def parse_exth(data, pos):
ret = {}
n = 0
if (pos != data.find('EXTH')):
LOG(0, "EXTH header not found where it should be @%d" % pos)
return None
else:
end = pos + calcsize(EXTH_FMT)
(hlen, count) = unpack(EXTH_FMT, data[pos:end])
LOG(4, "pos: %d, EXTH header len: %d, record count: %d" % (
pos, hlen, count))
pos = end
while n < count:
end = pos + calcsize(">2I")
t, l = unpack(">2I", data[pos:end])
v = data[end:pos + l]
if l - 8 == 4:
v = unpack(">I", v)[0]
if t in EXTH_RECORD_TYPES:
rec = EXTH_RECORD_TYPES[t]
LOG(4, "EXTH record '%s' @%d+%d: '%s'" % (
rec, pos, l - 8, v))
if rec not in ret:
ret[rec] = [v]
else:
ret[rec].append(v)
else:
LOG(4, "Found an unknown EXTH record type %d @%d+%d: '%s'" %
(t, pos, l - 8, repr(v)))
pos += l
n += 1
return ret
def delete_collection(kjd, collection):
cn = COLLNAME % collection
LOG(3, "Deleting collection %s" % cn)
if cn in kjd:
del kjd[cn]
else:
LOG(1, 'Collection %s does not exist' % collection)
def add_item(kjd, collection, hash):
cn = COLLNAME % collection
if not ((cn) in kjd):
LOG(1, "Error. collection %s does not exist" % collection)
else:
if hash in kjd[cn]['items']:
LOG(1, "%s was already in %s" % (hash, cn))
else:
kjd[cn]['items'].append(hash)
update_ts(kjd[cn])
def add_collection(kjd, collection):
time_ms = int(time() * 1000)
new_item = {}
cn = COLLNAME % collection
LOG(3, "Adding collection %s" % cn)
if not ((cn) in kjd):
kjd[cn] = {'items': [], 'lastAccess': time_ms}
else:
LOG(1, "Collection %s already exists" % collection)
update_ts(kjd[cn])
def remove_item(kjd, collection, hash):
cn = COLLNAME % collection
if not ((cn) in kjd):
LOG(1, "Error. collection %s does not exist" % collection)
else:
if hash not in kjd[cn]['items']:
return
else:
kjd[cn]['items'].remove(hash)
update_ts(kjd[cn])
def get_books(progress_func=lambda: None):
ret = {}
files = glob.glob("%s/*" % BOOKPATH)
for c, fn in enumerate(files):
progress_func(c)
LOG(3, "\n - Processing file #%d: %s" % (c, fn))
key = make_hash(fn.replace(BOOKPATH, KINDLE_INTERNAL_PATH))
val = ebook.Book(fn)
if val.is_a_book:
ret[key] = val
return ret
def load_data():
try:
return json.load(open(JSONFILE, 'r'))
except IOError:
LOG(2, "File %s not found" % JSONFILE)
return dict()
def __init__(self, fn):
self.filename = fn
# Set some fields to defaults
self.title = fn
self.author = "??"
self.language = "??"
self.is_a_book = False
f = open(fn)
d = f.read(68)
f.close()
encodings = {
1252: 'cp1252',
65001: 'utf-8'
}
supported_types = ('BOOKMOBI', 'TEXtREAd')
self.type = d[60:68]
if self.type not in supported_types:
LOG(1, "Unsupported file type %s" % (self.type))
return None
try:
db = parse_palmdb(fn)
except:
return None
self.is_a_book = True
# now we have a better guess at the title, use it for now
self.title = db.name
self.records = db.records
rec0 = self.records[0].data
#LOG(5,repr(rec0))
if self.type == 'BOOKMOBI':
LOG(3, "This is a MOBI book")
self.mobi = {}
for field, pos, fmt in MOBI_HDR_FIELDS:
end = pos + calcsize(fmt)
if (end > len(rec0) or
("header_len" in self.mobi
and end > self.mobi["header_len"])):
continue
LOG(4, "field: %s, fmt: %s, @ [%d:%d], data: %s" % (
field, fmt, pos, end, repr(rec0[pos:end])))
(self.mobi[field], ) = unpack(">%s" % fmt, rec0[pos:end])
LOG(3, "self.mobi: %s" % repr(self.mobi))
# Get and decode the book name
if self.mobi['locale_language'] in LANGUAGES:
lang = LANGUAGES[self.mobi['locale_language']]
if self.mobi['locale_country'] == 0:
LOG(2, "Book language: %s" % lang[0][1])
self.language = "%s (%s)" % (lang[0][1], lang[0][0])
elif self.mobi['locale_country'] in lang:
country = lang[self.mobi['locale_country']]
LOG(2, "Book language is %s (%s)" % (
lang[0][1], country[1]))
self.language = "%s (%s-%s)" % (
lang[0][1],
lang[0][0],
country[0]
)
pos = self.mobi['full_name_offs']
end = pos + self.mobi['full_name_len']
self.title = rec0[pos:end].decode(encodings[self.mobi['encoding']])
LOG(2, "Book name: %s" % self.title)
if self.mobi['id'] != 'MOBI':
LOG(0, "Mobi header missing!")
return None
if (0x40 & self.mobi['exth_flags']): # check for EXTH
self.exth = parse_exth(rec0, self.mobi['header_len'] + 16)
LOG(3, "EXTH header: %s" % repr(self.exth))
if 'author' in self.exth:
self.author = ' & '.join(self.exth['author'])
else:
self.author = "n/a"
self.rawdata = d
if (('updated title' in self.exth) and
(type(self.exth['updated title']) is str)):
self.title = ' '.join(self.exth['updated title'])
elif self.type == 'TEXtREAd':
LOG(2, "This is an older MOBI book")
self.rawdata = d
compression, data_len, rec_count, rec_size, pos = unpack(
PRC_HDRFMT, rec0[:calcsize(PRC_HDRFMT)])
LOG(3, "compression %d, data_len %d, rec_count %d, rec_size %d" %
(compression, data_len, rec_count, rec_size))
if compression == 2:
data = uncompress(self.records[1].data)
else:
data = self.records[1].data
from BeautifulSoup import BeautifulSoup
soup = BeautifulSoup(data)
self.metadata = soup.fetch("dc-metadata")
try:
self.title = soup.fetch("dc:title")[0].getText()
self.author = soup.fetch("dc:creator")[0].getText()
self.language = soup.fetch("dc:language")[0].getText()
except:
self.title, self.author, self.language = ("Unknown", "Unknown",
"en-us")