python replit request 설정

import requests
from bs4 import BeautifulSoup

arra = requests.get('https://www.indeed.com/jobs?q=python&limit=50')
#  > html 전체를 긁어온것

print(arra)

soup = BeautifulSoup(arra.text, 'html.parser')

# print(soup.title)
# print(soup.title.name)
# print(soup.a)
# print(soup.p['class'])
# soup.find_all(class="accessibilityMenu")
# print(soup.find(id="skipToJobs"))

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

links = pagination.find_all('a')

pages = []

for link in links[:-1]:
  pages.append(int(link.string))

pages = pages[:-1] # 0부터 마지막 전까지
max_page = pages[-1]

Packages

 

-> requests인데, Python HTTP for Humans. 검색 -> install

https://requests.readthedocs.io/en/latest/

import requests

arra = requests.get('https://www.indeed.com/jobs?q=python&limit=50')
#  > html 전체를 긁어온것

print(arra)

-> beautifulsoup4 -> install

https://www.crummy.com/software/BeautifulSoup/bs4/doc/
 >> html_doc은 위에서 requests가 가져옴 

from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc, 'html.parser')