Spaces:
Runtime error
Runtime error
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import urllib.request
|
3 |
+
|
4 |
+
import bs4
|
5 |
+
import lxml
|
6 |
+
|
7 |
+
def find_it1(url):
|
8 |
+
source = urllib.request.urlopen(url).read()
|
9 |
+
soup = bs.BeautifulSoup(source,'lxml')
|
10 |
+
# title of the page
|
11 |
+
print(soup.title)
|
12 |
+
|
13 |
+
# get attributes:
|
14 |
+
print(soup.title.name)
|
15 |
+
|
16 |
+
# get values:
|
17 |
+
print(soup.title.string)
|
18 |
+
|
19 |
+
# beginning navigation:
|
20 |
+
print(soup.title.parent.name)
|
21 |
+
|
22 |
+
# getting specific values:
|
23 |
+
print(soup.p)
|
24 |
+
print(soup.find_all('p'))
|
25 |
+
for paragraph in soup.find_all('p'):
|
26 |
+
print(paragraph.string)
|
27 |
+
print(str(paragraph.text))
|
28 |
+
|
29 |
+
for url in soup.find_all('a'):
|
30 |
+
print(url.get('href'))
|
31 |
+
print(soup.get_text())
|
32 |
+
|
33 |
+
|
34 |
+
|
35 |
+
def find_it2(url):
|
36 |
+
response = requests.get(url,a1=None,q2=None,q3=None)
|
37 |
+
try:
|
38 |
+
response.raise_for_status()
|
39 |
+
soup = BeautifulSoup(response.content, 'lxml')
|
40 |
+
out = 'URL Links:\n'.join([p.text for p in soup.find_all('a')])
|
41 |
+
return out
|
42 |
+
except Exception as e:
|
43 |
+
print (e)
|
44 |
+
return e
|
45 |
+
|
46 |
+
|
47 |
+
with gr.Blocks() as app:
|
48 |
+
with gr.Row():
|
49 |
+
inp = gr.Textbox()
|
50 |
+
btn = gr.Button()
|
51 |
+
outp = gr.Textbox()
|
52 |
+
btn.click(find_it2,inp,outp)
|
53 |
+
app.launc()
|
54 |
+
|