StackOverflow extract_jobs

Python 공부 7일차

StackOverflow extract_jobs

# so.py
import requests
from bs4 import BeautifulSoup

URL = f"https://stackoverflow.com/jobs?q=python&sort=i"

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) // strip=True: BeautifulSoup이 알아서 공백제거 처리
  return int(last_page)

def extract_jobs(last_page):
  jobs = []
  for page in  range(last_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:
      print(result["data-jobid"])

def get_jobs():
  last_page = get_last_page()
  return []

# main.py
from so import get_jobs as get_so_jobs

so_jobs = get_so_jobs()