mirror of
https://github.com/Bunsly/JobSpy.git
synced 2026-03-05 12:04:33 -08:00
Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
6f1490458c | ||
|
|
6bb7d81ba8 | ||
|
|
0e046432d1 |
@@ -1,6 +1,6 @@
|
||||
[tool.poetry]
|
||||
name = "python-jobspy"
|
||||
version = "1.1.62"
|
||||
version = "1.1.65"
|
||||
description = "Job scraper for LinkedIn, Indeed, Glassdoor & ZipRecruiter"
|
||||
authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
|
||||
homepage = "https://github.com/Bunsly/JobSpy"
|
||||
|
||||
@@ -236,7 +236,7 @@ class LinkedInScraper(Scraper):
|
||||
"""
|
||||
try:
|
||||
response = self.session.get(
|
||||
f"{self.base_url}/jobs-guest/jobs/api/jobPosting/{job_id}", timeout=5
|
||||
f"{self.base_url}/jobs/view/{job_id}", timeout=5
|
||||
)
|
||||
response.raise_for_status()
|
||||
except:
|
||||
|
||||
@@ -198,6 +198,7 @@ def extract_salary(
|
||||
if not salary_str:
|
||||
return None, None, None, None
|
||||
|
||||
annual_max_salary = None
|
||||
min_max_pattern = r"\$(\d+(?:,\d+)?(?:\.\d+)?)([kK]?)\s*[-—–]\s*(?:\$)?(\d+(?:,\d+)?(?:\.\d+)?)([kK]?)"
|
||||
|
||||
def to_int(s):
|
||||
@@ -238,6 +239,8 @@ def extract_salary(
|
||||
annual_max_salary = max_salary
|
||||
|
||||
# Ensure salary range is within specified limits
|
||||
if not annual_max_salary:
|
||||
return None, None, None, None
|
||||
if (
|
||||
lower_limit <= annual_min_salary <= upper_limit
|
||||
and lower_limit <= annual_max_salary <= upper_limit
|
||||
|
||||
@@ -200,7 +200,7 @@ class ZipRecruiterScraper(Scraper):
|
||||
script_tag = soup.find("script", type="application/json")
|
||||
if script_tag:
|
||||
job_json = json.loads(script_tag.string)
|
||||
job_url_val = job_json["model"]["saveJobURL"]
|
||||
job_url_val = job_json["model"].get("saveJobURL", "")
|
||||
m = re.search(r"job_url=(.+)", job_url_val)
|
||||
if m:
|
||||
job_url_direct = m.group(1)
|
||||
|
||||
Reference in New Issue
Block a user