def __init__(self, path_to_folder):
self.path = path_to_folder
files = []
for r, d, f in os.walk(self.path):
for file in f:
if '.mobi' in file:
files.append(os.path.join(r, file))
for f in files:
book = Mobi(f)
book.parse()
try:
title = book.title()
author = book.author()
author = author.decode()
title = title.decode()
result = author + ' - ' + title + "\n"
print(result)
w = Files()
w.save_file(result)
except:
print("pass", f)
def readMobi(eBook):
#Open up our book and parse it
book = Mobi(eBook)
book.parse()
#Return the information we want
return(book.title().decode("utf-8") + " " + book.author().decode("utf-8"))
def _getFallbackReader(self):
if self.bookFallback is None:
try:
self.bookFallback = Mobi(str(self.filePath))
# Need to parse all the header data in the book
self.bookFallback.parse()
except:
log("MobiEBook: Expected exception for secondary reader, book %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
return self.bookFallback
def read_mobi_data(nombre_comp):
try:
book = Mobi(nombre_comp)
book.parse()
tit = book.title().decode('utf-8')
aut = book.author().decode('utf-8')
return [aut, tit, '.mobi']
except Exception as err:
print(os.path.join(nombre_comp) + ' ERROR:' + str(err))
return [None, None, None]
def extract_metadata_mobi(self, book):
book = Mobi(book)
book.parse()
try:
cover_image = book.readImageRecord(0)
except KeyError:
cover_image = None
title = book.title().decode("utf-8")
author = book.author().decode("utf-8")
book_config = book.config
try:
description = self.stripTags(
book_config['exth']['records'][103].decode("utf-8"))
except KeyError:
description = None
try:
identifier = book_config['exth']['records'][104].decode("utf-8")
except KeyError:
identifier = None
try:
publisher = book_config['exth']['records'][101].decode("utf-8")
except KeyError:
publisher = None
date = None
rights = None
try:
ftags = book_config['exth']['records'][105].decode("utf-8")
if ":" in ftags:
ftags = ftags.replace(":", ",")
elif ";" in ftags:
ftags = ftags.replace(";", ",")
# elif re.search(r"\s", ftags): # Must be final assignment to avoid spliting on multiple delimeters
# ftags = ftags.replace(" ", ",")
except KeyError:
ftags = None
return [
title,
author,
cover_image,
book.f.name,
description,
identifier,
publisher,
date,
rights,
ftags,
]
def collect_book_tokens(self, book_path):
book = Mobi(book_path)
book.parse()
records = []
sentences = []
all_words = []
for record in tqdm(book, desc='record_no'):
record = record.decode('utf-8','replace')
for item in BeautifulSoup(record, 'lxml').find_all('p'):
block = item.text.lower()
tokens = word_tokenize(block)
all_words += tokens
return all_words
def read_mobi(filepath):
book = Mobi(filepath)
book.parse()
records = []
for record in book:
records.append(record)
full_text = ' '.join(records)
title = book.title().decode('utf-8')
author = book.author().decode('utf-8')
doc = {
'filepath': filepath,
'full_text': full_text,
'title': title,
'author': author,
}
return doc
def generate_mobi_name(in_filename,
template=Template(u'$author - $title.$extn')):
# NOTE assume in_filename is in correct encoding (ideally Unicode string) and will "just work"
book = Mobi(in_filename)
book.parse()
# title is sometimes different compared with "503" entry. E.g. compare 'Broken Homes' and 'Broken Homes (PC Peter Grant Book 4)' for https://www.amazon.com/Broken-Homes-Peter-Grant-Book-ebook/dp/B00DYX9OPC/
author, title = book.author(), book.title(
) # returns bytes. NOTE not going to use these...
#print(type(author))
#print((author, title))
book_codepage = book.config.get('mobi', {}).get(
'text Encoding', 1252
) # not sure if this is text encoding for content or all meta data (e.g. titles)
#print(book_codepage)
"""
import pprint
pprint.pprint(book.config)
"""
BOOK_CODEPAGE2ENCODING = {
1252: 'windows-1252',
65001: 'utf-8',
}
#print(BOOK_CODEPAGE2ENCODING[book_codepage]) # use this with names
#print((author, title))
author = book.config['exth']['records'][100]
title = book.config['exth']['records'].get(503) or book.config['mobi'].get(
'Full Name'
) # NOTE if both exist, may want the longest one. So far all books from Amazon I've seen have consistently been 503 (e.g. "SERIES Book X")
author = author.decode(BOOK_CODEPAGE2ENCODING[book_codepage])
title = title.decode(BOOK_CODEPAGE2ENCODING[book_codepage])
extn = os.path.splitext(in_filename)[1]
extn = extn[1:] # removed leading period
#print((author, title, extn))
#print('%s - %s' % (author, title))
new_filename = template.substitute(author=author, title=title,
extn=extn) # TODO use a dict?
#new_filename = ' .... ??? <1of 2> "hello"...........' ## DEBUG
new_filename = safe_filename(new_filename)
#print(repr(new_filename))
return new_filename
def __init__(self, path_to_folder):
self.path = path_to_folder
files = []
for r, d, f in os.walk(self.path):
for file in f:
if '.mobi' in file:
files.append(os.path.join(r, file))
for f in files:
book = Mobi(f)
book.parse()
try:
title = book.title()
author = book.author()
author = author.decode()
title = title.decode()
new_name = str("Kindle/" + author + " - " + title + ".mobi")
os.rename(f, new_name)
except:
print("pass", f)
from mobi import Mobi
import os
path = os.path.dirname(__file__)
book = Mobi(f"{path}/test/CharlesDarwin.mobi");
book.parse();
for record in book:
print(record)
import pprint
pprint.pprint(book.config)
from mobi import Mobi
import pprint
book = Mobi("test/CharlesDarwin.mobi")
book.parse()
for record in book:
print(record)
pprint.pprint(book.config)
def setUp(self):
path = pathjoin(PATH, self.path)
self.mobi = Mobi(path)
from mobi import Mobi
collins = "C:/Users/Anchpop/Google Drive/book/Calibre library/HarperCollins Publishers/Collins French to English (One Way) (115)/Collins French to English (One - HarperCollins Publishers.mobi"
potter = "C:/Users/Anchpop/Google Drive/book/Calibre library/J.K. Rowling/Harry Potter et la Coupe de Feu (La (110)/Harry Potter et la Coupe de Feu - J.K. Rowling.mobi"
book = Mobi(potter)
book.parse()
for record in book:
if record:
print(record)
#!/usr/bin/env python2.7
from mobi import Mobi
book = Mobi("../zdic.prc");
book.parse();
for record in book:
print record,
