turtlebasket
/
JobSpy
mirror of https://github.com/Bunsly/JobSpy
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

minor fix

pull/169/head v1.1.58
Cullen Watson 2024-07-15 21:19:01 -05:00
parent 48631ea271
commit 6330c14879
3 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/jobspy/__init__.py
View File

@ -210,13 +210,13 @@ def scrape_jobs(
"is_remote", "is_remote",
"job_level", "job_level",
"job_function", "job_function",
"company_industry",
"listing_type", "listing_type",
"emails", "emails",
"description", "description",
"company_url", "company_url",
"company_url_direct", "company_url_direct",
"company_addresses", "company_addresses",
"company_industry",
"company_num_employees", "company_num_employees",
"company_revenue", "company_revenue",
"company_description", "company_description",

1
src/jobspy/scrapers/indeed/__init__.py
View File

@ -244,6 +244,7 @@ class IndeedScraper(Scraper):
.replace("Iv1", "") .replace("Iv1", "")
.replace("_", " ") .replace("_", " ")
.title() .title()
.strip()
if employer_details.get("industry") if employer_details.get("industry")
else None else None
), ),

6
src/jobspy/scrapers/linkedin/__init__.py
View File

@ -219,7 +219,7 @@ class LinkedInScraper(Scraper):
job_url=f"{self.base_url}/jobs/view/{job_id}", job_url=f"{self.base_url}/jobs/view/{job_id}",
compensation=compensation, compensation=compensation,
job_type=job_details.get("job_type"), job_type=job_details.get("job_type"),
job_level=job_details.get("job_level"), job_level=job_details.get("job_level", "").lower(),
company_industry=job_details.get("company_industry"), company_industry=job_details.get("company_industry"),
description=job_details.get("description"), description=job_details.get("description"),
job_url_direct=job_details.get("job_url_direct"), job_url_direct=job_details.get("job_url_direct"),
@ -351,7 +351,7 @@ class LinkedInScraper(Scraper):
job_level = job_level_span.get_text(strip=True) job_level = job_level_span.get_text(strip=True)
return job_level return job_level
@staticmethod @staticmethod
def _parse_company_industry(soup_industry: BeautifulSoup) -> str | None: def _parse_company_industry(soup_industry: BeautifulSoup) -> str | None:
""" """
@ -373,7 +373,7 @@ class LinkedInScraper(Scraper):
if industry_span: if industry_span:
industry = industry_span.get_text(strip=True) industry = industry_span.get_text(strip=True)
return industry return industry
def _parse_job_url_direct(self, soup: BeautifulSoup) -> str | None: def _parse_job_url_direct(self, soup: BeautifulSoup) -> str | None:
""" """