Merge branch 'v3' into main

This commit is contained in:
EP 2024-09-01 09:19:24 -04:00 committed by GitHub
commit 28e4f29e21
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 170 additions and 13 deletions

View File

@ -577,7 +577,6 @@ For further assistance, please create an issue on the [GitHub repository](https:
- [LinkedIn Developer Documentation](https://developer.linkedin.com/) - [LinkedIn Developer Documentation](https://developer.linkedin.com/)
- [Lang Chain Developer Documentation](https://python.langchain.com/v0.2/docs/integrations/components/) - [Lang Chain Developer Documentation](https://python.langchain.com/v0.2/docs/integrations/components/)
Remember to always use LinkedIn_AIHawk responsibly and in compliance with LinkedIn's terms of service.
If you encounter any issues, you can open an issue on [GitHub](https://github.com/feder-cr/linkedIn_auto_jobs_applier_with_AI/issues). If you encounter any issues, you can open an issue on [GitHub](https://github.com/feder-cr/linkedIn_auto_jobs_applier_with_AI/issues).
Please add valuable details to the subject and to the description. If you need new feature then please reflect this. Please add valuable details to the subject and to the description. If you need new feature then please reflect this.

Binary file not shown.

View File

@ -65,18 +65,8 @@ class LinkedInAuthenticator:
print("Security check not completed. Please try again later.") print("Security check not completed. Please try again later.")
def is_logged_in(self): def is_logged_in(self):
self.driver.get('https://www.linkedin.com/feed') self.driver.get('https://www.linkedin.com/')
try: return self.driver.current_url == 'https://www.linkedin.com/feed/'
WebDriverWait(self.driver, 10).until(
EC.presence_of_element_located((By.CLASS_NAME, 'share-box-feed-entry__trigger'))
)
buttons = self.driver.find_elements(By.CLASS_NAME, 'share-box-feed-entry__trigger')
if any(button.text.strip() == 'Start a post' for button in buttons):
print("User is already logged in.")
return True
except TimeoutException:
pass
return False
def wait_for_page_load(self, timeout=10): def wait_for_page_load(self, timeout=10):
try: try:

168
src/linkedin-api.py Normal file
View File

@ -0,0 +1,168 @@
from typing import Dict, List
from linkedin_api import Linkedin
from typing import Optional, Union, Literal
from urllib.parse import urlencode
class LinkedInEvolvedAPI(Linkedin):
def __init__(self, username, password):
super().__init__(username, password)
def search_jobs(
self,
keywords: Optional[str] = None,
companies: Optional[List[str]] = None,
experience: Optional[
List[
Union[
Literal["1"],
Literal["2"],
Literal["3"],
Literal["4"],
Literal["5"],
Literal["6"],
]
]
] = None,
job_type: Optional[
List[
Union[
Literal["F"],
Literal["C"],
Literal["P"],
Literal["T"],
Literal["I"],
Literal["V"],
Literal["O"],
]
]
] = None,
job_title: Optional[List[str]] = None,
industries: Optional[List[str]] = None,
location_name: Optional[str] = None,
remote: Optional[List[Union[Literal["1"], Literal["2"], Literal["3"]]]] = None,
listed_at=24 * 60 * 60,
distance: Optional[int] = None,
easy_apply: Optional[bool] = True,
limit=-1,
offset=0,
**kwargs,
) -> List[Dict]:
"""Perform a LinkedIn search for jobs.
:param keywords: Search keywords (str)
:type keywords: str, optional
:param companies: A list of company URN IDs (str)
:type companies: list, optional
:param experience: A list of experience levels, one or many of "1", "2", "3", "4", "5" and "6" (internship, entry level, associate, mid-senior level, director and executive, respectively)
:type experience: list, optional
:param job_type: A list of job types , one or many of "F", "C", "P", "T", "I", "V", "O" (full-time, contract, part-time, temporary, internship, volunteer and "other", respectively)
:type job_type: list, optional
:param job_title: A list of title URN IDs (str)
:type job_title: list, optional
:param industries: A list of industry URN IDs (str)
:type industries: list, optional
:param location_name: Name of the location to search within. Example: "Kyiv City, Ukraine"
:type location_name: str, optional
:param remote: Filter for remote jobs, onsite or hybrid. onsite:"1", remote:"2", hybrid:"3"
:type remote: list, optional
:param listed_at: maximum number of seconds passed since job posting. 86400 will filter job postings posted in last 24 hours.
:type listed_at: int/str, optional. Default value is equal to 24 hours.
:param distance: maximum distance from location in miles
:type distance: int/str, optional. If not specified, None or 0, the default value of 25 miles applied.
:param easy_apply: filter for jobs that are easy to apply to
:type easy_apply: bool, optional. Default value is True.
:param limit: maximum number of results obtained from API queries. -1 means maximum which is defined by constants and is equal to 1000 now.
:type limit: int, optional, default -1
:param offset: indicates how many search results shall be skipped
:type offset: int, optional
:return: List of jobs
:rtype: list
"""
count = Linkedin._MAX_SEARCH_COUNT
if limit is None:
limit = -1
query: Dict[str, Union[str, Dict[str, str]]] = {
"origin": "JOB_SEARCH_PAGE_QUERY_EXPANSION"
}
if keywords:
query["keywords"] = "KEYWORD_PLACEHOLDER"
if location_name:
query["locationFallback"] = "LOCATION_PLACEHOLDER"
query["selectedFilters"] = {}
if companies:
query["selectedFilters"]["company"] = f"List({','.join(companies)})"
if experience:
query["selectedFilters"]["experience"] = f"List({','.join(experience)})"
if job_type:
query["selectedFilters"]["jobType"] = f"List({','.join(job_type)})"
if job_title:
query["selectedFilters"]["title"] = f"List({','.join(job_title)})"
if industries:
query["selectedFilters"]["industry"] = f"List({','.join(industries)})"
if distance:
query["selectedFilters"]["distance"] = f"List({distance})"
if remote:
query["selectedFilters"]["workplaceType"] = f"List({','.join(remote)})"
if easy_apply:
query["selectedFilters"]["easyApply"] = "List(true)"
query["selectedFilters"]["timePostedRange"] = f"List(r{listed_at})"
query["spellCorrectionEnabled"] = "true"
query_string = (
str(query)
.replace(" ", "")
.replace("'", "")
.replace("KEYWORD_PLACEHOLDER", keywords or "")
.replace("LOCATION_PLACEHOLDER", location_name or "")
.replace("{", "(")
.replace("}", ")")
)
results = []
while True:
if limit > -1 and limit - len(results) < count:
count = limit - len(results)
default_params = {
"decorationId": "com.linkedin.voyager.dash.deco.jobs.search.JobSearchCardsCollection-174",
"count": count,
"q": "jobSearch",
"query": query_string,
"start": len(results) + offset,
}
res = self._fetch(
f"/voyagerJobsDashJobCards?{urlencode(default_params, safe='(),:')}",
headers={"accept": "application/vnd.linkedin.normalized+json+2.1"},
)
data = res.json()
elements = data.get("included", [])
new_data = []
for e in elements:
trackingUrn = e.get("trackingUrn")
if trackingUrn:
trackingUrn = trackingUrn.split(":")[-1]
e["job_id"] = trackingUrn
if e.get("$type") == "com.linkedin.voyager.dash.jobs.JobPosting":
new_data.append(e)
if not new_data:
break
results.extend(new_data)
if (
(-1 < limit <= len(results))
or len(results) / count >= Linkedin._MAX_REPEATED_REQUESTS
) or len(elements) == 0:
break
self.logger.debug(f"results grew to {len(results)}")
return results