ad3laid3/JB
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(scraper): correct quotation escape in smart_careers_crawler regex

Browse source
This commit is contained in:
JobsBoard Deployer 2026-09-05 12:26:54 -04:00
parent 5792a79377
commit fb3d886527
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
scraper/scrapers/smart_careers_crawler.py
View file

@ -111,7 +111,7 @@ class SmartCareersCrawler:
if provider and slug:
return provider, slug, r.url
links = re.findall(r"href=['"]([^'"]*(?:career|jobs|work-at|join|greenhouse|lever|ashby)[^'"]*)['"]", r.text, re.IGNORECASE)
links = re.findall(r'href=[\'"]([^\'"]*(?:career|jobs|work-at|join|greenhouse|lever|ashby)[^\'"]*)[\'"]', r.text, re.IGNORECASE)
for link in links[:5]:
target = link if link.startswith("http") else urljoin(base_url, link)
provider, slug = self.detect_ats_from_url_or_html(target)