app.py

import gradio as gr
import urllib.request
import requests
import bs4
import lxml

def find_all(url,q=None,num=None):
    rawp = []
    source = urllib.request.urlopen(url).read()
    soup = bs4.BeautifulSoup(source,'lxml')
    # title of the page
    print(soup.title)
    # get attributes:
    print(soup.title.name)
    # get values:
    print(soup.title.string)
    # beginning navigation:
    print(soup.title.parent.name)
    # getting specific values:
    #print(soup.p)
    #print(soup.find_all('p'))


    rawp.append([tag.name for tag in soup.find_all()] )
    #soup_list = [tag for tag in soup.find_all()]
    #for tag in soup.find_all('h1','h2','h3','p','div','ul'):
    #for tag in soup_list:
        #print(tag.findChildren("a" , recursive=False))
        #try:
            #n = tag.get(tag.string)
        #rawp.append({f'{tag.name}':tag.string,"parent":tag.parent.name})
        #rawp.append({tag.name:tag.string,"parent":tag.parent.name})
        #except Exception as e:
        #    print (e)
     #   rawp.append({f'{tag.name}':f'{tag.string}'})
    
        #rawp.append(tag.string)
    #for url in soup.find_all('a'):
    #print(url.get('href'))
        
    #print(soup.get_text())

    
    return rawp


def find_it(url,q=None,num=None):
    out = []
    source = urllib.request.urlopen(url).read()
    soup = bs4.BeautifulSoup(source,'lxml')
    
    for p in soup.find_all(f'{q}'):
        try:
            print(soup.select(f'{p.name}:first-child').name)
            #print(p.findChildren())
        except Exception as e:
            print (e)
        #out.append(p)
        out.append([{q:p.string,"parent":p.parent.parent.name,"first-child":soup.select(f'{p.name}:first-child').name,"content":p}])
        #out.append(p.parent.name)

    for url in soup.find_all('a'):
        print(url.get('href'))
        
    #print(soup.get_text())
    return out    
    
def find_it2(url):
    response = requests.get(url,a1=None,q2=None,q3=None)
    try:
        response.raise_for_status()
        soup = BeautifulSoup(response.content, 'lxml')
        out = 'URL Links:\n'.join([p.text for p in soup.find_all('a')])
        return out
    except Exception as e:
        print (e)
        return e


with gr.Blocks() as app:
    with gr.Row():
        inp = gr.Textbox()
        q = gr.Textbox(value="p")
        num = gr.Number(value=1)
    with gr.Row():
        all_btn = gr.Button("Load")
        find_btn = gr.Button("Find")
    with gr.Row():
        rawp = gr.JSON()
        outp = gr.JSON()
    
    all_btn.click(find_all,[inp,q,num],[rawp])
    find_btn.click(find_it,[inp,q,num],[outp])
    
app.launch()