File size: 1,289 Bytes
b4f27a3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 | import selenium.webdriver as webdriver
from selenium.webdriver.chrome.service import Service
import time
from bs4 import BeautifulSoup
def scrape_website(website):
print("launching chrome browser...")
chrome_driver_path = "./chromedriver.exe"
options = webdriver.ChromeOptions()
driver = webdriver.Chrome(service=Service(chrome_driver_path), options=options)
try:
driver.get(website)
print('page loaded..,')
html = driver.page_source
time.sleep(10)
return html
finally:
driver.quit()
def extract_body_content(html_content):
soup = BeautifulSoup(html_content, "html.parser")
body_content = soup.body
if body_content:
return str(body_content)
return ""
def clean_body_content(body_content):
soup = BeautifulSoup(body_content, "html.parser")
for script_or_style in soup({"script", "style"}):
script_or_style.extract()
cleaned_content = soup.get_text(separator="\n")
cleaned_content = "\n".join(
line.strip() for line in cleaned_content.splitlines() if line.strip()
)
return cleaned_content
def split_dom_content(dom_content,max_length=6000):
return [
dom_content[i: i+max_length] for i in range(0, len(dom_content), max_length)
]
|