
}
private static string AssignCategory(ImdbEntry entry) =>
entry.Category.ToLower() switch
{
var category when string.Equals(category, "movie", StringComparison.OrdinalIgnoreCase) => "movies",
var category when string.Equals(category, "tvSeries", StringComparison.OrdinalIgnoreCase) => "tv",
_ => "unknown",
};
private static string GetCacheKey(string category, string title, int year) => $"{category.ToLowerInvariant()}:{year}:{title.ToLowerInvariant()}";
}

View File

@@ -0,0 +1,9 @@
namespace Producer.Features.Crawlers.Dmm;
public class GithubConfiguration
{
private const string Prefix = "GITHUB";
private const string PatVariable = "PAT";
public string? PAT { get; init; } = Prefix.GetOptionalEnvironmentVariableAsString(PatVariable);
}

View File

@@ -1,6 +0,0 @@
namespace Producer.Features.Crawlers.Dmm;
public interface IDMMFileDownloader
{
Task<string> DownloadFileToTempPath(CancellationToken cancellationToken);
}

View File

@@ -1,17 +0,0 @@
namespace Producer.Features.Crawlers.Dmm;
public static class ServiceCollectionExtensions
{
public static IServiceCollection AddDmmSupport(this IServiceCollection services)
{
services.AddHttpClient<IDMMFileDownloader, DMMFileDownloader>(DMMFileDownloader.ClientName, client =>
{
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;
}
}

View File

@@ -1,10 +1,11 @@
namespace Producer.Features.Crawlers.EzTv;
public class EzTvCrawler(IHttpClientFactory httpClientFactory, ILogger<EzTvCrawler> logger, IDataStorage storage, ScrapeConfiguration scrapeConfiguration) : BaseXmlCrawler(httpClientFactory, logger, storage)
public class EzTvCrawler(IHttpClientFactory httpClientFactory, ILogger<EzTvCrawler> logger, IDataStorage storage) : BaseXmlCrawler(httpClientFactory, logger, storage)
{
protected override string Url => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncEzTvJob", StringComparison.OrdinalIgnoreCase))?.Url ?? string.Empty;
protected override string Url => "https://eztv1.xyz/ezrss.xml";
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>

View File

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

View File

@@ -1,13 +1,13 @@
namespace Producer.Features.Crawlers.Tgx;
public partial class TgxCrawler(IHttpClientFactory httpClientFactory, ILogger<TgxCrawler> logger, IDataStorage storage, ScrapeConfiguration scrapeConfiguration) : BaseXmlCrawler(httpClientFactory, logger, storage)
public partial class TgxCrawler(IHttpClientFactory httpClientFactory, ILogger<TgxCrawler> logger, IDataStorage storage) : 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 => scrapeConfiguration.Scrapers.FirstOrDefault(x => x.Name.Equals("SyncTgxJob", StringComparison.OrdinalIgnoreCase))?.Url ?? string.Empty;
protected override string Url => "https://tgx.rs/rss";
protected override string Source => "TorrentGalaxy";
protected override IReadOnlyDictionary<string, string> Mappings

View File

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

View File

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

View File

@@ -5,6 +5,7 @@ internal static class ServiceCollectionExtensions
internal static IServiceCollection AddQuartz(this IServiceCollection services, IConfiguration configuration)
{
var scrapeConfiguration = services.LoadConfigurationFromConfig<ScrapeConfiguration>(configuration, ScrapeConfiguration.SectionName);
var githubConfiguration = services.LoadConfigurationFromEnv<GithubConfiguration>();
var rabbitConfiguration = services.LoadConfigurationFromEnv<RabbitMqConfiguration>();
var jobTypes = Assembly.GetAssembly(typeof(BaseJob))
@@ -18,13 +19,18 @@ internal static class ServiceCollectionExtensions
services.AddTransient(type);
}
if (!string.IsNullOrEmpty(githubConfiguration.PAT))
{
services.AddTransient<SyncDmmJob>();
}
var openMethod = typeof(ServiceCollectionExtensions).GetMethod(nameof(AddJobWithTrigger), BindingFlags.NonPublic | BindingFlags.Static | BindingFlags.Instance);
services.AddQuartz(
quartz =>
{
RegisterAutomaticRegistrationJobs(jobTypes, openMethod, quartz, scrapeConfiguration);
RegisterDmmJob(quartz, scrapeConfiguration);
RegisterDmmJob(githubConfiguration, quartz, scrapeConfiguration);
RegisterTorrentioJob(services, quartz, configuration, scrapeConfiguration);
RegisterPublisher(quartz, rabbitConfiguration);
});
@@ -58,8 +64,13 @@ internal static class ServiceCollectionExtensions
}
}
private static void RegisterDmmJob(IServiceCollectionQuartzConfigurator quartz, ScrapeConfiguration scrapeConfiguration) =>
AddJobWithTrigger<SyncDmmJob>(quartz, SyncDmmJob.Key, SyncDmmJob.Trigger, scrapeConfiguration);
private static void RegisterDmmJob(GithubConfiguration githubConfiguration, IServiceCollectionQuartzConfigurator quartz, ScrapeConfiguration scrapeConfiguration)
{
if (!string.IsNullOrEmpty(githubConfiguration.PAT))
{
AddJobWithTrigger<SyncDmmJob>(quartz, SyncDmmJob.Key, SyncDmmJob.Trigger, scrapeConfiguration);
}
}
private static void RegisterTorrentioJob(
IServiceCollection services,

View File

@@ -1,12 +1,12 @@
// Global using directives
global using System.Collections.Concurrent;
global using System.IO.Compression;
global using System.Reflection;
global using System.Text;
global using System.Text.Json;
global using System.Text.RegularExpressions;
global using System.Xml.Linq;
global using FuzzySharp;
global using FuzzySharp.Extractor;
global using FuzzySharp.PreProcess;
global using FuzzySharp.SimilarityRatio.Scorer;
global using FuzzySharp.SimilarityRatio.Scorer.StrategySensitive;

View File

@@ -12,8 +12,7 @@ builder.Services
.RegisterMassTransit()
.AddDataStorage()
.AddCrawlers()
.AddDmmSupport()
.AddQuartz(builder.Configuration);
var app = builder.Build();
app.Run();
app.Run();

View File

@@ -1 +1 @@
rank-torrent-name==0.2.13
rank-torrent-name==0.1.8

View File

@@ -9,23 +9,12 @@ RUN dotnet restore -a $TARGETARCH
RUN dotnet publish -c Release --no-restore -o /src/out -a $TARGETARCH
FROM mcr.microsoft.com/dotnet/aspnet:8.0-alpine3.19
FROM mcr.microsoft.com/dotnet/aspnet:8.0-alpine
WORKDIR /app
ENV PYTHONUNBUFFERED=1
RUN apk add --update --no-cache python3=~3.11 py3-pip && ln -sf python3 /usr/bin/python
COPY --from=build /src/out .
RUN rm -rf /app/python && mkdir -p /app/python
RUN pip3 install -r /app/requirements.txt -t /app/python
RUN addgroup -S qbit && adduser -S -G qbit qbit
USER qbit
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
CMD pgrep -f dotnet || exit 1
ENV PYTHONNET_PYDLL=/usr/lib/libpython3.11.so.1.0
ENTRYPOINT ["dotnet", "QBitCollector.dll"]

View File

@@ -13,8 +13,7 @@ public static class ServiceCollectionExtensions
internal static IServiceCollection AddServiceConfiguration(this IServiceCollection services)
{
services.AddQBitTorrentClient();
services.RegisterPythonEngine();
services.AddSingleton<IRankTorrentName, RankTorrentName>();
services.AddSingleton<IParseTorrentTitle, ParseTorrentTitle>();
services.AddSingleton<QbitRequestProcessor>();
services.AddHttpClient();
services.AddSingleton<ITrackersService, TrackersService>();
@@ -44,7 +43,6 @@ public static class ServiceCollectionExtensions
{
var rabbitConfiguration = services.LoadConfigurationFromEnv<RabbitMqConfiguration>();
var redisConfiguration = services.LoadConfigurationFromEnv<RedisConfiguration>();
var qbitConfiguration = services.LoadConfigurationFromEnv<QbitConfiguration>();
services.AddStackExchangeRedisCache(
option =>
@@ -81,8 +79,8 @@ public static class ServiceCollectionExtensions
e.ConfigureConsumer<WriteQbitMetadataConsumer>(context);
e.ConfigureConsumer<PerformQbitMetadataRequestConsumer>(context);
e.ConfigureSaga<QbitMetadataSagaState>(context);
e.ConcurrentMessageLimit = qbitConfiguration.Concurrency;
e.PrefetchCount = qbitConfiguration.Concurrency;
e.ConcurrentMessageLimit = 5;
e.PrefetchCount = 5;
});
});
});
@@ -99,7 +97,7 @@ public static class ServiceCollectionExtensions
cfg.UseTimeout(
timeout =>
{
timeout.Timeout = TimeSpan.FromMinutes(3);
timeout.Timeout = TimeSpan.FromMinutes(1);
});
})
.RedisRepository(redisConfiguration.ConnectionString, options =>
@@ -111,7 +109,7 @@ public static class ServiceCollectionExtensions
{
var qbitConfiguration = services.LoadConfigurationFromEnv<QbitConfiguration>();
var client = new QBittorrentClient(new(qbitConfiguration.Host));
client.Timeout = TimeSpan.FromSeconds(20);
client.Timeout = TimeSpan.FromSeconds(10);
services.AddSingleton<IQBittorrentClient>(client);
}

View File

@@ -1,6 +1,6 @@
namespace QBitCollector.Features.Qbit;
public class QbitRequestProcessor(IQBittorrentClient client, ITrackersService trackersService, ILogger<QbitRequestProcessor> logger, QbitConfiguration configuration)
public class QbitRequestProcessor(IQBittorrentClient client, ITrackersService trackersService, ILogger<QbitRequestProcessor> logger)
{
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(60));
timeoutCts.CancelAfter(TimeSpan.FromSeconds(30));
try
{
@@ -30,7 +30,7 @@ public class QbitRequestProcessor(IQBittorrentClient client, ITrackersService tr
break;
}
await Task.Delay(TimeSpan.FromMilliseconds(200), timeoutCts.Token);
await Task.Delay(TimeSpan.FromSeconds(1), timeoutCts.Token);
}
}
catch (OperationCanceledException) when (timeoutCts.IsCancellationRequested)

View File

@@ -5,10 +5,7 @@ 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);
}

View File

@@ -3,11 +3,10 @@ namespace QBitCollector.Features.Worker;
public static class QbitMetaToTorrentMeta
{
public static IReadOnlyList<TorrentFile> MapMetadataToFilesCollection(
IRankTorrentName rankTorrentName,
IParseTorrentTitle torrentTitle,
Torrent torrent,
string ImdbId,
IReadOnlyList<TorrentContent> Metadata,
ILogger<WriteQbitMetadataConsumer> logger)
IReadOnlyList<TorrentContent> Metadata)
{
try
{
@@ -25,31 +24,23 @@ public static class QbitMetaToTorrentMeta
Size = metadataEntry.Size,
};
var parsedTitle = rankTorrentName.Parse(file.Title, false);
if (!parsedTitle.Success)
{
logger.LogWarning("Failed to parse title {Title} for metadata mapping", file.Title);
continue;
}
var parsedTitle = torrentTitle.Parse(file.Title);
file.ImdbSeason = parsedTitle.Response?.Season?.FirstOrDefault() ?? 0;
file.ImdbEpisode = parsedTitle.Response?.Episode?.FirstOrDefault() ?? 0;
file.ImdbSeason = parsedTitle.Seasons.FirstOrDefault();
file.ImdbEpisode = parsedTitle.Episodes.FirstOrDefault();
files.Add(file);
}
return files;
}
catch (Exception ex)
catch (Exception)
{
logger.LogWarning("Failed to map metadata to files collection: {Exception}", ex.Message);
return [];
}
}
public static async Task<IReadOnlyList<SubtitleFile>> MapMetadataToSubtitlesCollection(IDataStorage storage, string InfoHash, IReadOnlyList<TorrentContent> Metadata,
ILogger<WriteQbitMetadataConsumer> logger)
public static async Task<IReadOnlyList<SubtitleFile>> MapMetadataToSubtitlesCollection(IDataStorage storage, string InfoHash, IReadOnlyList<TorrentContent> Metadata)
{
try
{
@@ -79,9 +70,8 @@ public static class QbitMetaToTorrentMeta
return files;
}
catch (Exception ex)
catch (Exception)
{
logger.LogWarning("Failed to map metadata to subtitles collection: {Exception}", ex.Message);
return [];
}
}

View File

@@ -53,12 +53,6 @@ public class QbitMetadataSagaStateMachine : MassTransitStateMachine<QbitMetadata
.Then(
context =>
{
if (!context.Message.WithFiles)
{
logger.LogInformation("No files written for torrent {InfoHash} in Saga {SagaId}", context.Saga.Torrent.InfoHash, context.Saga.CorrelationId);
return;
}
logger.LogInformation("Metadata Written for torrent {InfoHash} in Saga {SagaId}", context.Saga.Torrent.InfoHash, context.Saga.CorrelationId);
})
.TransitionTo(Completed)

View File

@@ -16,7 +16,7 @@ public record WriteQbitMetadata(Torrent Torrent, QBitMetadataResponse Metadata,
}
[EntityName("metadata-written-qbit-collector")]
public record QbitMetadataWritten(QBitMetadataResponse Metadata, bool WithFiles) : CorrelatedBy<Guid>
public record QbitMetadataWritten(QBitMetadataResponse Metadata) : CorrelatedBy<Guid>
{
public Guid CorrelationId { get; init; } = Metadata.CorrelationId;

View File

@@ -1,36 +1,25 @@
namespace QBitCollector.Features.Worker;
public class WriteQbitMetadataConsumer(IRankTorrentName rankTorrentName, IDataStorage dataStorage, ILogger<WriteQbitMetadataConsumer> logger) : IConsumer<WriteQbitMetadata>
public class WriteQbitMetadataConsumer(IParseTorrentTitle parseTorrentTitle, IDataStorage dataStorage) : IConsumer<WriteQbitMetadata>
{
public async Task Consume(ConsumeContext<WriteQbitMetadata> context)
{
var request = context.Message;
if (request.Metadata.Metadata.Count == 0)
var torrentFiles = QbitMetaToTorrentMeta.MapMetadataToFilesCollection(parseTorrentTitle, request.Torrent, request.ImdbId, request.Metadata.Metadata);
if (torrentFiles.Any())
{
await context.Publish(new QbitMetadataWritten(request.Metadata, false));
return;
await dataStorage.InsertFiles(torrentFiles);
var subtitles = await QbitMetaToTorrentMeta.MapMetadataToSubtitlesCollection(dataStorage, request.Torrent.InfoHash, request.Metadata.Metadata);
if (subtitles.Any())
{
await dataStorage.InsertSubtitles(subtitles);
}
}
var torrentFiles = QbitMetaToTorrentMeta.MapMetadataToFilesCollection(
rankTorrentName, request.Torrent, request.ImdbId, request.Metadata.Metadata, logger);
if (!torrentFiles.Any())
{
await context.Publish(new QbitMetadataWritten(request.Metadata, false));
return;
}
await dataStorage.InsertFiles(torrentFiles);
var subtitles = await QbitMetaToTorrentMeta.MapMetadataToSubtitlesCollection(
dataStorage, request.Torrent.InfoHash, request.Metadata.Metadata, logger);
if (subtitles.Any())
{
await dataStorage.InsertSubtitles(subtitles);
}
await context.Publish(new QbitMetadataWritten(request.Metadata, true));
await context.Publish(new QbitMetadataWritten(request.Metadata));
}
}

View File

@@ -1,11 +1,17 @@
// Global using directives
global using System.Text.Json;
global using System.Text.Json.Serialization;
global using System.Threading.Channels;
global using MassTransit;
global using MassTransit.Mediator;
global using Microsoft.AspNetCore.Builder;
global using Microsoft.Extensions.Caching.Distributed;
global using Microsoft.Extensions.Caching.Memory;
global using Microsoft.Extensions.DependencyInjection;
global using Polly;
global using Polly.Extensions.Http;
global using PromKnight.ParseTorrentTitle;
global using QBitCollector.Extensions;
global using QBitCollector.Features.Qbit;
global using QBitCollector.Features.Trackers;
@@ -15,6 +21,4 @@ global using SharedContracts.Configuration;
global using SharedContracts.Dapper;
global using SharedContracts.Extensions;
global using SharedContracts.Models;
global using SharedContracts.Python;
global using SharedContracts.Python.RTN;
global using SharedContracts.Requests;

View File

@@ -18,6 +18,7 @@
<PackageReference Include="Microsoft.Extensions.Http" Version="8.0.0" />
<PackageReference Include="Microsoft.Extensions.Http.Polly" Version="8.0.3" />
<PackageReference Include="Polly" Version="8.3.1" />
<PackageReference Include="PromKnight.ParseTorrentTitle" Version="1.0.4" />
<PackageReference Include="QBittorrent.Client" Version="1.9.23349.1" />
<PackageReference Include="Serilog" Version="3.1.1" />
<PackageReference Include="Serilog.AspNetCore" Version="8.0.1" />
@@ -30,30 +31,10 @@
<None Include="Configuration\logging.json">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
<Content Remove="eng\**" />
<None Remove="eng\**" />
<None Update="requirements.txt">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\shared\SharedContracts.csproj" />
</ItemGroup>
<ItemGroup Condition="'$(Configuration)' == 'Debug'">
<Content Remove="python\**" />
<None Include="python\**">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
</ItemGroup>
<ItemGroup>
<Compile Remove="eng\**" />
</ItemGroup>
<ItemGroup>
<EmbeddedResource Remove="eng\**" />
</ItemGroup>
</Project>

View File

@@ -6,12 +6,6 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "shared", "shared", "{2C0A0F
EndProject
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "QBitCollector", "QBitCollector.csproj", "{1EF124BE-6EBE-4D9E-846C-FFF814999F3B}"
EndProject
Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "eng", "eng", "{2F2EA33A-1303-405D-939B-E9394D262BC9}"
ProjectSection(SolutionItems) = preProject
eng\install-python-reqs.ps1 = eng\install-python-reqs.ps1
eng\install-python-reqs.sh = eng\install-python-reqs.sh
EndProjectSection
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|Any CPU = Debug|Any CPU

View File

@@ -1,3 +0,0 @@
Remove-Item -Recurse -Force ../python
mkdir -p ../python
python -m pip install -r ../requirements.txt -t ../python/

View File

@@ -1,5 +0,0 @@
#!/bin/bash
rm -rf ../python
mkdir -p ../python
python3 -m pip install -r ../requirements.txt -t ../python/

View File

@@ -1 +0,0 @@
rank-torrent-name==0.2.13

View File

@@ -8,14 +8,12 @@ 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};CommandTimeout={CommandTimeout}";
public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};";
}

View File

@@ -152,8 +152,7 @@ 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())
ON CONFLICT ("infoHash", "fileIndex") DO NOTHING;
(@InfoHash, @FileIndex, @Title, @Size, @ImdbId, @ImdbSeason, @ImdbEpisode, @KitsuId, @KitsuEpisode, Now(), Now());
""";
await connection.ExecuteAsync(query, files);
@@ -169,7 +168,11 @@ public class DapperDataStorage(PostgresConfiguration configuration, RabbitMqConf
("infoHash", "fileIndex", "fileId", "title")
VALUES
(@InfoHash, @FileIndex, @FileId, @Title)
ON CONFLICT ("infoHash", "fileIndex") DO NOTHING;
ON CONFLICT
("infoHash", "fileIndex")
DO UPDATE SET
"fileId" = COALESCE(subtitles."fileId", EXCLUDED."fileId"),
"title" = COALESCE(subtitles."title", EXCLUDED."title");
""";
await connection.ExecuteAsync(query, subtitles);

View File

@@ -1,19 +0,0 @@
namespace SharedContracts.Extensions;
public static class DictionaryExtensions
{
public static ConcurrentDictionary<TKey, TValue> ToConcurrentDictionary<TSource, TKey, TValue>(
this IEnumerable<TSource> source,
Func<TSource, TKey> keySelector,
Func<TSource, TValue> valueSelector) where TKey : notnull
{
var concurrentDictionary = new ConcurrentDictionary<TKey, TValue>();
foreach (var element in source)
{
concurrentDictionary.TryAdd(keySelector(element), valueSelector(element));
}
return concurrentDictionary;
}
}

View File

@@ -1,6 +1,5 @@
// Global using directives
global using System.Collections.Concurrent;
global using System.Text.Json;
global using System.Text.Json.Serialization;
global using System.Text.RegularExpressions;

View File

@@ -2,6 +2,5 @@ namespace SharedContracts.Python.RTN;
public interface IRankTorrentName
{
ParseTorrentTitleResponse Parse(string title, bool trashGarbage = true, bool logErrors = false, bool throwOnErrors = false);
List<ParseTorrentTitleResponse?> BatchParse(IReadOnlyCollection<string> titles, int chunkSize = 500, int workers = 20, bool trashGarbage = true, bool logErrors = false, bool throwOnErrors = false);
ParseTorrentTitleResponse Parse(string title);
}

View File

@@ -12,102 +12,32 @@ public class RankTorrentName : IRankTorrentName
_pythonEngineService = pythonEngineService;
InitModules();
}
public ParseTorrentTitleResponse Parse(string title, bool trashGarbage = true, bool logErrors = false, bool throwOnErrors = false)
{
try
{
using var gil = Py.GIL();
var result = _rtn?.parse(title, trashGarbage);
return ParseResult(result);
}
catch (Exception ex)
{
if (logErrors)
public ParseTorrentTitleResponse Parse(string title) =>
_pythonEngineService.ExecutePythonOperationWithDefault(
() =>
{
_pythonEngineService.Logger.LogError(ex, "Python Error: {Message} ({OperationName})", ex.Message, nameof(Parse));
}
if (throwOnErrors)
{
throw;
}
return new(false, null);
}
}
var result = _rtn?.parse(title);
return ParseResult(result);
}, new ParseTorrentTitleResponse(false, null), nameof(Parse), throwOnErrors: false, logErrors: false);
public List<ParseTorrentTitleResponse?> BatchParse(IReadOnlyCollection<string> titles, int chunkSize = 500, int workers = 20, bool trashGarbage = true, bool logErrors = false, bool throwOnErrors = false)
private static ParseTorrentTitleResponse ParseResult(dynamic result)
{
var responses = new List<ParseTorrentTitleResponse?>();
try
{
if (titles.Count == 0)
{
return responses;
}
using var gil = Py.GIL();
var pythonList = new PyList(titles.Select(x => new PyString(x).As<PyObject>()).ToArray());
PyList results = _rtn?.batch_parse(pythonList, trashGarbage, chunkSize, workers);
if (results == null)
{
return responses;
}
responses.AddRange(results.Select(ParseResult));
}
catch (Exception ex)
{
if (logErrors)
{
_pythonEngineService.Logger.LogError(ex, "Python Error: {Message} ({OperationName})", ex.Message, nameof(Parse));
}
if (throwOnErrors)
{
throw;
}
}
return responses;
}
private static ParseTorrentTitleResponse? ParseResult(dynamic result)
{
try
{
if (result == null)
{
return new(false, null);
}
var json = result.model_dump_json()?.As<string?>();
if (json is null || string.IsNullOrEmpty(json))
{
return new(false, null);
}
var mediaType = result.GetAttr("type")?.As<string>();
if (string.IsNullOrEmpty(mediaType))
{
return new(false, null);
}
var response = JsonSerializer.Deserialize<RtnResponse>(json);
response.IsMovie = mediaType.Equals("movie", StringComparison.OrdinalIgnoreCase);
return new(true, response);
}
catch
if (result == null)
{
return new(false, null);
}
var json = result.model_dump_json()?.As<string?>();
if (json is null || string.IsNullOrEmpty(json))
{
return new(false, null);
}
var response = JsonSerializer.Deserialize<RtnResponse>(json);
return new(true, response);
}
private void InitModules() =>

View File

@@ -76,8 +76,23 @@ public class RtnResponse
[JsonPropertyName("extended")]
public bool Extended { get; set; }
public bool IsMovie { get; set; }
// [JsonPropertyName("is_show")]
// public bool IsTvShow { get; set; }
//
// [JsonPropertyName("is_movie")]
// public bool IsMovie { get; set; }
public string ToJson() => this.AsJson();
public bool IsMovie => !TvRegexes.Any(regex => regex.IsMatch(RawTitle)) && Season?.Count == 0 && Episode?.Count == 0;
private static List<Regex> TvRegexes { get; set; } =
[
new(@"[se]\d\d", RegexOptions.IgnoreCase),
new(@"\b(tv|complete)\b", RegexOptions.IgnoreCase),
new(@"\b(saisons?|stages?|seasons?).?\d", RegexOptions.IgnoreCase),
new(@"[a-z]\s?\-\s?\d{2,4}\b", RegexOptions.IgnoreCase),
new(@"\d{2,4}\s?\-\s?\d{2,4}\b", RegexOptions.IgnoreCase),
];
}

View File

@@ -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="8.0.3" />
<PackageReference Include="Npgsql" Version="8.0.2" />
<PackageReference Include="pythonnet" Version="3.0.3" />
<PackageReference Include="Serilog" Version="3.1.1" />
<PackageReference Include="Serilog.Extensions.Hosting" Version="8.0.0" />

View File

@@ -8,14 +8,12 @@ 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};CommandTimeout={CommandTimeout}";
public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};";
}

View File

@@ -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="8.0.3" />
<PackageReference Include="Npgsql" Version="8.0.1" />
<PackageReference Include="Serilog" Version="3.1.1" />
<PackageReference Include="Serilog.AspNetCore" Version="8.0.1" />
<PackageReference Include="Serilog.Sinks.Console" Version="5.0.1" />

View File

@@ -82,4 +82,11 @@ public static class ServiceCollectionExtensions
x.AddConsumer<PerformIngestionConsumer>();
}
internal static IServiceCollection AddServiceConfiguration(this IServiceCollection services)
{
services.AddSingleton<IParseTorrentTitle, ParseTorrentTitle>();
return services;
}
}

View File

@@ -5,6 +5,7 @@ global using MassTransit;
global using MassTransit.Mediator;
global using Microsoft.AspNetCore.Builder;
global using Microsoft.Extensions.DependencyInjection;
global using PromKnight.ParseTorrentTitle;
global using SharedContracts.Configuration;
global using SharedContracts.Dapper;
global using SharedContracts.Extensions;

Some files were not shown because too many files have changed in this diff Show More