app.py

import gradio as gr
import requests
import bs4

def link_find(url):
    out = []
    source = requests.get(url)
    if source.status_code ==200:
        #soup = bs4.BeautifulSoup(source.content,'lxml')
        soup = bs4.BeautifulSoup(source.content,'html.parser')
        
        rawp=(f'RAW TEXT RETURNED: {soup.text}')
        cnt=0
        cnt+=len(rawp)
        #out.append(rawp)
        #out.append("HTML fragments: ")
        q=("a","p","span","content","article")
        for p in soup.find_all("a"):
            out.append({"LINK TITLE":p.get('title'),"URL":p.get('href'),"STRING":p.string,"TREE":[]})    
    else:
        pass
    return out
#https://huggingface.co/spaces/Omnibus/crawl

def sitemap(url):
    uri=""
    if url != "" and url != None:    
        link1=link_find(url)
        for i,ea in enumerate(link1):
            print(ea)
            try:
                if not ea['URL'].startswith("http"):
                    
                    uri1=url.split("//")[0]
                    uri2=url.split("//")[1]
                    uri3=uri2.split("/")[0]
                    uri=f'{uri1}//{uri3}'
                    print(uri)
                out_list=link_find(f"{uri}{ea['URL']}")
                link1[i]['TREE']=ea["TREE"].append(out_list)
            except Exception as e:
                print (e)
    return link1
with gr.Blocks() as app:
    inp=gr.Textbox()
    btn=gr.Button()
    outp=gr.JSON()
    btn.click(sitemap,inp,outp)
app.launch()