Spaces:
Sleeping
Sleeping
Update split_files_to_excel.py
Browse files- split_files_to_excel.py +5 -4
split_files_to_excel.py
CHANGED
@@ -524,7 +524,7 @@ def split_in_df(files):
|
|
524 |
|
525 |
# -------------------------------------------------------------------------------- SPLIT FILES BY KEYWORDS
|
526 |
|
527 |
-
def split_by_keywords(files, key_words,words_limit=1000):
|
528 |
extracted_content = []
|
529 |
|
530 |
tabLine = []
|
@@ -543,7 +543,7 @@ def split_by_keywords(files, key_words,words_limit=1000):
|
|
543 |
|
544 |
for index, line in enumerate(lines):
|
545 |
print(line)
|
546 |
-
for key in
|
547 |
line = line.lower()
|
548 |
|
549 |
if key in line:
|
@@ -646,7 +646,8 @@ def split_by_keywords(files, key_words,words_limit=1000):
|
|
646 |
# doc_data[key] = value
|
647 |
|
648 |
df = pd.concat([df, pd.DataFrame([doc_data])], ignore_index=True)
|
649 |
-
|
650 |
df.to_excel("dataframe_keywords.xlsx", index=False)
|
651 |
-
|
652 |
return "dataframe_keywords.xlsx"
|
|
|
|
524 |
|
525 |
# -------------------------------------------------------------------------------- SPLIT FILES BY KEYWORDS
|
526 |
|
527 |
+
def split_by_keywords(files, key_words, words_limit=1000):
|
528 |
extracted_content = []
|
529 |
|
530 |
tabLine = []
|
|
|
543 |
|
544 |
for index, line in enumerate(lines):
|
545 |
print(line)
|
546 |
+
for key in key_words:
|
547 |
line = line.lower()
|
548 |
|
549 |
if key in line:
|
|
|
646 |
# doc_data[key] = value
|
647 |
|
648 |
df = pd.concat([df, pd.DataFrame([doc_data])], ignore_index=True)
|
649 |
+
|
650 |
df.to_excel("dataframe_keywords.xlsx", index=False)
|
651 |
+
|
652 |
return "dataframe_keywords.xlsx"
|
653 |
+
|