def ExtractFiles(self, output_dir=os.getcwdu(), debug_dump=False):
html_files = set([])
try:
x = self.get_encoding()
codecs.lookup(x)
enc = x
except:
enc = 'cp1252'
for path in self.Contents():
fpath = path
if not isinstance(path, unicode_type):
fpath = path.decode(enc)
lpath = os.path.join(output_dir, fpath)
self._ensure_dir(lpath)
try:
data = self.GetFile(path)
except:
self.log.exception('Failed to extract %s from CHM, ignoring' %
path)
continue
if lpath.find(';') != -1:
# fix file names with ";<junk>" at the end, see _reformat()
lpath = lpath.split(';')[0]
try:
with open(lpath, 'wb') as f:
f.write(data)
try:
if 'html' in guess_mimetype(path)[0]:
html_files.add(lpath)
except:
pass
except:
if iswindows and len(lpath) > 250:
self.log.warn('%r filename too long, skipping' % path)
continue
raise
if debug_dump:
import shutil
shutil.copytree(output_dir, os.path.join(debug_dump, 'debug_dump'))
for lpath in html_files:
with open(lpath, 'r+b') as f:
data = f.read()
data = self._reformat(data, lpath)
if isinstance(data, unicode_type):
data = data.encode('utf-8')
f.seek(0)
f.truncate()
f.write(data)
self._extracted = True
files = [
y for y in os.listdir(output_dir)
if os.path.isfile(os.path.join(output_dir, y))
]
if self.hhc_path not in files:
for f in files:
if f.lower() == self.hhc_path.lower():
self.hhc_path = f
break
if self.hhc_path not in files and files:
for f in files:
if f.partition('.')[-1].lower() in {
'html', 'htm', 'xhtm', 'xhtml'
}:
self.hhc_path = f
break
if self.hhc_path == '.hhc' and self.hhc_path not in files:
from calibre import walk
for x in walk(output_dir):
if os.path.basename(x).lower() in ('index.htm', 'index.html',
'contents.htm',
'contents.html'):
self.hhc_path = os.path.relpath(x, output_dir)
break
if self.hhc_path not in files and files:
self.hhc_path = files[0]
def ExtractFiles(self, output_dir=os.getcwdu(), debug_dump=False):
html_files = set([])
try:
x = self.GetEncoding()
codecs.lookup(x)
enc = x
except:
enc = 'cp1252'
for path in self.Contents():
fpath = path
if not isinstance(path, unicode):
fpath = path.decode(enc)
lpath = os.path.join(output_dir, fpath)
self._ensure_dir(lpath)
try:
data = self.GetFile(path)
except:
self.log.exception('Failed to extract %s from CHM, ignoring'%path)
continue
if lpath.find(';') != -1:
# fix file names with ";<junk>" at the end, see _reformat()
lpath = lpath.split(';')[0]
try:
with open(lpath, 'wb') as f:
f.write(data)
try:
if 'html' in guess_mimetype(path)[0]:
html_files.add(lpath)
except:
pass
except:
if iswindows and len(lpath) > 250:
self.log.warn('%r filename too long, skipping'%path)
continue
raise
if debug_dump:
import shutil
shutil.copytree(output_dir, os.path.join(debug_dump, 'debug_dump'))
for lpath in html_files:
with open(lpath, 'r+b') as f:
data = f.read()
data = self._reformat(data, lpath)
if isinstance(data, unicode):
data = data.encode('utf-8')
f.seek(0)
f.truncate()
f.write(data)
self._extracted = True
files = [x for x in os.listdir(output_dir) if
os.path.isfile(os.path.join(output_dir, x))]
if self.hhc_path not in files:
for f in files:
if f.lower() == self.hhc_path.lower():
self.hhc_path = f
break
if self.hhc_path not in files and files:
for f in files:
if f.partition('.')[-1].lower() in {'html', 'htm', 'xhtm',
'xhtml'}:
self.hhc_path = f
break
if self.hhc_path == '.hhc' and self.hhc_path not in files:
from calibre import walk
for x in walk(output_dir):
if os.path.basename(x).lower() in ('index.htm', 'index.html',
'contents.htm', 'contents.html'):
self.hhc_path = os.path.relpath(x, output_dir)
break
if self.hhc_path not in files and files:
self.hhc_path = files[0]