9cf2f9f298
This will remove imports from __future__ that are no longer needed. https://docs.python.org/3.5/library/2to3.html#2to3fixer-future
59 lines
1.6 KiB
Python
59 lines
1.6 KiB
Python
"""
|
|
Annotations Tool Mixin
|
|
This file contains global variables and functions used in the various Annotation Tools.
|
|
"""
|
|
|
|
|
|
from os.path import basename, splitext
|
|
|
|
from lxml import etree
|
|
from six.moves.html_parser import HTMLParser
|
|
from six.moves.urllib.parse import urlparse
|
|
|
|
|
|
def get_instructions(xmltree):
|
|
""" Removes <instructions> from the xmltree and returns them as a string, otherwise None. """
|
|
instructions = xmltree.find('instructions')
|
|
if instructions is not None:
|
|
instructions.tag = 'div'
|
|
xmltree.remove(instructions)
|
|
return etree.tostring(instructions, encoding='unicode')
|
|
return None
|
|
|
|
|
|
def get_extension(srcurl):
|
|
"""get the extension of a given url """
|
|
if 'youtu' in srcurl:
|
|
return 'video/youtube'
|
|
else:
|
|
disassembled = urlparse(srcurl)
|
|
file_ext = splitext(basename(disassembled.path))[1]
|
|
return 'video/' + file_ext.replace('.', '')
|
|
|
|
|
|
class MLStripper(HTMLParser):
|
|
"helper function for html_to_text below"
|
|
def __init__(self):
|
|
HTMLParser.__init__(self)
|
|
self.reset()
|
|
self.fed = []
|
|
|
|
def handle_data(self, data):
|
|
"""takes the data in separate chunks"""
|
|
self.fed.append(data)
|
|
|
|
def handle_entityref(self, name):
|
|
"""appends the reference to the body"""
|
|
self.fed.append('&%s;' % name)
|
|
|
|
def get_data(self):
|
|
"""joins together the seperate chunks into one cohesive string"""
|
|
return ''.join(self.fed)
|
|
|
|
|
|
def html_to_text(html):
|
|
"strips the html tags off of the text to return plaintext"
|
|
htmlstripper = MLStripper()
|
|
htmlstripper.feed(html)
|
|
return htmlstripper.get_data()
|