README.md

@@ -2,15 +2,18 @@
 
 ## Description
 
-This project is a web scraper designed to extract data from websites.
+This project is a web scraper designed to extract data from websites. It can be customized to scrape various types of data and save it in different formats.
 
 ## Features
 
-☑️ Extracts data from web pages
+- Extracts data from web pages
+<!-- - Supports multiple data formats (CSV, JSON, etc.)
+- Customizable scraping rules
+- Error handling and logging -->
 
-## Usage
+## Installation
 
-### With Docker
+### Using Docker
 
 1. Clone the repository:
 
@@ -24,51 +27,57 @@ git clone https://git.wmi.amu.edu.pl/s500042/webscraper
 cd webscraper
 ```
 
-3. Build the Docker image and run it using `start.py` script:
+3. Build the Docker image and run it using script:
+   - On Linux, ?Mac <!-- I haven't tested it yet -->
 
 ```bash
-python scripts/start.py
+./start.sh
 ```
 
-On Mac, you'll have to use
+- Windows 🤡
 
 ```bash
-python3 scripts/start.py
+python start.py
 ```
 
-4. Check `/app/dist/data.json` file to see the extracted data.
+This one will work just fine on Linux, but on Mac, you'll have to use
+
+```bash
+python3 start.py
+```
 
 ### Without Docker
 
 1. Clone the repository:
 
 ```bash
-git clone https://git.wmi.amu.edu.pl/s500042/webscraper
+git clone https://github.com/yourusername/webscraper.git
 ```
 
-2. Install the required dependencies:
+2. Navigate to the project directory:
 
 ```bash
-pip install -r app/requirements.txt
+cd webscraper/app
+```
+
+3. Install the required dependencies:
+
+```bash
+pip install -r requirements.txt
 ```
 
 If you're on Arch Linux, you'll need to create a virtual environment.
 Here's is a [Step by step guide](#) that will help you create it.
 
-3. Run `run_with_no_docker.py` script:
+## Usage
+
+1. Configure the scraper by editing the `config.json` file.
+2. Run the scraper:
 
 ```bash
-python scripts/run_with_no_docker.py
+python scraper.py
 ```
 
-On Mac you'll, need to use:
-
-```bash
-python3 scripts/run_with_no_docker.py
-```
-
-4. Check `/app/dist/data.json` file to see the extracted data.
-
 ## License
 
 This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

scripts/commands.py

@@ -0,0 +1,33 @@
+import subprocess
+
+
+def quitCondition(command: str) -> bool:
+    return command in ["q", "quit", "exit", "stop"]
+
+
+def helpCondition(command: str) -> bool:
+    return command in ["h", "help"]
+
+
+def clearCondition(command: str) -> bool:
+    return command in ["c", "clear", "cls"]
+
+
+def systemCommand(command: str) -> str:
+    words = command[slice(1, len(command))].split()
+    if words[0] == "":
+        return "Command not found. Write 'h' for help."
+    return subprocess.run(
+        f'docker exec -it webscraper {" ".join(words)}',
+        shell=True,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+    ).stdout.decode()
+
+
+def restartCondition(command: str) -> bool:
+    return command in ["r", "restart"]
+
+
+def runCondition(command: str) -> bool:
+    return command in ["run"]

scripts/get_path.py

@@ -1,30 +0,0 @@
-import os
-from run_command import run_command
-
-
-def get_path():
-    pwd = run_command("pwd")
-    splitted = pwd.split("/")
-    splitted[-1] = splitted[-1].replace("\n", "")
-
-    print(splitted[: splitted.index("webscraper") + 1])
-
-    if splitted.count("webscraper") > 1 and "webscraper" in splitted:
-        for i in range(len(splitted) - 1, -1, -1):
-            potential_path = "/".join(splitted[: i + 1])
-            if "webscraper" in potential_path:
-                script_path = f"{potential_path}/scripts"
-                if os.path.isdir(script_path):
-                    return potential_path
-                else:
-                    return "This is not a valid webscraper project."
-    else:
-        return "/".join(splitted[: splitted.index("webscraper") + 1])
-
-
-def run_main():
-    print(get_path())
-
-
-if __name__ == "__main__":
-    run_main()

scripts/run_command.py

@@ -1,13 +0,0 @@
-import subprocess
-import sys
-
-
-def run_command(command: str) -> str:
-    process = subprocess.run(
-        command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE
-    )
-    if process.returncode != 0:
-        print(f"Error running command: {command}")
-        print(process.stderr.decode())
-        sys.exit(process.returncode)
-    return process.stdout.decode()

scripts/run_with_no_docker.py

@@ -1,17 +0,0 @@
-import subprocess
-import os
-from run_command import run_command
-from get_path import get_path
-
-
-def run_main():
-    path = get_path()
-    try:
-        result = run_command(f"python3 {path}/app/main.py")
-        print(result)
-    except subprocess.CalledProcessError as e:
-        print(f"Error occurred: {e.stderr}")
-
-
-if __name__ == "__main__":
-    run_main()

scripts/start.py

@@ -1,15 +1,24 @@
 import subprocess
 import os
-from run_command import run_command
+import sys
+
+
+def run_command(command: str) -> str:
+    process = subprocess.run(
+        command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+    )
+    if process.returncode != 0:
+        print(f"Error running command: {command}")
+        print(process.stderr.decode())
+        sys.exit(process.returncode)
+    return process.stdout.decode()
 
 
 def main():
-    docker_compose_file = os.getenv(
+    docker_compose_file = os.getenv("DOCKER_COMPOSE_FILE", "./app/docker-compose.yaml")
-        "DOCKER_COMPOSE_FILE", "$WEBSCRAPER/app/docker-compose.yaml"
-    )
     service_name = os.getenv("SERVICE_NAME", "webscraper")
     script_name = os.getenv("SCRIPT_NAME", "main.py")
-    try:
+
     print("Starting Docker Compose services...\n")
     run_command(f"docker compose -f {docker_compose_file} up -d")
 
@@ -17,9 +26,6 @@ def main():
 
     print("Stopping and removing Docker Compose services...")
     run_command(f"docker compose -f {docker_compose_file} down")
-    except subprocess.CalledProcessError as e:
-        print("An error occurred while running the script.")
-        print(e)
 
 
 if __name__ == "__main__":

scripts/threads/commands.py

@@ -1,57 +0,0 @@
-from run_command import run_command
-
-
-def quitCondition(command: str) -> bool:
-    return command in ["q", "quit", "exit", "stop"]
-
-
-def quitService(path: str):
-    print("Stopping and removing Docker Compose services...")
-    run_command(f"docker compose -f {path}/app/docker-compose.yaml down")
-    return None
-
-
-def helpCondition(command: str) -> bool:
-    return command in ["h", "help"]
-
-
-def clearCondition(command: str) -> bool:
-    return command in ["c", "clear", "cls"]
-
-
-def systemCommand(command: str) -> str:
-    words = command[1:].split()
-    if words[0] == "":
-        return "Command not found. Write 'h' for help."
-    print(
-        run_command(
-            f'docker exec -it webscraper {" ".join(words)}',
-        )
-    )
-    return None
-
-
-def restartCondition(command: str) -> bool:
-    return command in ["r", "restart"]
-
-
-def restartService(path: str):
-    print("Restarting Docker Compose services...")
-    run_command(f"docker compose -f {path}/app/docker-compose.yaml down")
-    run_command(f"docker compose -f {path}/app/docker-compose.yaml up -d")
-    print("Composed!")
-    return None
-
-
-def runCondition(command: str) -> bool:
-    return command in ["run"]
-
-
-def runService():
-    print("Running main.py...")
-    print(
-        run_command(
-            "docker exec -it webscraper python main.py",
-        )
-    )
-    return None

scripts/threads/help_list.py

@@ -1,9 +0,0 @@
-def help_list():
-    return """
-["h", "help"], - for help.
-["q", "quit", "exit", "stop"], - to stop program.
-["c", "clear", "cls"], - to clear console.
-["r", "restart"], - to restart Docker Compose services.
-["run"], - to run main.py in docker container.
-["$..."], - to evaluate command in docker container.
-"""

scripts/threads/prompt.py

@@ -1,30 +1,65 @@
+import commands
+import subprocess
 import sys
-from threads.commands import *
+import threading
-from run_command import run_command
-from get_path import get_path
-from threads.help_list import help_list
 
 
 def prompt():
     while True:
         command = input("> ")
-        if quitCondition(command):
+        if commands.quitCondition(command):
-            quitService(get_path())
+            print("Stopping and removing Docker Compose services...")
+            subprocess.run(
+                "docker compose -f ../app/docker-compose.yaml down",
+                shell=True,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+            )
             break
-        if helpCondition(command):
+        if commands.helpCondition(command):
-            print(help_list())
+            print(
+                """
+["h", "help"], - for help.
+["q", "quit", "exit", "stop"], - to stop program.
+["c", "clear", "cls"], - to clear console.
+["r", "restart"], - to restart Docker Compose services.
+["run"], - to run main.py in docker container.
+["$..."], - to evaluate command in docker container.
+"""
+            )
             continue
-        if clearCondition(command):
+        if commands.clearCondition(command):
-            run_command("clear")
+            print("\n" * 100)
             continue
         if command.startswith("$"):
-            systemCommand(command)
+            print(commands.systemCommand(command))
             continue
-        if restartCondition(command):
+        if commands.restartCondition(command):
-            restartService(get_path())
+            print("Restarting Docker Compose services...")
+            subprocess.run(
+                "docker compose -f ../app/docker-compose.yaml down",
+                shell=True,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+            )
+            subprocess.run(
+                "docker compose -f ../app/docker-compose.yaml up -d",
+                shell=True,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+            )
+            print("Composed!")
             continue
-        if runCondition(command):
+        if commands.runCondition(command):
-            runService()
+            print("Running main.py...")
+            print(
+                subprocess.run(
+                    "docker exec -it webscraper python main.py",
+                    shell=True,
+                    stdout=subprocess.PIPE,
+                    stderr=subprocess.PIPE,
+                ).stdout.decode()
+            )
             continue
         if command == "":
             continue

scripts/watch.py

@@ -1,20 +1,26 @@
+import subprocess
 import time
 import os
 import threading
 from threads.prompt import prompt
-from run_command import run_command
+
-from get_path import get_path
+
+def run_command(command: str) -> str:
+    process = subprocess.run(
+        command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+    )
+    if process.returncode != 0:
+        print(f"Error running command: {command}")
+        return process.stderr.decode()
+    return process.stdout.decode()
+
 
 thread = threading.Thread(target=prompt)
 
 
 def main():
-    path = get_path()
-    docker_compose_file = os.getenv(
-        "DOCKER_COMPOSE_FILE", f"{path}/app/docker-compose.yaml"
-    )
     print("Starting Docker Compose services...")
-    run_command(f"docker compose -f {docker_compose_file} up -d")
+    run_command("docker compose -f ../app/docker-compose.yaml up -d")
     print("Composed!\n")
     print("Running main.py...")
     print(run_command("docker exec -it webscraper python main.py"))
@@ -25,9 +31,10 @@ def main():
     print("\nWatching for changes...")
     thread.start()
 
+    path_to_watch = "/home/paprykdev/uni/webscraper/app"
     before = {
-        f: os.stat(os.path.join(path, "app", f)).st_mtime
+        f: os.stat(os.path.join(path_to_watch, f)).st_mtime
-        for f in os.listdir(os.path.join(path, "app"))
+        for f in os.listdir(path_to_watch)
         if f.endswith(".py")
     }
 
@@ -36,8 +43,8 @@ def main():
             break
         time.sleep(1)
         after = {
-            f: os.stat(os.path.join(path, "app", f)).st_mtime
+            f: os.stat(os.path.join(path_to_watch, f)).st_mtime
-            for f in os.listdir(os.path.join(path, "app"))
+            for f in os.listdir(path_to_watch)
             if f.endswith(".py")
         }
         for f in before: