def new_book(filename, category=None):
import zipfile
if zipfile.is_zipfile(filename): # filename.endswith('.zip'):
fn = zip_get_filename(filename)
else:
fn = filename
# сортируем по длине расширений: длинные в начале
# т.е. вначале .html.gz а потом .gz
file_types_l = list(file_types)
file_types_l.sort(lambda ft1, ft2: cmp(max(map(len, file_types[ft2][0])), max(map(len, file_types[ft1][0]))))
# search parser
for type in file_types_l:
for s in file_types[type][0]:
if fn.endswith(s):
file_parser = file_types[type][1]()
external_filter = file_types[type][2]
encoding = file_types[type][3]
book = file_parser.new_book(
filename, category=category, external_filter=external_filter, encoding=encoding
)
return book, file_parser
# suffix not found -> plain text
file_parser = plain_text_parser()
book = file_parser.new_book(filename, category=category)
return book, file_parser
def get_file(filename):
if zipfile.is_zipfile(filename): #filename.endswith('.zip'):
fn = tempfile.mktemp()
zip_fn = miscutils.zip_get_filename(filename)
open(fn, 'w').write(zipfile.ZipFile(filename).read(zip_fn))
else:
fn = filename
return fn
def get_file(filename):
if zipfile.is_zipfile(filename): #filename.endswith('.zip'):
fn = tempfile.mktemp()
zip_fn = miscutils.zip_get_filename(filename)
open(fn, 'w').write(zipfile.ZipFile(filename).read(zip_fn))
elif filename.endswith('.gz'): #FIXME must be header test
fn = tempfile.mktemp()
open(fn, 'w').write(gzip.GzipFile(filename).read())
elif filename.endswith('.bz2'): #FIXME must be header test
fn = tempfile.mktemp()
open(fn, 'w').write(bz2.BZ2File(filename).read())
else:
fn = filename
return fn
def new_book(filename, category=None):
import zipfile
if zipfile.is_zipfile(filename): #filename.endswith('.zip'):
fn = zip_get_filename(filename)
else:
fn = filename
type=detect_type(fn)
file_parser = file_types[type][1]()
external_filter = file_types[type][2]
encoding = file_types[type][3]
book = file_parser.new_book(
filename, category=category,
external_filter=external_filter,
encoding=encoding)
book.file_type=type
return book, file_parser
