from subprocess import call
import datetime
from os.path import splitext
import sys
import urllib
file_url = sys.argv[1]
name, extension = splitext(file_url)
ext = str.lower(str(extension))
new_file_name = "document" + ext
urllib.urlretrieve(file_url, new_file_name)
# Convert the .html into a document.
call(["libreoffice", "--headless", "--invisible", "--convert-to", "pdf", new_file_name])
# Now export it to AWS.
from ExportUtilities import ExportUtilities
print ExportUtilities.export_to_aws(
"document.pdf", "ocexportpdf", "document_" + datetime.datetime.now().strftime("%s") + ".pdf"
)
import os
os.remove("document.pdf")
for key in new_colstyles:
new_styles['col.' + col_class][key] = new_colstyles[key]
col['class'] = col_class
del col['style']
col_num += 1
new_styles_string = ''
for key in new_styles:
new_styles_string += key + "{"
for style in new_styles[key]:
new_styles_string += style + ': ' + new_colstyles[style] +';'
new_styles_string += "} "
css = open('pdf_stylesheet.css', 'r').read()
import datetime
s3_filename = dom.h2.get_text() + '_' + datetime.datetime.now().strftime('%s') + '.pdf'
HTML(string=dom.prettify()).write_pdf(s3_filename, stylesheets=[CSS(
string=css+new_styles_string)])
from ExportUtilities import ExportUtilities
print ExportUtilities.export_to_aws(s3_filename, 'ocexportpdf')
import os
os.remove(s3_filename)
from subprocess import call
import datetime
# Convert the .html into a document.
call(['libreoffice', '--headless', '--invisible', '--convert-to', 'odt', 'document.html'])
# Now export it to AWS.
from ExportUtilities import ExportUtilities
print ExportUtilities.export_to_aws(
'document.odt', 'ocexportword', 'document_' + datetime.datetime.now().strftime('%s') + '.odt')
import os
os.remove('document.odt')
