스택오버플로우 구직 사이트 Scraping

Example of Scrapping Process

1. html이 포함된 객체를 불러오기
2. Parsing html in indeed_result object
3. find "div" which have s-pagination className
4. find title, company_name, location, link for company card included in each page

Code

main.py

from so import get_jobs as get_so_jobs
jobs = get_so_jobs()

so.py

import requests
from bs4 import BeautifulSoup


URL = "https://stackoverflow.com/jobs?q=python"

def get_last_page():

  result = requests.get(URL)
  soup = BeautifulSoup(result.text,"html.parser")
  pagination = soup.find("div",{"class" : "s-pagination"})
  links = pagination.find_all("a")
  last_page = links[-2].get_text(strip=True)

  return int(last_page)
  
def extract_job(html):
  title = html.find("h2",{ "class" : "mb4" }).find("a")["title"]
  company, location = html.find("h3",{ "class" : "mb4" }).find_all("span",recursive=False)
  company = company.get_text(strip=True)
  location = location.get_text(strip=True) 
  job_id = html["data-jobid"]
  link = f"https://stackoverflow.com/jobs/{job_id}"
  # link = "https://stackoverflow.com/" + html.find("h2",{ "class" : "mb4" }).find("a")["href"]
  return {"title": title, "company" : company , "location": location, "link" : link}

def extract_jobs(last_page):
  jobs= []
  for page in range(last_page):
    print(f"scrapping SO {page+1}")
    res = requests.get(f"{URL}&pg={page+1}")
    html = BeautifulSoup(res.text,"html.parser")
    job_cards = html.find_all("div",{"class" :"-job"})

    
    for job_card in job_cards:
      job = extract_job(job_card)
      jobs.append(job)
    
  return jobs


def get_jobs():
  
  last_page = get_last_page()
  jobs = extract_jobs(last_page)
  
  return jobs