def rename_slide(old, new, root=None, relink=True, verbose=False):
THUMB_NAME = "-thumb.jpg"
FULL_NAME = "-full.jpg"
if root is None:
root = '.' # current directory
if not os.path.exists(old):
raise IOError("%s does not exist" % old)
if not is_slide(old):
raise TypeError("%s is not a valid slide" % old)
old_slide_name = os.path.basename(old)
new_slide_name = os.path.basename(new)
inner_file, slide_type = parse_slide(old)
#relink first so we don't have to worry about adjusting file paths
if relink:
renamer = mv_refs(old_slide_name, new_slide_name)
parse_folder(root, actions=[renamer], verbose=verbose)
#rename inner file
inner_pieces = os.path.splitext(inner_file)
new_inner_file = os.path.join(old,new_slide_name+inner_pieces[1])
safe_rename(inner_file, new_inner_file)
#rename -thumb.jpg if it exists
old_thumb = os.path.join(old,old_slide_name+THUMB_NAME)
new_thumb = os.path.join(old,new_slide_name+THUMB_NAME)
if os.path.exists(old_thumb): safe_rename(old_thumb,new_thumb)
#rename -full.jpg if it exists
old_full = os.path.join(old,old_slide_name+FULL_NAME)
new_full = os.path.join(old,new_slide_name+FULL_NAME)
if os.path.exists(old_full): safe_rename(old_full,new_full)
#rename outer parent folder
safe_rename(old, new)
def parse_slide_folders(path): # filter all file paths for only folders that contain a file with the same name directly inside filepaths = [] dirs = set([]) base_depth = path.count(os.sep) CUTOFF = 1 # only go one directory deep for root, dirnames, filenames in os.walk(path): if root.count(os.sep) - base_depth <= CUTOFF: parsed = parse_slide(root) if parsed is not None: slide_filename = parsed[0] filepaths.append(os.path.split(slide_filename)) dirs.add(root) # for filename in filenames: # parent_path, parent_name = os.path.split(root) # if is_slide(filename): # filepaths.append((root, filename)) # dirs.add(root) return filepaths, list(dirs)
def parse_slide_folders(path):
# filter all file paths for only folders that contain a file with the same name directly inside
filepaths = []
dirs = set([])
base_depth = path.count(os.sep)
CUTOFF = 1 # only go one directory deep
for root, dirnames, filenames in os.walk(path):
if root.count(os.sep) - base_depth <= CUTOFF:
parsed = parse_slide(root)
if parsed is not None:
slide_filename = parsed[0]
filepaths.append(os.path.split(slide_filename))
dirs.add(root)
# for filename in filenames:
# parent_path, parent_name = os.path.split(root)
# if is_slide(filename):
# filepaths.append((root, filename))
# dirs.add(root)
return filepaths, list(dirs)
def parse_meta(filename):
slide_file = parse_slide(filename)
if slide_file is None: return None
with ZipFile(filename, 'r') as z:
with(z.open(slide_file[0])) as f:
slide_type = slide_file[1]
title_string = None
description_string = None
if slide_type == ".htm" or slide_type == ".html":
soup = BeautifulSoup(f.read(), "lxml")
title = soup.find('meta', {'name':'veeva_title'})
if title is not None:
title_string = title.get('content', None)
description = soup.find('meta', {'name':'veeva_description'})
if description is not None:
description_string = description.get('content', None)
if slide_type == ".pdf":
doc = PDFDocument()
parser = PDFParser(f)
# omfg this is so janky, there needs to be a better library
parser.set_document(doc)
doc.set_parser(parser)
metadata = doc.info
if len(metadata) > 0:
latest = metadata[-1]
try:
if latest['Title'] != '': title_string = latest['Title']
except KeyError:
title_string = None
try:
if latest['Subject'] != '': description_string = latest['Subject']
except KeyError:
description_string = None
if slide_type == ".jpg" or slide_type == ".jpeg":
tmp_file_name = str(uuid.uuid1()) + ".jpg"
with open(tmp_file_name, 'wb') as tf:
tf.write(f.read())
xmpfile = XMPFiles(file_path=tmp_file_name)
xmp = xmpfile.get_xmp()
xmpfile.close_file()
try:
title_string = xmp.get_localized_text(consts.XMP_NS_DC, 'title', None, 'x-default')
except XMPError:
title_string = None
try:
description_string = xmp.get_localized_text(consts.XMP_NS_DC, 'description', None, 'x-default')
except XMPError:
description_string = None
os.remove(tmp_file_name)
return {"filename": filename, "veeva_title": title_string, "veeva_description": description_string}
def parse_meta(filename, htmlonly=False):
slide_file = parse_slide(filename)
if slide_file is None:
return {
'filename': os.path.basename(filename),
'veeva_title': os.path.splitext(os.path.basename(filename))[0],
'veeva_description':
os.path.splitext(os.path.basename(filename))[0]
}
with ZipFile(filename, 'r') as z:
with (z.open(slide_file[0])) as f:
slide_type = slide_file[1]
title_string = None
description_string = None
if slide_type == ".htm" or slide_type == ".html":
soup = BeautifulSoup(f.read(), "lxml")
title = soup.find('meta', {'name': 'veeva_title'})
if title is not None:
title_string = title.get('content', None)
description = soup.find('meta', {'name': 'veeva_description'})
if description is not None:
description_string = description.get('content', None)
if slide_type == ".pdf" and not htmlonly:
doc = PDFDocument()
parser = PDFParser(f)
# omfg this is so janky, there needs to be a better library
parser.set_document(doc)
doc.set_parser(parser)
metadata = doc.info
if len(metadata) > 0:
latest = metadata[-1]
try:
if latest['Title'] != '':
title_string = latest['Title']
except KeyError:
title_string = None
try:
if latest['Subject'] != '':
description_string = latest['Subject']
except KeyError:
description_string = None
if slide_type == ".jpg" or slide_type == ".jpeg" and not htmlonly:
tmp_file_name = str(uuid.uuid1()) + ".jpg"
with open(tmp_file_name, 'wb') as tf:
tf.write(f.read())
xmpfile = XMPFiles(file_path=tmp_file_name)
xmp = xmpfile.get_xmp()
xmpfile.close_file()
try:
title_string = xmp.get_localized_text(
consts.XMP_NS_DC, 'title', None, 'x-default')
except XMPError:
title_string = None
try:
description_string = xmp.get_localized_text(
consts.XMP_NS_DC, 'description', None, 'x-default')
except XMPError:
description_string = None
os.remove(tmp_file_name)
return {
"filename": filename,
"veeva_title": title_string,
"veeva_description": description_string
}
