대나무숲 1 돌파

import requests

from bs4 import BeautifulSoup

​

LIMIT = 50

URL = "http://www.indeed.com/jobs?q=python&limit={LIMIT}"

​

def extract_indeed_pages():

result = requests.get(URL)

soup = BeautifulSoup(result.text, "html.parser")

pagination = soup.find("div", {"class":"pagination"})

links = pagination.find_all('a')

pages = []

for link in links[:-1]:

pages.append(int(link.string))

max_page = pages[-1]

return max_page

​

​

def extract_job(html):

title = html.find("h2", {

"class": "jobTitle"

}).find("span", title=True).text

​

company = html.find("span", {"class": "companyName"})

​

company_anchor = company.find("a")

if company:

company_anchor = company.find("a")

if company_anchor is not None:

company = str(company_anchor.string)

else:

company = str(company.string)

​

location = html.find("div", {"class": "companyLocation"}).string

job_id = html["data-jk"]

return {

"title": title,

"company": company,

"location": location,

"link": f"https://www.indeed.com/viewjob?jk={job_id}&tk=1fpkb65caocag800&from=serp&vjs=3"

}

​

​

def extract_jobs(last_page):

jobs = []

for page in range(last_page):

result = requests.get(f"{URL}&start={page*LIMIT}")

​

soup = BeautifulSoup(result.text, "html.parser")

​

results = soup.find_all("a", {"class": "fs-unmask"})

​

for result in results:

job = extract_job(result)

jobs.append(job)

return jobs

​

///////////////////////indeed.py ///////////////////////

​

from indeed import extract_indeed_pages, extract_job, extract_jobs

​

last_indeed_page = extract_indeed_pages()

​

indeed_jobs = extract_jobs(last_indeed_page)

​

print(indeed_jobs)

​

/////////////////main.py//////////////////