turtlebasket/JobSpy
1
0
Fork 0
mirror of https://github.com/Bunsly/JobSpy.git synced 2026-03-05 03:54:31 -08:00
Code Issues Packages Projects Releases Wiki Activity

Add tests (#18)

Browse Source
This commit is contained in:
Cullen Watson
2023-08-27 13:09:02 -05:00
committed by GitHub
parent 33f6768ec8
commit 32a5bb37cd
4 changed files with 96 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
api/core/scrapers/ziprecruiter/__init__.py
View File

@@ -96,7 +96,9 @@ class ZipRecruiterScraper(Scraper):
title = job.find("h2", {"class": "title"}).text
company = job.find("a", {"class": "company_name"}).text.strip()
description, job_url = ZipRecruiterScraper.get_description(job_url, session)
description, updated_job_url = ZipRecruiterScraper.get_description(job_url, session)
if updated_job_url is not None:
job_url = updated_job_url
if description is None:
description = job.find("p", {"class": "job_snippet"}).text.strip()
@@ -185,7 +187,7 @@ class ZipRecruiterScraper(Scraper):
@staticmethod
def get_description(
job_page_url: str, session: tls_client.Session
) -> Tuple[Optional[str], str]:
) -> Tuple[Optional[str], Optional[str]]:
"""
Retrieves job description by going to the job page url
:param job_page_url:
@@ -196,7 +198,7 @@ class ZipRecruiterScraper(Scraper):
job_page_url, headers=ZipRecruiterScraper.headers(), allow_redirects=True
)
if response.status_code not in range(200, 400):
return None
return None, None
html_string = response.content
soup_job = BeautifulSoup(html_string, "html.parser")