def process_text(self, text):
try:
tree = fromstring(clean_html(text))
except etree.XMLSyntaxError:
return xhtmlim(text)
self._parse_element(tree)
return html2md(etree.tostring(tree, method="xml", encoding=unicode))
def process_text(self, text):
try:
tree = fromstring(clean_html(text))
except etree.XMLSyntaxError:
return xhtmlim(text)
for el in tree.find_class('tags'):
el.drop_tree()
self._parse_element(tree)
return html2md(etree.tostring(tree, method="xml", encoding=unicode))
def process_node_body(self, html):
try:
html = autolink(html_cleaner.clean_html(html))
#To stay on the safe side escape all % characters
html = html.replace(u"%", u"%%")
doc = filter_style(fromstring(html))
for el in doc.iter(u'img'):
src = el.get(u"src").replace(u"%%", u"%")
if not src:
el.getparent().remove(el)
if src.startswith(djsettings.APP_URL):
src.replace(djsettings.APP_URL, u"/", 1)
if src.startswith(djsettings.MEDIA_URL):
elem_id = el.get(u"id")
try:
if elem_id and elem_id.startswith(self.image_id_prefix):
image_id = int(elem_id.replace(self.image_id_prefix, ""))
image = Image.objects.get(id=image_id)
self.existing_images.append(image)
self.set_image_attributes(el, image)
continue
except:
logger.error(u'Malformed id (%s)found on our own img url %s' % (elem_id, src))
try:
image = Image.objects.get(image=src.replace(djsettings.MEDIA_URL,u""))
self.set_image_attributes(el, image)
self.existing_images.append(image)
continue
except:
logger.error(u'Unable to locate img stored under url %s in Image table' % src)
if src.startswith(u"/"):
src = src.replace(u"/", djsettings.APP_URL, 1)
image_file = download_image_file(src)
image = Image(image=image_file, upload_url=src)
image.save()
self.new_images.append(image)
self.set_image_attributes(el, image)
return etree.tounicode(doc, method="html")
except ValidationError:
for image in self.new_images:
image.delete()
raise
except Exception:
logger.exception(u'Unhandled exception while parsing "%s" body' % html)
for image in self.new_images:
image.delete()
raise ValidationError(_(u"Unexpected error happened :("))
def process_entry(self, entry):
out = super(LorFeedProcessor, self).process_entry(entry)
out['tags'] = []
tree = fromstring(entry['summary'])
for el in tree.find_class('tags'):
for t in el.find_class('tag'):
out['tags'].append(t.text.strip())
return out
def process_text(self, text):
try:
tree = fromstring(clean_html(text))
except etree.XMLSyntaxError:
return xhtmlim(text)
rm = False
for el in tree.iterchildren():
if el.tag.lower() == 'a' and el.get('name').lower().startswith('cutid'):
rm = True
if rm:
el.drop_tree()
self._parse_element(tree)
return html2md(etree.tostring(tree, method="xml", encoding=unicode))
