Skip to content

Commit

Permalink
Added 2 new scrapers for Qubiz and Orange
Browse files Browse the repository at this point in the history
  • Loading branch information
GabrielRezeanu03 committed Jun 13, 2024
1 parent e972e95 commit b489ca2
Show file tree
Hide file tree
Showing 2 changed files with 139 additions and 0 deletions.
74 changes: 74 additions & 0 deletions sites/orange.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,74 @@
#
#
#
# Orange > https://www.orange.ro/jobs/joburi-disponibile


import requests
import uuid
from sites.website_scraper_api import WebsiteScraperAPI

class OrangeScraper(WebsiteScraperAPI):

"""
A class for scraping job data from Nagarro website.
"""
url = 'https://www.orange.ro/ux-admin/api/jobs/getJobs?&order=closing_date&direction=desc'
url_logo = 'https://www.orange.ro/imagini/orange-logo-static.svg'
company_name = 'Orange'

def __init__(self):
"""
Defining de url, company name for the request and formatted data list for the jobs scrapped
"""
super().__init__(self.company_name, self.url, self.url_logo)

def request_headers(self):
"""
Set the request headers.
"""
self.headers = {
'Accept': 'application/json'
}

def get_response(self):
"""
Send a GET request and retrieve the response.
"""
self.job_details = requests.get(
self.url,
headers=self.headers).json()
self.get_jobs_response(self.job_details)

def scrape_jobs(self):
"""
Scrape job data from Orange website.
"""
self.job_titles = self.get_job_details(['title'])
self.job_cities = [job_city[0]['name'] for job_city in self.get_job_details(['location'])]
self.job_urls = self.get_job_details(['url'])

self.format_data()

def format_data(self):
job_country = 'Romania'
for job_title, job_url, job_city in zip(self.job_titles, self.job_urls):
self.create_jobs_dict(job_title, job_url, job_country, job_city)
print(self.create_jobs_dict)


def sent_to_future(self):
self.send_to_viitor()

def return_data(self):
self.request_headers()
self.get_response()
self.scrape_jobs()
return self.formatted_data, self.company_name

if __name__ == "__main__":
Orange = OrangeScraper()
Orange.request_headers()
Orange.get_response()
Orange.scrape_jobs()
Orange.send_to_viitor()
65 changes: 65 additions & 0 deletions sites/qubiz.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,65 @@
#
#
#
#
## Qubiz > https://www.qubiz.com/jobs

from sites.website_scraper_bs4 import BS4Scraper

class QubizScraper(BS4Scraper):

"""
A class for scraping job data from Qubiz website.
"""
url = 'https://www.qubiz.com/jobs'
url_logo = 'https://assets-global.website-files.com/603e16fd5761f8f7787bf39a/64491d149607dd73d0e80235_LogoWebsiteAnniversary.svg'
company_name = 'Qubiz'

def __init__(self):
"""
Initialize the BS4Scraper class.
"""
super().__init__(self.company_name, self.url_logo)

def get_response(self):
self.get_content(self.url)

def scrape_jobs(self):
"""
Scrape job data from Qubiz website.
"""

job_titles_elements = self.get_jobs_elements('class_', 'head-2-job-title')
job_urls_elements = self.get_jobs_elements('class_', 'button-blue---job-openings w-button')
job_cities_elements = self.get_jobs_elements('class_', 'text-block-12')

self.job_titles = self.get_jobs_details_text(job_titles_elements)
self.job_urls = self.get_jobs_details_href(job_urls_elements)
self.job_cities = self.get_jobs_details_text(job_cities_elements)

self.format_data()

def sent_to_future(self):
self.send_to_viitor()

def return_data(self):
self.get_response()
self.scrape_jobs()
return self.formatted_data, self.company_name

def format_data(self):
"""
Iterate over all job details and send to the create jobs dictionary.
"""
job_country = "Romania"
for job_title, job_url, job_city in zip(self.job_titles, self.job_urls, self.job_cities):
self.create_jobs_dict(job_title, job_url, job_country, job_city, remote='on-site', county=None)

if __name__ == "__main__":
Qubiz = QubizScraper()
Qubiz.get_response()
Qubiz.scrape_jobs()
# Qubiz.sent_to_future()



0 comments on commit b489ca2

Please sign in to comment.