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
class BaseTestCase(unittest.TestCase):
path = None
def setUp(self):
path = pathjoin(PATH, self.path)
self.mobi = Mobi(path)
def tearDown(self):
self.mobi.close()
def _getFallbackReader(self):
if self.bookFallback is None:
try:
self.bookFallback = Mobi(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 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 __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 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 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 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)
#coding: utf-8
from mobi import Mobi
import os
from pprint import pprint
book = Mobi('test/1.mobi')
print("Title: %s" % book.title)
print("Author: %s" % book.author)
print("Publisher: %s" % book.publisher)
print("Language: %s" % book.language)
print("ISBN: %s" % book.isbn)
#pprint(book.palmdb)
#pprint(book.palmdoc)
#pprint(book.mobi)
#book.extract('output')
print(book.layout())
class MobiEBook(EBookBase):
def __init__(self, filePath, removeFileWhenComplete=False):
EBookBase.__init__(self, filePath, removeFileWhenComplete)
self.book = None
self.bookFallback = None
try:
self.book = KMobi(self.filePath)
except:
log("MobiEBook: Failed to process eBook %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
# A secondary Mobi reader, if the first can not handle the given file
def _getFallbackReader(self):
if self.bookFallback is None:
try:
self.bookFallback = Mobi(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 getTitle(self):
# Default the title to the filename - this should be overwritten
title = None
if self.book is not None:
try:
title = self.book.title
except:
log("MobiEBook: Failed to get title for mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
# If we failed to get the title, use the fallback Mobi reader
if title in [None, ""]:
fallback = self._getFallbackReader()
if fallback is not None:
try:
title = fallback.title()
except:
log("MobiEBook: Failed to get title using fallback mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
if title in [None, ""]:
title = self.getFallbackTitle()
try:
log("MobiEBook: Title is %s for book %s" % (title.decode('utf-8', 'ignore'), self.filePath))
except:
pass
return title
def getAuthor(self):
author = ""
if self.book is not None:
try:
author = self.book.author
except:
log("MobiEBook: Failed to get author for mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
# If we failed to get the author, use the fallback Mobi reader
if author in [None, ""]:
fallback = self._getFallbackReader()
if fallback is not None:
try:
author = fallback.author()
except:
log("MobiEBook: Failed to get author using fallback mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
try:
log("MobiEBook: Author is %s for book %s" % (author.decode('utf-8', 'ignore'), self.filePath))
except:
pass
return author
def extractCoverImage(self):
log("MobiEBook: Extracting cover for %s" % self.filePath)
# Get the location that the book is to be extracted to
extractDir = os_path_join(Settings.getTempLocation(), 'mobi_extracted')
# Check if the mobi extract directory already exists
if dir_exists(extractDir):
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to delete directory %s" % extractDir)
# Extract the contents of the book so we can get the cover image
try:
kindleunpack.unpackBook(self.filePath, extractDir, None, '2', True)
except:
log("MobiEBook: Failed to extract cover for %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
coverTargetName = None
if dir_exists(extractDir):
coverImages = self._findCoverImage(extractDir)
if len(coverImages) > 0:
coverImageSrc = coverImages[0]
log("MobiEBook: Found cover file %s" % coverImageSrc)
coverFileName, oldExt = os.path.splitext(self.fileName)
cacheCoverName = "%s.jpg" % coverFileName
coverTargetName = os_path_join(Settings.getCoverCacheLocation(), cacheCoverName)
# Now move the file to the covers cache directory
copy = xbmcvfs.copy(coverImageSrc, coverTargetName)
if copy:
log("MobiEBook: copy successful for %s" % coverTargetName)
else:
log("MobiEBook: copy failed from %s to %s" % (coverImageSrc, coverTargetName))
else:
log("MobiEBook: No cover image found for %s" % self.filePath)
# Now tidy up the extracted data
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to tidy up directory %s" % extractDir)
else:
log("MobiEBook: Failed to extract Mobi file %s" % self.filePath)
return coverTargetName
def _findCoverImage(self, dirPath):
coverImages = []
dirs, files = xbmcvfs.listdir(dirPath)
for aFile in files:
if aFile.startswith('cover') and (aFile.endswith('jpg') or aFile.endswith('jpeg') or aFile.endswith('png')):
# Add this image to the list
coverImages.append(os_path_join(dirPath, aFile))
# Now check any of the directories
for aDir in dirs:
coverImages = coverImages + self._findCoverImage(os_path_join(dirPath, aDir))
return coverImages
def getChapterDetails(self):
log("MobiEBook: Extracting chapter list for %s" % self.filePath)
# Get the location that the book is to be extracted to
extractDir = os_path_join(Settings.getTempLocation(), 'mobi_extracted')
# Check if the mobi extract directory already exists
if dir_exists(extractDir):
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to delete directory %s" % extractDir)
# Extract the contents of the book so we can get the cover image
try:
kindleunpack.unpackBook(self.filePath, extractDir, None, '2', True)
except:
log("MobiEBook: Failed to unpack book for %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
chapterDetails = []
if dir_exists(extractDir):
tocNcx = self._findTocNcx(extractDir)
if tocNcx not in [None, ""]:
log("MobiEBook: TOC file found: %s" % tocNcx)
# Now we have the TOC file, we need to parse it, we already have
# a tool for that, as it is the ePub format
try:
# Read the contents of the TOC file into a string
tocFile = xbmcvfs.File(tocNcx, 'r')
tocStr = tocFile.read()
tocFile.close()
# Now load it into the parser
toc = epub.ncx.parse_toc(tocStr)
# Get all the chapters
for navPoint in toc.nav_map.nav_point:
# Get each of the chapter labels
for aLabelGroup in navPoint.labels:
if aLabelGroup not in [None, ""]:
for aLabel in aLabelGroup:
if aLabel not in [None, ""]:
log("MobiEBook: Adding chapter %s with src %s" % (aLabel, navPoint.src))
detail = {'title': aLabel.encode("utf-8"), 'link': navPoint.src}
chapterDetails.append(detail)
# Only need the first string for this label group
break
del toc
except:
log("MobiEBook: Failed to process TOC %s with error: %s" % (tocNcx, traceback.format_exc()), xbmc.LOGERROR)
else:
log("MobiEBook: Failed to find TOC file")
# Check if we have any chapters, if there are none, then we should show the whole book
if (len(chapterDetails) < 1) or (not Settings.onlyShowWholeBookIfChapters()):
htmlFiles = self._findHtmlFiles(extractDir)
# Check if there are any html files
if len(htmlFiles) > 0:
keyHtmlFile = None
for htmlFile in htmlFiles:
if htmlFile.endswith('book.html'):
keyHtmlFile
break
if keyHtmlFile is None:
keyHtmlFile = htmlFiles[0]
detail = {'title': ADDON.getLocalizedString(32016), 'link': keyHtmlFile}
chapterDetails.insert(0, detail)
# Now tidy up the extracted data
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to tidy up directory %s" % extractDir)
else:
log("MobiEBook: Failed to extract Mobi file %s" % self.filePath)
return chapterDetails
def _findTocNcx(self, dirPath):
tocNcx = None
dirs, files = xbmcvfs.listdir(dirPath)
for aFile in files:
if aFile.lower() == 'toc.ncx':
# Found the table of contents file
tocNcx = os_path_join(dirPath, aFile)
break
# Now check any of the directories
for aDir in dirs:
if tocNcx is None:
tocNcx = self._findTocNcx(os_path_join(dirPath, aDir))
return tocNcx
def _findHtmlFiles(self, dirPath):
htmlFiles = []
dirs, files = xbmcvfs.listdir(dirPath)
for aFile in files:
if aFile.endswith('.html'):
# Add this page to the list
htmlFiles.append(aFile)
# Now check any of the directories
for aDir in dirs:
htmlFiles = htmlFiles + self._findHtmlFiles(os_path_join(dirPath, aDir))
return htmlFiles
# Get the text for a given chapter
def getChapterContents(self, chapterLink):
log("MobiEBook: Getting chapter contents for %s" % chapterLink)
# Find out the name of the page that this chapter is stored in
sections = chapterLink.split('#')
bookFileName = None
chapterStartFlag = None
if len(sections) > 0:
bookFileName = sections[0]
if len(sections) > 1:
chapterStartFlag = sections[1]
# Get the content of the chapter, this will be in HTML
chapterContent = ""
# Get the location that the book is to be extracted to
extractDir = os_path_join(Settings.getTempLocation(), 'mobi_extracted')
# Check if the mobi extract directory already exists
if dir_exists(extractDir):
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to delete directory %s" % extractDir)
# Extract the contents of the book so we can get the chapter contents
try:
kindleunpack.unpackBook(self.filePath, extractDir, None, '2', True)
except:
log("MobiEBook: Failed to unpack book for %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
# Find the file containing the book contents
bookFileLocation = self._findBookFile(extractDir, bookFileName)
bookContents = ""
if bookFileLocation not in [None, ""]:
# Read the contents of the file
try:
# Read the contents of the book file into a string
bookFile = xbmcvfs.File(bookFileLocation, 'r')
bookContents = bookFile.read()
bookFile.close()
except:
log("MobiEBook: Failed to read contents of book %s with error: %s" % (bookFileName, traceback.format_exc()), xbmc.LOGERROR)
else:
log("MobiEBook: Failed to find book content file %s" % bookFileName)
# Cleanup the extract directory
if dir_exists(extractDir):
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to delete directory %s" % extractDir)
chapterContent = ""
if bookContents not in [None, ""]:
if chapterStartFlag is not None:
# Split out the chapter (For now just add the whole book)
# Split based on page markers
pageBreaks = bookContents.split('<mbp:pagebreak/>')
anchorHtml = "<a id=\"%s\"" % chapterStartFlag
# Find which section contains this anchor
for page in pageBreaks:
if anchorHtml in page.decode("utf-8"):
log("MobiEBook: Found page for chapter marker %s" % chapterStartFlag)
chapterContent = self._mobiHtmlParsing(page)
break
else:
log("MobiEBook: Chapter start flag, showing whole book")
chapterContent = self._mobiHtmlParsing(bookContents)
if chapterContent not in [None, ""]:
chapterContent = self.convertHtmlIntoKodiText(chapterContent)
return chapterContent
# Finds the given book file
def _findBookFile(self, dirPath, bookFileName):
bookFile = None
dirs, files = xbmcvfs.listdir(dirPath)
for aFile in files:
if aFile.lower() == bookFileName:
# Found a match, set the value
bookFile = os_path_join(dirPath, aFile)
break
# Now check any of the directories
for aDir in dirs:
if bookFile is None:
bookFile = self._findBookFile(os_path_join(dirPath, aDir), bookFileName)
return bookFile
def _mobiHtmlParsing(self, chapterContentIn):
# There are no line-breaks in the mobi file, so add them for each
# html paragraph tag
chapterContent = chapterContentIn.replace('</p>', '</p>\n')
# Headings are just shown in larger fornts for mobi
chapterContent = re.sub(r'<font size="5">(.*?)</font>', r'<h1>\1</h1>', chapterContent)
return chapterContent
from mobi import Mobi
book = Mobi("test/CharlesDarwin.mobi");
book.parse();
for record in book:
print record,
import pprint
pprint.pprint(book.config)
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,
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)
class MobiEBook(EBookBase):
def __init__(self, filePath, removeFileWhenComplete=False):
EBookBase.__init__(self, filePath, removeFileWhenComplete)
self.book = None
self.bookFallback = None
try:
self.book = KMobi(self.filePath)
except:
log("MobiEBook: Failed to process eBook %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
# A secondary Mobi reader, if the first can not handle the given file
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 getTitle(self):
# Default the title to the filename - this should be overwritten
title = None
if self.book is not None:
try:
title = self.book.title
except:
log("MobiEBook: Failed to get title for mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
# If we failed to get the title, use the fallback Mobi reader
if title in [None, ""]:
fallback = self._getFallbackReader()
if fallback is not None:
try:
title = fallback.title()
except:
log("MobiEBook: Failed to get title using fallback mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
if title in [None, ""]:
title = self.getFallbackTitle()
try:
log("MobiEBook: Title is %s for book %s" % (title.decode('utf-8', 'ignore'), self.filePath))
except:
pass
return title
def getAuthor(self):
author = ""
if self.book is not None:
try:
author = self.book.author
except:
log("MobiEBook: Failed to get author for mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
# If we failed to get the author, use the fallback Mobi reader
if author in [None, ""]:
fallback = self._getFallbackReader()
if fallback is not None:
try:
author = fallback.author()
except:
log("MobiEBook: Failed to get author using fallback mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
try:
log("MobiEBook: Author is %s for book %s" % (author.decode('utf-8', 'ignore'), self.filePath))
except:
pass
return author
def getDescription(self):
description = ""
if self.book is not None:
try:
description = self.book.description
except:
log("MobiEBook: Failed to get description for mobi %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
if description is None:
description = ""
else:
description = self.convertHtmlIntoKodiText(description)
return description
def extractCoverImage(self):
log("MobiEBook: Extracting cover for %s" % self.filePath)
# Get the location that the book is to be extracted to
extractDir = os_path_join(Settings.getTempLocation(), 'mobi_extracted')
# Check if the mobi extract directory already exists
if dir_exists(extractDir):
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to delete directory %s" % extractDir)
# Extract the contents of the book so we can get the cover image
try:
kindleunpack.unpackBook(self.filePath, extractDir, None, '2', True)
except:
log("MobiEBook: Failed to extract cover for %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
coverTargetName = None
if dir_exists(extractDir):
coverImages = self._findCoverImage(extractDir)
if len(coverImages) > 0:
coverImageSrc = coverImages[0]
log("MobiEBook: Found cover file %s" % coverImageSrc)
coverFileName, oldExt = os.path.splitext(self.fileName)
cacheCoverName = "%s.jpg" % coverFileName
coverTargetName = os_path_join(Settings.getCoverCacheLocation(), cacheCoverName)
# Now move the file to the covers cache directory
copy = xbmcvfs.copy(coverImageSrc, coverTargetName)
if copy:
log("MobiEBook: copy successful for %s" % coverTargetName)
else:
log("MobiEBook: copy failed from %s to %s" % (coverImageSrc, coverTargetName))
else:
log("MobiEBook: No cover image found for %s" % self.filePath)
# Now tidy up the extracted data
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to tidy up directory %s" % extractDir)
else:
log("MobiEBook: Failed to extract Mobi file %s" % self.filePath)
return coverTargetName
def _findCoverImage(self, dirPath):
coverImages = []
dirs, files = xbmcvfs.listdir(dirPath)
for aFile in files:
if aFile.startswith('cover') and (aFile.endswith('jpg') or aFile.endswith('jpeg') or aFile.endswith('png')):
# Add this image to the list
coverImages.append(os_path_join(dirPath, aFile))
# Now check any of the directories
for aDir in dirs:
coverImages = coverImages + self._findCoverImage(os_path_join(dirPath, aDir))
return coverImages
def getChapterDetails(self):
log("MobiEBook: Extracting chapter list for %s" % self.filePath)
# Get the location that the book is to be extracted to
extractDir = os_path_join(Settings.getTempLocation(), 'mobi_extracted')
# Check if the mobi extract directory already exists
if dir_exists(extractDir):
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to delete directory %s" % extractDir)
# Extract the contents of the book so we can get the cover image
try:
kindleunpack.unpackBook(self.filePath, extractDir, None, '2', True)
except:
log("MobiEBook: Failed to unpack book for %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
chapterDetails = []
if dir_exists(extractDir):
tocNcx = self._findTocNcx(extractDir)
if tocNcx not in [None, ""]:
log("MobiEBook: TOC file found: %s" % tocNcx)
# Now we have the TOC file, we need to parse it, we already have
# a tool for that, as it is the ePub format
try:
# Read the contents of the TOC file into a string
tocFile = xbmcvfs.File(tocNcx, 'r')
tocStr = tocFile.read()
tocFile.close()
# Now load it into the parser
toc = epub.ncx.parse_toc(tocStr)
# Get all the chapters
for navPoint in toc.nav_map.nav_point:
# Get each of the chapter labels
for aLabelGroup in navPoint.labels:
if aLabelGroup not in [None, ""]:
for aLabel in aLabelGroup:
if aLabel not in [None, ""]:
log("MobiEBook: Adding chapter %s with src %s" % (aLabel, navPoint.src))
detail = {'title': aLabel.encode("utf-8"), 'link': navPoint.src}
chapterDetails.append(detail)
# Only need the first string for this label group
break
del toc
except:
log("MobiEBook: Failed to process TOC %s with error: %s" % (tocNcx, traceback.format_exc()), xbmc.LOGERROR)
else:
log("MobiEBook: Failed to find TOC file")
# Check if we have any chapters, if there are none, then we should show the whole book
if (len(chapterDetails) < 1) or (not Settings.onlyShowWholeBookIfChapters()):
htmlFiles = self._findHtmlFiles(extractDir)
# Check if there are any html files
if len(htmlFiles) > 0:
keyHtmlFile = None
for htmlFile in htmlFiles:
if htmlFile.endswith('book.html'):
keyHtmlFile
break
if keyHtmlFile is None:
keyHtmlFile = htmlFiles[0]
detail = {'title': ADDON.getLocalizedString(32016), 'link': keyHtmlFile}
chapterDetails.insert(0, detail)
# Now tidy up the extracted data
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to tidy up directory %s" % extractDir)
else:
log("MobiEBook: Failed to extract Mobi file %s" % self.filePath)
return chapterDetails
def _findTocNcx(self, dirPath):
tocNcx = None
dirs, files = xbmcvfs.listdir(dirPath)
for aFile in files:
if aFile.lower() == 'toc.ncx':
# Found the table of contents file
tocNcx = os_path_join(dirPath, aFile)
break
# Now check any of the directories
for aDir in dirs:
if tocNcx is None:
tocNcx = self._findTocNcx(os_path_join(dirPath, aDir))
return tocNcx
def _findHtmlFiles(self, dirPath):
htmlFiles = []
dirs, files = xbmcvfs.listdir(dirPath)
for aFile in files:
if aFile.endswith('.html'):
# Add this page to the list
htmlFiles.append(aFile)
# Now check any of the directories
for aDir in dirs:
htmlFiles = htmlFiles + self._findHtmlFiles(os_path_join(dirPath, aDir))
return htmlFiles
# Get the text for a given chapter
def getChapterContents(self, chapterLink):
log("MobiEBook: Getting chapter contents for %s" % chapterLink)
# Find out the name of the page that this chapter is stored in
sections = chapterLink.split('#')
bookFileName = None
chapterStartFlag = None
if len(sections) > 0:
bookFileName = sections[0]
if len(sections) > 1:
chapterStartFlag = sections[1]
# Get the content of the chapter, this will be in HTML
chapterContent = ""
# Get the location that the book is to be extracted to
extractDir = os_path_join(Settings.getTempLocation(), 'mobi_extracted')
# Check if the mobi extract directory already exists
if dir_exists(extractDir):
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to delete directory %s" % extractDir)
# Extract the contents of the book so we can get the chapter contents
try:
kindleunpack.unpackBook(self.filePath, extractDir, None, '2', True)
except:
log("MobiEBook: Failed to unpack book for %s with error: %s" % (self.filePath, traceback.format_exc()), xbmc.LOGERROR)
# Find the file containing the book contents
bookFileLocation = self._findBookFile(extractDir, bookFileName)
bookContents = ""
if bookFileLocation not in [None, ""]:
# Read the contents of the file
try:
# Read the contents of the book file into a string
bookFile = xbmcvfs.File(bookFileLocation, 'r')
bookContents = bookFile.read()
bookFile.close()
except:
log("MobiEBook: Failed to read contents of book %s with error: %s" % (bookFileName, traceback.format_exc()), xbmc.LOGERROR)
else:
log("MobiEBook: Failed to find book content file %s" % bookFileName)
# Cleanup the extract directory
if dir_exists(extractDir):
try:
shutil.rmtree(extractDir, True)
except:
log("MobiEBook: Failed to delete directory %s" % extractDir)
chapterContent = ""
if bookContents not in [None, ""]:
if chapterStartFlag is not None:
# Split out the chapter (For now just add the whole book)
# Split based on page markers
pageBreaks = bookContents.split('<mbp:pagebreak/>')
anchorHtml = "<a id=\"%s\"" % chapterStartFlag
# Find which section contains this anchor
for page in pageBreaks:
if anchorHtml in page.decode("utf-8"):
log("MobiEBook: Found page for chapter marker %s" % chapterStartFlag)
chapterContent = self._mobiHtmlParsing(page)
break
else:
log("MobiEBook: Chapter start flag, showing whole book")
chapterContent = self._mobiHtmlParsing(bookContents)
if chapterContent not in [None, ""]:
chapterContent = self.convertHtmlIntoKodiText(chapterContent)
return chapterContent
# Finds the given book file
def _findBookFile(self, dirPath, bookFileName):
bookFile = None
dirs, files = xbmcvfs.listdir(dirPath)
for aFile in files:
if aFile.lower() == bookFileName:
# Found a match, set the value
bookFile = os_path_join(dirPath, aFile)
break
# Now check any of the directories
for aDir in dirs:
if bookFile is None:
bookFile = self._findBookFile(os_path_join(dirPath, aDir), bookFileName)
return bookFile
def _mobiHtmlParsing(self, chapterContentIn):
# There are no line-breaks in the mobi file, so add them for each
# html paragraph tag
chapterContent = chapterContentIn.replace('</p>', '</p>\n')
# Headings are just shown in larger fornts for mobi
chapterContent = re.sub(r'<font size="5">(.*?)</font>', r'<h1>\1</h1>', chapterContent)
return chapterContent
