mrq/stable-diffusion-utils
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added cache folder to pull from if an image exists (to remove needless refetches in the future)

Browse Source
This commit is contained in:
mrq 2023-02-08 19:21:24 +00:00
parent 0d5bbfa465
commit d1d5153874
4 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
data/config/examples/fetch.json
View File

@ -1,6 +1,7 @@
{
"booru": "e621",
"output": "./images/downloaded/",
"images": "./images/cache/",
"limit": 320,
"concurrency": 4,
"userAgent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36",

0
images/cache/.gitkeep vendored Executable file
View File

11
src/fetch.js
View File

@ -45,6 +45,7 @@ let config = {
output: `./images/downloaded/`, // directory to save your files
cache: `./data/cache.json`, // JSON file of cached tags, will speed up processing when used for the renamer script
images: `./images/cache/`, // total cache of images, will copy if file exists here
limit: 320, // how many posts to pull in one go
concurrency: 4, // how many file requests to keep in flight at the same time
@ -139,6 +140,11 @@ let parse = async () => {
console.log(`Skipping existing file: ${booru.urls.posts}${post.id}`)
continue;
}
if ( FS.existsSync(`${config.images}${post.filename}`) ) {
console.log(`Copying cached file: ${booru.urls.posts}${post.id}`)
FS.copyFileSync(`${config.images}${post.filename}`, `${config.output}${post.filename}`)
continue;
}
if ( config.filter ) {
let filtered = null;
@ -173,6 +179,11 @@ let parse = async () => {
res.body.pipe(dest);
dest.on('close', () => {
console.log(`Downloaded: ${booru.urls.posts}${post.id}`)
if ( FS.existsSync(`${config.images}`) ) {
FS.copyFileSync(`${config.output}${post.filename}`, `${config.images}${post.filename}`)
}
resolve()
});
dest.on('error', reject);

9
src/fetch.py
View File

@ -50,6 +50,7 @@ config = {
'output': './images/downloaded/', # directory to save your files
'cache': './data/cache.json', # JSON file of cached tags, will speed up processing when used for the renamer script
'images': './images/cache/', # total cache of images, will copy if file exists here
'limit': 320, # how many posts to pull in one go
@ -127,6 +128,11 @@ def parse():
if os.path.exists(f"{config['output']}{post['filename']}"):
print(f"Skipping existing file: {booru['urls']['posts']}{post['id']}")
continue
if os.path.exists(f"{config['images']}{post['filename']}"):
print(f"Copying cached file: {booru['urls']['posts']}{post['id']}")
shutil.copy(os.path.join(config['images'], post['filename']), os.path.join(config['output'], post['filename']))
continue
if post['url'] is None:
print(f"Skipping file that requires logging in: {booru['urls']['posts']}{post['id']}")
@ -151,6 +157,9 @@ def parse():
if not config['skipSave']:
urllib.request.urlretrieve(post['url'], f"{config['output']}{post['filename']}")
if os.path.exists(f"{config['images']}"):
shutil.copy(os.path.join(config['output'], post['filename']), os.path.join(config['images'], post['filename']))
print(f"Downloaded : {booru['urls']['posts']}{post['id']}")
if config['rateLimit']: