feat: update README and main.py to clarify port usage and add error handling for socket port

feat: enhance WebRTC stats collection by logging connection state changes

.github/workflows/feature-pr-build.yml

@@ -1,4 +1,4 @@
-name: Build Docker Image for Pull Request
+name: Build Docker Images for Pull Request
 
 on:
   pull_request:
@@ -25,3 +25,13 @@ jobs:
           platforms: |
             linux/amd64
             linux/arm64
+      
+      - name: Build monolith Docker image
+        uses: docker/build-push-action@v6.13.0
+        with:
+          context: .
+          tags: ${{ github.repository_owner }}/${{ github.event.repository.name }}:${{ github.event.pull_request.number }}-monolith
+          file: ./Monolith.dockerfile
+          platforms: |
+            linux/amd64
+            linux/arm64

.github/workflows/monolith.yml

@@ -0,0 +1,37 @@
+name: Build and Push Docker Image
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  REGISTRY_URL: gitea.kobim.cloud
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository actions
+        uses: actions/checkout@v2
+        
+      - name: Setup Docker Environment
+        uses: ./.github/actions/setup-docker-environment
+        
+      - name: Log in to Docker registry
+        uses: docker/login-action@v3.3.0
+        with:
+          registry: ${{ env.REGISTRY_URL }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.REGISTRY_TOKEN }}
+          
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v6.13.0
+        with:
+          context: .
+          push: true
+          tags: ${{ env.REGISTRY_URL }}/${{ github.repository_owner }}/${{ github.event.repository.name }}-monolith:latest
+          file: ./Monolith.dockerfile
+          platforms: |
+            linux/amd64
+            linux/arm64

.gitignore

@@ -297,3 +297,10 @@ __pycache__/
 test/
 venv/
 .venv/
+
+# Node.js
+node_modules/
+npm-debug.log
+yarn-error.log
+yarn-debug.log*
+background.bundle.js

Dockerfile

@@ -1,8 +1,15 @@
-FROM python:3.13.1-slim-bookworm
+FROM debian:bookworm-slim
 
-# Install dependencies
+# Install Python and curl
+RUN apt-get update && apt-get install -y python3 python3-pip python3-venv curl
+
+# Create and activate a virtual environment
+RUN python3 -m venv /app/venv
+ENV PATH="/app/venv/bin:$PATH"
+
+# Install dependencies with venv
 COPY requirements.txt /app/requirements.txt
-RUN pip install --no-cache-dir -r /app/requirements.txt
+RUN /app/venv/bin/pip install -r /app/requirements.txt
 
 # Copy the application
 COPY main.py /app
@@ -10,4 +17,7 @@ COPY utils/ /app/utils
 WORKDIR /app
 
 # Run the application
-CMD ["python", "main.py"]
+CMD ["/app/venv/bin/python", "main.py"]
+
+# Healthcheck
+HEALTHCHECK --interval=5s --timeout=10s --retries=5 --start-period=5s CMD curl -f http://localhost:9092/heartbeat || exit 1

Monolith.dockerfile

@@ -0,0 +1,50 @@
+FROM node:22.14.0-bookworm-slim AS build
+
+# Copy the webrtc-internals-exporter files
+COPY webrtc-internals-exporter /tmp/webrtc-internals-exporter
+
+WORKDIR /tmp/webrtc-internals-exporter/webpack
+
+# Install dependencies
+RUN --mount=type=cache,target=/root/.npm \
+    npm install
+
+# Build the project
+RUN npm run build
+
+FROM selenium/standalone-chromium:129.0
+
+# Install Python-virtualenv
+RUN sudo apt-get update && sudo sudo apt-get install -y python3-venv
+
+WORKDIR /tmp
+
+# Install Telegraf
+RUN wget -q https://repos.influxdata.com/influxdata-archive_compat.key && \
+    echo '393e8779c89ac8d958f81f942f9ad7fb82a25e133faddaf92e15b16e6ac9ce4c influxdata-archive_compat.key' | sha256sum -c && \
+    cat influxdata-archive_compat.key | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/influxdata-archive_compat.gpg > /dev/null && \
+    echo 'deb [signed-by=/etc/apt/trusted.gpg.d/influxdata-archive_compat.gpg] https://repos.influxdata.com/debian stable main' | sudo tee /etc/apt/sources.list.d/influxdata.list && \
+    sudo apt-get update && sudo apt-get install -y telegraf
+
+# Create and activate a virtual environment
+RUN python3 -m venv ./venv
+ENV PATH="/tmp/venv/bin:$PATH"
+
+# Install dependencies with venv
+COPY requirements.txt ./requirements.txt
+RUN ./venv/bin/pip install -r ./requirements.txt
+
+# Copy files
+COPY main.py .
+COPY utils/ ./utils
+COPY telegraf.conf ./telegraf.conf
+COPY webrtc-internals-exporter /tmp/webrtc-internals-exporter
+COPY --from=build /tmp/webrtc-internals-exporter/background.bundle.js /tmp/webrtc-internals-exporter/background.bundle.js
+COPY --chown="${SEL_UID}:${SEL_GID}" monolith-entrypoint.sh /opt/bin/collector.sh
+
+# Run the entrypoint
+RUN chmod +x /opt/bin/collector.sh
+ENTRYPOINT ["/opt/bin/collector.sh"]
+
+# Healthcheck
+HEALTHCHECK --interval=5s --timeout=10s --retries=5 --start-period=5s CMD curl -f http://localhost:9092/heartbeat || exit 1

README.md

@@ -10,19 +10,12 @@ peertube-collector is a project designed to collect and analyze WebRTC statistic
 - Docker Engine Community version is required. To install Docker CE, follow the official [install instructions](https://docs.docker.com/engine/install/).
 
 ### Ports: 
-#### Docker to Host:
-- 4444 (Selenium)
 
-Ports can be opened in the host machine's firewall with:
-```sh
-ufw allow from 172.30.0.0/16 to any port 4444
-```
-
-#### External (OPTIONAL):
-These ports are actively used by selenium and the collector services. By defaut they should not be blocked by the firewall, but if so, they can be opened in the host machine's firewall.
+#### External (OPTIONAL PROBABLY NOT NEEDED!!!):
+These ports are actively used by selenium and the collector services.
 
 - 50000:60000/udp (WebRTC)
-  - Needed for WebRTC NAT traversal, otherwise the browser will not connect to any peer.
+  - WebRTC NAT traversal requires a range of ports to be open.
     The range needs to be fairly large since the port is chosen randomly by the STUN server.
 - 27107/tcp (MongoDB)
 
@@ -31,34 +24,62 @@ Ports can be opened in the host machine's firewall with:
 ufw allow 50000:60000/udp
 ufw allow 27107/tcp
 ```
-## Setup
+## Setup with Docker Compose
 
 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. Ajust the firewall settings to allow the necessary ports if needed
-
 4. Start the Docker containers:
     ```sh
-    docker compose up
-    ```
-    or in detached mode:
-    ```sh
-    docker compose up -d
+    docker compose up --abort-on-container-failure
     ```
 
 The collector will start gathering WebRTC stats from the Selenium container and sending them to the Telegraf service.
 
 To stop the Docker containers run: `docker compose down -v`
 
+### Setup with Monolithic image:
+
+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. Ajust the firewall settings to allow the necessary ports if needed
+4. Start the Docker container:
+    ```sh
+    docker run --rm -p 7900:7900 --env-file .env --name peertube-collector gitea.kobim.cloud/kobim/peertube-collector-monolith:latest
+    ```
+
+
+### Environment Variables
+
+| Environment Variable            | Service              | Default Value                  | Description                                                                                                                                                |
+| ------------------------------- | -------------------- | ------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `TELEGRAF_HOSTNAME`             | telegraf             | None, **must** be set          | Hostname used to identify the host/user between sessions                                                                                                   |
+| `TELEGRAF_MONGODB_DSN`          | telegraf             | `mongodb://stats_user...`      | DSN for the MongoDB service                                                                                                                                |
+| `TELEGRAF_MONGODB_DATABASE`     | telegraf             | `statistics`                   | Database name for the MongoDB service                                                                                                                      |
+| `VIDEO_URL`                     | collector            | `https://tube.kobim.cloud/...` | URL for the video to be analyzed                                                                                                                           |
+| `HUB_URL`                       | collector            | None                           | URL for the Selenium Hub. If not set, the local Chrome driver will be used                                                                                 |
+| `SOCKET_URL`                    | collector            | `localhost`                    | Socket URL for Telegraf service                                                                                                                            |
+| `SOCKET_PORT`                   | collector & telegraf | `8094`                         | Socket port for Telegraf service                                                                                                                           |
+| `WEBRTC_INTERNALS_PATH`         | collector            | None                           | **Absolute** path for WebRTC internals exporter extension. When **not** set the extension path is construced relative to the current main script location. |
+| `WEBRTC_INTERNALS_EXPORTER_URL` | WebRTC extension     | `http://localhost:9092`        | Server URL for the WebRTC internals exporter extension                                                                                                     |
+
+Variables can be set in the `.env` file.
+An example configuration is provided in the `.env.example` file.
+
 ### Monitoring
 A noVNC server is available at [http://localhost:7900](http://localhost:7900/?autoconnect=1&resize=scale&password=secret) to monitor the Selenium container. The password is `secret`.
 
@@ -75,6 +96,10 @@ The `docker-compose.yml` file defines the following services:
 
 The `Dockerfile` sets up the Python environment and installs the necessary dependencies to run the `main.py` script.
 
+### Monolithic Dockerfile
+
+`Monolith.dockerfile` is a single Dockerfile that combines the Selenium, Telegraf, and Collector services into a single container. This is useful for deployment in a single container environment.
+
 ### Main Python Script
 
 The `main.py` script sets up the Selenium WebDriver, collects WebRTC stats, and sends them to the Telegraf service.
@@ -82,44 +107,10 @@ The `main.py` script sets up the Selenium WebDriver, collects WebRTC stats, and
 ### WebRTC Internals Exporter
 
 The `webrtc-internals-exporter` directory contains a Chromium extension that collects WebRTC stats from the browser.
+It uses Webpack to replace the server collector endpoint with an environment variable.
 
-## Working Project Structure
+# Credits
 
-```
-peertube-collector/
-├── requirements.txt
-├── telegraf.conf
-├── docker-compose.yml
-├── Dockerfile
-├── main.py
-├── .env
-└── utils/
-└── webrtc-internals-exporter/
-```
-
----
-
-# Server
-
-The repository contains a `server` directory with a simple MongoDB server (with initializations scripts) and WebUI that serves the WebRTC stats collected by the collector.
-
-Based this awesome example configuration: [MongoDB Docker Compose examples](https://github.com/TGITS/docker-compose-examples/tree/main/mongodb-docker-compose-examples).
-
-## Setup
-
-1. Change to the `server` directory:
-    ```sh
-    cd server
-    ```
-
-2. Create and configure the environment file based on the `.env.example` file:
-    ```sh
-    cp .env.example .env
-    ```
-
-3. Start the Docker containers:
-    ```sh
-    docker compose up
-    ```
-
-The WebUI control panel will be available at [http://localhost:8081](http://localhost:8081).
+- [WebRTC Internals Exporter](https://github.com/vpalmisano/webrtc-internals-exporter)
+  - [WebRTC debugging with Prometheus/Grafana](https://medium.com/@vpalmisano/webrtc-debugging-with-prometheus-grafana-254b6ac71063)
+- [MongoDB Docker Compose examples](https://github.com/TGITS/docker-compose-examples/tree/main/mongodb-docker-compose-examples)

docker-compose.yml

@@ -3,18 +3,19 @@ services:
     container_name: selenium-standalone-chromium
     image: selenium/standalone-chromium:129.0
     volumes:
-      - ./webrtc-internals-exporter:/tmp/webrtc-internals-exporter:ro
+      - build-extension:/tmp/webrtc-internals-exporter
     shm_size: "2g"
     attach: false
-    depends_on:
-      telegraf:
-        condition: service_healthy
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:4444/wd/hub/status"]
       interval: 5s
       timeout: 10s
       retries: 5
-    network_mode: host
+    pull_policy: always
+    ports:
+      - "7900:7900"
+    networks:
+      - backend
 
   telegraf:
     container_name: telegraf
@@ -25,11 +26,32 @@ services:
       - DATABASE=${TELEGRAF_MONGODB_DATABASE:?"Database name is required"}
       - DSN=${TELEGRAF_MONGODB_DSN:?"DSN is required"}
       - HOSTNAME=${TELEGRAF_HOSTNAME:?"Hostname is required"}
+      - SOCKET_PORT=${SOCKET_PORT:?"Socket port is required"}
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:8080"]
       interval: 5s
       timeout: 10s
       retries: 5
+    pull_policy: always
+    networks:
+      - backend
+  build-extension:
+    container_name: build-extension
+    image: node:22.14.0-bookworm-slim
+    volumes:
+      - ./webrtc-internals-exporter:/tmp/webrtc-internals-exporter:ro
+      - build-extension:/tmp/webrtc-internals-exporter-build
+    working_dir: /tmp/webrtc-internals-exporter-build/webpack
+    command:
+      - /bin/bash
+      - -c
+      - |
+        cp -r /tmp/webrtc-internals-exporter/* /tmp/webrtc-internals-exporter-build
+        npm install
+        npm run build
+    environment:
+      - WEBRTC_INTERNALS_EXPORTER_URL=http://collector
+    pull_policy: always
     networks:
       - backend
 
@@ -44,12 +66,14 @@ services:
         condition: service_healthy
       telegraf:
         condition: service_healthy
+      build-extension:
+        condition: service_completed_successfully
     environment:
       - VIDEO_URL=${VIDEO_URL:?"Video URL is required"}
-    ports:
-      - "9092:9092"
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
+      - SOCKET_URL=telegraf
+      - HUB_URL=http://selenium:4444
+      - WEBRTC_INTERNALS_PATH=/tmp/webrtc-internals-exporter
+    pull_policy: always
     networks:
       - backend
 
@@ -57,4 +81,7 @@ networks:
   backend:
     ipam:
       config:
-        - subnet: 172.30.0.0/16
+        - subnet: 172.100.0.0/16
+
+volumes:
+  build-extension:

main.py

@@ -4,10 +4,13 @@ import time
 import socket
 import logging
 import os
+import argparse
+from yaspin import yaspin
 from functools import partial
 from http.server import HTTPServer
 from utils.PostHandler import Handler
 from utils.ColoredFormatter import ColoredFormatter
+from utils.Convenience import *
 from bs4 import BeautifulSoup as bs
 from selenium import webdriver
 from selenium.webdriver.chrome.options import Options
@@ -17,10 +20,11 @@ from selenium.webdriver.support.wait import WebDriverWait
 from selenium.webdriver.support import expected_conditions as ec
 
 logger = logging.getLogger(__name__)
+args = None
 
 def setupLogger():
     logging_format = "[%(asctime)s] (%(levelname)s) %(module)s - %(funcName)s: %(message)s"
-    logging.basicConfig(level=logging.INFO, format=logging_format)
+    logging.basicConfig(level=firstValid(args.log_level, os.getenv('LOG_LEVEL'), default='INFO'), format=logging_format) # type: ignore
     (logger := logging.getLogger(__name__)).setLevel(logging.INFO)
     logger.propagate = False
     (logger_handler := logging.StreamHandler()).setFormatter(
@@ -28,43 +32,59 @@ def setupLogger():
     )
     logger.addHandler(logger_handler)
     
+
+def setupArgParser():
+    parser = argparse.ArgumentParser(description='Collector for PeerTube stats.')
+    parser.add_argument('-u', '--url', type=str, help='URL of the video to collect stats for.')
+    parser.add_argument('--socket-url', type=str, help='URL of the socket to send the stats to. Default: localhost')
+    parser.add_argument('--socket-port', type=int, help='Port of the socket to send the stats to. Default: 8094')
+    parser.add_argument('--hub-url', type=str, help='URL of the Selenium hub to connect to. If not provided, local Chrome driver will be used.')
+    parser.add_argument('--webrtc-internals-path', type=str, help='Path to the WebRTC internals extension.')
+    parser.add_argument('--log-level', type=str, help='Log level to use. Default: INFO')
+    
+    return parser
+
 def interrupt_handler(signum, driver: webdriver.Remote):
     logger.info(f'Handling signal {signum} ({signal.Signals(signum).name}).')
     
     driver.quit()
     raise SystemExit
 
-def setupChromeDriver():
+@yaspin()
+def setupChromeDriver(command_executor: str | None, webrtc_internals_path: str) -> webdriver.Remote | webdriver.Chrome:
     logger.log(logging.INFO, 'Setting up Chrome driver.')
     chrome_options = Options()
     #chrome_options.add_argument("--headless")
     chrome_options.add_argument("--no-sandbox")
     chrome_options.add_argument("--mute-audio")
     chrome_options.add_argument("--window-size=1280,720")
-    #chrome_options.add_argument("--disable-dev-shm-usage")
     chrome_options.add_argument("--no-default-browser-check")
     chrome_options.add_argument("--disable-features=WebRtcHideLocalIpsWithMdns")
-    #chrome_options.add_argument(f"--load-extension={os.path.abspath(os.path.join(os.path.dirname(__file__), 'webrtc-internals-exporter'))}")
-    chrome_options.add_argument("--load-extension=/tmp/webrtc-internals-exporter")
+    chrome_options.add_argument(f"--load-extension={webrtc_internals_path}")
     chrome_options.add_experimental_option('prefs', {'intl.accept_languages': 'en,en_US'})
 
-    #driver = webdriver.Chrome(options=chrome_options)
-    driver = webdriver.Remote(command_executor='http://host.docker.internal:4444', options=chrome_options)
+    if command_executor is not None:
+        driver = webdriver.Remote(command_executor=command_executor, options=chrome_options)
+        logger.warning(f'Using Selenium hub at {command_executor}.')
+    else:
+        driver = webdriver.Chrome(options=chrome_options)
+        logger.warning('No Selenium hub URL provided, using local Chrome driver.')
+    
     logger.log(logging.INFO, 'Chrome driver setup complete.')
     
     return driver
 
-def saveStats(stats: list):
+def saveStats(stats: list, socket_url: str, socket_port: int):
     try:
         sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
         logger.log(logging.DEBUG, f'Saving stats: {json.dumps(stats, indent=4)}')
-        sock.sendto(json.dumps(stats).encode(), ('telegraf', 8094))
+        sock.sendto(json.dumps(stats).encode(), (socket_url, socket_port))
         sock.close()
         logger.log(logging.DEBUG, 'Sent stats to socket.')
     except socket.error as e:
         logger.error(f'Got socket error: {e}')
 
-def downloadStats(driver: webdriver.Chrome, peersDict: dict):
+def downloadStats(driver: webdriver.Remote | webdriver.Chrome, peersDict: dict, socket_url: str, socket_port: int):
     html = driver.find_element(By.CLASS_NAME ,'vjs-stats-list').get_attribute('innerHTML')
     if html is not None:
         htmlBS = bs(html, 'html.parser')
@@ -155,11 +175,12 @@ def downloadStats(driver: webdriver.Chrome, peersDict: dict):
         'session': driver.session_id
     }
 
-    saveStats([stats])
+    saveStats([stats], socket_url, socket_port)
 
 def convert_to_bytes(down, downUnit):
     return float(down) * (1024 ** {'B': 0, 'KB': 1, 'MB': 2, 'GB': 3}[downUnit])
 
+@yaspin()
 def setupStats(driver: webdriver.Remote, url: str):
     logger.log(logging.INFO, 'Setting up stats.')
     actions = ActionChains(driver)
@@ -167,7 +188,13 @@ def setupStats(driver: webdriver.Remote, url: str):
 
     driver.get(url)
 
-    wait.until(ec.presence_of_element_located((By.CLASS_NAME, 'vjs-big-play-button')))
+    try:
+        wait.until(ec.presence_of_element_located((By.CLASS_NAME, 'vjs-big-play-button')))
+    except Exception:
+        logger.error('Timeout while waiting for the big play button to be present.')
+        driver.quit()
+        raise SystemExit(1)
+
     actions.click(driver.find_element(By.CLASS_NAME ,'video-js')).perform()
     wait.until(ec.visibility_of_element_located((By.CLASS_NAME, 'vjs-control-bar')))
     actions.context_click(driver.find_element(By.CLASS_NAME ,'video-js')).perform()
@@ -180,20 +207,35 @@ def setupStats(driver: webdriver.Remote, url: str):
     return driver
 
 if __name__ == '__main__':
+    args = setupArgParser().parse_args()
+    
     setupLogger()
     
-    driver = setupChromeDriver()
+    command_executor = firstValid(args.hub_url, os.getenv('HUB_URL'), default=None)
+    webrtc_internals_path = firstValid(
+        args.webrtc_internals_path,
+        os.getenv('WEBRTC_INTERNALS_PATH'), 
+        default=os.path.abspath(os.path.join(os.path.dirname(__file__), 'webrtc-internals-exporter'))
+        )
+    
+    driver = setupChromeDriver(command_executor, webrtc_internals_path)
 
     signal.signal(signal.SIGINT, lambda signum, frame: interrupt_handler(signum, driver))
     
-    url = os.getenv('VIDEO_URL')
+    url = firstValid(args.url, os.getenv('VIDEO_URL'), default=None)
     if url is None:
-        logger.error('VIDEO_URL environment variable is not set.')
+        logger.error('VIDEO_URL environment variable or --url argument is required.')
         raise SystemExit(1)
     
     setupStats(driver, url)
     
-    logger.log(logging.INFO, 'Starting server collector.')
-    httpd = HTTPServer(('', 9092), partial(Handler, downloadStats, driver, logger))
-    logger.info('Server collector started.')
+    socket_url = firstValid(args.socket_url, os.getenv('SOCKET_URL'), default='localhost')
+    try:
+        socket_port = int(firstValid(args.socket_port, os.getenv('SOCKET_PORT'), default=8094))
+    except ValueError:
+        logger.error('Invalid socket port provided. Exiting.')
+        raise SystemExit(1)
+    
+    logger.info('Starting server collector.')
+    httpd = HTTPServer(('', 9092), partial(Handler, downloadStats, driver, logger, socket_url, socket_port))
     httpd.serve_forever()

monolith-entrypoint.sh

@@ -0,0 +1,53 @@
+#!/bin/bash
+
+if [ -z "$TELEGRAF_HOSTNAME" ]; then
+    echo "Error: TELEGRAF_HOSTNAME is not set"
+    exit 1
+fi
+
+if [ -z "$TELEGRAF_MONGODB_DSN" ]; then
+    echo "Error: TELEGRAF_MONGODB_DSN is not set"
+    exit 1
+fi
+
+if [ -z "$TELEGRAF_MONGODB_DATABASE" ]; then
+    echo "Error: TELEGRAF_MONGODB_DATABASE is not set"
+    exit 1
+fi
+
+if [ -z "$SOCKET_PORT" ]; then
+    echo "Error: SOCKET_PORT is not set"
+    exit 1
+fi
+
+if [ -z "$VIDEO_URL" ]; then
+    echo "Error: VIDEO_URL is not set"
+    exit 1
+fi
+
+# Set the environment variables
+export DSN=$TELEGRAF_MONGODB_DSN
+export DATABASE=$TELEGRAF_MONGODB_DATABASE
+export HOSTNAME=$TELEGRAF_HOSTNAME
+
+# Start the Selenium hub
+/opt/bin/entry_point.sh > /dev/null 2>&1 &
+
+# Wait for Selenium hub to be ready
+printf 'Waiting for Selenium standalone to be ready'
+timeout=30
+while ! curl -sSL "http://localhost:4444/wd/hub/status" 2>/dev/null | jq -e '.value.ready' | grep -q true; do
+    printf '.'
+    sleep 1
+    ((timeout--))
+    if [ $timeout -le 0 ]; then
+        echo "Error: Selenium standalone did not become ready in time. Exiting..."
+        exit 1
+    fi
+done
+
+printf '\n'
+
+# Start the Telegraf agent and the main script
+telegraf --config ./telegraf.conf &
+./venv/bin/python main.py

requirements.txt

@@ -1,2 +1,3 @@
 selenium
 beautifulsoup4
+yaspin

server/README.md

@@ -0,0 +1,30 @@
+# Server
+
+The repository contains a `server` directory with a simple MongoDB server (with initializations scripts) and WebUI that serves the WebRTC stats collected by the collector.
+
+It's not mandatory to run and use this service, it's provided just as an example of how to store collected data.
+
+## Setup
+
+1. Change to the `server` directory:
+    ```sh
+    cd server
+    ```
+
+2. Create and configure the environment file based on the `.env.example` file:
+    ```sh
+    cp .env.example .env
+    ```
+
+3. Start the Docker containers:
+    ```sh
+    docker compose up
+    ```
+
+The WebUI control panel will be available at [http://localhost:8081](http://localhost:8081).
+
+# Credits
+
+- [WebRTC Internals Exporter](https://github.com/vpalmisano/webrtc-internals-exporter)
+  - [WebRTC debugging with Prometheus/Grafana](https://medium.com/@vpalmisano/webrtc-debugging-with-prometheus-grafana-254b6ac71063)
+- [MongoDB Docker Compose examples](https://github.com/TGITS/docker-compose-examples/tree/main/mongodb-docker-compose-examples)

telegraf.conf

@@ -7,7 +7,7 @@
     dedup_interval = "600s"
 
 [[inputs.socket_listener]]
-    service_address = "udp://:8094"
+    service_address = "udp://:${SOCKET_PORT}"
     data_format = "xpath_json"
     [[inputs.socket_listener.xpath]]
         metric_name = "'peertube'"

utils/Convenience.py

@@ -0,0 +1,5 @@
+def firstValid(*args, default):
+    for arg in args:
+        if arg is not None:
+            return arg
+    return default

utils/PostHandler.py

@@ -3,10 +3,12 @@ import logging
 from http.server import BaseHTTPRequestHandler
 
 class Handler(BaseHTTPRequestHandler):
-    def __init__(self, custom_func, driver, logger, *args, **kwargs):
+    def __init__(self, custom_func, driver, logger, socket_url, socket_port, *args, **kwargs):
         self._custom_func = custom_func
         self.logger = logger
         self.driver = driver
+        self._socket_url = socket_url
+        self._socket_port = socket_port
         super().__init__(*args, **kwargs)
         
     def do_POST(self):
@@ -14,7 +16,7 @@ class Handler(BaseHTTPRequestHandler):
             content_length = int(self.headers['Content-Length'])
             post_data = self.rfile.read(content_length)
             self.logger.log(logging.DEBUG, f"POST request,\nPath: {self.path}\nHeaders:\n{self.headers}\n\nBody:\n{post_data.decode('utf-8')}")
-            self._custom_func(self.driver, json.loads(post_data.decode('utf-8')))
+            self._custom_func(self.driver, json.loads(post_data.decode('utf-8')), self._socket_url, self._socket_port)
             self.send_response(200)
             self.end_headers()
             self.wfile.write(b'POST request received')
@@ -24,6 +26,11 @@ class Handler(BaseHTTPRequestHandler):
             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')
+        if self.path == '/heartbeat':
+            self.send_response(200)
+            self.end_headers()
+            self.wfile.write(b'Heartbeat OK')
+        else:
+            self.send_response(404)
+            self.end_headers()
+            self.wfile.write(b'404 Not Found')

webrtc-internals-exporter/background.js

@@ -6,17 +6,17 @@ function log(...args) {
 
 log("loaded");
 
-import "/assets/pako.min.js";
+import "./assets/pako.min.js";
 
 const DEFAULT_OPTIONS = {
-  url: "http://localhost:9092",
+  url: process.env.WEBRTC_INTERNALS_EXPORTER_URL + ":9092",
   username: "",
   password: "",
   updateInterval: 2,
   gzip: false,
   job: "webrtc-internals-exporter",
-  enabledOrigins: { },
-  enabledStats: ["data-channel", "local-candidate", "remote-candidate"]
+  enabledOrigins: {},
+  enabledStats: ["data-channel", "local-candidate", "remote-candidate", "candidate-pair"]
 };
 
 const options = {};

webrtc-internals-exporter/manifest.json

@@ -40,7 +40,7 @@
     }
   ],
   "background": {
-    "service_worker": "background.js",
+    "service_worker": "background.bundle.js",
     "type": "module"
   },
   "web_accessible_resources": [

webrtc-internals-exporter/override.js

@@ -22,7 +22,7 @@ class WebrtcInternalExporter {
     });
 
     window.postMessage({ event: "webrtc-internal-exporter:ready" });
-    this.collectAllStats();
+    setInterval(() => this.collectAndPostAllStats(), this.updateInterval);
   }
 
   randomId() {
@@ -40,6 +40,9 @@ class WebrtcInternalExporter {
     pc.iceCandidateErrors = [];
     this.peerConnections.set(id, pc);
     pc.addEventListener("connectionstatechange", () => {
+      log(`connectionStateChange: ${pc.connectionState}`);
+      this.collectAndPostAllStats();
+
       if (pc.connectionState === "closed") {
         this.peerConnections.delete(id);
       }
@@ -83,24 +86,27 @@ class WebrtcInternalExporter {
   }
 
   async collectAndPostSingleStat(id) {
-    const stats = await this.collectStats(id, this.collectAndPostSingleStat);
+    const stats = await this.collectStats(id);
     if (Object.keys(stats).length === 0 || !stats) return;
 
     window.postMessage(
       {
         event: "webrtc-internal-exporter:peer-connection-stats",
-        stats
+        stats: [stats]
       },
-      stats
+      [stats]
     );
+
+    log(`Single stat collected:`, [stats]);
   }
 
-  async collectAllStats() {
+  async collectAndPostAllStats() {
     const stats = [];
 
-    for (const [id, pc] of this.peerConnections) {
+    for (const [id] of this.peerConnections) {
       if (this.url && this.enabled) {
-        const pcStats = await this.collectStats(id, pc);
+        const pcStats = await this.collectStats(id);
+        if (Object.keys(pcStats).length === 0 || !pcStats) continue;
         stats.push(pcStats);
       }
     }
@@ -108,28 +114,24 @@ class WebrtcInternalExporter {
     window.postMessage(
       {
         event: "webrtc-internal-exporter:peer-connections-stats",
-        data: JSON.parse(JSON.stringify(stats)),
+        data: stats
       },
+      stats
     );
 
-    log(`Stats collected:`, JSON.parse(JSON.stringify(stats)));
+    log(`Stats collected:`, stats);
     
-    setTimeout(this.collectAllStats.bind(this), this.updateInterval);
     return stats;
   }
 
   /**
    * @param {string} id
-   * @param {RTCPeerConnection} pc
-   * @param {Function} binding
    */
-  async collectStats(id, pc, binding) {
-    var completeStats = {};
+  async collectStats(id) {
+    var pc = this.peerConnections.get(id);
+    if (!pc) return;
 
-    if (!pc) {
-      pc = this.peerConnections.get(id);
-      if (!pc) return;
-    }
+    var completeStats = {};
 
     if (this.url && this.enabled) {
       try {
@@ -157,10 +159,6 @@ class WebrtcInternalExporter {
 
     if (pc.connectionState === "closed") {
       this.peerConnections.delete(id);
-    } else {
-      if (binding) {
-        setTimeout(binding.bind(this), this.updateInterval, id);
-      }
     }
 
     return completeStats;

webrtc-internals-exporter/webpack/babel.config.js

@@ -0,0 +1,3 @@
+module.exports = {
+  shouldPrintComment: () => false
+};

webrtc-internals-exporter/webpack/build.js

@@ -0,0 +1,26 @@
+const { execSync } = require('child_process');
+const args = process.argv.slice(2);
+
+let url = '';
+
+args.forEach((arg, index) => {
+    if (arg === '-u' || arg === '--url') {
+        url = args[index + 1];
+    } else if (arg === '-h' || arg === '--help') {
+        console.log('Usage: npm run build -- [-u|--url <url>]');
+        console.log('Options:');
+        console.log('  -u, --url <url>  URL to use for the extension collector server');
+        console.log('  -h, --help       Display this help message');
+        process.exit(0);
+    } else if (arg.startsWith('-')) {
+        console.error(`Unrecognized argument: ${arg}`);
+        process.exit(1);
+    }
+});
+
+if (url) {
+  console.log(`Building with URL: ${url}`);
+  execSync(`webpack --env URL=${url}`, { stdio: 'inherit' });
+} else {
+  execSync('webpack', { stdio: 'inherit' });
+}

webrtc-internals-exporter/webpack/package.json

@@ -0,0 +1,33 @@
+{
+  "name": "webrtc-internals-exporter",
+  "version": "1.0.0",
+  "private": true,
+  "scripts": {
+    "build": "node build.js"
+  },
+  "keywords": [],
+  "author": "Mirko Milovanovic",
+  "license": "MIT",
+  "devDependencies": {
+    "babel-loader": "^8.2.2",
+    "clean-webpack-plugin": "^3.0.0",
+    "copy-webpack-plugin": "^12.0.2",
+    "dotenv": "^16.4.7",
+    "file-loader": "^6.2.0",
+    "html-webpack-plugin": "^5.3.1",
+    "mini-css-extract-plugin": "^1.6.0",
+    "postcss": "^8.2.14",
+    "postcss-loader": "^5.2.0",
+    "postcss-preset-env": "^10.1.4",
+    "sass": "^1.32.12",
+    "sass-loader": "^11.0.1",
+    "serve": "^14.2.4",
+    "style-loader": "^2.0.0",
+    "terser-webpack-plugin": "^5.1.1",
+    "ts-loader": "^9.1.2",
+    "typescript": "^4.2.4",
+    "webpack": "^5.38.1",
+    "webpack-cli": "^4.7.2",
+    "webpack-dev-server": "^5.2.0"
+  }
+}

webrtc-internals-exporter/webpack/webpack.config.js

@@ -0,0 +1,34 @@
+const path = require('path');
+const { EnvironmentPlugin } = require('webpack');
+const envPath = path.resolve(__dirname, '../../.env');
+const envConfig = require('dotenv').config({ path: envPath }).parsed;
+
+module.exports = (env) => {
+  const url = env.URL || 'http://localhost';
+
+  return {
+    entry: '../background.js',
+    target: 'web',
+    mode: 'production',
+    module: {
+      rules: [
+        {
+          test: /\.js?$/,
+          use: 'babel-loader',
+          exclude: /node_modules/,
+        },
+      ],
+    },
+    resolve: { extensions: ['.tsx', '.ts', '.js'] },
+    output: {
+      filename: 'background.bundle.js',
+      path: path.resolve(__dirname, '../'),
+      publicPath: '',
+    },
+    plugins: [
+      new EnvironmentPlugin({
+        WEBRTC_INTERNALS_EXPORTER_URL: envConfig.WEBRTC_INTERNALS_EXPORTER_URL || url
+      }),
+    ],
+  };
+};