Created
December 22, 2022 09:20
-
-
Save fr0der1c/0509bf87b10df9d36707ae763cf1c121 to your computer and use it in GitHub Desktop.
Logseq find unused assets & find missing assets
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import shutil | |
assets_dir = './assets' | |
journal_dir = './journals' | |
pages_dir = './pages' | |
to_delete_dir = './to_delete' | |
def get_all_assets() -> list[str]: | |
if not os.path.exists(to_delete_dir): | |
os.makedirs(to_delete_dir) | |
assets_files = os.listdir(assets_dir) | |
return assets_files | |
if __name__=='__main__': | |
assets_files = get_all_assets() | |
referenced_files = [] | |
for dirname in [journal_dir, pages_dir]: | |
for filename in os.listdir(dirname): | |
if filename.endswith('.md'): | |
with open(os.path.join(dirname, filename)) as f: | |
for line in f: | |
for asset in assets_files: | |
if asset in line: | |
referenced_files.append(asset) | |
for asset in assets_files: | |
if asset not in referenced_files and not asset.endswith(".edn"): | |
print("assets/"+asset) | |
shutil.move(os.path.join(assets_dir, asset), to_delete_dir) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import re | |
from delete_unused_assets import get_all_assets | |
def get_all_referenced_image_filenames() -> list[tuple[str, str]]: | |
current_dir = os.getcwd() | |
journals_dir = os.path.join(current_dir, 'journals') | |
pages_dir = os.path.join(current_dir, 'pages') | |
journals_files = ['journals/'+f for f in os.listdir(journals_dir) if f.endswith('.md')] | |
pages_files = ['pages/'+f for f in os.listdir(pages_dir) if f.endswith('.md')] | |
all_files = journals_files + pages_files | |
image_references = [] | |
for filename in all_files: | |
with open(filename, 'r') as f: | |
file_contents = f.read() | |
for item in re.findall(r'!\[\]\((.+?)\)', file_contents): | |
image_references.append((filename, item)) | |
image_references = [(item[0], item[1][10:]) for item in image_references if item[1].startswith("../")] | |
return image_references | |
if __name__=='__main__': | |
all_referenced = get_all_referenced_image_filenames() | |
all_assets = get_all_assets() | |
for md_filename, image_filename in all_referenced: | |
if image_filename not in all_assets: | |
print(f"Image {image_filename} in {md_filename} missing") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment