File size: 1,196 Bytes
d6afb45 176890c d6afb45 |
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 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
import gradio as gr
import urllib.request
import bs4
import lxml
def find_it1(url):
source = urllib.request.urlopen(url).read()
soup = bs.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'))
for paragraph in soup.find_all('p'):
print(paragraph.string)
print(str(paragraph.text))
for url in soup.find_all('a'):
print(url.get('href'))
print(soup.get_text())
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()
btn = gr.Button()
outp = gr.Textbox()
btn.click(find_it2,inp,outp)
app.launch()
|