Last active
October 5, 2020 16:17
-
-
Save chris-lovejoy/e6f0f49efccb2eb31ffb69fa4ef21abc to your computer and use it in GitHub Desktop.
job detail extraction
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def extract_job_title_indeed(job_elem): | |
title_elem = job_elem.find('h2', class_='title') | |
title = title_elem.text.strip() | |
return title | |
def extract_company_indeed(job_elem): | |
company_elem = job_elem.find('span', class_='company') | |
company = company_elem.text.strip() | |
return company | |
def extract_link_indeed(job_elem): | |
link = job_elem.find('a')['href'] | |
link = 'www.Indeed.co.uk/' + link | |
return link | |
def extract_date_indeed(job_elem): | |
date_elem = job_elem.find('span', class_='date') | |
date = date_elem.text.strip() | |
return date |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment