def generateBook(bookDir, raw, fixedimage):
# sanity check Topaz file extraction
if not os.path.exists(bookDir) :
print("Can not find directory with unencrypted book")
return 1
dictFile = os.path.join(bookDir,'dict0000.dat')
if not os.path.exists(dictFile) :
print("Can not find dict0000.dat file")
return 1
pageDir = os.path.join(bookDir,'page')
if not os.path.exists(pageDir) :
print("Can not find page directory in unencrypted book")
return 1
imgDir = os.path.join(bookDir,'img')
if not os.path.exists(imgDir) :
print("Can not find image directory in unencrypted book")
return 1
glyphsDir = os.path.join(bookDir,'glyphs')
if not os.path.exists(glyphsDir) :
print("Can not find glyphs directory in unencrypted book")
return 1
metaFile = os.path.join(bookDir,'metadata0000.dat')
if not os.path.exists(metaFile) :
print("Can not find metadata0000.dat in unencrypted book")
return 1
svgDir = os.path.join(bookDir,'svg')
if not os.path.exists(svgDir) :
os.makedirs(svgDir)
if buildXML:
xmlDir = os.path.join(bookDir,'xml')
if not os.path.exists(xmlDir) :
os.makedirs(xmlDir)
otherFile = os.path.join(bookDir,'other0000.dat')
if not os.path.exists(otherFile) :
print("Can not find other0000.dat in unencrypted book")
return 1
print("Updating to color images if available")
spath = os.path.join(bookDir,'color_img')
dpath = os.path.join(bookDir,'img')
filenames = os.listdir(spath)
filenames = sorted(filenames)
for filename in filenames:
imgname = filename.replace('color','img')
sfile = os.path.join(spath,filename)
dfile = os.path.join(dpath,imgname)
imgdata = open(sfile,'rb').read()
open(dfile,'wb').write(imgdata)
print("Creating cover.jpg")
isCover = False
cpath = os.path.join(bookDir,'img')
cpath = os.path.join(cpath,'img0000.jpg')
if os.path.isfile(cpath):
cover = open(cpath, 'rb').read()
cpath = os.path.join(bookDir,'cover.jpg')
open(cpath, 'wb').write(cover)
isCover = True
print('Processing Dictionary')
dict = Dictionary(dictFile)
print('Processing Meta Data and creating OPF')
meta_array = getMetaArray(metaFile)
# replace special chars in title and authors like & < >
title = meta_array.get('Title','No Title Provided')
title = title.replace('&','&')
title = title.replace('<','<')
title = title.replace('>','>')
meta_array['Title'] = title
authors = meta_array.get('Authors','No Authors Provided')
authors = authors.replace('&','&')
authors = authors.replace('<','<')
authors = authors.replace('>','>')
meta_array['Authors'] = authors
if buildXML:
xname = os.path.join(xmlDir, 'metadata.xml')
mlst = []
for key in meta_array:
mlst.append('<meta name="' + key + '" content="' + meta_array[key] + '" />\n')
metastr = "".join(mlst)
mlst = None
open(xname, 'wb').write(metastr)
print('Processing StyleSheet')
# get some scaling info from metadata to use while processing styles
# and first page info
fontsize = '135'
if 'fontSize' in meta_array:
fontsize = meta_array['fontSize']
# also get the size of a normal text page
# get the total number of pages unpacked as a safety check
filenames = os.listdir(pageDir)
numfiles = len(filenames)
spage = '1'
if 'firstTextPage' in meta_array:
spage = meta_array['firstTextPage']
pnum = int(spage)
if pnum >= numfiles or pnum < 0:
# metadata is wrong so just select a page near the front
# 10% of the book to get a normal text page
pnum = int(0.10 * numfiles)
# print "first normal text page is", spage
# get page height and width from first text page for use in stylesheet scaling
pname = 'page%04d.dat' % (pnum - 1)
fname = os.path.join(pageDir,pname)
flat_xml = convert2xml.fromData(dict, fname)
(ph, pw) = getPageDim(flat_xml)
if (ph == '-1') or (ph == '0') : ph = '11000'
if (pw == '-1') or (pw == '0') : pw = '8500'
meta_array['pageHeight'] = ph
meta_array['pageWidth'] = pw
if 'fontSize' not in meta_array.keys():
meta_array['fontSize'] = fontsize
# process other.dat for css info and for map of page files to svg images
# this map is needed because some pages actually are made up of multiple
# pageXXXX.xml files
xname = os.path.join(bookDir, 'style.css')
flat_xml = convert2xml.fromData(dict, otherFile)
# extract info.original.pid to get original page information
pageIDMap = {}
pageidnums = stylexml2css.getpageIDMap(flat_xml)
if len(pageidnums) == 0:
filenames = os.listdir(pageDir)
numfiles = len(filenames)
for k in range(numfiles):
pageidnums.append(k)
# create a map from page ids to list of page file nums to process for that page
for i in range(len(pageidnums)):
id = pageidnums[i]
if id in pageIDMap.keys():
pageIDMap[id].append(i)
else:
pageIDMap[id] = [i]
# now get the css info
cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
open(xname, 'wb').write(cssstr)
if buildXML:
xname = os.path.join(xmlDir, 'other0000.xml')
open(xname, 'wb').write(convert2xml.getXML(dict, otherFile))
print('Processing Glyphs')
gd = GlyphDict()
filenames = os.listdir(glyphsDir)
filenames = sorted(filenames)
glyfname = os.path.join(svgDir,'glyphs.svg')
glyfile = open(glyfname, 'w')
glyfile.write('<?xml version="1.0" standalone="no"?>\n')
glyfile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
glyfile.write('<svg width="512" height="512" viewBox="0 0 511 511" xmlns="http://www.w3.org/2000/svg" version="1.1">\n')
glyfile.write('<title>Glyphs for %s</title>\n' % meta_array['Title'])
glyfile.write('<defs>\n')
counter = 0
for filename in filenames:
# print ' ', filename
print('.', end=' ')
fname = os.path.join(glyphsDir,filename)
flat_xml = convert2xml.fromData(dict, fname)
if buildXML:
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
open(xname, 'wb').write(convert2xml.getXML(dict, fname))
gp = GParser(flat_xml)
for i in range(0, gp.count):
path = gp.getPath(i)
maxh, maxw = gp.getGlyphDim(i)
fullpath = '<path id="gl%d" d="%s" fill="black" /><!-- width=%d height=%d -->\n' % (counter * 256 + i, path, maxw, maxh)
glyfile.write(fullpath)
gd.addGlyph(counter * 256 + i, fullpath)
counter += 1
glyfile.write('</defs>\n')
glyfile.write('</svg>\n')
glyfile.close()
print(" ")
# start up the html
# also build up tocentries while processing html
htmlFileName = "book.html"
hlst = []
hlst.append('<?xml version="1.0" encoding="utf-8"?>\n')
hlst.append('<!DOCTYPE HTML PUBLIC "-//W3C//DTD XHTML 1.1 Strict//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11-strict.dtd">\n')
hlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">\n')
hlst.append('<head>\n')
hlst.append('<meta http-equiv="content-type" content="text/html; charset=utf-8"/>\n')
hlst.append('<title>' + meta_array['Title'] + ' by ' + meta_array['Authors'] + '</title>\n')
hlst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
hlst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
hlst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
hlst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
hlst.append('<link href="style.css" rel="stylesheet" type="text/css" />\n')
hlst.append('</head>\n<body>\n')
print('Processing Pages')
# Books are at 1440 DPI. This is rendering at twice that size for
# readability when rendering to the screen.
scaledpi = 1440.0
filenames = os.listdir(pageDir)
filenames = sorted(filenames)
numfiles = len(filenames)
xmllst = []
elst = []
for filename in filenames:
# print ' ', filename
print(".", end=' ')
fname = os.path.join(pageDir,filename)
flat_xml = convert2xml.fromData(dict, fname)
# keep flat_xml for later svg processing
xmllst.append(flat_xml)
if buildXML:
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
open(xname, 'wb').write(convert2xml.getXML(dict, fname))
# first get the html
pagehtml, tocinfo = flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
elst.append(tocinfo)
hlst.append(pagehtml)
# finish up the html string and output it
hlst.append('</body>\n</html>\n')
htmlstr = "".join(hlst)
hlst = None
open(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
print(" ")
print('Extracting Table of Contents from Amazon OCR')
# first create a table of contents file for the svg images
tlst = []
tlst.append('<?xml version="1.0" encoding="utf-8"?>\n')
tlst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
tlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >')
tlst.append('<head>\n')
tlst.append('<title>' + meta_array['Title'] + '</title>\n')
tlst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
tlst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
tlst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
tlst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
tlst.append('</head>\n')
tlst.append('<body>\n')
tlst.append('<h2>Table of Contents</h2>\n')
start = pageidnums[0]
if (raw):
startname = 'page%04d.svg' % start
else:
startname = 'page%04d.xhtml' % start
tlst.append('<h3><a href="' + startname + '">Start of Book</a></h3>\n')
# build up a table of contents for the svg xhtml output
tocentries = "".join(elst)
elst = None
toclst = tocentries.split('\n')
toclst.pop()
for entry in toclst:
print(entry)
title, pagenum = entry.split('|')
id = pageidnums[int(pagenum)]
if (raw):
fname = 'page%04d.svg' % id
else:
fname = 'page%04d.xhtml' % id
tlst.append('<h3><a href="'+ fname + '">' + title + '</a></h3>\n')
tlst.append('</body>\n')
tlst.append('</html>\n')
tochtml = "".join(tlst)
open(os.path.join(svgDir, 'toc.xhtml'), 'wb').write(tochtml)
# now create index_svg.xhtml that points to all required files
slst = []
slst.append('<?xml version="1.0" encoding="utf-8"?>\n')
slst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
slst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >')
slst.append('<head>\n')
slst.append('<title>' + meta_array['Title'] + '</title>\n')
slst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
slst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
slst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
slst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
slst.append('</head>\n')
slst.append('<body>\n')
print("Building svg images of each book page")
slst.append('<h2>List of Pages</h2>\n')
slst.append('<div>\n')
idlst = sorted(pageIDMap.keys())
numids = len(idlst)
cnt = len(idlst)
previd = None
for j in range(cnt):
pageid = idlst[j]
if j < cnt - 1:
nextid = idlst[j+1]
else:
nextid = None
print('.', end=' ')
pagelst = pageIDMap[pageid]
flst = []
for page in pagelst:
flst.append(xmllst[page])
flat_svg = "".join(flst)
flst=None
svgxml = flatxml2svg.convert2SVG(gd, flat_svg, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi)
if (raw) :
pfile = open(os.path.join(svgDir,'page%04d.svg' % pageid),'w')
slst.append('<a href="svg/page%04d.svg">Page %d</a>\n' % (pageid, pageid))
else :
pfile = open(os.path.join(svgDir,'page%04d.xhtml' % pageid), 'w')
slst.append('<a href="svg/page%04d.xhtml">Page %d</a>\n' % (pageid, pageid))
previd = pageid
pfile.write(svgxml)
pfile.close()
counter += 1
slst.append('</div>\n')
slst.append('<h2><a href="svg/toc.xhtml">Table of Contents</a></h2>\n')
slst.append('</body>\n</html>\n')
svgindex = "".join(slst)
slst = None
open(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
print(" ")
# build the opf file
opfname = os.path.join(bookDir, 'book.opf')
olst = []
olst.append('<?xml version="1.0" encoding="utf-8"?>\n')
olst.append('<package xmlns="http://www.idpf.org/2007/opf" unique-identifier="guid_id">\n')
# adding metadata
olst.append(' <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">\n')
if 'GUID' in meta_array:
olst.append(' <dc:identifier opf:scheme="GUID" id="guid_id">' + meta_array['GUID'] + '</dc:identifier>\n')
if 'ASIN' in meta_array:
olst.append(' <dc:identifier opf:scheme="ASIN">' + meta_array['ASIN'] + '</dc:identifier>\n')
if 'oASIN' in meta_array:
olst.append(' <dc:identifier opf:scheme="oASIN">' + meta_array['oASIN'] + '</dc:identifier>\n')
olst.append(' <dc:title>' + meta_array['Title'] + '</dc:title>\n')
olst.append(' <dc:creator opf:role="aut">' + meta_array['Authors'] + '</dc:creator>\n')
olst.append(' <dc:language>en</dc:language>\n')
olst.append(' <dc:date>' + meta_array['UpdateTime'] + '</dc:date>\n')
if isCover:
olst.append(' <meta name="cover" content="bookcover"/>\n')
olst.append(' </metadata>\n')
olst.append('<manifest>\n')
olst.append(' <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n')
olst.append(' <item id="stylesheet" href="style.css" media-type="text/css"/>\n')
# adding image files to manifest
filenames = os.listdir(imgDir)
filenames = sorted(filenames)
for filename in filenames:
imgname, imgext = os.path.splitext(filename)
if imgext == '.jpg':
imgext = 'jpeg'
if imgext == '.svg':
imgext = 'svg+xml'
olst.append(' <item id="' + imgname + '" href="img/' + filename + '" media-type="image/' + imgext + '"/>\n')
if isCover:
olst.append(' <item id="bookcover" href="cover.jpg" media-type="image/jpeg" />\n')
olst.append('</manifest>\n')
# adding spine
olst.append('<spine>\n <itemref idref="book" />\n</spine>\n')
if isCover:
olst.append(' <guide>\n')
olst.append(' <reference href="cover.jpg" type="cover" title="Cover"/>\n')
olst.append(' </guide>\n')
olst.append('</package>\n')
opfstr = "".join(olst)
olst = None
open(opfname, 'wb').write(opfstr)
print('Processing Complete')
return 0
def generateBook(bookDir, raw, fixedimage):
# sanity check Topaz file extraction
if not os.path.exists(bookDir) :
print "Can not find directory with unencrypted book"
return 1
dictFile = os.path.join(bookDir,'dict0000.dat')
if not os.path.exists(dictFile) :
print "Can not find dict0000.dat file"
return 1
pageDir = os.path.join(bookDir,'page')
if not os.path.exists(pageDir) :
print "Can not find page directory in unencrypted book"
return 1
imgDir = os.path.join(bookDir,'img')
if not os.path.exists(imgDir) :
print "Can not find image directory in unencrypted book"
return 1
glyphsDir = os.path.join(bookDir,'glyphs')
if not os.path.exists(glyphsDir) :
print "Can not find glyphs directory in unencrypted book"
return 1
metaFile = os.path.join(bookDir,'metadata0000.dat')
if not os.path.exists(metaFile) :
print "Can not find metadata0000.dat in unencrypted book"
return 1
svgDir = os.path.join(bookDir,'svg')
if not os.path.exists(svgDir) :
os.makedirs(svgDir)
if buildXML:
xmlDir = os.path.join(bookDir,'xml')
if not os.path.exists(xmlDir) :
os.makedirs(xmlDir)
otherFile = os.path.join(bookDir,'other0000.dat')
if not os.path.exists(otherFile) :
print "Can not find other0000.dat in unencrypted book"
return 1
print "Updating to color images if available"
spath = os.path.join(bookDir,'color_img')
dpath = os.path.join(bookDir,'img')
filenames = os.listdir(spath)
filenames = sorted(filenames)
for filename in filenames:
imgname = filename.replace('color','img')
sfile = os.path.join(spath,filename)
dfile = os.path.join(dpath,imgname)
imgdata = file(sfile,'rb').read()
file(dfile,'wb').write(imgdata)
print "Creating cover.jpg"
isCover = False
cpath = os.path.join(bookDir,'img')
cpath = os.path.join(cpath,'img0000.jpg')
if os.path.isfile(cpath):
cover = file(cpath, 'rb').read()
cpath = os.path.join(bookDir,'cover.jpg')
file(cpath, 'wb').write(cover)
isCover = True
print 'Processing Dictionary'
dict = Dictionary(dictFile)
print 'Processing Meta Data and creating OPF'
meta_array = getMetaArray(metaFile)
# replace special chars in title and authors like & < >
title = meta_array.get('Title','No Title Provided')
title = title.replace('&','&')
title = title.replace('<','<')
title = title.replace('>','>')
meta_array['Title'] = title
authors = meta_array.get('Authors','No Authors Provided')
authors = authors.replace('&','&')
authors = authors.replace('<','<')
authors = authors.replace('>','>')
meta_array['Authors'] = authors
if buildXML:
xname = os.path.join(xmlDir, 'metadata.xml')
mlst = []
for key in meta_array:
mlst.append('<meta name="' + key + '" content="' + meta_array[key] + '" />\n')
metastr = "".join(mlst)
mlst = None
file(xname, 'wb').write(metastr)
print 'Processing StyleSheet'
# get some scaling info from metadata to use while processing styles
# and first page info
fontsize = '135'
if 'fontSize' in meta_array:
fontsize = meta_array['fontSize']
# also get the size of a normal text page
# get the total number of pages unpacked as a safety check
filenames = os.listdir(pageDir)
numfiles = len(filenames)
spage = '1'
if 'firstTextPage' in meta_array:
spage = meta_array['firstTextPage']
pnum = int(spage)
if pnum >= numfiles or pnum < 0:
# metadata is wrong so just select a page near the front
# 10% of the book to get a normal text page
pnum = int(0.10 * numfiles)
# print "first normal text page is", spage
# get page height and width from first text page for use in stylesheet scaling
pname = 'page%04d.dat' % (pnum + 1)
fname = os.path.join(pageDir,pname)
flat_xml = convert2xml.fromData(dict, fname)
(ph, pw) = getPageDim(flat_xml)
if (ph == '-1') or (ph == '0') : ph = '11000'
if (pw == '-1') or (pw == '0') : pw = '8500'
meta_array['pageHeight'] = ph
meta_array['pageWidth'] = pw
if 'fontSize' not in meta_array.keys():
meta_array['fontSize'] = fontsize
# process other.dat for css info and for map of page files to svg images
# this map is needed because some pages actually are made up of multiple
# pageXXXX.xml files
xname = os.path.join(bookDir, 'style.css')
flat_xml = convert2xml.fromData(dict, otherFile)
# extract info.original.pid to get original page information
pageIDMap = {}
pageidnums = stylexml2css.getpageIDMap(flat_xml)
if len(pageidnums) == 0:
filenames = os.listdir(pageDir)
numfiles = len(filenames)
for k in range(numfiles):
pageidnums.append(k)
# create a map from page ids to list of page file nums to process for that page
for i in range(len(pageidnums)):
id = pageidnums[i]
if id in pageIDMap.keys():
pageIDMap[id].append(i)
else:
pageIDMap[id] = [i]
# now get the css info
cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
file(xname, 'wb').write(cssstr)
if buildXML:
xname = os.path.join(xmlDir, 'other0000.xml')
file(xname, 'wb').write(convert2xml.getXML(dict, otherFile))
print 'Processing Glyphs'
gd = GlyphDict()
filenames = os.listdir(glyphsDir)
filenames = sorted(filenames)
glyfname = os.path.join(svgDir,'glyphs.svg')
glyfile = open(glyfname, 'w')
glyfile.write('<?xml version="1.0" standalone="no"?>\n')
glyfile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
glyfile.write('<svg width="512" height="512" viewBox="0 0 511 511" xmlns="http://www.w3.org/2000/svg" version="1.1">\n')
glyfile.write('<title>Glyphs for %s</title>\n' % meta_array['Title'])
glyfile.write('<defs>\n')
counter = 0
for filename in filenames:
# print ' ', filename
print '.',
fname = os.path.join(glyphsDir,filename)
flat_xml = convert2xml.fromData(dict, fname)
if buildXML:
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
gp = GParser(flat_xml)
for i in xrange(0, gp.count):
path = gp.getPath(i)
maxh, maxw = gp.getGlyphDim(i)
fullpath = '<path id="gl%d" d="%s" fill="black" /><!-- width=%d height=%d -->\n' % (counter * 256 + i, path, maxw, maxh)
glyfile.write(fullpath)
gd.addGlyph(counter * 256 + i, fullpath)
counter += 1
glyfile.write('</defs>\n')
glyfile.write('</svg>\n')
glyfile.close()
print " "
# start up the html
# also build up tocentries while processing html
htmlFileName = "book.html"
hlst = []
hlst.append('<?xml version="1.0" encoding="utf-8"?>\n')
hlst.append('<!DOCTYPE HTML PUBLIC "-//W3C//DTD XHTML 1.1 Strict//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11-strict.dtd">\n')
hlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">\n')
hlst.append('<head>\n')
hlst.append('<meta http-equiv="content-type" content="text/html; charset=utf-8"/>\n')
hlst.append('<title>' + meta_array['Title'] + ' by ' + meta_array['Authors'] + '</title>\n')
hlst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
hlst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
hlst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
hlst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
hlst.append('<link href="style.css" rel="stylesheet" type="text/css" />\n')
hlst.append('</head>\n<body>\n')
print 'Processing Pages'
# Books are at 1440 DPI. This is rendering at twice that size for
# readability when rendering to the screen.
scaledpi = 1440.0
filenames = os.listdir(pageDir)
filenames = sorted(filenames)
numfiles = len(filenames)
xmllst = []
elst = []
for filename in filenames:
# print ' ', filename
print ".",
fname = os.path.join(pageDir,filename)
flat_xml = convert2xml.fromData(dict, fname)
# keep flat_xml for later svg processing
xmllst.append(flat_xml)
if buildXML:
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
# first get the html
pagehtml, tocinfo = flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
elst.append(tocinfo)
hlst.append(pagehtml)
# finish up the html string and output it
hlst.append('</body>\n</html>\n')
htmlstr = "".join(hlst)
hlst = None
file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
print " "
print 'Extracting Table of Contents from Amazon OCR'
# first create a table of contents file for the svg images
tlst = []
tlst.append('<?xml version="1.0" encoding="utf-8"?>\n')
tlst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
tlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >')
tlst.append('<head>\n')
tlst.append('<title>' + meta_array['Title'] + '</title>\n')
tlst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
tlst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
tlst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
tlst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
tlst.append('</head>\n')
tlst.append('<body>\n')
tlst.append('<h2>Table of Contents</h2>\n')
start = pageidnums[0]
if (raw):
startname = 'page%04d.svg' % start
else:
startname = 'page%04d.xhtml' % start
tlst.append('<h3><a href="' + startname + '">Start of Book</a></h3>\n')
# build up a table of contents for the svg xhtml output
tocentries = "".join(elst)
elst = None
toclst = tocentries.split('\n')
toclst.pop()
for entry in toclst:
print entry
title, pagenum = entry.split('|')
id = pageidnums[int(pagenum)]
if (raw):
fname = 'page%04d.svg' % id
else:
fname = 'page%04d.xhtml' % id
tlst.append('<h3><a href="'+ fname + '">' + title + '</a></h3>\n')
tlst.append('</body>\n')
tlst.append('</html>\n')
tochtml = "".join(tlst)
file(os.path.join(svgDir, 'toc.xhtml'), 'wb').write(tochtml)
# now create index_svg.xhtml that points to all required files
slst = []
slst.append('<?xml version="1.0" encoding="utf-8"?>\n')
slst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
slst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >')
slst.append('<head>\n')
slst.append('<title>' + meta_array['Title'] + '</title>\n')
slst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
slst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
slst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
slst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
slst.append('</head>\n')
slst.append('<body>\n')
print "Building svg images of each book page"
slst.append('<h2>List of Pages</h2>\n')
slst.append('<div>\n')
idlst = sorted(pageIDMap.keys())
numids = len(idlst)
cnt = len(idlst)
previd = None
for j in range(cnt):
pageid = idlst[j]
if j < cnt - 1:
nextid = idlst[j+1]
else:
nextid = None
print '.',
pagelst = pageIDMap[pageid]
flst = []
for page in pagelst:
flst.append(xmllst[page])
flat_svg = "".join(flst)
flst=None
svgxml = flatxml2svg.convert2SVG(gd, flat_svg, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi)
if (raw) :
pfile = open(os.path.join(svgDir,'page%04d.svg' % pageid),'w')
slst.append('<a href="svg/page%04d.svg">Page %d</a>\n' % (pageid, pageid))
else :
pfile = open(os.path.join(svgDir,'page%04d.xhtml' % pageid), 'w')
slst.append('<a href="svg/page%04d.xhtml">Page %d</a>\n' % (pageid, pageid))
previd = pageid
pfile.write(svgxml)
pfile.close()
counter += 1
slst.append('</div>\n')
slst.append('<h2><a href="svg/toc.xhtml">Table of Contents</a></h2>\n')
slst.append('</body>\n</html>\n')
svgindex = "".join(slst)
slst = None
file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
print " "
# build the opf file
opfname = os.path.join(bookDir, 'book.opf')
olst = []
olst.append('<?xml version="1.0" encoding="utf-8"?>\n')
olst.append('<package xmlns="http://www.idpf.org/2007/opf" unique-identifier="guid_id">\n')
# adding metadata
olst.append(' <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">\n')
if 'GUID' in meta_array:
olst.append(' <dc:identifier opf:scheme="GUID" id="guid_id">' + meta_array['GUID'] + '</dc:identifier>\n')
if 'ASIN' in meta_array:
olst.append(' <dc:identifier opf:scheme="ASIN">' + meta_array['ASIN'] + '</dc:identifier>\n')
if 'oASIN' in meta_array:
olst.append(' <dc:identifier opf:scheme="oASIN">' + meta_array['oASIN'] + '</dc:identifier>\n')
olst.append(' <dc:title>' + meta_array['Title'] + '</dc:title>\n')
olst.append(' <dc:creator opf:role="aut">' + meta_array['Authors'] + '</dc:creator>\n')
olst.append(' <dc:language>en</dc:language>\n')
olst.append(' <dc:date>' + meta_array['UpdateTime'] + '</dc:date>\n')
if isCover:
olst.append(' <meta name="cover" content="bookcover"/>\n')
olst.append(' </metadata>\n')
olst.append('<manifest>\n')
olst.append(' <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n')
olst.append(' <item id="stylesheet" href="style.css" media-type="text/css"/>\n')
# adding image files to manifest
filenames = os.listdir(imgDir)
filenames = sorted(filenames)
for filename in filenames:
imgname, imgext = os.path.splitext(filename)
if imgext == '.jpg':
imgext = 'jpeg'
if imgext == '.svg':
imgext = 'svg+xml'
olst.append(' <item id="' + imgname + '" href="img/' + filename + '" media-type="image/' + imgext + '"/>\n')
if isCover:
olst.append(' <item id="bookcover" href="cover.jpg" media-type="image/jpeg" />\n')
olst.append('</manifest>\n')
# adding spine
olst.append('<spine>\n <itemref idref="book" />\n</spine>\n')
if isCover:
olst.append(' <guide>\n')
olst.append(' <reference href="cover.jpg" type="cover" title="Cover"/>\n')
olst.append(' </guide>\n')
olst.append('</package>\n')
opfstr = "".join(olst)
olst = None
file(opfname, 'wb').write(opfstr)
print 'Processing Complete'
return 0