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

fix: generic url

pull/85/head
Cullen 2024-01-22 20:18:00 -06:00
parent fb5dd6b981
commit 2ff586f8bc
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/jobspy/scrapers/glassdoor/__init__.py
View File

@ -88,7 +88,7 @@ class GlassdoorScraper(Scraper):
def process_job(self, job_data): def process_job(self, job_data):
"""Processes a single job and fetches its description.""" """Processes a single job and fetches its description."""
job_id = job_data["jobview"]["job"]["listingId"] job_id = job_data["jobview"]["job"]["listingId"]
job_url = f'https://www.glassdoor.com/job-listing/?jl={job_id}' job_url = f'{self.url}/job-listing/?jl={job_id}'
if job_url in self.seen_urls: if job_url in self.seen_urls:
return None return None
self.seen_urls.add(job_url) self.seen_urls.add(job_url)
@ -169,7 +169,7 @@ class GlassdoorScraper(Scraper):
def fetch_job_description(self, job_id): def fetch_job_description(self, job_id):
"""Fetches the job description for a single job ID.""" """Fetches the job description for a single job ID."""
url = "https://www.glassdoor.com/graph" url = f"{self.url}/graph"
body = [ body = [
{ {
"operationName": "JobDetailQuery", "operationName": "JobDetailQuery",