Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -7,13 +7,17 @@ from bs4 import BeautifulSoup
|
|
| 7 |
|
| 8 |
EXCLUDED_FILES = ['app.py', 'requirements.txt', 'pre-requirements.txt', 'packages.txt', 'README.md','.gitattributes', "backup.py","Dockerfile"]
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
def download_file(url, local_filename):
|
| 11 |
if url.startswith('http://') or url.startswith('https://'):
|
| 12 |
try:
|
| 13 |
with requests.get(url, stream=True) as r:
|
| 14 |
r.raise_for_status()
|
| 15 |
with open(local_filename, 'wb') as f:
|
| 16 |
-
for chunk in r.iter_content(chunk_size=8192):
|
| 17 |
f.write(chunk)
|
| 18 |
return local_filename
|
| 19 |
except requests.exceptions.HTTPError as err:
|
|
@@ -51,19 +55,22 @@ def show_download_links():
|
|
| 51 |
def main():
|
| 52 |
st.sidebar.title('Web Datasets 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()
|
| 57 |
-
with open("history.txt", "a") as file:
|
| 58 |
-
file.write(f"{url}\n")
|
| 59 |
if st.sidebar.button('📂 Show Download Links'):
|
| 60 |
show_download_links()
|
| 61 |
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
st.text_area("URL history", value="".join(history_urls), height=200)
|
| 67 |
|
| 68 |
if __name__ == "__main__":
|
| 69 |
main()
|
|
|
|
| 7 |
|
| 8 |
EXCLUDED_FILES = ['app.py', 'requirements.txt', 'pre-requirements.txt', 'packages.txt', 'README.md','.gitattributes', "backup.py","Dockerfile"]
|
| 9 |
|
| 10 |
+
# Create a history.txt file if it doesn't exist yet
|
| 11 |
+
with open("history.txt", "a+") as f:
|
| 12 |
+
f.close()
|
| 13 |
+
|
| 14 |
def download_file(url, local_filename):
|
| 15 |
if url.startswith('http://') or url.startswith('https://'):
|
| 16 |
try:
|
| 17 |
with requests.get(url, stream=True) as r:
|
| 18 |
r.raise_for_status()
|
| 19 |
with open(local_filename, 'wb') as f:
|
| 20 |
+
for chunk in r.iter_content(chunk_size=8192):
|
| 21 |
f.write(chunk)
|
| 22 |
return local_filename
|
| 23 |
except requests.exceptions.HTTPError as err:
|
|
|
|
| 55 |
def main():
|
| 56 |
st.sidebar.title('Web Datasets Bulk Downloader')
|
| 57 |
url = st.sidebar.text_input('Please enter a Web URL to bulk download text and files')
|
| 58 |
+
|
| 59 |
+
# Save the history of URL entered as a text file
|
| 60 |
+
if url:
|
| 61 |
+
with open("history.txt", "a") as f:
|
| 62 |
+
f.write(url + "\n")
|
| 63 |
+
|
| 64 |
if st.sidebar.button('📥 Get All the Content'):
|
| 65 |
download_html_and_files(url)
|
| 66 |
show_download_links()
|
|
|
|
|
|
|
| 67 |
if st.sidebar.button('📂 Show Download Links'):
|
| 68 |
show_download_links()
|
| 69 |
|
| 70 |
+
# Display history as markdown
|
| 71 |
+
with open("history.txt", "r") as f:
|
| 72 |
+
history = f.read()
|
| 73 |
+
st.markdown(f"### History\n\n{history}")
|
|
|
|
| 74 |
|
| 75 |
if __name__ == "__main__":
|
| 76 |
main()
|