import urllib.request
from bs4 import BeautifulSoup
import sys

urls = [
    "https://support.google.com/flow/answer/17104535?hl=en",
    "https://www.mindstudio.ai/blog/what-is-google-flow-tools-custom-ai-workflows-no-code",
    "https://www.wisdomai.com/insights/TheAIGRID/google-flow-tools-creative-workflows-remix-tools-ai-image-video-cf3232c1",
    "https://support.google.com/flow/answer/16353334?hl=en&co=GENIE.Platform=Desktop"
]

for url in urls:
    print(f"\n\n--- CONTENT FOR {url} ---\n\n")
    try:
        req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'})
        html = urllib.request.urlopen(req, timeout=10).read()
        soup = BeautifulSoup(html, 'html.parser')
        
        # Remove script and style elements
        for script in soup(["script", "style"]):
            script.extract()
            
        text = soup.get_text(separator='\n')
        lines = (line.strip() for line in text.splitlines())
        chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
        text = '\n'.join(chunk for chunk in chunks if chunk)
        print(text[:3000] + "\n...[TRUNCATED]" if len(text) > 3000 else text)
    except Exception as e:
        print(f"Error fetching {url}: {e}")