def scraped_job(job_dict):
company_name = job_dict['company'].strip()
company, created_company = Company.objects.get_or_create(
slug=slugify(company_name),
name=company_name,
)
if created_company:
if job_dict['logo'] is not None:
download_and_save_image(company, job_dict['logo'])
source_category = job_dict['source_category']
job_dict.pop('source_category')
job_dict.pop('logo')
job_dict.update({'company': company})
job, created_job = Job.objects.update_or_create(**job_dict)
if created_job:
tag, _ = Tag.objects.get_or_create(name=source_category)
if not job.tags.filter(name=tag).exists():
job.tags.add(tag)
job.save()
tags = []
extracted_tags = extract_and_normalize_tags(job.role)
for t in extracted_tags:
t, _ = Tag.objects.get_or_create(name=t)
tags.append(t)
job.tags.add(*tags)
job.save()
def _create_job(scraper, company, job_data):
"""
Creates or updates a Job and it's Tags
:param scraper: Scraper object
:param company: Company object
:param job_data: dictionary containing
"""
try:
job, created_job = Job.objects.update_or_create(
company=company,
link=job_data['link'],
via_source=scraper,
defaults={
'role': job_data['role'],
'date_published': job_data['date_published'],
'description': job_data['description'],
}
)
except:
# TODO: add logging here to see what sort of errors we get
return None
if created_job:
tag, _ = Tag.objects.get_or_create(name=job_data['source_category'])
if not job.tags.filter(name=tag).exists():
job.tags.add(tag)
tags = []
extracted_tags = extract_and_normalize_tags(job.role)
for tag_name in extracted_tags:
tag, _ = Tag.objects.get_or_create(name=tag_name)
tags.append(tag)
job.tags.add(*tags)
job.save()
return job
