public/kcc
1
0
Fork 0
mirror of https://github.com/ciromattia/kcc synced 2025-12-27 00:22:54 +00:00
Code Issues Releases Wiki Activity

remove non images early (#1007)

Browse Source
This commit is contained in:
Alex Xu
2025-07-02 10:17:54 -07:00
committed by GitHub
parent 6f960aa1d0
commit f41d5327e0
2 changed files with 16 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
kindlecomicconverter/comic2ebook.py
View File

@@ -823,6 +823,19 @@ def getPanelViewSize(deviceres, size):
return str(int(x)), str(int(y)) return str(int(x)), str(int(y))
def removeNonImages(filetree):
for root, dirs, files in os.walk(filetree):
for name in files:
_, ext = getImageFileName(name)
if ext not in ('.png', '.jpg', '.jpeg', '.gif', '.webp', '.jp2'):
if os.path.exists(os.path.join(root, name)):
os.remove(os.path.join(root, name))
# remove empty nested folders
for root, dirs, files in os.walk(filetree, False):
if not files and not dirs:
os.rmdir(root)
def sanitizeTree(filetree): def sanitizeTree(filetree):
chapterNames = {} chapterNames = {}
page = 1 page = 1
@@ -831,13 +844,13 @@ def sanitizeTree(filetree):
dirs.sort(key=OS_SORT_KEY) dirs.sort(key=OS_SORT_KEY)
files.sort(key=OS_SORT_KEY) files.sort(key=OS_SORT_KEY)
for name in files: for name in files:
splitname = os.path.splitext(name) _, ext = getImageFileName(name)
# 9999 page limit # 9999 page limit
slugified = f'kcc-{page:04}' slugified = f'kcc-{page:04}'
page += 1 page += 1
newKey = os.path.join(root, slugified + splitname[1]) newKey = os.path.join(root, slugified + ext)
key = os.path.join(root, name) key = os.path.join(root, name)
if key != newKey: if key != newKey:
os.replace(key, newKey) os.replace(key, newKey)
@@ -991,10 +1004,6 @@ def detectSuboptimalProcessing(tmppath, orgpath):
os.remove(os.path.join(root, name)) os.remove(os.path.join(root, name))
except OSError as e: except OSError as e:
raise RuntimeError(f"{name}: {e}") raise RuntimeError(f"{name}: {e}")
# remove empty nested folders
for root, dirs, files in os.walk(tmppath, False):
if not files and not dirs:
os.rmdir(root)
if alreadyProcessed: if alreadyProcessed:
print("WARNING: Source files are probably created by KCC. The second conversion will decrease quality.") print("WARNING: Source files are probably created by KCC. The second conversion will decrease quality.")
if GUI: if GUI:
@@ -1310,6 +1319,7 @@ def makeBook(source, qtgui=None):
path = getWorkFolder(source) path = getWorkFolder(source)
print("Checking images...") print("Checking images...")
getComicInfo(os.path.join(path, "OEBPS", "Images"), source) getComicInfo(os.path.join(path, "OEBPS", "Images"), source)
removeNonImages(os.path.join(path, "OEBPS", "Images"))
detectSuboptimalProcessing(os.path.join(path, "OEBPS", "Images"), source) detectSuboptimalProcessing(os.path.join(path, "OEBPS", "Images"), source)
chapterNames, cover_path = sanitizeTree(os.path.join(path, 'OEBPS', 'Images')) chapterNames, cover_path = sanitizeTree(os.path.join(path, 'OEBPS', 'Images'))
cover = image.Cover(cover_path, options) cover = image.Cover(cover_path, options)

6
kindlecomicconverter/shared.py
View File

@@ -48,12 +48,6 @@ class HTMLStripper(HTMLParser):
def getImageFileName(imgfile): def getImageFileName(imgfile):
name, ext = os.path.splitext(imgfile) name, ext = os.path.splitext(imgfile)
ext = ext.lower() ext = ext.lower()
if (name.startswith('.') and len(name) == 1):
return None
if name.startswith('._'):
return None
if ext not in ['.png', '.jpg', '.jpeg', '.gif', '.webp', '.jp2', '.j2k', '.jpx']:
return None
return [name, ext] return [name, ext]