Untitled

mail@pastecode.io avatar
unknown
python
3 years ago
1.0 kB
4
Indexable
Never
import time
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
from urllib.parse import urljoin
from bs4 import BeautifulSoup

driver = webdriver.Chrome(ChromeDriverManager().install())
driver.get("https://solid.jobs/offers/it")
time.sleep(0.5)
scroll_pause_time = 1
screen_height = driver.execute_script("return window.screen.height;")
i = 1

while True:
    driver.execute_script("window.scrollTo(0, {screen_height}*{i});".format(screen_height=screen_height, i=i))  
    i += 1
    time.sleep(scroll_pause_time)
    scroll_height = driver.execute_script("return document.body.scrollHeight;")
    if (screen_height) * i > scroll_height:
        break
        
urls = []
soup = BeautifulSoup(driver.page_source, "html.parser")
for parent in soup.find_all(class_="font-weight-400 h5"):
    a_tag = parent.find("a", class_="color-dark-grey color-blue-onhover")
    base = "https://solid.jobs/offers/it"
    link = a_tag.attrs['href']
    url = urljoin(base, link)
    urls.append(url)