import urllib.request
from bs4 import BeautifulSoup

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

for name, url in urls.items():
    try:
        req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'})
        html = urllib.request.urlopen(req, timeout=15).read()
        soup = BeautifulSoup(html, 'html.parser')
        
        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)
        
        filename = f"{name}.txt"
        with open(filename, "w", encoding="utf-8") as f:
            f.write(text)
        print(f"Downloaded {url} -> {filename} ({len(text)} chars)")
    except Exception as e:
        print(f"Error fetching {url}: {e}")