def metablock(parsed): """ Remove HTML tags, entities and superfluous characters from meta blocks. """ parsed = " ".join(parsed.replace("\n", "").split()).replace(" ,", ",") return escape(strip_tags(decode_entities(parsed)))
def add_post(self, title=None, content=None, old_url=None, pub_date=None, tags=None, categories=None, comments=None): """ Adds a post to the post list for processing. - ``title`` and ``content`` are strings for the post. - ``old_url`` is a string that a redirect will be created for. - ``pub_date`` is assumed to be a ``datetime`` object. - ``tags`` and ``categories`` are sequences of strings. - ``comments`` is a sequence of dicts - each dict should be the return value of ``add_comment``. """ if not title: title = strip_tags(content).split(". ")[0] title = decode_entities(title) if categories is None: categories = [] if tags is None: tags = [] if comments is None: comments = [] self.posts.append({ "title": force_text(title), "publish_date": pub_date, "content": force_text(content), "categories": categories, "tags": tags, "comments": comments, "old_url": old_url, }) return self.posts[-1]
def add_post(self, title=None, pub_date=None, tags=None, content=None, comments=None, old_url=None, categories=None): """ Adds a post to the post list for processing. Attributes: pub_date is assumed to be a datetime object. """ if not title: title = decode_entities(strip_tags(content).split(". ")[0]) if categories is None: categories = [] if tags is None: tags = [] if comments is None: comments = [] self.posts.append({ "title": title, "publish_date": pub_date, "content": content, "categories": categories, "tags": tags, "comments": comments, "old_url": old_url, }) return self.posts[-1]
def metablock(context, nodelist): """ Remove HTML tags, entities and superfluous characters from meta blocks. """ parsed = nodelist.render(context) parsed = " ".join(parsed.replace("\n", "").split()).replace(" ,", ",") return strip_tags(decode_entities(parsed))
def add_page(self, title=None, content=None, old_url=None, tags=None, old_id=None, old_parent_id=None): """ Adds a page to the list of pages to be imported - used by the Wordpress importer. """ if not title: text = decode_entities(strip_tags(content)).replace("\n", " ") title = text.split(". ")[0] if tags is None: tags = [] self.pages.append({ "title": title, "content": content, "tags": tags, "old_url": old_url, "old_id": old_id, "old_parent_id": old_parent_id, })
def metablock(parsed): """ Remove HTML tags, entities and superfluous characters from meta blocks. """ parsed = " ".join(parsed.replace("\n", "").split()).replace(" ,", ",") return strip_tags(decode_entities(parsed))