name, ext = os.path.splitext(fname)
if ext.lower() == ".html":
logger.info("Deleting html file: %s", f['id'])
num_html_deleted += 1
omeka_client.delete('files', f['id'])
#Second pass do the conversion if required
if not args['do_not_convert']:
for f in omeka_client.get_files_for_item(item['id']):
fname = f['original_filename']
name, ext = os.path.splitext(fname)
if ext.lower() in [".docx", ".doc", ".odt", ".rtf"]:
num_docs_found += 1
res, data = omeka_client.get_file(f['file_urls']['original'])
download_file = os.path.join(temp_dir, fname)
out = open(download_file, 'wb')
out.write(data)
out.close()
logger.info("Converting office doc file %s to HTML", f['id'])
out_dir, x = os.path.split(download_file)
html_file = os.path.join(temp_dir, name + ".html")
word2html.convert(download_file, html_file , True, True, False)
if omeka_client.post_file_from_filename(html_file, item['id']):
num_html_uploaded += 1
logger.info("Uploaded %s successfully", f['id'])
logger.info("********************")
name, ext = os.path.splitext(fname)
if ext.lower() == ".html":
logger.info("Deleting html file: %s", f['id'])
num_html_deleted += 1
omeka_client.delete('files', f['id'])
#Second pass do the conversion if required
if not args['do_not_convert']:
for f in omeka_client.get_files_for_item(item['id']):
fname = f['original_filename']
name, ext = os.path.splitext(fname)
if ext.lower() in [".docx", ".doc", ".odt", ".rtf"]:
num_docs_found += 1
res, data = omeka_client.get_file(f['file_urls']['original'])
download_file = os.path.join(temp_dir, fname)
out = open(download_file, 'wb')
out.write(data)
out.close()
logger.info("Converting office doc file %s to HTML", f['id'])
out_dir, x = os.path.split(download_file)
html_file = os.path.join(temp_dir, name + ".html")
word2html.convert(download_file, html_file, True, True, False)
if omeka_client.post_file_from_filename(html_file, item['id']):
num_html_uploaded += 1
logger.info("Uploaded %s successfully", f['id'])
logger.info("********************")
logger.info("SUMMARY:")
