File size: 608 Bytes
e008495
 
 
 
 
 
78a3b6c
 
 
 
 
 
 
 
 
 
 
 
 
e008495
1cc2027
e008495
 
 
 
 
4a8b2d1
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
from scrapling.fetchers import Fetcher

def scrape_url(url: str) -> str:
    try:
        page = Fetcher.get(url)

        # Extract raw text safely
        elements = page.css("body *::text")

        texts = []

        for el in elements:
            try:
                # Try extracting text
                txt = str(el)
                if txt:
                    texts.append(txt)
            except:
                continue

        cleaned = [t.strip() for t in texts if t.strip()]

        return " ".join(cleaned)

    except Exception as e:
        print("SCRAPING ERROR:", e)
        return ""