first commit v2

This commit is contained in:
feder-cr 2024-08-22 10:42:49 +01:00
parent 2dcd7943e8
commit d8b7e7fda6
18 changed files with 663 additions and 1398 deletions

View file

@ -1,4 +1,3 @@
import csv
import os
import random
import time
@ -10,6 +9,7 @@ from selenium.webdriver.common.by import By
import utils
from job import Job
from linkedIn_easy_applier import LinkedInEasyApplier
import json
class EnvironmentKeys:
@ -45,15 +45,15 @@ class LinkedInJobManager:
self.resume_dir = None
self.output_file_directory = Path(parameters['outputFileDirectory'])
self.env_config = EnvironmentKeys()
self.old_question()
#self.old_question()
def set_gpt_answerer(self, gpt_answerer):
self.gpt_answerer = gpt_answerer
def old_question(self):
"""
Load old answers from a CSV file into a dictionary.
"""
def set_resume_generator_manager(self, resume_generator_manager):
self.resume_generator_manager = resume_generator_manager
""" def old_question(self):
self.set_old_answers = {}
file_path = 'data_folder/output/old_Questions.csv'
if os.path.exists(file_path):
@ -62,13 +62,11 @@ class LinkedInJobManager:
for row in csv_reader:
if len(row) == 3:
answer_type, question_text, answer = row
self.set_old_answers[(answer_type.lower(), question_text.lower())] = answer
self.set_old_answers[(answer_type.lower(), question_text.lower())] = answer"""
def start_applying(self):
self.easy_applier_component = LinkedInEasyApplier(
self.driver, self.resume_dir, self.set_old_answers, self.gpt_answerer
)
self.easy_applier_component = LinkedInEasyApplier(self.driver, self.resume_dir, self.set_old_answers, self.gpt_answerer, self.resume_generator_manager)
searches = list(product(self.positions, self.locations))
random.shuffle(searches)
page_sleep = 0
@ -127,50 +125,50 @@ class LinkedInJobManager:
job_results = self.driver.find_element(By.CLASS_NAME, "jobs-search-results-list")
utils.scroll_slow(self.driver, job_results)
utils.scroll_slow(self.driver, job_results, step=300, reverse=True)
job_list_elements = self.driver.find_elements(By.CLASS_NAME, 'scaffold-layout__list-container')[0].find_elements(By.CLASS_NAME, 'jobs-search-results__list-item')
if not job_list_elements:
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]
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...")
self.write_to_file(job.company, job.location, job.title, job.link, "skipped")
self.write_to_file(job, "skipped")
continue
try:
if job.apply_method not in {"Continue", "Applied", "Apply"}:
self.easy_applier_component.job_apply(job)
self.write_to_file(job, "success")
except Exception as e:
utils.printred(traceback.format_exc())
self.write_to_file(job.company, job.location, job.title, job.link, "failed")
continue
self.write_to_file(job.company, job.location, job.title, job.link, "success")
self.write_to_file(job, "failed")
continue
except Exception as e:
traceback.format_exc()
raise e
def write_to_file(self, company, job_title, link, job_location, file_name):
to_write = [company, job_title, link, job_location]
file_path = self.output_file_directory / f"{file_name}.csv"
with open(file_path, 'a', newline='', encoding='utf-8') as f:
writer = csv.writer(f)
writer.writerow(to_write)
def record_gpt_answer(self, answer_type, question_text, gpt_response):
to_write = [answer_type, question_text, gpt_response]
file_path = self.output_file_directory / "registered_jobs.csv"
try:
with open(file_path, 'a', newline='', encoding='utf-8') as f:
writer = csv.writer(f)
writer.writerow(to_write)
except Exception as e:
utils.printred(f"Error writing registered job: {e}")
utils.printred(f"Details: Answer type: {answer_type}, Question: {question_text}")
def write_to_file(self, job, file_name):
data = {
"company": job.company,
"job_title": job.title,
"link": job.link,
"job_location": job.location,
"pdf_path": job.pdf_path
}
file_path = self.output_file_directory / f"{file_name}.json"
if not file_path.exists():
with open(file_path, 'w', encoding='utf-8') as f:
json.dump([data], f, indent=4)
else:
with open(file_path, 'r+', encoding='utf-8') as f:
try:
existing_data = json.load(f)
except json.JSONDecodeError:
existing_data = []
existing_data.append(data)
f.seek(0)
json.dump(existing_data, f, indent=4)
f.truncate()
def get_base_search_url(self, parameters):
url_parts = []
@ -205,12 +203,6 @@ class LinkedInJobManager:
company = job_tile.find_element(By.CLASS_NAME, 'job-card-container__primary-description').text
except:
pass
try:
hiring_line = job_tile.find_element(By.XPATH, '//span[contains(.,\' is hiring for this\')]')
hiring_line_text = hiring_line.text
name_terminating_index = hiring_line_text.find(' is hiring for this')
except:
pass
try:
job_location = job_tile.find_element(By.CLASS_NAME, 'job-card-container__metadata-item').text
except: