Replace Selenium with Playwright for browser automation

config.py

@@ -4,7 +4,6 @@
 
 #config related to logging must have prefix LOG_
 LOG_LEVEL = 'ERROR'
-LOG_SELENIUM_LEVEL = ERROR
 LOG_TO_FILE = False
 LOG_TO_CONSOLE = False
 
@@ -17,6 +16,6 @@
 JOB_MIN_APPLICATIONS = 1
 
 LLM_MODEL_TYPE = 'openai'
-LLM_MODEL = 'gpt-4o-mini'
+LLM_MODEL = 'gpt-5-mini'
 # Only required for OLLAMA models
 LLM_API_URL = ''

main.py

@@ -7,11 +7,9 @@
 import click
 import inquirer
 import yaml
-from selenium import webdriver
-from selenium.common.exceptions import WebDriverException
-from selenium.webdriver.chrome.service import Service as ChromeService
-from webdriver_manager.chrome import ChromeDriverManager
 import re
+from src.utils.patch_lib_resume_builder import apply_patch
+apply_patch()
 from src.libs.resume_and_cover_builder import ResumeFacade, ResumeGenerator, StyleManager
 from src.resume_schemas.job_application_profile import JobApplicationProfile
 from src.resume_schemas.resume import Resume

requirements.txt

@@ -14,7 +14,7 @@ langchain-ollama==0.1.3
 langchain-openai==0.1.17
 langchain-text-splitters==0.2.2
 langsmith==0.1.93
-Levenshtein==0.25.1
+Levenshtein>=0.26.0
 loguru==0.7.2
 openai==1.37.1
 pdfminer.six==20221105
@@ -23,9 +23,7 @@ python-dotenv~=1.0.1
 PyYAML~=6.0.2
 regex==2024.7.24
 reportlab==4.2.2
-selenium==4.9.1
-webdriver-manager==4.0.2
+playwright>=1.40.0
 pytest
 pytest-mock
-pytest-cov
-undetected-chromedriver==3.5.5
+pytest-cov

src/libs/resume_and_cover_builder/resume_facade.py

@@ -37,8 +37,8 @@ def __init__(self, api_key, style_manager, resume_generator, resume_object, outp
         self.resume_generator.set_resume_object(resume_object)
         self.selected_style = None  # Property to store the selected style
 
-    def set_driver(self, driver):
-         self.driver = driver
+    def set_driver(self, page):
+         self.driver = page
 
     def prompt_user(self, choices: list[str], message: str) -> str:
         """
@@ -69,10 +69,8 @@ def prompt_for_text(self, message: str) -> str:
 
 
     def link_to_job(self, job_url):
-        self.driver.get(job_url)
-        self.driver.implicitly_wait(10)
-        body_element = self.driver.find_element("tag name", "body")
-        body_element = body_element.get_attribute("outerHTML")
+        self.driver.goto(job_url, wait_until="networkidle")
+        body_element = self.driver.locator("body").inner_html()
         self.llm_job_parser = LLMParser(openai_api_key=global_config.API_KEY)
         self.llm_job_parser.set_body_html(body_element)
 
@@ -105,7 +103,7 @@ def create_resume_pdf_job_tailored(self) -> tuple[bytes, str]:
         suggested_name = hashlib.md5(self.job.link.encode()).hexdigest()[:10]
 
         result = HTML_to_PDF(html_resume, self.driver)
-        self.driver.quit()
+        self.driver.close()
         return result, suggested_name
 
 
@@ -125,7 +123,7 @@ def create_resume_pdf(self) -> tuple[bytes, str]:
 
         html_resume = self.resume_generator.create_resume(style_path)
         result = HTML_to_PDF(html_resume, self.driver)
-        self.driver.quit()
+        self.driver.close()
         return result
 
     def create_cover_letter(self) -> tuple[bytes, str]:
@@ -149,5 +147,5 @@ def create_cover_letter(self) -> tuple[bytes, str]:
 
 
         result = HTML_to_PDF(cover_letter_html, self.driver)
-        self.driver.quit()
+        self.driver.close()
         return result, suggested_name

src/logging.py

@@ -3,9 +3,8 @@
 import sys
 import logging
 from loguru import logger
-from selenium.webdriver.remote.remote_connection import LOGGER as selenium_logger
 
-from config import LOG_LEVEL, LOG_SELENIUM_LEVEL, LOG_TO_CONSOLE, LOG_TO_FILE
+from config import LOG_LEVEL, LOG_TO_CONSOLE, LOG_TO_FILE
 
 
 def remove_default_loggers():
@@ -52,29 +51,5 @@ def get_log_filename():
         )
 
 
-def init_selenium_logger():
-    """Initialize and configure selenium logger to write to selenium.log."""
-    log_file = "log/selenium.log"
-    os.makedirs(os.path.dirname(log_file), exist_ok=True)
-
-    selenium_logger.handlers.clear()
-
-    selenium_logger.setLevel(LOG_SELENIUM_LEVEL)
-
-    # Create file handler for selenium logger
-    file_handler = logging.handlers.TimedRotatingFileHandler(
-        log_file, when="D", interval=1, backupCount=5
-    )
-    file_handler.setLevel(LOG_SELENIUM_LEVEL)
-
-    # Define a simplified format for selenium logger entries
-    formatter = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
-    file_handler.setFormatter(formatter)
-
-    # Add the file handler to selenium_logger
-    selenium_logger.addHandler(file_handler)
-
-
 remove_default_loggers()
 init_loguru_logger()
-init_selenium_logger()

src/utils/chrome_utils.py

@@ -1,93 +1,66 @@
-import os
-import time
-from selenium import webdriver
-from selenium.webdriver.chrome.service import Service as ChromeService
-from selenium.webdriver.chrome.options import Options
-from webdriver_manager.chrome import ChromeDriverManager  # Import webdriver_manager
 import urllib
+from playwright.sync_api import sync_playwright
 from src.logging import logger
 
-def chrome_browser_options():
-    logger.debug("Setting Chrome browser options")
-    options = Options()
-    options.add_argument("--start-maximized")
-    options.add_argument("--no-sandbox")
-    options.add_argument("--disable-dev-shm-usage")
-    options.add_argument("--ignore-certificate-errors")
-    options.add_argument("--disable-extensions")
-    options.add_argument("--disable-gpu")  # Opzionale, utile in alcuni ambienti
-    options.add_argument("window-size=1200x800")
-    options.add_argument("--disable-background-timer-throttling")
-    options.add_argument("--disable-backgrounding-occluded-windows")
-    options.add_argument("--disable-translate")
-    options.add_argument("--disable-popup-blocking")
-    options.add_argument("--no-first-run")
-    options.add_argument("--no-default-browser-check")
-    options.add_argument("--disable-logging")
-    options.add_argument("--disable-autofill")
-    options.add_argument("--disable-plugins")
-    options.add_argument("--disable-animations")
-    options.add_argument("--disable-cache")
-    options.add_argument("--incognito")
-    options.add_argument("--allow-file-access-from-files")  # Consente l'accesso ai file locali
-    options.add_argument("--disable-web-security")         # Disabilita la sicurezza web
-    logger.debug("Using Chrome in incognito mode")
-
-    return options
+_playwright = None
+_browser = None
 
-def init_browser() -> webdriver.Chrome:
+
+def _get_browser():
+    """Get or create a shared Playwright browser instance."""
+    global _playwright, _browser
+    if _browser is None or not _browser.is_connected():
+        logger.debug("Launching Playwright Chromium browser")
+        _playwright = sync_playwright().start()
+        _browser = _playwright.chromium.launch(headless=True)
+    return _browser
+
+
+def init_browser():
+    """Initialize and return a new Playwright browser page."""
     try:
-        options = chrome_browser_options()
-        # Use webdriver_manager to handle ChromeDriver
-        driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
-        logger.debug("Chrome browser initialized successfully.")
-        return driver
+        browser = _get_browser()
+        page = browser.new_page(viewport={"width": 1200, "height": 800})
+        logger.debug("Playwright browser page initialized successfully.")
+        return page
     except Exception as e:
         logger.error(f"Failed to initialize browser: {str(e)}")
         raise RuntimeError(f"Failed to initialize browser: {str(e)}")
 
 
-
-def HTML_to_PDF(html_content, driver):
+def HTML_to_PDF(html_content, page):
     """
-    Converte una stringa HTML in un PDF e restituisce il PDF come stringa base64.
+    Convert an HTML string to PDF and return it as a base64 string.
 
-    :param html_content: Stringa contenente il codice HTML da convertire.
-    :param driver: Istanza del WebDriver di Selenium.
-    :return: Stringa base64 del PDF generato.
-    :raises ValueError: Se l'input HTML non è una stringa valida.
-    :raises RuntimeError: Se si verifica un'eccezione nel WebDriver.
+    :param html_content: HTML string to convert.
+    :param page: Playwright page instance.
+    :return: Base64 string of the generated PDF.
     """
-    # Validazione del contenuto HTML
+    import base64
+
     if not isinstance(html_content, str) or not html_content.strip():
-        raise ValueError("Il contenuto HTML deve essere una stringa non vuota.")
+        raise ValueError("HTML content must be a non-empty string.")
 
-    # Codifica l'HTML in un URL di tipo data
     encoded_html = urllib.parse.quote(html_content)
     data_url = f"data:text/html;charset=utf-8,{encoded_html}"
 
     try:
-        driver.get(data_url)
-        # Attendi che la pagina si carichi completamente
-        time.sleep(2)  # Potrebbe essere necessario aumentare questo tempo per HTML complessi
+        page.goto(data_url, wait_until="networkidle")
 
-        # Esegue il comando CDP per stampare la pagina in PDF
-        pdf_base64 = driver.execute_cdp_cmd("Page.printToPDF", {
-            "printBackground": True,          # Includi lo sfondo nella stampa
-            "landscape": False,               # Stampa in verticale (False per ritratto)
-            "paperWidth": 8.27,               # Larghezza del foglio in pollici (A4)
-            "paperHeight": 11.69,             # Altezza del foglio in pollici (A4)
-            "marginTop": 0.8,                  # Margine superiore in pollici (circa 2 cm)
-            "marginBottom": 0.8,               # Margine inferiore in pollici (circa 2 cm)
-            "marginLeft": 0.5,                 # Margine sinistro in pollici (circa 1.27 cm)
-            "marginRight": 0.5,                # Margine destro in pollici (circa 1.27 cm)
-            "displayHeaderFooter": False,      # Non visualizzare intestazioni e piè di pagina
-            "preferCSSPageSize": True,         # Preferire le dimensioni della pagina CSS
-            "generateDocumentOutline": False,  # Non generare un sommario del documento
-            "generateTaggedPDF": False,        # Non generare PDF taggato
-            "transferMode": "ReturnAsBase64"   # Restituire il PDF come stringa base64
-        })
-        return pdf_base64['data']
+        pdf_bytes = page.pdf(
+            print_background=True,
+            landscape=False,
+            width="8.27in",
+            height="11.69in",
+            margin={
+                "top": "0.8in",
+                "bottom": "0.8in",
+                "left": "0.5in",
+                "right": "0.5in",
+            },
+            prefer_css_page_size=True,
+        )
+        return base64.b64encode(pdf_bytes).decode("utf-8")
     except Exception as e:
-        logger.error(f"Si è verificata un'eccezione WebDriver: {e}")
-        raise RuntimeError(f"Si è verificata un'eccezione WebDriver: {e}")
+        logger.error(f"Playwright PDF generation error: {e}")
+        raise RuntimeError(f"Playwright PDF generation error: {e}")