def saveLog():
if not os.path.exists(lazylibrarian.CONFIG['LOGDIR']):
return 'LOGDIR does not exist'
basename = os.path.join(lazylibrarian.CONFIG['LOGDIR'], 'lazylibrarian.log')
outfile = os.path.join(lazylibrarian.CONFIG['LOGDIR'], 'debug')
passchars = string.ascii_letters + string.digits + '_/' # _/ used by slack and googlebooks
redactlist = ['api -> ', 'apikey -> ', 'pass -> ', 'password -> ', 'token -> ', 'using api [',
'apikey=', 'key=', 'apikey%3D', "apikey': u'", "apikey': ', 'keys ->'"]
with open(outfile + '.tmp', 'w') as out:
nextfile = True
extn = 0
redacts = 0
while nextfile:
fname = basename
if extn > 0:
fname = fname + '.' + str(extn)
if not os.path.exists(fname):
logger.debug("logfile [%s] does not exist" % fname)
nextfile = False
else:
logger.debug('Processing logfile [%s]' % fname)
linecount = 0
for line in reverse_readline(fname):
for item in redactlist:
startpos = line.find(item)
if startpos >= 0:
startpos += len(item)
endpos = startpos
while endpos < len(line) and not line[endpos] in passchars:
endpos += 1
while endpos < len(line) and line[endpos] in passchars:
endpos += 1
if endpos != startpos:
line = line[:startpos] + '<redacted>' + line[endpos:]
redacts += 1
out.write("%s\n" % line)
if "Debug log ON" in line:
logger.debug('Found "Debug log ON" line %s in %s' % (linecount, fname))
nextfile = False
break
linecount += 1
extn += 1
with open(outfile + '.log', 'w') as logfile:
logfile.write(logHeader())
lines = 0
for line in reverse_readline(outfile + '.tmp'):
logfile.write("%s\n" % line)
lines += 1
os.remove(outfile + '.tmp')
logger.debug("Redacted %s passwords/apikeys" % redacts)
logger.debug("%s log lines written to %s" % (lines, outfile + '.log'))
with zipfile.ZipFile(outfile + '.zip', 'w') as myzip:
myzip.write(outfile + '.log', 'debug.log')
os.remove(outfile + '.log')
return "Debug log saved as %s" % (outfile + '.zip')
def get_book_info(fname):
# only handles epub, mobi and opf for now,
# for pdf see below
res = {}
if '.' not in fname:
return res
words = fname.split('.')
extn = words[len(words) - 1]
if extn == "mobi":
try:
book = Mobi(fname)
book.parse()
except:
return res
res['creator'] = book.author()
res['title'] = book.title()
res['language'] = book.language()
res['identifier'] = book.isbn()
res['type'] = "mobi"
return res
"""
# none of the pdfs in my library had language,isbn
# most didn't have author, or had the wrong author
# (author set to publisher, or software used)
# so probably not much point in looking at pdfs
#
# if (extn == "pdf"):
# pdf = PdfFileReader(open(fname, "rb"))
# txt = pdf.getDocumentInfo()
# repackage the data here to get components we need
# res = {}
# for s in ['title','language','creator']:
# res[s] = txt[s]
# res['identifier'] = txt['isbn']
# res['type'] = "pdf"
# return res
"""
if extn == "epub":
# prepare to read from the .epub file
zipdata = zipfile.ZipFile(fname)
# find the contents metafile
txt = zipdata.read('META-INF/container.xml')
tree = ElementTree.fromstring(txt)
n = 0
cfname = ""
if not len(tree):
return res
while n < len(tree[0]):
att = tree[0][n].attrib
if 'full-path' in att:
cfname = att['full-path']
n = n + 1
# grab the metadata block from the contents metafile
txt = zipdata.read(cfname)
tree = ElementTree.fromstring(txt)
res['type'] = "epub"
else:
if extn == "opf":
txt = open(fname).read()
tree = ElementTree.fromstring(txt)
res['type'] = "opf"
else:
return ""
# repackage the data
if not len(tree):
return res
n = 0
while n < len(tree[0]):
tag = str(tree[0][n].tag).split('}')[1]
txt = tree[0][n].text
attrib = str(tree[0][n].attrib)
isbn = ""
if 'title' in tag.lower():
res['title'] = txt
elif 'language' in tag.lower():
res['language'] = txt
elif 'creator' in tag.lower():
res['creator'] = txt
elif 'identifier' in tag.lower() and 'isbn' in attrib.lower():
if formatter.is_valid_isbn(txt):
res['identifier'] = txt
n = n + 1
return res
def create_cover(issuefile=None, refresh=False):
if lazylibrarian.CONFIG[
'IMP_CONVERT'] == 'None': # special flag to say "no covers required"
return
if issuefile is None or not os.path.isfile(issuefile):
logger.debug('No issuefile %s' % issuefile)
return
base, extn = os.path.splitext(issuefile)
if not extn:
logger.debug('Unable to create cover for %s, no extension?' %
issuefile)
return
coverfile = base + '.jpg'
if os.path.isfile(coverfile):
if refresh:
os.remove(coverfile)
else:
logger.debug('Cover for %s exists' % issuefile)
return # quit if cover already exists and we didn't want to refresh
logger.debug('Creating cover for %s' % issuefile)
data = '' # result from unzip or unrar
extn = extn.lower()
if extn in ['.cbz', '.epub']:
try:
data = zipfile.ZipFile(issuefile)
except Exception as why:
logger.debug("Failed to read zip file %s, %s %s" %
(issuefile, type(why).__name__, str(why)))
data = ''
elif extn in ['.cbr']:
try:
# unrar will complain if the library isn't installed, needs to be compiled separately
# see https://pypi.python.org/pypi/unrar/ for instructions
# Download source from http://www.rarlab.com/rar_add.htm
# note we need LIBRARY SOURCE not a binary package
# make lib; sudo make install-lib; sudo ldconfig
# lib.unrar should then be able to find libunrar.so
from lib.unrar import rarfile
data = rarfile.RarFile(issuefile)
except Exception as why:
logger.debug("Failed to read rar file %s, %s %s" %
(issuefile, type(why).__name__, str(why)))
data = ''
if data:
img = ''
try:
for member in data.namelist():
memlow = member.lower()
if '-00.' in memlow or '000.' in memlow or 'cover.' in memlow:
if memlow.endswith('.jpg') or memlow.endswith('.jpeg'):
img = data.read(member)
break
if img:
with open(coverfile, 'wb') as f:
f.write(img)
return
else:
logger.debug("Failed to find image in %s" % issuefile)
except Exception as why:
logger.debug("Failed to extract image from %s, %s %s" %
(issuefile, type(why).__name__, str(why)))
elif extn == '.pdf':
generator = ""
if len(lazylibrarian.CONFIG['IMP_CONVERT']
): # allow external convert to override libraries
generator = "external program: %s" % lazylibrarian.CONFIG[
'IMP_CONVERT']
if "gsconvert.py" in lazylibrarian.CONFIG['IMP_CONVERT']:
msg = "Use of gsconvert.py is deprecated, equivalent functionality is now built in. "
msg += "Support for gsconvert.py may be removed in a future release. See wiki for details."
logger.warn(msg)
converter = lazylibrarian.CONFIG['IMP_CONVERT']
postfix = ''
# if not os.path.isfile(converter): # full path given, or just program_name?
# converter = os.path.join(os.getcwd(), lazylibrarian.CONFIG['IMP_CONVERT'])
if 'convert' in converter and 'gs' not in converter:
# tell imagemagick to only convert first page
postfix = '[0]'
try:
params = [
converter,
'%s%s' % (issuefile, postfix),
'%s' % coverfile
]
res = subprocess.check_output(params, stderr=subprocess.STDOUT)
if res:
logger.debug('%s reports: %s' %
(lazylibrarian.CONFIG['IMP_CONVERT'], res))
except Exception as e:
# logger.debug(params)
logger.debug('External "convert" failed %s %s' %
(type(e).__name__, str(e)))
elif platform.system() == "Windows":
GS = os.path.join(os.getcwd(), "gswin64c.exe")
generator = "local gswin64c"
if not os.path.isfile(GS):
GS = os.path.join(os.getcwd(), "gswin32c.exe")
generator = "local gswin32c"
if not os.path.isfile(GS):
params = ["where", "gswin64c"]
try:
GS = subprocess.check_output(
params, stderr=subprocess.STDOUT).strip()
generator = "gswin64c"
except Exception as e:
logger.debug("where gswin64c failed: %s %s" %
(type(e).__name__, str(e)))
if not os.path.isfile(GS):
params = ["where", "gswin32c"]
try:
GS = subprocess.check_output(
params, stderr=subprocess.STDOUT).strip()
generator = "gswin32c"
except Exception as e:
logger.debug("where gswin32c failed: %s %s" %
(type(e).__name__, str(e)))
if not os.path.isfile(GS):
logger.debug("No gswin found")
generator = "(no windows ghostscript found)"
else:
# noinspection PyBroadException
try:
params = [GS, "--version"]
res = subprocess.check_output(params,
stderr=subprocess.STDOUT)
logger.debug("Found %s [%s] version %s" %
(generator, GS, res))
generator = "%s version %s" % (generator, res)
issuefile = issuefile.split('[')[0]
params = [
GS, "-sDEVICE=jpeg", "-dNOPAUSE", "-dBATCH", "-dSAFER",
"-dFirstPage=1", "-dLastPage=1", "-dUseCropBox",
"-sOutputFile=%s" % coverfile, issuefile
]
res = subprocess.check_output(params,
stderr=subprocess.STDOUT)
if not os.path.isfile(coverfile):
logger.debug("Failed to create jpg: %s" % res)
except Exception: # as why:
logger.debug("Failed to create jpg for %s" % issuefile)
logger.debug('Exception in gswin create_cover: %s' %
traceback.format_exc())
else: # not windows
try:
# noinspection PyUnresolvedReferences
from wand.image import Image
interface = "wand"
except ImportError:
try:
# No PythonMagick in python3
# noinspection PyUnresolvedReferences
import PythonMagick
interface = "pythonmagick"
except ImportError:
interface = ""
try:
if interface == 'wand':
generator = "wand interface"
with Image(filename=issuefile + '[0]') as img:
img.save(filename=coverfile)
elif interface == 'pythonmagick':
generator = "pythonmagick interface"
img = PythonMagick.Image()
# PythonMagick requires filenames to be str, not unicode
if type(issuefile) is unicode:
issuefile = unaccented_str(issuefile)
if type(coverfile) is unicode:
coverfile = unaccented_str(coverfile)
img.read(issuefile + '[0]')
img.write(coverfile)
else:
GS = os.path.join(os.getcwd(), "gs")
generator = "local gs"
if not os.path.isfile(GS):
GS = ""
params = ["which", "gs"]
try:
GS = subprocess.check_output(
params, stderr=subprocess.STDOUT).strip()
generator = GS
except Exception as e:
logger.debug("which gs failed: %s %s" %
(type(e).__name__, str(e)))
if not os.path.isfile(GS):
logger.debug("Cannot find gs")
generator = "(no gs found)"
else:
params = [GS, "--version"]
res = subprocess.check_output(
params, stderr=subprocess.STDOUT)
logger.debug("Found gs [%s] version %s" %
(GS, res))
generator = "%s version %s" % (generator, res)
issuefile = issuefile.split('[')[0]
params = [
GS, "-sDEVICE=jpeg", "-dNOPAUSE", "-dBATCH",
"-dSAFER", "-dFirstPage=1", "-dLastPage=1",
"-dUseCropBox",
"-sOutputFile=%s" % coverfile, issuefile
]
res = subprocess.check_output(
params, stderr=subprocess.STDOUT)
if not os.path.isfile(coverfile):
logger.debug("Failed to create jpg: %s" % res)
except Exception as e:
logger.debug("Unable to create cover for %s using %s %s" %
(issuefile, type(e).__name__, generator))
logger.debug('Exception in create_cover: %s' %
traceback.format_exc())
if os.path.isfile(coverfile):
setperm(coverfile)
logger.debug("Created cover for %s using %s" %
(issuefile, generator))
return
# if not recognised extension or cover creation failed
try:
shutil.copyfile(
os.path.join(lazylibrarian.PROG_DIR, 'data/images/nocover.jpg'),
coverfile)
setperm(coverfile)
except Exception as why:
logger.debug("Failed to copy nocover file, %s %s" %
(type(why).__name__, str(why)))
return
def saveLog():
if not os.path.exists(lazylibrarian.CONFIG['LOGDIR']):
return 'LOGDIR does not exist'
popen_list = [sys.executable, lazylibrarian.FULL_PATH]
popen_list += lazylibrarian.ARGS
header = "Startup cmd: %s\n" % str(popen_list)
header += 'Interface: %s\n' % lazylibrarian.CONFIG['HTTP_LOOK']
header += 'Loglevel: %s\n' % lazylibrarian.LOGLEVEL
for item in lazylibrarian.CONFIG_GIT:
header += '%s: %s\n' % (item.lower(), lazylibrarian.CONFIG[item])
header += "Python version: %s\n" % sys.version.split('\n')
header += "Distribution: %s\n" % str(platform.dist())
header += "System: %s\n" % str(platform.system())
header += "Machine: %s\n" % str(platform.machine())
header += "Platform: %s\n" % str(platform.platform())
header += "uname: %s\n" % str(platform.uname())
header += "version: %s\n" % str(platform.version())
header += "mac_ver: %s\n" % str(platform.mac_ver())
basename = os.path.join(lazylibrarian.CONFIG['LOGDIR'], 'lazylibrarian.log')
outfile = os.path.join(lazylibrarian.CONFIG['LOGDIR'], 'debug')
passchars = string.ascii_letters + string.digits + '_/' # _/ used by slack and googlebooks
redactlist = ['api -> ', 'apikey -> ', 'pass -> ', 'password -> ', 'token -> ', 'using api [',
'apikey=', 'key=', 'apikey%3D', "apikey': u'", "apikey': '"]
with open(outfile + '.tmp', 'w') as out:
nextfile = True
extn = 0
redacts = 0
while nextfile:
fname = basename
if extn > 0:
fname = fname + '.' + str(extn)
if not os.path.exists(fname):
logger.debug("logfile [%s] does not exist" % fname)
nextfile = False
else:
logger.debug('Processing logfile [%s]' % fname)
linecount = 0
for line in reverse_readline(fname):
for item in redactlist:
startpos = line.find(item)
if startpos >= 0:
startpos += len(item)
endpos = startpos
while endpos < len(line) and not line[endpos] in passchars:
endpos += 1
while endpos < len(line) and line[endpos] in passchars:
endpos += 1
if endpos != startpos:
line = line[:startpos] + '<redacted>' + line[endpos:]
redacts += 1
out.write("%s\n" % line)
if "Debug log ON" in line:
logger.debug('Found "Debug log ON" line %s in %s' % (linecount, fname))
nextfile = False
break
linecount += 1
extn += 1
with open(outfile + '.log', 'w') as logfile:
logfile.write(header)
lines = 0 # len(header.split('\n'))
for line in reverse_readline(outfile + '.tmp'):
logfile.write("%s\n" % line)
lines += 1
os.remove(outfile + '.tmp')
logger.debug("Redacted %s passwords/apikeys" % redacts)
logger.debug("%s log lines written to %s" % (lines, outfile + '.log'))
with zipfile.ZipFile(outfile + '.zip', 'w') as myzip:
myzip.write(outfile + '.log', 'debug.log')
os.remove(outfile + '.log')
return "Debug log saved as %s" % (outfile + '.zip')
def get_book_info(fname):
# only handles epub, mobi, azw3 and opf for now,
# for pdf see notes below
res = {}
extn = os.path.splitext(fname)[1]
if not extn:
return res
if extn == ".mobi" or extn == ".azw3":
res['type'] = extn[1:]
try:
book = Mobi(fname)
book.parse()
except Exception as e:
logger.debug('Unable to parse mobi in %s, %s' % (fname, str(e)))
return res
res['creator'] = book.author()
res['title'] = book.title()
res['language'] = book.language()
res['identifier'] = book.isbn()
return res
"""
# none of the pdfs in my library had language,isbn
# most didn't have author, or had the wrong author
# (author set to publisher, or software used)
# so probably not much point in looking at pdfs
#
if (extn == ".pdf"):
pdf = PdfFileReader(open(fname, "rb"))
txt = pdf.getDocumentInfo()
# repackage the data here to get components we need
res = {}
for s in ['title','language','creator']:
res[s] = txt[s]
res['identifier'] = txt['isbn']
res['type'] = "pdf"
return res
"""
elif extn == ".epub":
res['type'] = "epub"
# prepare to read from the .epub file
try:
zipdata = zipfile.ZipFile(fname)
except Exception as e:
logger.debug('Unable to parse zipfile %s, %s' % (fname, str(e)))
return res
# find the contents metafile
txt = zipdata.read('META-INF/container.xml')
tree = ElementTree.fromstring(txt)
n = 0
cfname = ""
if not len(tree):
return res
while n < len(tree[0]):
att = tree[0][n].attrib
if 'full-path' in att:
cfname = att['full-path']
break
n = n + 1
# grab the metadata block from the contents metafile
txt = zipdata.read(cfname)
elif extn == ".opf":
res['type'] = "opf"
txt = open(fname).read()
# sanitize any unmatched html tags or ElementTree won't parse
dic = {'<br>': '', '</br>': ''}
txt = replace_all(txt, dic)
# repackage epub or opf metadata
try:
tree = ElementTree.fromstring(txt)
except Exception as e:
logger.error("Error parsing metadata from %s, %s" % (fname, str(e)))
return res
if not len(tree):
return res
n = 0
while n < len(tree[0]):
tag = str(tree[0][n].tag).lower()
if '}' in tag:
tag = tag.split('}')[1]
txt = tree[0][n].text
attrib = str(tree[0][n].attrib).lower()
if 'title' in tag:
res['title'] = txt
elif 'language' in tag:
res['language'] = txt
elif 'creator' in tag:
res['creator'] = txt
elif 'identifier' in tag and 'isbn' in attrib:
if is_valid_isbn(txt):
res['identifier'] = txt
n = n + 1
return res
