Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
import streamlit as st
|
2 |
import requests
|
3 |
-
from bs4 import BeautifulSoup
|
4 |
import os
|
5 |
import urllib
|
6 |
import base64
|
|
|
7 |
|
8 |
EXCLUDED_FILES = ['app.py', 'requirements.txt', 'pre-requirements.txt', 'packages.txt', 'README.md','.gitattributes', "backup.py","Dockerfile"]
|
9 |
|
@@ -22,16 +22,13 @@ def download_file(url, local_filename):
|
|
22 |
def download_html_and_files(url):
|
23 |
html_content = requests.get(url).text
|
24 |
soup = BeautifulSoup(html_content, 'html.parser')
|
25 |
-
|
26 |
base_url = urllib.parse.urlunparse(urllib.parse.urlparse(url)._replace(path='', params='', query='', fragment=''))
|
27 |
-
|
28 |
for link in soup.find_all('a'):
|
29 |
file_url = urllib.parse.urljoin(base_url, link.get('href'))
|
30 |
local_filename = urllib.parse.urlparse(file_url).path.split('/')[-1]
|
31 |
if local_filename:
|
32 |
link['href'] = local_filename
|
33 |
download_file(file_url, local_filename)
|
34 |
-
|
35 |
with open("index.html", "w") as file:
|
36 |
file.write(str(soup))
|
37 |
|
@@ -52,8 +49,8 @@ def show_download_links():
|
|
52 |
st.sidebar.markdown(get_download_link(file), unsafe_allow_html=True)
|
53 |
|
54 |
def main():
|
55 |
-
st.sidebar.title('Bulk
|
56 |
-
url = st.sidebar.text_input('Please enter a URL to bulk download text and files')
|
57 |
if st.sidebar.button('📥 Get All the Content'):
|
58 |
download_html_and_files(url)
|
59 |
show_download_links()
|
|
|
1 |
import streamlit as st
|
2 |
import requests
|
|
|
3 |
import os
|
4 |
import urllib
|
5 |
import base64
|
6 |
+
from bs4 import BeautifulSoup
|
7 |
|
8 |
EXCLUDED_FILES = ['app.py', 'requirements.txt', 'pre-requirements.txt', 'packages.txt', 'README.md','.gitattributes', "backup.py","Dockerfile"]
|
9 |
|
|
|
22 |
def download_html_and_files(url):
|
23 |
html_content = requests.get(url).text
|
24 |
soup = BeautifulSoup(html_content, 'html.parser')
|
|
|
25 |
base_url = urllib.parse.urlunparse(urllib.parse.urlparse(url)._replace(path='', params='', query='', fragment=''))
|
|
|
26 |
for link in soup.find_all('a'):
|
27 |
file_url = urllib.parse.urljoin(base_url, link.get('href'))
|
28 |
local_filename = urllib.parse.urlparse(file_url).path.split('/')[-1]
|
29 |
if local_filename:
|
30 |
link['href'] = local_filename
|
31 |
download_file(file_url, local_filename)
|
|
|
32 |
with open("index.html", "w") as file:
|
33 |
file.write(str(soup))
|
34 |
|
|
|
49 |
st.sidebar.markdown(get_download_link(file), unsafe_allow_html=True)
|
50 |
|
51 |
def main():
|
52 |
+
st.sidebar.title('Web Bulk Downloader')
|
53 |
+
url = st.sidebar.text_input('Please enter a Web URL to bulk download text and files')
|
54 |
if st.sidebar.button('📥 Get All the Content'):
|
55 |
download_html_and_files(url)
|
56 |
show_download_links()
|