Spaces:
Paused
Paused
File size: 1,694 Bytes
840261a |
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 48 49 50 51 |
import time
import os
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from bs4 import BeautifulSoup
class BrowserScraper:
def __init__(self):
self.options = Options()
self.options.add_argument("--headless")
self.options.add_argument("--no-sandbox")
self.options.add_argument("--disable-dev-shm-usage")
chrome_bin = os.getenv("CHROME_BIN")
if chrome_bin:
self.options.binary_location = chrome_bin
def fetch_page_metadata(self, url):
"""
Uses explicit Browser (Selenium) to scrape the page title and summary.
This fulfills the requirement of 'real browser operation'.
"""
driver = None
try:
print(f"🌍 Browser Navigating to: {url}")
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service, options=self.options)
driver.get(url)
time.sleep(2) # Wait for JS to load
title = driver.title
content = driver.find_element("tag name", "body").text[:500] # Get first 500 chars for summary
return {
"title": title,
"summary": content,
"status": "success"
}
except Exception as e:
return {
"title": "Error",
"summary": str(e),
"status": "failed"
}
finally:
if driver:
driver.quit()
|