Spaces:
Sleeping
Sleeping
Update scrape_3gpp.py
Browse files- scrape_3gpp.py +1 -5
scrape_3gpp.py
CHANGED
|
@@ -71,21 +71,17 @@ import gradio as gr
|
|
| 71 |
|
| 72 |
|
| 73 |
def scrape(url, excel_file, folder_name, status_list, sorted_files, progress=gr.Progress()):
|
| 74 |
-
|
| 75 |
-
print("ENTERING SCRAPE FUNCTION")
|
| 76 |
filenames = []
|
| 77 |
status_filenames = []
|
| 78 |
df = pd.DataFrame() # Initialize df to ensure it's always defined
|
| 79 |
|
| 80 |
# Try to process the Excel file if provided and valid
|
| 81 |
-
print(f"WE ARE TESTING IF OS.PATH.EXISTS WITH THIS FILE : {excel_file}")
|
| 82 |
if excel_file and os.path.exists(excel_file):
|
| 83 |
try:
|
| 84 |
df = pd.read_excel(excel_file)
|
| 85 |
print(f"Initial DataFrame size: {len(df)}")
|
| 86 |
|
| 87 |
-
|
| 88 |
-
print(f"WE ARE TRYING TO LOOK AT df.columns : {df.columns.tolist()}")
|
| 89 |
if 'TDoc Status' in df.columns and status_list:
|
| 90 |
df = df[df['TDoc Status'].isin(status_list)]
|
| 91 |
print(f"Filtered DataFrame size: {len(df)}")
|
|
|
|
| 71 |
|
| 72 |
|
| 73 |
def scrape(url, excel_file, folder_name, status_list, sorted_files, progress=gr.Progress()):
|
|
|
|
|
|
|
| 74 |
filenames = []
|
| 75 |
status_filenames = []
|
| 76 |
df = pd.DataFrame() # Initialize df to ensure it's always defined
|
| 77 |
|
| 78 |
# Try to process the Excel file if provided and valid
|
|
|
|
| 79 |
if excel_file and os.path.exists(excel_file):
|
| 80 |
try:
|
| 81 |
df = pd.read_excel(excel_file)
|
| 82 |
print(f"Initial DataFrame size: {len(df)}")
|
| 83 |
|
| 84 |
+
|
|
|
|
| 85 |
if 'TDoc Status' in df.columns and status_list:
|
| 86 |
df = df[df['TDoc Status'].isin(status_list)]
|
| 87 |
print(f"Filtered DataFrame size: {len(df)}")
|