def html_after_read(self, book, chapter):
if not chapter.content:
return None
(_, chapter.content) = tidy_cleanup(chapter.get_content(), **self.options)
return chapter.content
def html_after_read(self, book, chapter):
if not chapter.content:
return None
(_, chapter.content) = tidy_cleanup(chapter.get_content(),
**self.options)
return chapter.content
def _fix_merged_content(self, content):
"""
After concatenated content, we need to make sure the structure of chapter is correct.
For example: endnotes should always go at the end of the chapter and fix endnotes references
Args:
- content (`str`) chapter's html string content
"""
# there might be some cases where the html content of the chapter it's no fully clean
# because of old importer class. Let's apply some cleanup just in case
content = tidy_cleanup(content, **TidyPlugin.OPTIONS)[1]
utf8_parser = html.HTMLParser(encoding='utf-8')
tree = html.document_fromstring(content, parser=utf8_parser)
# first we check if there are endnotes
endnotes = tree.xpath('.//ol[@class="endnotes"]')
if len(endnotes) == 0:
return content
# let's create a new final block of endnotes to merge them all
endnotes_block = etree.SubElement(tree.find('body'), 'ol',
{'class': 'endnotes'})
idx_endnote = 1
for note in tree.xpath('.//li[starts-with(@id, "endnote-")]'):
key = note.get('id', '').replace('endnote-', '')
# let's find the reference, otherwise we delete the endnote
try:
sup = tree.xpath('//sup[@data-id="{}"]'.format(key))[0]
except IndexError:
self.notifier.warning(
_("Reference not found for endnote: {}").format(note.text))
continue
# make sure reference number is correct
sup.text = '{}'.format(idx_endnote)
idx_endnote += 1
endnotes_block.append(note)
# remove old endnotes block from content
for oldblock in endnotes:
oldblock.drop_tree()
# let's use only body and its content
return etree.tostring(tree.find('body'),
encoding='utf-8',
xml_declaration=False)