turtlebasket/JobSpy
1
0
Fork 0
mirror of https://github.com/Bunsly/JobSpy.git synced 2026-03-07 13:04:32 -08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Ability to query by time posted for linkedin, indeed, glassdoor, ziprecruiter (#103)

Browse Source
This commit is contained in:
VitaminB16
2024-02-09 20:02:03 +00:00
committed by GitHub
parent 2563c5ca08
commit 91b137ef86
7 changed files with 53 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
src/jobspy/scrapers/linkedin/__init__.py
View File

@@ -59,6 +59,12 @@ class LinkedInScraper(Scraper):
url_lock = Lock()
page = scraper_input.offset // 25 + 25 if scraper_input.offset else 0
seconds_old = (
scraper_input.hours_old * 3600
if scraper_input.hours_old
else None
)
def job_type_code(job_type_enum):
mapping = {
JobType.FULL_TIME: "F",
@@ -85,7 +91,8 @@ class LinkedInScraper(Scraper):
"pageNum": 0,
"start": page + scraper_input.offset,
"f_AL": "true" if scraper_input.easy_apply else None,
"f_C": ','.join(map(str, scraper_input.linkedin_company_ids)) if scraper_input.linkedin_company_ids else None
"f_C": ','.join(map(str, scraper_input.linkedin_company_ids)) if scraper_input.linkedin_company_ids else None,
"f_TPR": f"r{seconds_old}",
}
params = {k: v for k, v in params.items() if v is not None}
@@ -101,7 +108,9 @@ class LinkedInScraper(Scraper):
response.raise_for_status()
except requests.HTTPError as e:
raise LinkedInException(f"bad response status code: {e.response.status_code}")
raise LinkedInException(
f"bad response status code: {e.response.status_code}"
)
except ProxyError as e:
raise LinkedInException("bad proxy")
except Exception as e:
@@ -145,11 +154,11 @@ class LinkedInScraper(Scraper):
compensation = None
if salary_tag:
salary_text = salary_tag.get_text(separator=' ').strip()
salary_values = [currency_parser(value) for value in salary_text.split('-')]
salary_text = salary_tag.get_text(separator=" ").strip()
salary_values = [currency_parser(value) for value in salary_text.split("-")]
salary_min = salary_values[0]
salary_max = salary_values[1]
currency = salary_text[0] if salary_text[0] != '$' else 'USD'
currency = salary_text[0] if salary_text[0] != "$" else "USD"
compensation = Compensation(
min_amount=int(salary_min),
@@ -294,17 +303,17 @@ class LinkedInScraper(Scraper):
@staticmethod
def headers() -> dict:
return {
'authority': 'www.linkedin.com',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'accept-language': 'en-US,en;q=0.9',
'cache-control': 'max-age=0',
'sec-ch-ua': '"Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120"',
"authority": "www.linkedin.com",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
"accept-language": "en-US,en;q=0.9",
"cache-control": "max-age=0",
"sec-ch-ua": '"Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120"',
# 'sec-ch-ua-mobile': '?0',
# 'sec-ch-ua-platform': '"macOS"',
# 'sec-fetch-dest': 'document',
# 'sec-fetch-mode': 'navigate',
# 'sec-fetch-site': 'none',
# 'sec-fetch-user': '?1',
'upgrade-insecure-requests': '1',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
"upgrade-insecure-requests": "1",
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
}