afiqzudinhadi/linkedIn_auto_jobs_applier_with_AI
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

reformat code

Browse source
This commit is contained in:
queukat 2024-09-08 17:46:00 +03:00
parent ad85b9587f
commit 5efe6c3048
4 changed files with 82 additions and 98 deletions
Download patch file Download diff file Expand all files Collapse all files

26
src/gpt.py
View file

@ -3,11 +3,11 @@ import os
import re import re
import textwrap import textwrap
import time import time
from datetime import datetime
from abc import ABC, abstractmethod from abc import ABC, abstractmethod
from typing import Dict, List, Union from datetime import datetime
from pathlib import Path from pathlib import Path
from typing import Dict, List from typing import Dict, List
from typing import Union
import httpx import httpx
from Levenshtein import distance from Levenshtein import distance
@ -16,39 +16,42 @@ from langchain_core.messages.ai import AIMessage
from langchain_core.output_parsers import StrOutputParser from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompt_values import StringPromptValue from langchain_core.prompt_values import StringPromptValue
from langchain_core.prompts import ChatPromptTemplate from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
import src.strings as strings import src.strings as strings
from src.utils import logger from src.utils import logger
load_dotenv() load_dotenv()
class AIModel(ABC): class AIModel(ABC):
@abstractmethod @abstractmethod
def invoke(self, prompt: str) -> str: def invoke(self, prompt: str) -> str:
pass pass
class OpenAIModel(AIModel): class OpenAIModel(AIModel):
def __init__(self, api_key: str, llm_model: str, llm_api_url: str): def __init__(self, api_key: str, llm_model: str, llm_api_url: str):
from langchain_openai import ChatOpenAI from langchain_openai import ChatOpenAI
self.model = ChatOpenAI(model_name=llm_model, openai_api_key=api_key, self.model = ChatOpenAI(model_name=llm_model, openai_api_key=api_key,
temperature=0.4, base_url=llm_api_url) temperature=0.4, base_url=llm_api_url)
def invoke(self, prompt: str) -> str: def invoke(self, prompt: str) -> str:
print("invoke in openai") print("invoke in openai")
response = self.model.invoke(prompt) response = self.model.invoke(prompt)
return response return response
class ClaudeModel(AIModel): class ClaudeModel(AIModel):
def __init__(self, api_key: str, llm_model: str, llm_api_url: str): def __init__(self, api_key: str, llm_model: str, llm_api_url: str):
from langchain_anthropic import ChatAnthropic from langchain_anthropic import ChatAnthropic
self.model = ChatAnthropic(model=llm_model, api_key=api_key, self.model = ChatAnthropic(model=llm_model, api_key=api_key,
temperature=0.4, base_url=llm_api_url) temperature=0.4, base_url=llm_api_url)
def invoke(self, prompt: str) -> str: def invoke(self, prompt: str) -> str:
response = self.model.invoke(prompt) response = self.model.invoke(prompt)
return response return response
class OllamaModel(AIModel): class OllamaModel(AIModel):
def __init__(self, api_key: str, llm_model: str, llm_api_url: str): def __init__(self, api_key: str, llm_model: str, llm_api_url: str):
from langchain_ollama import ChatOllama from langchain_ollama import ChatOllama
@ -58,6 +61,7 @@ class OllamaModel(AIModel):
response = self.model.invoke(prompt) response = self.model.invoke(prompt)
return response return response
class AIAdapter: class AIAdapter:
def __init__(self, config: dict, api_key: str): def __init__(self, config: dict, api_key: str):
self.model = self._create_model(config, api_key) self.model = self._create_model(config, api_key)
@ -67,7 +71,7 @@ class AIAdapter:
llm_model = config['llm_model'] llm_model = config['llm_model']
llm_api_url = config['llm_api_url'] llm_api_url = config['llm_api_url']
print('Using {0} with {1} from {2}'.format(llm_model_type, llm_model, llm_api_url)) print('Using {0} with {1} from {2}'.format(llm_model_type, llm_model, llm_api_url))
if llm_model_type == "openai": if llm_model_type == "openai":
return OpenAIModel(api_key, llm_model, llm_api_url) return OpenAIModel(api_key, llm_model, llm_api_url)
elif llm_model_type == "claude": elif llm_model_type == "claude":
@ -80,9 +84,9 @@ class AIAdapter:
def invoke(self, prompt: str) -> str: def invoke(self, prompt: str) -> str:
return self.model.invoke(prompt) return self.model.invoke(prompt)
class LLMLogger: class LLMLogger:
def __init__(self, llm: Union[OpenAIModel, OllamaModel, ClaudeModel]): def __init__(self, llm: Union[OpenAIModel, OllamaModel, ClaudeModel]):
self.llm = llm self.llm = llm
@ -189,7 +193,6 @@ class LLMLogger:
class LoggerChatModel: class LoggerChatModel:
def __init__(self, llm: Union[OpenAIModel, OllamaModel, ClaudeModel]): def __init__(self, llm: Union[OpenAIModel, OllamaModel, ClaudeModel]):
self.llm = llm self.llm = llm
@ -247,7 +250,6 @@ class LoggerChatModel:
time.sleep(30) time.sleep(30)
continue continue
def parse_llmresult(self, llmresult: AIMessage) -> Dict[str, Dict]: def parse_llmresult(self, llmresult: AIMessage) -> Dict[str, Dict]:
logger.debug("Parsing LLM result: %s", llmresult) logger.debug("Parsing LLM result: %s", llmresult)
@ -454,12 +456,14 @@ class GPTAnswerer:
chain = prompt | self.llm_cheap | StrOutputParser() chain = prompt | self.llm_cheap | StrOutputParser()
output = chain.invoke({"question": question}) output = chain.invoke({"question": question})
match = re.search(r"(Personal information|Self Identification|Legal Authorization|Work Preferences|Education Details|Experience Details|Projects|Availability|Salary Expectations|Certifications|Languages|Interests|Cover letter)", output, re.IGNORECASE) match = re.search(
r"(Personal information|Self Identification|Legal Authorization|Work Preferences|Education Details|Experience Details|Projects|Availability|Salary Expectations|Certifications|Languages|Interests|Cover letter)",
output, re.IGNORECASE)
if not match: if not match:
raise ValueError("Could not extract section name from the response.") raise ValueError("Could not extract section name from the response.")
section_name = match.group(1).lower().replace(" ", "_") section_name = match.group(1).lower().replace(" ", "_")
if section_name == "cover_letter": if section_name == "cover_letter":
chain = chains.get(section_name) chain = chains.get(section_name)
output = chain.invoke({"resume": self.resume, "job_description": self.job_description}) output = chain.invoke({"resume": self.resume, "job_description": self.job_description})

11
src/linkedIn_easy_applier.py
View file

@ -37,7 +37,6 @@ class LinkedInEasyApplier:
logger.debug("LinkedInEasyApplier initialized successfully") logger.debug("LinkedInEasyApplier initialized successfully")
def _load_questions_from_json(self) -> List[dict]: def _load_questions_from_json(self) -> List[dict]:
output_file = 'answers.json' output_file = 'answers.json'
logger.debug("Loading questions from JSON file: %s", output_file) logger.debug("Loading questions from JSON file: %s", output_file)
@ -60,7 +59,6 @@ class LinkedInEasyApplier:
logger.error("Error loading questions data from JSON file: %s", tb_str) logger.error("Error loading questions data from JSON file: %s", tb_str)
raise Exception(f"Error loading questions data from JSON file: \nTraceback:\n{tb_str}") raise Exception(f"Error loading questions data from JSON file: \nTraceback:\n{tb_str}")
def check_for_premium_redirect(self, job: Any, max_attempts=3): def check_for_premium_redirect(self, job: Any, max_attempts=3):
current_url = self.driver.current_url current_url = self.driver.current_url
@ -79,7 +77,6 @@ class LinkedInEasyApplier:
raise Exception( raise Exception(
f"Redirected to LinkedIn Premium page and failed to return after {max_attempts} attempts. Job application aborted.") f"Redirected to LinkedIn Premium page and failed to return after {max_attempts} attempts. Job application aborted.")
def job_apply(self, job: Any): def job_apply(self, job: Any):
logger.debug("Starting job application for job: %s", job) logger.debug("Starting job application for job: %s", job)
@ -167,7 +164,6 @@ class LinkedInEasyApplier:
if method.get('find_elements'): if method.get('find_elements'):
buttons = self.driver.find_elements(By.XPATH, method['xpath']) buttons = self.driver.find_elements(By.XPATH, method['xpath'])
if buttons: if buttons:
for index, button in enumerate(buttons): for index, button in enumerate(buttons):
@ -209,7 +205,6 @@ class LinkedInEasyApplier:
logger.error("No clickable 'Easy Apply' button found after 2 attempts. Page source:\n%s", page_source) logger.error("No clickable 'Easy Apply' button found after 2 attempts. Page source:\n%s", page_source)
raise Exception("No clickable 'Easy Apply' button found") raise Exception("No clickable 'Easy Apply' button found")
def _get_job_description(self) -> str: def _get_job_description(self) -> str:
logger.debug("Getting job description") logger.debug("Getting job description")
try: try:
@ -541,7 +536,6 @@ class LinkedInEasyApplier:
wrapped_lines.append(line) wrapped_lines.append(line)
return wrapped_lines return wrapped_lines
lines = split_text_by_width(cover_letter_text, "Helvetica", 12, max_width) lines = split_text_by_width(cover_letter_text, "Helvetica", 12, max_width)
for line in lines: for line in lines:
@ -567,7 +561,6 @@ class LinkedInEasyApplier:
logger.error(f"Traceback: {tb_str}") logger.error(f"Traceback: {tb_str}")
raise raise
file_size = os.path.getsize(file_path_pdf) file_size = os.path.getsize(file_path_pdf)
max_file_size = 2 * 1024 * 1024 # 2 MB max_file_size = 2 * 1024 * 1024 # 2 MB
logger.debug(f"Cover letter file size: {file_size} bytes") logger.debug(f"Cover letter file size: {file_size} bytes")
@ -670,7 +663,6 @@ class LinkedInEasyApplier:
for item in self.all_data: for item in self.all_data:
logger.debug( logger.debug(
f"Comparing sanitized stored question: '{self._sanitize_text(item['question'])}' and type: '{item.get('type')}' with current question: '{self._sanitize_text(question_text)}' and type: '{question_type}'") f"Comparing sanitized stored question: '{self._sanitize_text(item['question'])}' and type: '{item.get('type')}' with current question: '{self._sanitize_text(question_text)}' and type: '{question_type}'")
@ -697,7 +689,6 @@ class LinkedInEasyApplier:
answer = self.gpt_answerer.answer_question_textual_wide_range(question_text) answer = self.gpt_answerer.answer_question_textual_wide_range(question_text)
logger.debug(f"Generated textual answer: {answer}") logger.debug(f"Generated textual answer: {answer}")
self._save_questions_to_json({'type': question_type, 'question': question_text, 'answer': answer}) self._save_questions_to_json({'type': question_type, 'question': question_text, 'answer': answer})
self._enter_text(text_field, answer) self._enter_text(text_field, answer)
logger.debug("Entered new answer into the textbox and saved it to JSON.") logger.debug("Entered new answer into the textbox and saved it to JSON.")
@ -730,7 +721,6 @@ class LinkedInEasyApplier:
logger.debug("Entered existing date answer") logger.debug("Entered existing date answer")
return True return True
self._save_questions_to_json({'type': 'date', 'question': question_text, 'answer': answer_text}) self._save_questions_to_json({'type': 'date', 'question': question_text, 'answer': answer_text})
self._enter_text(date_field, answer_text) self._enter_text(date_field, answer_text)
logger.debug("Entered new date answer") logger.debug("Entered new date answer")
@ -752,7 +742,6 @@ class LinkedInEasyApplier:
logger.debug(f"Dropdown options found: {options}") logger.debug(f"Dropdown options found: {options}")
question_text = question.find_element(By.TAG_NAME, 'label').text.lower() question_text = question.find_element(By.TAG_NAME, 'label').text.lower()
logger.debug(f"Processing dropdown or combobox question: {question_text}") logger.debug(f"Processing dropdown or combobox question: {question_text}")

4
src/linkedIn_job_manager.py
View file

@ -452,9 +452,9 @@ class LinkedInJobManager:
existing_data = json.load(f) existing_data = json.load(f)
for applied_job in existing_data: for applied_job in existing_data:
if applied_job['company'].strip().lower() == company.strip().lower(): if applied_job['company'].strip().lower() == company.strip().lower():
utils.printyellow(f"Already applied at {company} (once per company policy), skipping...") utils.printyellow(
f"Already applied at {company} (once per company policy), skipping...")
return True return True
except json.JSONDecodeError: except json.JSONDecodeError:
continue continue
return False return False

139
src/linkedin-api.py
View file

@ -1,58 +1,59 @@
from typing import Dict, List
from linkedin_api import Linkedin
from typing import Optional, Union, Literal
from urllib.parse import quote, urlencode
import logging import logging
import json from typing import Dict, List
from typing import Optional, Union, Literal
from urllib.parse import urlencode
from linkedin_api import Linkedin
# set log to all debug # set log to all debug
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
class LinkedInEvolvedAPI(Linkedin): class LinkedInEvolvedAPI(Linkedin):
already_applied_jobs: List[str] = [] already_applied_jobs: List[str] = []
def __init__(self, username, password): def __init__(self, username, password):
super().__init__(username, password) super().__init__(username, password)
def search_jobs( def search_jobs(
self, self,
keywords: Optional[str] = None, keywords: Optional[str] = None,
companies: Optional[List[str]] = None, companies: Optional[List[str]] = None,
experience: Optional[ experience: Optional[
List[ List[
Union[ Union[
Literal["1"], Literal["1"],
Literal["2"], Literal["2"],
Literal["3"], Literal["3"],
Literal["4"], Literal["4"],
Literal["5"], Literal["5"],
Literal["6"], Literal["6"],
]
] ]
] ] = None,
] = None, job_type: Optional[
job_type: Optional[ List[
List[ Union[
Union[ Literal["F"],
Literal["F"], Literal["C"],
Literal["C"], Literal["P"],
Literal["P"], Literal["T"],
Literal["T"], Literal["I"],
Literal["I"], Literal["V"],
Literal["V"], Literal["O"],
Literal["O"], ]
] ]
] ] = None,
] = None, job_title: Optional[List[str]] = None,
job_title: Optional[List[str]] = None, industries: Optional[List[str]] = None,
industries: Optional[List[str]] = None, location_name: Optional[str] = None,
location_name: Optional[str] = None, remote: Optional[List[Union[Literal["1"], Literal["2"], Literal["3"]]]] = None,
remote: Optional[List[Union[Literal["1"], Literal["2"], Literal["3"]]]] = None, listed_at: None | int = None,
listed_at: None | int = None, distance: Optional[int] = None,
distance: Optional[int] = None, easy_apply: Optional[bool] = True,
easy_apply: Optional[bool] = True, limit=-1,
limit=-1, offset=0,
offset=0, **kwargs,
**kwargs,
) -> List[Dict]: ) -> List[Dict]:
"""Perform a LinkedIn search for jobs. """Perform a LinkedIn search for jobs.
@ -154,21 +155,21 @@ class LinkedInEvolvedAPI(Linkedin):
e["job_id"] = trackingUrn e["job_id"] = trackingUrn
if e.get("$type") == "com.linkedin.voyager.dash.jobs.JobPosting": if e.get("$type") == "com.linkedin.voyager.dash.jobs.JobPosting":
new_data.append(e) new_data.append(e)
if not new_data: if not new_data:
break break
results.extend(new_data) results.extend(new_data)
if ( if (
(-1 < limit <= len(results)) (-1 < limit <= len(results))
or len(results) / count >= Linkedin._MAX_REPEATED_REQUESTS or len(results) / count >= Linkedin._MAX_REPEATED_REQUESTS
) or len(elements) == 0: ) or len(elements) == 0:
break break
self.logger.debug(f"results grew to {len(results)}") self.logger.debug(f"results grew to {len(results)}")
return results return results
def get_fields_for_easy_apply(self,job_id: str) -> List[Dict]: def get_fields_for_easy_apply(self, job_id: str) -> List[Dict]:
"""Get fields needed for easy apply jobs. """Get fields needed for easy apply jobs.
:param job_id: Job ID :param job_id: Job ID
@ -181,14 +182,12 @@ class LinkedInEvolvedAPI(Linkedin):
cookie_str = "; ".join([f"{k}={v}" for k, v in cookies.items()]) cookie_str = "; ".join([f"{k}={v}" for k, v in cookies.items()])
headers: Dict[str, str] = self._headers() headers: Dict[str, str] = self._headers()
headers["Accept"] = "application/vnd.linkedin.normalized+json+2.1" headers["Accept"] = "application/vnd.linkedin.normalized+json+2.1"
headers["csrf-token"] = cookies["JSESSIONID"].replace('"', "") headers["csrf-token"] = cookies["JSESSIONID"].replace('"', "")
headers["Cookie"] = cookie_str headers["Cookie"] = cookie_str
headers["Connection"] = "keep-alive" headers["Connection"] = "keep-alive"
default_params = { default_params = {
"decorationId": "com.linkedin.voyager.dash.deco.jobs.OnsiteApplyApplication-67", "decorationId": "com.linkedin.voyager.dash.deco.jobs.OnsiteApplyApplication-67",
"jobPostingUrn": f"urn:li:fsd_jobPosting:{job_id}", "jobPostingUrn": f"urn:li:fsd_jobPosting:{job_id}",
@ -217,26 +216,26 @@ class LinkedInEvolvedAPI(Linkedin):
except ValueError: except ValueError:
self.logger.error("Failed to parse JSON response") self.logger.error("Failed to parse JSON response")
return [] return []
form_components = [] form_components = []
for item in data.get("included", []): for item in data.get("included", []):
if 'formComponent' in item: if 'formComponent' in item:
urn = item['urn'] urn = item['urn']
try: try:
title = item['title']['text'] title = item['title']['text']
except TypeError: except TypeError:
title = urn title = urn
form_component_type = list(item['formComponent'].keys())[0] form_component_type = list(item['formComponent'].keys())[0]
form_component_details = item['formComponent'][form_component_type] form_component_details = item['formComponent'][form_component_type]
component_info = { component_info = {
'title': title, 'title': title,
'urn': urn, 'urn': urn,
'formComponentType': form_component_type, 'formComponentType': form_component_type,
} }
if 'textSelectableOptions' in form_component_details: if 'textSelectableOptions' in form_component_details:
options = [ options = [
opt['optionText']['text'] for opt in form_component_details['textSelectableOptions'] opt['optionText']['text'] for opt in form_component_details['textSelectableOptions']
@ -244,18 +243,18 @@ class LinkedInEvolvedAPI(Linkedin):
component_info['selectableOptions'] = options component_info['selectableOptions'] = options
elif 'selectableOptions' in form_component_details: elif 'selectableOptions' in form_component_details:
options = [ options = [
opt['textSelectableOption']['optionText']['text'] opt['textSelectableOption']['optionText']['text']
for opt in form_component_details['selectableOptions'] for opt in form_component_details['selectableOptions']
] ]
component_info['selectableOptions'] = options component_info['selectableOptions'] = options
form_components.append(component_info) form_components.append(component_info)
return form_components return form_components
def apply_to_job(self,job_id: str, fields: dict, followCompany: bool = True) -> bool: def apply_to_job(self, job_id: str, fields: dict, followCompany: bool = True) -> bool:
return False return False
# ToDo: Implement apply to job parser first # ToDo: Implement apply to job parser first
# How need to be implemented: # How need to be implemented:
# 1. Get fields for easy apply job from the previous method (get_fields_for_easy_apply) # 1. Get fields for easy apply job from the previous method (get_fields_for_easy_apply)
@ -265,11 +264,11 @@ class LinkedInEvolvedAPI(Linkedin):
# {'title': 'Quanti anni di esperienza di lavoro hai con Router?', 'urn': 'urn:li:fsd_formElement:urn:li:jobs_applyformcommon_easyApplyFormElement:(4013860791,9478711764,numeric)', 'formComponentType': 'singleLineTextFormComponent', 'response': '5'} # {'title': 'Quanti anni di esperienza di lavoro hai con Router?', 'urn': 'urn:li:fsd_formElement:urn:li:jobs_applyformcommon_easyApplyFormElement:(4013860791,9478711764,numeric)', 'formComponentType': 'singleLineTextFormComponent', 'response': '5'}
# To fill, you can temporary use input() function to get the data from the user manually for testing purposes (for the further implementation, the question will be asked to AI implementation and automatically filled) # To fill, you can temporary use input() function to get the data from the user manually for testing purposes (for the further implementation, the question will be asked to AI implementation and automatically filled)
# Build a working payload. # Build a working payload.
# EXAMPLE OF WORKING PAYLOAD # EXAMPLE OF WORKING PAYLOAD
# 4005350454 is job_id, so need to be replaced with the job_id # 4005350454 is job_id, so need to be replaced with the job_id
#{ # {
# "followCompany": true, # "followCompany": true,
# "responses": [ # "responses": [
# { # {
@ -349,23 +348,19 @@ class LinkedInEvolvedAPI(Linkedin):
# } # }
# ], # ],
# "trackingId": "" # "trackingId": ""
#} # }
# Push the commit to the repository and create a pull request to the v3 branch. # Push the commit to the repository and create a pull request to the v3 branch.
def set_job_as_applied(self, job_id: str) -> None: def set_job_as_applied(self, job_id: str) -> None:
self.already_applied_jobs.append(job_id) self.already_applied_jobs.append(job_id)
## EXAMPLE USAGE ## EXAMPLE USAGE
if __name__ == "__main__": if __name__ == "__main__":
api: LinkedInEvolvedAPI = LinkedInEvolvedAPI(username="", password="") api: LinkedInEvolvedAPI = LinkedInEvolvedAPI(username="", password="")
jobs = api.search_jobs(keywords="Frontend Developer", location_name="Italia", limit=100, easy_apply=True, offset=1, listed_at=None) jobs = api.search_jobs(keywords="Frontend Developer", location_name="Italia", limit=100, easy_apply=True, offset=1,
listed_at=None)
for job in jobs: for job in jobs:
job_id: str = job["job_id"] job_id: str = job["job_id"]
print(f"Job ID: {job_id}") print(f"Job ID: {job_id}")
@ -379,7 +374,3 @@ if __name__ == "__main__":
for field in fields: for field in fields:
print(field) print(field)
break break