minor improvements

.gitignore

@@ -292,6 +292,7 @@ TSWLatexianTemp*
 
 .ipynb_checkpoints/
 env/
+.env
 __pycache__/
 test/
 venv/

README.md

@@ -0,0 +1,63 @@
+# PeerTube collector
+
+peertube-collector is a project designed to collect and analyze WebRTC statistics from a Chromium browser and export them to a Prometheus PushGateway service. This project includes a Docker setup for running the necessary services.
+
+## Working Project Structure
+
+```
+peertube-collector/
+├── requirements.txt
+├── telegraf.conf
+├── docker-compose.yml
+├── Dockerfile
+├── main.py
+├── .env
+└── utils/
+└── webrtc-internals-exporter/
+```
+
+
+## Prerequisites
+
+- Docker
+- Docker Compose
+
+## Setup
+
+1. Clone the repository:
+    ```sh
+    git clone <repository-url>
+    cd peertube-collector
+    ```
+
+2. Create and configure the environment file based on the `.env.example` file:
+    ```sh
+    cp .env.example .env
+    ```
+
+
+3. Build and start the Docker containers:
+    ```sh
+    docker-compose up --build
+    ```
+
+## Components
+
+### Docker Compose
+
+The `docker-compose.yml` file defines the following services:
+- **selenium**: Runs a Selenium standalone Chromium container.
+- **telegraf**: Collects and sends metrics to the specified output.
+- **collector**: Runs the main Python application to collect WebRTC stats.
+
+### Dockerfile
+
+The `Dockerfile` sets up the Python environment and installs the necessary dependencies to run the `main.py` script.
+
+### Main Python Script
+
+The `main.py` script sets up the Selenium WebDriver, collects WebRTC stats, and sends them to the Telegraf service.
+
+### WebRTC Internals Exporter
+
+The `webrtc-internals-exporter` directory contains a Chromium extension that collects WebRTC stats from the browser.

docker-compose.yml

@@ -2,8 +2,6 @@ services:
   selenium:
     container_name: selenium-standalone-chromium
     image: selenium/standalone-chromium:129.0
-    ports:
-      - "7900:7900"
     volumes:
       - ./webrtc-internals-exporter:/tmp/webrtc-internals-exporter:ro
     shm_size: "2g"
@@ -13,19 +11,23 @@ services:
       interval: 5s
       timeout: 10s
       retries: 5
-    networks:
+    network_mode: host
-      - backend
 
   telegraf:
     container_name: telegraf
     image: telegraf:1.33.1
     volumes:
       - ./telegraf.conf:/etc/telegraf/telegraf.conf:ro
+    environment:
+      - DATABASE=${TELEGRAF_MONGODB_DATABASE:?"Database name is required"}
+      - DSN=${TELEGRAF_MONGODB_DSN:?"DSN is required"}
+      - HOSTNAME=${TELEGRAF_HOSTNAME:?"Hostname is required"}
     networks:
       - backend
 
   collector:
     container_name: collector
+    #image: gitea.kobim.cloud/kobim/peertube-collector
     build:
       context: .
       dockerfile: Dockerfile
@@ -34,6 +36,12 @@ services:
         condition: service_healthy
       telegraf:
         condition: service_started
+    environment:
+      - VIDEO_URL=${VIDEO_URL:?"Video URL is required"}
+    ports:
+      - "9092:9092"
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
     networks:
       - backend
 

example.env

@@ -0,0 +1,8 @@
+# User defined hostname persisted across all sessions, used to keep track of the same user
+TELEGRAF_HOSTNAME=
+# MongoDB connection string
+TELEGRAF_MONGODB_DSN=
+# MongoDB database name to store the data
+TELEGRAF_MONGODB_DATABASE=
+# URL of the video to be analyzed
+VIDEO_URL=

main.py

@@ -28,7 +28,7 @@ def setupLogger():
     )
     logger.addHandler(logger_handler)
 
-def interrupt_handler(signum, driver: webdriver.Chrome):
+def interrupt_handler(signum, driver: webdriver.Remote):
     logger.info(f'Handling signal {signum} ({signal.Signals(signum).name}).')
     
     driver.quit()
@@ -49,7 +49,7 @@ def setupChromeDriver():
     chrome_options.add_experimental_option('prefs', {'intl.accept_languages': 'en,en_US'})
         
     #driver = webdriver.Chrome(options=chrome_options)
-    driver = webdriver.Remote(command_executor='http://selenium-standalone-chromium:4444', options=chrome_options)
+    driver = webdriver.Remote(command_executor='http://host.docker.internal:4444', options=chrome_options)
     logger.log(logging.INFO, 'Chrome driver setup complete.')
     
     return driver
@@ -157,7 +157,7 @@ def downloadStats(driver: webdriver.Chrome, peersDict: dict):
 
     saveStats([stats])
     
-def setupStats(driver: webdriver.Chrome, url: str):
+def setupStats(driver: webdriver.Remote, url: str):
     logger.log(logging.INFO, 'Setting up stats.')
     actions = ActionChains(driver)
     wait = WebDriverWait(driver, 30, poll_frequency=0.2)
@@ -183,9 +183,14 @@ if __name__ == '__main__':
 
     signal.signal(signal.SIGINT, lambda signum, frame: interrupt_handler(signum, driver))
     
-    setupStats(driver, "https://tube.kobim.cloud/w/iN2T8PmbSb4HJTDA2rV3sg")
+    url = os.getenv('VIDEO_URL')
+    if url is None:
+        logger.error('VIDEO_URL environment variable is not set.')
+        raise SystemExit(1)
+    
+    setupStats(driver, url)
     
     logger.log(logging.INFO, 'Starting server collector.')
-    httpd = HTTPServer(('collector', 9092), partial(Handler, downloadStats, driver, logger))
+    httpd = HTTPServer(('', 9092), partial(Handler, downloadStats, driver, logger))
     logger.info('Server collector started.')
     httpd.serve_forever()

telegraf.conf

@@ -1,3 +1,7 @@
+[agent]
+    hostname = "${HOSTNAME}"
+    omit_hostname = false
+
 [[processors.dedup]]
     dedup_interval = "600s"
 
@@ -14,8 +18,7 @@
         [inputs.socket_listener.xpath.tags]
             url = "url"
             session = "session"
-            #id = ??
+            host = "host"
-            #state = ??
 
         [inputs.socket_listener.xpath.fields]
             player = "player"
@@ -26,8 +29,6 @@
     data_format = "json"
 
 [[outputs.mongodb]]
-    dsn = "mongodb://stats_user:%40z%5EVFhN7q%25vzit@192.168.86.120:27017/?authSource=statistics"
+    dsn = "${DSN}"
-    database = "statistics"
+    database = "${DATABASE}"
-    granularity = "seconds"
+    granularity = "seconds"
-
-#  docker run --rm -v .\peertube\statnerd\telegraf.conf:/etc/telegraf/telegraf.conf:ro -p 8094:8094/udp telegraf

utils/PostHandler.py

@@ -21,4 +21,9 @@ class Handler(BaseHTTPRequestHandler):
         else:
             self.send_response(404)
             self.end_headers()
-            self.wfile.write(b'404 Not Found')
+            self.wfile.write(b'404 Not Found')
+            
+    def do_GET(self):
+        self.send_response(404)
+        self.end_headers()
+        self.wfile.write(b'404 Not Found')

webrtc-internals-exporter/background.js

@@ -9,13 +9,15 @@ log("loaded");
 import "/assets/pako.min.js";
 
 const DEFAULT_OPTIONS = {
-  url: "http://collector:9092",
+  url: "http://localhost:9092",
   username: "",
   password: "",
   updateInterval: 2,
   gzip: false,
   job: "webrtc-internals-exporter",
   enabledOrigins: {
+    "http://*/*": true,
+    "https://*/*": true,
     "https://tube.kobim.cloud": true,
   },
   enabledStats: ["data-channel", "local-candidate", "remote-candidate"]