# Continue with more scraper implementations # 8. scrapers/linkedin_scraper.py files_content['scrapers/linkedin_scraper.py'] = """\"\"\"LinkedIn job scraper\"\"\" from selenium.webdriver.common.by import By from selenium.webdriver.common.keys import Keys from scrapers.base_scraper import BaseScraper import time class LinkedInScraper(BaseScraper): \"\"\"Scraper for LinkedIn jobs\"\"\" def __init__(self, settings): super().__init__(settings) self.platform = 'LinkedIn' self.base_url = 'https://www.linkedin.com' def login(self): \"\"\"Login to LinkedIn\"\"\" try: self.logger.info("Logging in to LinkedIn...") self.driver.get(f"{self.base_url}/login") self.random_delay() # Enter email email_input = self.safe_find_element(By.ID, 'username') if email_input: email_input.send_keys(self.settings.linkedin_email) self.random_delay(0.5, 1) # Enter password password_input = self.safe_find_element(By.ID, 'password') if password_input: password_input.send_keys(self.settings.linkedin_password) self.random_delay(0.5, 1) # Click login login_button = self.safe_find_element(By.XPATH, '//button[@type="submit"]') if login_button: self.safe_click(login_button) self.random_delay(3, 5) self.logger.info("Successfully logged in to LinkedIn") return True except Exception as e: self.logger.error(f"LinkedIn login failed: {str(e)}") return False def scrape_jobs(self): \"\"\"Scrape job listings from LinkedIn\"\"\" jobs = [] try: # Login first if not self.login(): return jobs # Navigate to jobs page for job_title in self.settings.job_titles: for location in self.settings.locations: self.logger.info(f"Searching for {job_title} in {location}...") # Build search URL search_url = self._build_search_url(job_title, location) self.driver.get(search_url) self.random_delay(2, 4) # Scroll and load more jobs self._scroll_to_load_jobs() # Extract job listings job_cards = self.driver.find_elements(By.CSS_SELECTOR, '.job-card-container') self.logger.info(f"Found {len(job_cards)} job cards") for card in job_cards[:20]: # Limit to first 20 try: job_data = self._extract_job_data(card) if job_data: jobs.append(job_data) except Exception as e: self.logger.warning(f"Failed to extract job: {str(e)}") continue except Exception as e: self.logger.error(f"Error scraping LinkedIn jobs: {str(e)}") return jobs def _build_search_url(self, job_title, location): \"\"\"Build LinkedIn job search URL\"\"\" job_title_encoded = job_title.replace(' ', '%20') location_encoded = location.replace(' ', '%20') url = f"{self.base_url}/jobs/search/?" url += f"keywords={job_title_encoded}" url += f"&location={location_encoded}" if self.settings.easy_apply_only: url += "&f_AL=true" # Easy Apply filter return url def _scroll_to_load_jobs(self): \"\"\"Scroll to load more jobs\"\"\" last_height = self.driver.execute_script("return document.body.scrollHeight") for _ in range(3): # Scroll 3 times self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);") self.random_delay(1, 2) new_height = self.driver.execute_script("return document.body.scrollHeight") if new_height == last_height: break last_height = new_height def _extract_job_data(self, card): \"\"\"Extract job data from job card\"\"\" try: # Extract job details title_elem = card.find_element(By.CSS_SELECTOR, '.job-card-list__title') company_elem = card.find_element(By.CSS_SELECTOR, '.job-card-container__company-name') location_elem = card.find_element(By.CSS_SELECTOR, '.job-card-container__metadata-item') link_elem = card.find_element(By.CSS_SELECTOR, 'a') job_data = { 'title': title_elem.text.strip(), 'company': company_elem.text.strip(), 'location': location_elem.text.strip(), 'url': link_elem.get_attribute('href'), 'platform': 'LinkedIn' } return job_data except Exception as e: self.logger.warning(f"Failed to extract job data: {str(e)}") return None """ # 9. scrapers/naukri_scraper.py files_content['scrapers/naukri_scraper.py'] = """\"\"\"Naukri.com job scraper\"\"\" from selenium.webdriver.common.by import By from scrapers.base_scraper import BaseScraper class NaukriScraper(BaseScraper): \"\"\"Scraper for Naukri.com jobs\"\"\" def __init__(self, settings): super().__init__(settings) self.platform = 'Naukri' self.base_url = 'https://www.naukri.com' def login(self): \"\"\"Login to Naukri\"\"\" try: self.logger.info("Logging in to Naukri...") self.driver.get(f"{self.base_url}/nlogin/login") self.random_delay(2, 3) # Enter email email_input = self.safe_find_element(By.ID, 'usernameField') if email_input: email_input.send_keys(self.settings.naukri_email) self.random_delay(0.5, 1) # Enter password password_input = self.safe_find_element(By.ID, 'passwordField') if password_input: password_input.send_keys(self.settings.naukri_password) self.random_delay(0.5, 1) # Click login login_button = self.safe_find_element(By.XPATH, '//button[@type="submit"]') if login_button: self.safe_click(login_button) self.random_delay(3, 5) self.logger.info("Successfully logged in to Naukri") return True except Exception as e: self.logger.error(f"Naukri login failed: {str(e)}") return False def scrape_jobs(self): \"\"\"Scrape job listings from Naukri\"\"\" jobs = [] try: # Login first if not self.login(): return jobs # Search for jobs for job_title in self.settings.job_titles: for location in self.settings.locations: self.logger.info(f"Searching Naukri for {job_title} in {location}...") # Build search URL search_url = self._build_search_url(job_title, location) self.driver.get(search_url) self.random_delay(2, 4) # Extract job listings job_cards = self.driver.find_elements(By.CSS_SELECTOR, '.jobTuple') self.logger.info(f"Found {len(job_cards)} jobs on Naukri") for card in job_cards[:20]: try: job_data = self._extract_job_data(card) if job_data: jobs.append(job_data) except Exception as e: self.logger.warning(f"Failed to extract job: {str(e)}") continue except Exception as e: self.logger.error(f"Error scraping Naukri jobs: {str(e)}") return jobs def _build_search_url(self, job_title, location): \"\"\"Build Naukri search URL\"\"\" job_title_encoded = job_title.replace(' ', '-') location_encoded = location.replace(' ', '-') url = f"{self.base_url}/{job_title_encoded}-jobs-in-{location_encoded}" return url def _extract_job_data(self, card): \"\"\"Extract job data from job card\"\"\" try: title_elem = card.find_element(By.CSS_SELECTOR, '.title') company_elem = card.find_element(By.CSS_SELECTOR, '.companyInfo') location_elem = card.find_element(By.CSS_SELECTOR, '.location') link_elem = card.find_element(By.CSS_SELECTOR, 'a') job_data = { 'title': title_elem.text.strip(), 'company': company_elem.text.strip(), 'location': location_elem.text.strip(), 'url': link_elem.get_attribute('href'), 'platform': 'Naukri' } return job_data except Exception as e: return None """ # 10. scrapers/hirist_scraper.py files_content['scrapers/hirist_scraper.py'] = """\"\"\"Hirist.com job scraper\"\"\" from selenium.webdriver.common.by import By from scrapers.base_scraper import BaseScraper class HiristScraper(BaseScraper): \"\"\"Scraper for Hirist.com jobs\"\"\" def __init__(self, settings): super().__init__(settings) self.platform = 'Hirist' self.base_url = 'https://www.hirist.com' def login(self): \"\"\"Login to Hirist\"\"\" try: self.logger.info("Logging in to Hirist...") self.driver.get(f"{self.base_url}/login") self.random_delay(2, 3) # Hirist login implementation # Note: Adjust selectors based on actual Hirist login page email_input = self.safe_find_element(By.NAME, 'email') if email_input: email_input.send_keys(self.settings.hirist_email) password_input = self.safe_find_element(By.NAME, 'password') if password_input: password_input.send_keys(self.settings.hirist_password) login_button = self.safe_find_element(By.XPATH, '//button[contains(text(), "Login")]') if login_button: self.safe_click(login_button) self.random_delay(3, 5) self.logger.info("Successfully logged in to Hirist") return True except Exception as e: self.logger.error(f"Hirist login failed: {str(e)}") return False def scrape_jobs(self): \"\"\"Scrape job listings from Hirist\"\"\" jobs = [] try: if not self.login(): return jobs for job_title in self.settings.job_titles: search_url = f"{self.base_url}/jobs/{job_title.replace(' ', '-').lower()}" self.driver.get(search_url) self.random_delay(2, 4) # Extract job listings (adjust selectors as needed) job_cards = self.driver.find_elements(By.CSS_SELECTOR, '.job-card') for card in job_cards[:15]: try: job_data = self._extract_job_data(card) if job_data: jobs.append(job_data) except: continue except Exception as e: self.logger.error(f"Error scraping Hirist: {str(e)}") return jobs def _extract_job_data(self, card): \"\"\"Extract job data from card\"\"\" try: title = card.find_element(By.CSS_SELECTOR, '.job-title').text company = card.find_element(By.CSS_SELECTOR, '.company-name').text url = card.find_element(By.CSS_SELECTOR, 'a').get_attribute('href') return { 'title': title, 'company': company, 'location': 'India', # Default 'url': url, 'platform': 'Hirist' } except: return None """ print("Created scraper implementations") print("Total files:", len(files_content))