Merge branch 'sarob-patch05' of https://github.com/sarob/Auto_Jobs_Ap…

…plier_AIHawk into sarob-patch05

README.md

@@ -555,12 +555,22 @@ Using this folder as a guide can be particularly helpful for:
 0. **Account language**
    To ensure the bot works, your account language must be set to English.
 
-2. **Data Folder:**
+1. **Data Folder:**
    Ensure that your data_folder contains the following files:
    - `secrets.yaml`
    - `config.yaml`
    - `plain_text_resume.yaml`
 
+2. **Output Folder:**
+    Contains the output of the bot.
+    - `data.json` results of the --collect mode
+    - `failed.json` failed applications
+    - `open_ai_calls.json` all the calls made to the LLM model
+    - `skipped.json` applications that were skipped
+    - `success.json` successful applications
+
+    **Note:** `answers.json` is not part of the output folder and can be found in the root of the project. It is used to store the answers of the questions asked to the user. Can be used to update the bot with corrected answers. Search for `Select an option`, `0`, `Authorized`, and `how many years of` to verify correct answers.
+
 3. **Run the Bot:**
 
    Auto_Jobs_Applier_AIHawk offers flexibility in how it handles your pdf resume:

data_folder/config.yaml

@@ -41,6 +41,9 @@ title_blacklist:
   - word1
   - word2
 
+location_blacklist:
+  - Brazil
+
 job_applicants_threshold:
   min_applicants: 0
   max_applicants: 30

data_folder_example/config.yaml

@@ -41,6 +41,9 @@ title_blacklist:
   - word1
   - word2
 
+location_blacklist:
+  - Brazil
+
 job_applicants_threshold:
   min_applicants: 0
   max_applicants: 30

main.py

@@ -48,21 +48,22 @@ def validate_config(config_yaml_path: Path) -> dict:
             'date': dict,
             'positions': list,
             'locations': list,
+            'location_blacklist': list,
             'distance': int,
-            'companyBlacklist': list,
-            'titleBlacklist': list,
+            'company_blacklist': list,
+            'title_blacklist': list,
             'llm_model_type': str,
             'llm_model': str
         }
 
         for key, expected_type in required_keys.items():
             if key not in parameters:
-                if key in ['companyBlacklist', 'titleBlacklist']:
+                if key in ['company_blacklist', 'title_blacklist', 'location_blacklist']:
                     parameters[key] = []
                 else:
                     raise ConfigError(f"Missing or invalid key '{key}' in config file {config_yaml_path}")
             elif not isinstance(parameters[key], expected_type):
-                if key in ['companyBlacklist', 'titleBlacklist'] and parameters[key] is None:
+                if key in ['company_blacklist', 'title_blacklist', 'location_blacklist'] and parameters[key] is None:
                     parameters[key] = []
                 else:
                     raise ConfigError(f"Invalid type for key '{key}' in config file {config_yaml_path}. Expected {expected_type}.")
@@ -97,7 +98,7 @@ def validate_config(config_yaml_path: Path) -> dict:
             raise ConfigError(f"Invalid distance value in config file {config_yaml_path}. Must be one of: {approved_distances}")
 
         # Ensure blacklists are lists
-        for blacklist in ['companyBlacklist', 'titleBlacklist']:
+        for blacklist in ['company_blacklist', 'title_blacklist','location_blacklist']:
             if not isinstance(parameters.get(blacklist), list):
                 raise ConfigError(f"'{blacklist}' must be a list in config file {config_yaml_path}")
             if parameters[blacklist] is None:

src/aihawk_easy_applier.py

@@ -839,15 +839,6 @@ def _save_questions_to_json(self, question_data: dict) -> None:
         output_file = 'answers.json'
         question_data['question'] = self._sanitize_text(question_data['question'])
 
-        # Check if the question already exists in the JSON file and bail out if it does
-        for item in self.all_data:
-            if self._sanitize_text(item['question']) == question_data['question'] and item['type'] == question_data['type']:
-                logger.debug(f"Question already exists in answers.json. Aborting save of: {item['question']}")
-                return
-            if self.current_job.company in item['answer']:
-                logger.debug(f"Answer contains the Company name. Aborting save of: {item['question']}")
-                return
-
         logger.debug(f"Saving question data to JSON: {question_data}")
         try:
             try:
@@ -865,7 +856,6 @@ def _save_questions_to_json(self, question_data: dict) -> None:
             data.append(question_data)
             with open(output_file, 'w') as f:
                 json.dump(data, f, indent=4)
-                self.all_data = data
             logger.debug("Question data saved successfully to JSON")
         except Exception:
             tb_str = traceback.format_exc()

src/aihawk_job_manager.py

@@ -49,6 +49,7 @@ def set_parameters(self, parameters):
         logger.debug("Setting parameters for AIHawkJobManager")
         self.company_blacklist = parameters.get('company_blacklist', []) or []
         self.title_blacklist = parameters.get('title_blacklist', []) or []
+        self.location_blacklist = parameters.get('location_blacklist', []) or []
         self.positions = parameters.get('positions', [])
         self.locations = parameters.get('locations', [])
         self.apply_once_at_company = parameters.get('apply_once_at_company', False)
@@ -276,8 +277,8 @@ def read_jobs(self):
             raise Exception("No job class elements found on page")
         job_list = [Job(*self.extract_job_information_from_tile(job_element)) for job_element in job_list_elements] 
         for job in job_list:            
-            if self.is_blacklisted(job.title, job.company, job.link):
-                utils.printyellow(f"Blacklisted {job.title} at {job.company}, skipping...")
+            if self.is_blacklisted(job.title, job.company, job.link, job.location):
+                utils.printyellow(f"Blacklisted {job.title} at {job.company} in {job.location}, skipping...")
                 self.write_to_file(job, "skipped")
                 continue
             try:
@@ -361,8 +362,8 @@ def apply_jobs(self):
             """
 
 
-            if self.is_blacklisted(job.title, job.company, job.link):
-                logger.debug(f"Job blacklisted: {job.title} at {job.company}")
+            if self.is_blacklisted(job.title, job.company, job.link, job.location):
+                logger.debug(f"Job blacklisted: {job.title} at {job.company} in {job.location}")
                 self.write_to_file(job, "skipped")
                 continue
             if self.is_already_applied_to_job(job.title, job.company, job.link):
@@ -467,16 +468,17 @@ def extract_job_information_from_tile(self, job_tile):
 
         return job_title, company, job_location, link, apply_method
 
-    def is_blacklisted(self, job_title, company, link):
-        logger.debug(f"Checking if job is blacklisted: {job_title} at {company}")
+    def is_blacklisted(self, job_title, company, link, job_location):
+        logger.debug(f"Checking if job is blacklisted: {job_title} at {company} in {job_location}")
         job_title_words = job_title.lower().split(' ')
         title_blacklisted = any(word in job_title_words for word in map(str.lower, self.title_blacklist))
         company_blacklisted = company.strip().lower() in (word.strip().lower() for word in self.company_blacklist)
+        location_blacklisted= job_location.strip().lower() in (word.strip().lower() for word in self.location_blacklist)
         link_seen = link in self.seen_jobs
-        is_blacklisted = title_blacklisted or company_blacklisted or link_seen
+        is_blacklisted = title_blacklisted or company_blacklisted or location_blacklisted or link_seen
         logger.debug(f"Job blacklisted status: {is_blacklisted}")
 
-        return title_blacklisted or company_blacklisted or link_seen
+        return title_blacklisted or company_blacklisted or location_blacklisted or link_seen
 
     def is_already_applied_to_job(self, job_title, company, link):
         link_seen = link in self.seen_jobs