Spaces:
Runtime error
Runtime error
Update backup.py
Browse files
backup.py
CHANGED
@@ -8,8 +8,12 @@ import hashlib
|
|
8 |
import json
|
9 |
|
10 |
EXCLUDED_FILES = ['app.py', 'requirements.txt', 'pre-requirements.txt', 'packages.txt', 'README.md','.gitattributes', "backup.py","Dockerfile"]
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
-
# Create a history.json file if it doesn't exist yet
|
13 |
if not os.path.exists("history.json"):
|
14 |
with open("history.json", "w") as f:
|
15 |
json.dump({}, f)
|
@@ -35,12 +39,10 @@ def download_html_and_files(url, subdir):
|
|
35 |
file_url = urllib.parse.urljoin(base_url, link.get('href'))
|
36 |
local_filename = os.path.join(subdir, urllib.parse.urlparse(file_url).path.split('/')[-1])
|
37 |
|
38 |
-
# Skip if the local filename is a directory
|
39 |
if not local_filename.endswith('/') and local_filename != subdir:
|
40 |
link['href'] = local_filename
|
41 |
download_file(file_url, local_filename)
|
42 |
|
43 |
-
# Save the modified HTML content
|
44 |
with open(os.path.join(subdir, "index.html"), "w") as file:
|
45 |
file.write(str(soup))
|
46 |
|
@@ -48,24 +50,28 @@ def list_files(directory_path='.'):
|
|
48 |
files = [f for f in os.listdir(directory_path) if os.path.isfile(os.path.join(directory_path, f))]
|
49 |
return [f for f in files if f not in EXCLUDED_FILES]
|
50 |
|
51 |
-
|
52 |
def show_file_operations(file_path):
|
53 |
st.write(f"File: {os.path.basename(file_path)}")
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
|
|
|
|
|
|
|
|
|
|
61 |
with open(file_path, "w") as f:
|
62 |
f.write(file_content)
|
63 |
-
st.success(f"File
|
64 |
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
|
70 |
def show_download_links(subdir):
|
71 |
st.write(f'Files for {subdir}:')
|
@@ -77,7 +83,6 @@ def show_download_links(subdir):
|
|
77 |
else:
|
78 |
st.write(f"File not found: {file}")
|
79 |
|
80 |
-
|
81 |
def get_download_link(file):
|
82 |
with open(file, "rb") as f:
|
83 |
bytes = f.read()
|
@@ -85,16 +90,19 @@ def get_download_link(file):
|
|
85 |
href = f'<a href="data:file/octet-stream;base64,{b64}" download=\'{os.path.basename(file)}\'>Click to download {os.path.basename(file)}</a>'
|
86 |
return href
|
87 |
|
88 |
-
|
89 |
def main():
|
90 |
st.sidebar.title('Web Datasets Bulk Downloader')
|
91 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
|
93 |
-
# Load history
|
94 |
with open("history.json", "r") as f:
|
95 |
history = json.load(f)
|
96 |
|
97 |
-
# Save the history of URL entered as a json file
|
98 |
if url:
|
99 |
subdir = hashlib.md5(url.encode()).hexdigest()
|
100 |
if not os.path.exists(subdir):
|
@@ -112,7 +120,6 @@ def main():
|
|
112 |
for subdir in history.values():
|
113 |
show_download_links(subdir)
|
114 |
|
115 |
-
# Display history as markdown
|
116 |
with st.expander("URL History and Downloaded Files"):
|
117 |
for url, subdir in history.items():
|
118 |
st.markdown(f"#### {url}")
|
|
|
8 |
import json
|
9 |
|
10 |
EXCLUDED_FILES = ['app.py', 'requirements.txt', 'pre-requirements.txt', 'packages.txt', 'README.md','.gitattributes', "backup.py","Dockerfile"]
|
11 |
+
URLS = {
|
12 |
+
"Chordify - Play Along Chords": "https://chordify.net/",
|
13 |
+
"National Guitar Academy - Guitar Learning": "https://www.guitaracademy.com/",
|
14 |
+
"Ultimate Guitar - Massive Song Database": "https://www.ultimate-guitar.com/",
|
15 |
+
}
|
16 |
|
|
|
17 |
if not os.path.exists("history.json"):
|
18 |
with open("history.json", "w") as f:
|
19 |
json.dump({}, f)
|
|
|
39 |
file_url = urllib.parse.urljoin(base_url, link.get('href'))
|
40 |
local_filename = os.path.join(subdir, urllib.parse.urlparse(file_url).path.split('/')[-1])
|
41 |
|
|
|
42 |
if not local_filename.endswith('/') and local_filename != subdir:
|
43 |
link['href'] = local_filename
|
44 |
download_file(file_url, local_filename)
|
45 |
|
|
|
46 |
with open(os.path.join(subdir, "index.html"), "w") as file:
|
47 |
file.write(str(soup))
|
48 |
|
|
|
50 |
files = [f for f in os.listdir(directory_path) if os.path.isfile(os.path.join(directory_path, f))]
|
51 |
return [f for f in files if f not in EXCLUDED_FILES]
|
52 |
|
|
|
53 |
def show_file_operations(file_path):
|
54 |
st.write(f"File: {os.path.basename(file_path)}")
|
55 |
+
unique_key = hashlib.md5(file_path.encode()).hexdigest()
|
56 |
+
col1, col2, col3 = st.columns(3)
|
57 |
+
|
58 |
+
with col1:
|
59 |
+
if st.button(f"✏️ Edit", key=f"edit_{unique_key}"):
|
60 |
+
file_content = ""
|
61 |
+
with open(file_path, "r") as f:
|
62 |
+
file_content = f.read()
|
63 |
+
file_content = st.text_area("Edit the file content:", value=file_content, height=250, key=f"text_area_{unique_key}")
|
64 |
+
|
65 |
+
with col2:
|
66 |
+
if st.button(f"💾 Save", key=f"save_{unique_key}"):
|
67 |
with open(file_path, "w") as f:
|
68 |
f.write(file_content)
|
69 |
+
st.success(f"File saved!")
|
70 |
|
71 |
+
with col3:
|
72 |
+
if st.button(f"🗑️ Delete", key=f"delete_{unique_key}"):
|
73 |
+
os.remove(file_path)
|
74 |
+
st.markdown(f"File deleted!")
|
75 |
|
76 |
def show_download_links(subdir):
|
77 |
st.write(f'Files for {subdir}:')
|
|
|
83 |
else:
|
84 |
st.write(f"File not found: {file}")
|
85 |
|
|
|
86 |
def get_download_link(file):
|
87 |
with open(file, "rb") as f:
|
88 |
bytes = f.read()
|
|
|
90 |
href = f'<a href="data:file/octet-stream;base64,{b64}" download=\'{os.path.basename(file)}\'>Click to download {os.path.basename(file)}</a>'
|
91 |
return href
|
92 |
|
|
|
93 |
def main():
|
94 |
st.sidebar.title('Web Datasets Bulk Downloader')
|
95 |
+
url_input_method = st.sidebar.radio("Choose URL Input Method", ["Enter URL", "Select from List"])
|
96 |
+
url = ""
|
97 |
+
if url_input_method == "Enter URL":
|
98 |
+
url = st.sidebar.text_input('Please enter a Web URL to bulk download text and files')
|
99 |
+
else:
|
100 |
+
selected_site = st.sidebar.selectbox("Select a Website", list(URLS.keys()))
|
101 |
+
url = URLS[selected_site]
|
102 |
|
|
|
103 |
with open("history.json", "r") as f:
|
104 |
history = json.load(f)
|
105 |
|
|
|
106 |
if url:
|
107 |
subdir = hashlib.md5(url.encode()).hexdigest()
|
108 |
if not os.path.exists(subdir):
|
|
|
120 |
for subdir in history.values():
|
121 |
show_download_links(subdir)
|
122 |
|
|
|
123 |
with st.expander("URL History and Downloaded Files"):
|
124 |
for url, subdir in history.items():
|
125 |
st.markdown(f"#### {url}")
|