Compare commits

...

5 Commits

Author SHA1 Message Date
Cullen Watson
811d4c40b4 chore:version 2024-10-24 15:28:25 -05:00
Cullen Watson
dba92d22c2 chore:version 2024-10-24 15:27:16 -05:00
Cullen Watson
10a3592a0f docs:file 2024-10-24 15:26:49 -05:00
Cullen Watson
b7905cc756 docs:file 2024-10-24 15:24:18 -05:00
Cullen Watson
6867d58829 docs:readme 2024-10-24 15:22:31 -05:00
3 changed files with 8 additions and 12 deletions

View File

@@ -2,8 +2,6 @@
**JobSpy** is a simple, yet comprehensive, job scraping library.
**Not technical?** Try out the web scraping tool on our site at [usejobspy.com](https://usejobspy.com).
*Looking to build a data-focused software product?* **[Book a call](https://bunsly.com/)** *to
work with us.*
@@ -63,8 +61,8 @@ zip_recruiter Software Developer TEKsystems Phoenix
```plaintext
Optional
├── site_name (list|str):
| linkedin, zip_recruiter, indeed, glassdoor
| (default is all four)
| linkedin, zip_recruiter, indeed, glassdoor, google
| (default is all)
├── search_term (str)
@@ -173,9 +171,9 @@ Indeed specific
## Supported Countries for Job Searching
### **LinkedIn**
### **LinkedIn / Google**
LinkedIn searches globally & uses only the `location` parameter.
LinkedIn & Google searches globally & uses only the `location` parameter.
### **ZipRecruiter**

View File

@@ -1,6 +1,6 @@
[tool.poetry]
name = "python-jobspy"
version = "1.1.73"
version = "1.1.74"
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"

View File

@@ -2,7 +2,7 @@
jobspy.scrapers.google
~~~~~~~~~~~~~~~~~~~
This module contains routines to scrape Glassdoor.
This module contains routines to scrape Google.
"""
from __future__ import annotations
@@ -34,12 +34,11 @@ class GoogleJobsScraper(Scraper):
self, proxies: list[str] | str | None = None, ca_cert: str | None = None
):
"""
Initializes GlassdoorScraper with the Glassdoor job search url
Initializes Google Scraper with the Goodle jobs search url
"""
site = Site(Site.GOOGLE)
super().__init__(site, proxies=proxies, ca_cert=ca_cert)
self.base_url = None
self.country = None
self.session = None
self.scraper_input = None
@@ -50,13 +49,12 @@ class GoogleJobsScraper(Scraper):
def scrape(self, scraper_input: ScraperInput) -> JobResponse:
"""
Scrapes Glassdoor for jobs with scraper_input criteria.
Scrapes Google for jobs with scraper_input criteria.
:param scraper_input: Information about job search criteria.
:return: JobResponse containing a list of jobs.
"""
self.scraper_input = scraper_input
self.scraper_input.results_wanted = min(900, scraper_input.results_wanted)
self.base_url = self.scraper_input.country.get_glassdoor_url()
self.session = create_session(
proxies=self.proxies, ca_cert=self.ca_cert, is_tls=False, has_retry=True