import requests
from bs4 import BeautifulSoup
URL = f"https://stackoverflow.com/jobs?q=python"
def get_last_page():
result = requests.get(URL)
soup = BeautifulSoup(result.text, "html.parser")
pages = soup.find("div", {"class": "s-pagination"}).find_all("a")
last_page = pages[-2].get_text(strip=True)
return int(last_page)
def extrct_job(html):
title = html.find("h2", {"class": "mb4"}).find("a")["title"]
company, loction = html.find("h3").find_all("span", recursive=False)
company = company.get_text(strip=True)
loction = loction.get_text(strip=True).strip("-").strip(" \r")
job_id = html['data-jobid']
return {
'title': title,
'company': company,
"loction": loction,
'apply_link': f"https://stackoverflow.com/jobs/{job_id}"
}
def extrct_jobs(last_page):
jobs = []
for page in range(last_page):
print (f"Scraping SO: Page : {page}")
result = requests.get(f"{URL}&pg={page+1}")
soup = BeautifulSoup(result.text, "html.parser")
results = soup.find_all("div", {"class": "-job"})
for result in results:
job = extrct_job(result)
jobs.append(job)
return jobs
def get_jobs():
last_page = get_last_page()
jobs = extrct_jobs(last_page)
return jobs