def process_pml(self, pml_path, html_path, close_all=False):
from calibre.ebooks.pml.pmlconverter import PML_HTMLizer
pclose = False
hclose = False
if not hasattr(pml_path, 'read'):
pml_stream = open(pml_path, 'rb')
pclose = True
else:
pml_stream = pml_path
pml_stream.seek(0)
if not hasattr(html_path, 'write'):
html_stream = open(html_path, 'wb')
hclose = True
else:
html_stream = html_path
ienc = pml_stream.encoding if pml_stream.encoding else 'cp1252'
if self.options.input_encoding:
ienc = self.options.input_encoding
self.log.debug('Converting PML to HTML...')
hizer = PML_HTMLizer()
html = hizer.parse_pml(pml_stream.read().decode(ienc), html_path)
html = '<html><head><title></title></head><body>%s</body></html>'%html
html_stream.write(html.encode('utf-8', 'replace'))
if pclose:
pml_stream.close()
if hclose:
html_stream.close()
return hizer.get_toc()
def process_pml(self, pml_path, html_path, close_all=False):
from calibre.ebooks.pml.pmlconverter import PML_HTMLizer
pclose = False
hclose = False
if not hasattr(pml_path, 'read'):
pml_stream = open(pml_path, 'rb')
pclose = True
else:
pml_stream = pml_path
pml_stream.seek(0)
if not hasattr(html_path, 'write'):
html_stream = open(html_path, 'wb')
hclose = True
else:
html_stream = html_path
ienc = pml_stream.encoding if pml_stream.encoding else 'cp1252'
if self.options.input_encoding:
ienc = self.options.input_encoding
self.log.debug('Converting PML to HTML...')
hizer = PML_HTMLizer()
html = hizer.parse_pml(pml_stream.read().decode(ienc), html_path)
html = '<html><head><title></title></head><body>%s</body></html>'%html
html_stream.write(html.encode('utf-8', 'replace'))
if pclose:
pml_stream.close()
if hclose:
html_stream.close()
return hizer.get_toc()
def extract_content(self, output_dir):
from calibre.ebooks.pml.pmlconverter import footnote_to_html, sidebar_to_html
from calibre.ebooks.pml.pmlconverter import PML_HTMLizer
output_dir = os.path.abspath(output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
title = self.mi.title
if not isinstance(title, unicode_type):
title = title.decode('utf-8', 'replace')
html = u'<html><head><title>%s</title></head><body>' % title
pml = u''
for i in range(1, self.header_record.num_text_pages + 1):
self.log.debug('Extracting text page %i' % i)
pml += self.get_text_page(i)
hizer = PML_HTMLizer()
html += hizer.parse_pml(pml, 'index.html')
toc = hizer.get_toc()
if self.header_record.footnote_count > 0:
html += '<br /><h1>%s</h1>' % _('Footnotes')
footnoteids = re.findall(
'\\w+(?=\x00)', self.section_data(self.header_record.footnote_offset).decode('cp1252' if self.encoding is None else self.encoding))
for fid, i in enumerate(range(self.header_record.footnote_offset + 1, self.header_record.footnote_offset + self.header_record.footnote_count)):
self.log.debug('Extracting footnote page %i' % i)
if fid < len(footnoteids):
fid = footnoteids[fid]
else:
fid = ''
html += footnote_to_html(fid, self.decompress_text(i))
if self.header_record.sidebar_count > 0:
html += '<br /><h1>%s</h1>' % _('Sidebar')
sidebarids = re.findall(
'\\w+(?=\x00)', self.section_data(self.header_record.sidebar_offset).decode('cp1252' if self.encoding is None else self.encoding))
for sid, i in enumerate(range(self.header_record.sidebar_offset + 1, self.header_record.sidebar_offset + self.header_record.sidebar_count)):
self.log.debug('Extracting sidebar page %i' % i)
if sid < len(sidebarids):
sid = sidebarids[sid]
else:
sid = ''
html += sidebar_to_html(sid, self.decompress_text(i))
html += '</body></html>'
with CurrentDir(output_dir):
with open('index.html', 'wb') as index:
self.log.debug('Writing text to index.html')
index.write(html.encode('utf-8'))
if not os.path.exists(os.path.join(output_dir, 'images/')):
os.makedirs(os.path.join(output_dir, 'images/'))
images = []
with CurrentDir(os.path.join(output_dir, 'images/')):
for i in range(0, self.header_record.num_image_pages):
name, img = self.get_image(self.header_record.image_data_offset + i)
images.append(name)
with open(name, 'wb') as imgf:
self.log.debug('Writing image %s to images/' % name)
imgf.write(img)
opf_path = self.create_opf(output_dir, images, toc)
return opf_path
def extract_content(self, output_dir):
from calibre.ebooks.pml.pmlconverter import footnote_to_html, sidebar_to_html
from calibre.ebooks.pml.pmlconverter import PML_HTMLizer
output_dir = os.path.abspath(output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
title = self.mi.title
if not isinstance(title, unicode):
title = title.decode('utf-8', 'replace')
html = u'<html><head><title>%s</title></head><body>' % title
pml = u''
for i in range(1, self.header_record.num_text_pages + 1):
self.log.debug('Extracting text page %i' % i)
pml += self.get_text_page(i)
hizer = PML_HTMLizer()
html += hizer.parse_pml(pml, 'index.html')
toc = hizer.get_toc()
if self.header_record.footnote_count > 0:
html += '<br /><h1>%s</h1>' % _('Footnotes')
footnoteids = re.findall('\w+(?=\x00)', self.section_data(self.header_record.footnote_offset).decode('cp1252' if self.encoding is None else self.encoding))
for fid, i in enumerate(range(self.header_record.footnote_offset + 1, self.header_record.footnote_offset + self.header_record.footnote_count)):
self.log.debug('Extracting footnote page %i' % i)
if fid < len(footnoteids):
fid = footnoteids[fid]
else:
fid = ''
html += footnote_to_html(fid, self.decompress_text(i))
if self.header_record.sidebar_count > 0:
html += '<br /><h1>%s</h1>' % _('Sidebar')
sidebarids = re.findall('\w+(?=\x00)', self.section_data(self.header_record.sidebar_offset).decode('cp1252' if self.encoding is None else self.encoding))
for sid, i in enumerate(range(self.header_record.sidebar_offset + 1, self.header_record.sidebar_offset + self.header_record.sidebar_count)):
self.log.debug('Extracting sidebar page %i' % i)
if sid < len(sidebarids):
sid = sidebarids[sid]
else:
sid = ''
html += sidebar_to_html(sid, self.decompress_text(i))
html += '</body></html>'
with CurrentDir(output_dir):
with open('index.html', 'wb') as index:
self.log.debug('Writing text to index.html')
index.write(html.encode('utf-8'))
if not os.path.exists(os.path.join(output_dir, 'images/')):
os.makedirs(os.path.join(output_dir, 'images/'))
images = []
with CurrentDir(os.path.join(output_dir, 'images/')):
for i in range(0, self.header_record.num_image_pages):
name, img = self.get_image(self.header_record.image_data_offset + i)
images.append(name)
with open(name, 'wb') as imgf:
self.log.debug('Writing image %s to images/' % name)
imgf.write(img)
opf_path = self.create_opf(output_dir, images, toc)
return opf_path
