Refactor JSON file retrieval logic to filter links by .json extension and extract only file names for improved clarity and efficiency.
This commit is contained in:
BIN
__pycache__/galdPl.cpython-312.pyc
Normal file
BIN
__pycache__/galdPl.cpython-312.pyc
Normal file
Binary file not shown.
13
main.py
13
main.py
@@ -17,11 +17,13 @@ def get_json_files_from_folder(folder):
|
|||||||
r.raise_for_status()
|
r.raise_for_status()
|
||||||
soup = BeautifulSoup(r.text, "html.parser")
|
soup = BeautifulSoup(r.text, "html.parser")
|
||||||
files = []
|
files = []
|
||||||
for a in soup.find_all("a", class_="ui basic label"):
|
# Hledáme odkazy s .json v href
|
||||||
|
for a in soup.find_all("a", href=lambda x: x and x.endswith('.json')):
|
||||||
href = a.get("href", "")
|
href = a.get("href", "")
|
||||||
if href.endswith(".json"):
|
if href.startswith("/gald/galdistream/src/branch/main/resources/"):
|
||||||
file_path = href.split("/resources/")[-1]
|
# Extrahujeme pouze název souboru
|
||||||
files.append(file_path)
|
file_name = href.split("/")[-1]
|
||||||
|
files.append(file_name)
|
||||||
return files
|
return files
|
||||||
|
|
||||||
def update_json_db():
|
def update_json_db():
|
||||||
@@ -30,7 +32,8 @@ def update_json_db():
|
|||||||
all_files = []
|
all_files = []
|
||||||
for folder in folders:
|
for folder in folders:
|
||||||
try:
|
try:
|
||||||
all_files += [f"{folder}/{file}" for file in get_json_files_from_folder(folder)]
|
files = get_json_files_from_folder(folder)
|
||||||
|
all_files += [f"{folder}/{file}" for file in files]
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
print(f"Chyba při získávání souborů ze složky {folder}: {e}")
|
print(f"Chyba při získávání souborů ze složky {folder}: {e}")
|
||||||
for file in all_files:
|
for file in all_files:
|
||||||
|
|||||||
Reference in New Issue
Block a user