gaur3009 commited on
Commit
e4c807c
Β·
verified Β·
1 Parent(s): 547b150

Update scraper.py

Browse files
Files changed (1) hide show
  1. scraper.py +4 -3
scraper.py CHANGED
@@ -2,11 +2,12 @@ import requests
2
  from bs4 import BeautifulSoup
3
 
4
  def scrape_url(url):
5
- """Fetch and extract text from a webpage."""
6
  try:
7
- res = requests.get(url, timeout=10)
8
  res.raise_for_status()
9
  soup = BeautifulSoup(res.text, 'html.parser')
10
- return soup.get_text(separator='\n', strip=True)
 
 
11
  except Exception as e:
12
  return f"[Error scraping {url}: {e}]"
 
2
  from bs4 import BeautifulSoup
3
 
4
  def scrape_url(url):
 
5
  try:
6
+ res = requests.get(url, timeout=10, headers={'User-Agent': 'Mozilla/5.0'})
7
  res.raise_for_status()
8
  soup = BeautifulSoup(res.text, 'html.parser')
9
+ for tag in soup(['script','style','']): tag.decompose()
10
+ text = soup.get_text(separator='\n', strip=True)
11
+ return text
12
  except Exception as e:
13
  return f"[Error scraping {url}: {e}]"