Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

py3: make rb input work

Browse Source
This commit is contained in:
Eli Schwartz 2019-04-29 01:52:41 -04:00
parent f2009fd991
commit 42cb67abb3
No known key found for this signature in database
GPG Key ID: CEB167EFB5722BD6
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/calibre/ebooks/rb/reader.py
View File

@ -64,7 +64,7 @@ class Reader(object):
toc = RBToc() toc = RBToc()
for i in range(pages): for i in range(pages):
name = unquote(self.stream.read(32).strip('\x00')) name = unquote(self.stream.read(32).strip(b'\x00'))
size, offset, flags = self.read_i32(), self.read_i32(), self.read_i32() size, offset, flags = self.read_i32(), self.read_i32(), self.read_i32()
toc.append(RBToc.Item(name=name, size=size, offset=offset, flags=flags)) toc.append(RBToc.Item(name=name, size=size, offset=offset, flags=flags))
@ -90,7 +90,7 @@ class Reader(object):
else: else:
output += self.stream.read(toc_item.size).decode('cp1252' if self.encoding is None else self.encoding, 'replace') output += self.stream.read(toc_item.size).decode('cp1252' if self.encoding is None else self.encoding, 'replace')
with open(os.path.join(output_dir, toc_item.name), 'wb') as html: with open(os.path.join(output_dir, toc_item.name.decode('utf-8')), 'wb') as html:
html.write(output.replace('<TITLE>', '<TITLE> ').encode('utf-8')) html.write(output.replace('<TITLE>', '<TITLE> ').encode('utf-8'))
def get_image(self, toc_item, output_dir): def get_image(self, toc_item, output_dir):
@ -100,7 +100,7 @@ class Reader(object):
self.stream.seek(toc_item.offset) self.stream.seek(toc_item.offset)
data = self.stream.read(toc_item.size) data = self.stream.read(toc_item.size)
with open(os.path.join(output_dir, toc_item.name), 'wb') as img: with open(os.path.join(output_dir, toc_item.name.decode('utf-8')), 'wb') as img:
img.write(data) img.write(data)
def extract_content(self, output_dir): def extract_content(self, output_dir):
@ -109,13 +109,14 @@ class Reader(object):
images = [] images = []
for item in self.toc: for item in self.toc:
if item.name.lower().endswith('html'): iname = item.name.decode('utf-8')
self.log.debug('HTML item %s found...' % item.name) if iname.lower().endswith('html'):
html.append(item.name) self.log.debug('HTML item %s found...' % iname)
html.append(iname)
self.get_text(item, output_dir) self.get_text(item, output_dir)
if item.name.lower().endswith('png'): if iname.lower().endswith('png'):
self.log.debug('PNG item %s found...' % item.name) self.log.debug('PNG item %s found...' % iname)
images.append(item.name) images.append(iname)
self.get_image(item, output_dir) self.get_image(item, output_dir)
opf_path = self.create_opf(output_dir, html, images) opf_path = self.create_opf(output_dir, html, images)