def _single_convert(self, input_file_object):
if input_file_object:
input_file_path = input_file_object.get_input_file_path()
output_file_name = rename_filename_with_extension(
os.path.basename(input_file_path), self.final_format)
intermediate_filename = str(time.time()).replace('.', '') + '.html'
output_file_path = os.path.join(self.tmp_dir, output_file_name)
intermediate_path = os.path.join(
self.tmp_dir, intermediate_filename)
with codecs.open(input_file_path, "r", "utf-8") as f:
cleaned_content = remove_tags(f.read())
with open(intermediate_path, 'w') as w:
w.write(cleaned_content)
converter = CONVERTER_LOCATION.format(
input_file_path=intermediate_path,
output_file_path=output_file_path)
self.execute(converter)
if os.path.isfile(output_file_path):
return output_file_path
else:
self.handle_failed_conversion(input_file_object)
log.error('Conversion failed from HTML => PDF')
return None
def _single_convert(self, input_file_object):
if input_file_object:
input_file_path = input_file_object.get_input_file_path()
log.info('Converting {} to TXT'.format(input_file_path))
html_to_text = html2text.HTML2Text()
html_to_text.ignore_links = html_to_text.ignore_images = True
try:
input_stream = input_file_object.get_input_stream()
except UnicodeDecodeError, e:
self.handle_failed_conversion(input_file_object)
log.error(
'Conversion failed from HTML => TXT for {} {}'.format(
input_file_path, e)
)
return None
soup = BeautifulSoup(input_stream)
invalid_attrs = 'href src width height target \
style color face size script'.split()
for attr in invalid_attrs:
[dom_el.extract() for dom_el in soup(attr)]
input_stream = unicode(soup)
try:
output_stream = html_to_text.handle(input_stream)
except e:
self.handle_failed_conversion(input_file_object)
log.error(
'Conversion failed from HTML => TXT for {} {}'.format(
input_file_path, e)
)
return None
output_file_name = rename_filename_with_extension(
os.path.basename(input_file_object.get_input_file_path()),
self.final_format)
output_file_path = os.path.join(self.tmp_dir, output_file_name)
write_stream(output_file_path, output_stream)
if os.path.isfile(output_file_path):
return output_file_path
else:
self.handle_failed_conversion(input_file_object)
def _single_convert(self, input_file_object):
if input_file_object:
input_file = input_file_object.get_input_file_path()
output_file_name = rename_filename_with_extension(
os.path.basename(input_file), self.final_format)
output_file_path = os.path.join(self.tmp_dir, output_file_name)
converter = CONVERTER_LOCATION.format(input_file_path=input_file,
output_file_dir=self.tmp_dir)
self.execute(converter)
if os.path.isfile(output_file_path):
return output_file_path
else:
self.handle_failed_conversion(input_file_object)
log.error('Conversion failed from PDF => HTML')
return None
def _single_convert(self, input_file_object):
if input_file_object:
input_file_path = input_file_object.get_input_file_path()
log.info('Converting {} to TXT'.format(input_file_path))
html_to_text = html2text.HTML2Text()
html_to_text.ignore_links = html_to_text.ignore_images = True
try:
input_stream = input_file_object.get_input_stream()
except UnicodeDecodeError, e:
self.handle_failed_conversion(input_file_object)
log.error(
'Conversion failed from HTML => TXT for {} {}'.format(
input_file_path, e))
return None
soup = BeautifulSoup(input_stream)
invalid_attrs = 'href src width height target \
style color face size script'.split()
for attr in invalid_attrs:
[dom_el.extract() for dom_el in soup(attr)]
input_stream = unicode(soup)
try:
output_stream = html_to_text.handle(input_stream)
except e:
self.handle_failed_conversion(input_file_object)
log.error(
'Conversion failed from HTML => TXT for {} {}'.format(
input_file_path, e))
return None
output_file_name = rename_filename_with_extension(
os.path.basename(input_file_object.get_input_file_path()),
self.final_format)
output_file_path = os.path.join(self.tmp_dir, output_file_name)
write_stream(output_file_path, output_stream)
if os.path.isfile(output_file_path):
return output_file_path
else:
self.handle_failed_conversion(input_file_object)
def _single_convert(self, input_file_object):
if input_file_object:
input_file_path = input_file_object.get_input_file_path()
output_file_name = rename_filename_with_extension(
os.path.basename(input_file_path), 'pdf')
output_file_path = self.tmp_dir
converter = CONVERTER_LOCATION.format(
output_file_path=output_file_path,
input_file_path=input_file_path)
self.execute(converter)
output_file = os.path.join(output_file_path, output_file_name)
if os.path.isfile(output_file):
return output_file
else:
self.handle_failed_conversion(input_file_object)
log.error('Conversion failed from DOC => PDF')
return None
def _single_convert(self, input_file_object):
if input_file_object:
input_file_path = input_file_object.get_input_file_path()
output_file_name = rename_filename_with_extension(
os.path.basename(input_file_path), 'pdf')
output_file_path = TMP_DIR
converter = CONVERTER_LOCATION.format(
output_file_path=output_file_path,
input_file_path=input_file_path)
self.execute(converter)
output_file = os.path.join(output_file_path, output_file_name)
if os.path.isfile(output_file):
return output_file
else:
self.handle_failed_conversion(input_file_path)
log.error('Conversion failed from RTF => PDF')
return None
def _single_convert(self, input_file_object):
if input_file_object:
input_stream = input_file_object.get_input_stream()
try:
output_stream = markdown2.markdown(input_stream)
except:
print "Conversion Unsuccessfull for txt_html"
return None
output_file_name = rename_filename_with_extension(
os.path.basename(input_file_object.get_input_file_path()),
self.final_format)
output_file_path = os.path.join(self.tmp_dir, output_file_name)
write_stream(output_file_path, output_stream)
if os.path.isfile(output_file_path):
return output_file_path
else:
self.handle_failed_conversion(input_file_object)
log.error('Conversion failed from TXT => HTML')
return None
def get_remote_location(self):
filename = rename_filename_with_extension(self.file_instance.filename,
self.output_format)
return os.path.join(app.config['REMOTE_DUMP_FOLDER'], self.doc_id,
filename)