python类strip_tags()的实例源码

def __str__(self):
        # Return the first few words of the content (with tags stripped)
        return Truncator(strip_tags(self.text)).words(10, truncate=' ...')

def clean_text(text):
    return strip_tags(force_text(text)).replace("\n\n\n", "\n\n").strip()

def item_description(self, item):
        content = strip_tags(getattr(item, self.item_description_field))
        return content

def __str__(self):
        return Truncator(strip_tags(self.body)).words(3, truncate="...")

def _format_value(self, key, value):
        if value:
            try:
                return strip_tags(str(value))
            except (TypeError, ValueError):
                pass

def item_title(self, item):
        """ ????????? ???????? """
        return strip_tags(item.text)

def get_info(cls, video_key):
        req = request.Request('http://vimeo.com/api/v2/video/%s.xml' % video_key, method='GET')
        try:
            logger.debug('{0.method} {0.full_url}'.format(req))
            response = request.urlopen(req, timeout=3)
        except error.URLError:
            return None

        if response.status != 200:
            return None

        dom = minidom.parseString(response.read())
        title = dom.getElementsByTagName('title').item(0)
        description = dom.getElementsByTagName('description').item(0)
        description = description.firstChild.data
        description = re.sub(r'<br\s*/?>\s*', '\n', description)
        thumbnail_large = dom.getElementsByTagName('thumbnail_large').item(0)
        width = dom.getElementsByTagName('width').item(0)
        width = int(width.firstChild.data)
        height = dom.getElementsByTagName('height').item(0)
        height = int(height.firstChild.data)
        embed_width = min(640, width)
        embed_height = int(embed_width * height / width)
        code = '<iframe src="//player.vimeo.com/video/{}" ' \
               'width="{}" height="{}" frameborder="0" ' \
               'webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>'
        return {
            'title': title.firstChild.data,
            'description': strip_tags(description),
            'preview_url': thumbnail_large.firstChild.data.replace('webp', 'jpg'),
            'embed': code.format(video_key, embed_width, embed_height)
        }

def clean(html, autoescape=None):
    """
        ????? ??? ???? ????????: striptags, linebreaksbr, typograf, safe
    """
    text = strip_tags(str(html))
    text = defaultfilters.linebreaksbr(text, autoescape=autoescape)
    text = typograf(text)
    return mark_safe(text)

def words_wo_stopwords(text):
    """
    Cleans text from stop words.
    """
    nltk_stopwords_list = stopwords.words('english')
    specifics = load_stop_words(stop_word_file=join(settings.BASE_DIR, "aggregator", 'data', 'stop_words.txt'))

    stopwords_list = list(set(nltk_stopwords_list + specifics + ["'s", "n't"]))

    words = word_tokenize(strip_tags(text))
    cleaned = [w for w in words if not w.lower() in stopwords_list]
    text = " ".join(cleaned)

    return text

def item_description(self, item):
        text = item.summary or ""
        return strip_tags(text)

def make_summaries(title):
    book = Books.objects.get(title=title)

    try:
        book.summary = await summarizer(data=strip_tags(book.review), sentences=(settings.SUMMARIZER_SENTENCES+3))
        book.save()
        print("Amazon summary saved to database: {0}".format(book.summary))
    except Exception as e:
        print(colored.red("[ERROR] At Amazon summary: {0}".format(e)))

def processs_content(post):
    text = words_wo_stopwords(strip_tags(post.content))
    #TODO this is duplicated job, should be improved
    words = word_tokenize(strip_tags(text))
    taggged = pos_tag(words)
    cleaned = filter_insignificant(taggged)
    text = " ".join(cleaned)
    wc = WordCloudMod().generate(text)
    result = list(wc.keys())[:10]

    if len(result) > 0:
        post = await save_tags(tags=result, entry=post)
        post.save()

def get_ttachment(post, data):
    attachment =  {
        'name': data['title'],
        'link': '{0}{1}/'.format(settings.DOMAIN, post.slug)
    }

    sentiment = post.sentiment or "N/A"
    summary = post.summary or ""
    attachment['description'] = strip_tags(summary) + " " + sentiment
    if post.image:
        attachment['picture'] = '{0}{1}'.format(settings.DOMAIN, post.image)

    return attachment

def save(self, *args, **kwargs):
        same_slug = True
        counter = 1
        while same_slug:
            same_slug = Post.objects.filter(slug=self.slug)
            if same_slug:
                self.slug += '_' + str(counter)
                counter += 1
            else:
                break
        self.short_content = strip_tags(self.content)[:100] + "..."
        super(Post, self).save(*args, **kwargs)

def send_multipart_email(subject, html_template, from_email, to_email):
    html = render_to_string(html_template)
    text_content = strip_tags(html)
    msg = EmailMultiAlternatives(subject, text_content, from_email, to_email)
    msg.attach_alternative(html, "text/html")
    msg.send()

def html2text(htmltext):
    text = HTMLParser().unescape(strip_tags(htmltext))
    text = '\n\n'.join(re.split(r'\s*\n\s*\n\s*', text))
    text = re.sub('\s\s\s+', ' ', text)
    wrapper = textwrap.TextWrapper(
        replace_whitespace=False, drop_whitespace=False, width=72)
    return '\n'.join(wrapper.wrap(text))

def plain(self):
        if not self._plain:
            self._plain = strip_tags(self.body)
        return self._plain

def __str__(self):
        return Truncator(strip_tags(self.text)).words(20)

def raw_text(self):
        return strip_tags(self.note_text)

    # title to display in list (either self.title or beginning of text if no title)