Spaces:
Runtime error
Runtime error
Update backup.py
Browse files
backup.py
CHANGED
|
@@ -6,12 +6,21 @@ import base64
|
|
| 6 |
from bs4 import BeautifulSoup
|
| 7 |
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 |
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"):
|
|
@@ -50,36 +59,67 @@ def list_files(directory_path='.'):
|
|
| 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
-
|
| 60 |
-
|
| 61 |
with open(file_path, "r") as f:
|
| 62 |
file_content = f.read()
|
| 63 |
-
|
|
|
|
| 64 |
|
| 65 |
with col2:
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
|
|
|
|
|
|
| 70 |
|
| 71 |
with col3:
|
| 72 |
-
|
|
|
|
| 73 |
os.remove(file_path)
|
| 74 |
st.markdown(f"File deleted!")
|
| 75 |
|
|
|
|
|
|
|
|
|
|
| 76 |
def show_download_links(subdir):
|
| 77 |
-
|
| 78 |
for file in list_files(subdir):
|
| 79 |
file_path = os.path.join(subdir, file)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
if os.path.isfile(file_path):
|
| 81 |
st.markdown(get_download_link(file_path), unsafe_allow_html=True)
|
| 82 |
-
show_file_operations(file_path)
|
| 83 |
else:
|
| 84 |
st.write(f"File not found: {file}")
|
| 85 |
|
|
@@ -92,6 +132,8 @@ def get_download_link(file):
|
|
| 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":
|
|
@@ -100,9 +142,15 @@ def main():
|
|
| 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):
|
|
@@ -112,18 +160,22 @@ def main():
|
|
| 112 |
with open("history.json", "w") as f:
|
| 113 |
json.dump(history, f)
|
| 114 |
|
|
|
|
| 115 |
if st.sidebar.button('📥 Get All the Content'):
|
| 116 |
download_html_and_files(url, history[url])
|
| 117 |
show_download_links(history[url])
|
| 118 |
|
|
|
|
| 119 |
if st.sidebar.button('📂 Show Download Links'):
|
| 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}")
|
| 126 |
show_download_links(subdir)
|
| 127 |
|
|
|
|
| 128 |
if __name__ == "__main__":
|
| 129 |
main()
|
|
|
|
| 6 |
from bs4 import BeautifulSoup
|
| 7 |
import hashlib
|
| 8 |
import json
|
| 9 |
+
import uuid
|
| 10 |
|
| 11 |
EXCLUDED_FILES = ['app.py', 'requirements.txt', 'pre-requirements.txt', 'packages.txt', 'README.md','.gitattributes', "backup.py","Dockerfile"]
|
| 12 |
URLS = {
|
| 13 |
"Chordify - Play Along Chords": "https://chordify.net/",
|
| 14 |
"National Guitar Academy - Guitar Learning": "https://www.guitaracademy.com/",
|
| 15 |
"Ultimate Guitar - Massive Song Database": "https://www.ultimate-guitar.com/",
|
| 16 |
+
"Wolf Alice": "https://www.chordie.com/song.php/songartist/Wolf+Alice/index.html",
|
| 17 |
+
"Everclear": "https://www.chordie.com/song.php/songartist/Everclear/index.html",
|
| 18 |
+
"Jungle": "https://www.ultimate-guitar.com/artist/jungle_47745",
|
| 19 |
+
"Mylie Cyrus": "https://www.ultimate-guitar.com/search.php?title=mile+cyrus&spelling=Mylie+cyrus",
|
| 20 |
+
"Kanye": "https://www.ultimate-guitar.com/search.php?search_type=title&value=Kanye%20west",
|
| 21 |
+
"Cat Stevens": "https://www.ultimate-guitar.com/search.php?search_type=title&value=cat%20stevens",
|
| 22 |
+
"Metric": "https://www.ultimate-guitar.com/search.php?search_type=title&value=Metric",
|
| 23 |
+
"John Lennon": "https://www.ultimate-guitar.com/search.php?search_type=title&value=John%20Lennon",
|
| 24 |
}
|
| 25 |
|
| 26 |
if not os.path.exists("history.json"):
|
|
|
|
| 59 |
files = [f for f in os.listdir(directory_path) if os.path.isfile(os.path.join(directory_path, f))]
|
| 60 |
return [f for f in files if f not in EXCLUDED_FILES]
|
| 61 |
|
| 62 |
+
def file_editor(file_path):
|
| 63 |
+
st.write(f"Editing File: {os.path.basename(file_path)}")
|
| 64 |
+
file_content = ""
|
| 65 |
+
|
| 66 |
+
with open(file_path, "r") as f:
|
| 67 |
+
file_content = f.read()
|
| 68 |
+
|
| 69 |
+
file_content = st.text_area("Edit the file content:", value=file_content, height=250)
|
| 70 |
+
|
| 71 |
+
if st.button("💾 Save"):
|
| 72 |
+
with open(file_path, "w") as f:
|
| 73 |
+
f.write(file_content)
|
| 74 |
+
st.success(f"File '{os.path.basename(file_path)}' saved!")
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
def show_file_operations(file_path, sequence_number):
|
| 78 |
st.write(f"File: {os.path.basename(file_path)}")
|
| 79 |
unique_key = hashlib.md5(file_path.encode()).hexdigest()
|
| 80 |
+
|
| 81 |
+
file_content = ""
|
| 82 |
+
|
| 83 |
col1, col2, col3 = st.columns(3)
|
| 84 |
|
| 85 |
with col1:
|
| 86 |
+
edit_key = f"edit_{unique_key}_{sequence_number}"
|
| 87 |
+
if st.button(f"✏️ Edit", key=edit_key):
|
| 88 |
with open(file_path, "r") as f:
|
| 89 |
file_content = f.read()
|
| 90 |
+
text_area_key = f"text_area_{unique_key}_{sequence_number}"
|
| 91 |
+
file_content = st.text_area("Edit the file content:", value=file_content, height=250, key=text_area_key)
|
| 92 |
|
| 93 |
with col2:
|
| 94 |
+
save_key = f"save_{unique_key}_{sequence_number}"
|
| 95 |
+
if st.button(f"💾 Save", key=save_key):
|
| 96 |
+
if file_content: # Ensure file_content is not empty
|
| 97 |
+
with open(file_path, "w") as f:
|
| 98 |
+
f.write(file_content)
|
| 99 |
+
st.success(f"File saved!")
|
| 100 |
|
| 101 |
with col3:
|
| 102 |
+
delete_key = f"delete_{unique_key}_{sequence_number}"
|
| 103 |
+
if st.button(f"🗑️ Delete", key=delete_key):
|
| 104 |
os.remove(file_path)
|
| 105 |
st.markdown(f"File deleted!")
|
| 106 |
|
| 107 |
+
|
| 108 |
+
file_sequence_numbers = {}
|
| 109 |
+
|
| 110 |
def show_download_links(subdir):
|
| 111 |
+
global file_sequence_numbers
|
| 112 |
for file in list_files(subdir):
|
| 113 |
file_path = os.path.join(subdir, file)
|
| 114 |
+
if file_path not in file_sequence_numbers:
|
| 115 |
+
file_sequence_numbers[file_path] = 1
|
| 116 |
+
else:
|
| 117 |
+
file_sequence_numbers[file_path] += 1
|
| 118 |
+
sequence_number = file_sequence_numbers[file_path]
|
| 119 |
+
|
| 120 |
if os.path.isfile(file_path):
|
| 121 |
st.markdown(get_download_link(file_path), unsafe_allow_html=True)
|
| 122 |
+
show_file_operations(file_path, sequence_number)
|
| 123 |
else:
|
| 124 |
st.write(f"File not found: {file}")
|
| 125 |
|
|
|
|
| 132 |
|
| 133 |
def main():
|
| 134 |
st.sidebar.title('Web Datasets Bulk Downloader')
|
| 135 |
+
|
| 136 |
+
# Selecting URL input method
|
| 137 |
url_input_method = st.sidebar.radio("Choose URL Input Method", ["Enter URL", "Select from List"])
|
| 138 |
url = ""
|
| 139 |
if url_input_method == "Enter URL":
|
|
|
|
| 142 |
selected_site = st.sidebar.selectbox("Select a Website", list(URLS.keys()))
|
| 143 |
url = URLS[selected_site]
|
| 144 |
|
| 145 |
+
# Reading or creating history.json
|
| 146 |
+
if not os.path.exists("history.json"):
|
| 147 |
+
with open("history.json", "w") as f:
|
| 148 |
+
json.dump({}, f)
|
| 149 |
+
|
| 150 |
with open("history.json", "r") as f:
|
| 151 |
history = json.load(f)
|
| 152 |
|
| 153 |
+
# Handling URL submission
|
| 154 |
if url:
|
| 155 |
subdir = hashlib.md5(url.encode()).hexdigest()
|
| 156 |
if not os.path.exists(subdir):
|
|
|
|
| 160 |
with open("history.json", "w") as f:
|
| 161 |
json.dump(history, f)
|
| 162 |
|
| 163 |
+
# Button for downloading content
|
| 164 |
if st.sidebar.button('📥 Get All the Content'):
|
| 165 |
download_html_and_files(url, history[url])
|
| 166 |
show_download_links(history[url])
|
| 167 |
|
| 168 |
+
# Button for showing download links
|
| 169 |
if st.sidebar.button('📂 Show Download Links'):
|
| 170 |
for subdir in history.values():
|
| 171 |
show_download_links(subdir)
|
| 172 |
|
| 173 |
+
# Expander for showing URL history and download links
|
| 174 |
with st.expander("URL History and Downloaded Files"):
|
| 175 |
for url, subdir in history.items():
|
| 176 |
st.markdown(f"#### {url}")
|
| 177 |
show_download_links(subdir)
|
| 178 |
|
| 179 |
+
|
| 180 |
if __name__ == "__main__":
|
| 181 |
main()
|