How to use the youtube-dl.youtube_dl.utils.clean_html function in youtube_dl

def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)

        m_error = re.search(
            r'<div class="block-error">\s*<div class="heading">\s*<div>(?P.+?)</div>\s*</div>', webpage)
        if m_error:
            raise ExtractorError(clean_html(m_error.group('msg')), expected=True)

        video_title = None
        duration = None
        video_thumbnail = None
        formats = []

        # most of the information is stored in the flashvars
        flashvars = self._html_search_regex(
            r'flashvars="(.+?)"', webpage, 'flashvars')

        infos = compat_urllib_parse_unquote(flashvars).split(r'&amp;')
        for info in infos:
            videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
            if videovars_match:
                key = videovars_match.group(1)
                val = videovars_match.group(2)</div>

def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
        """
        Like _search_regex, but strips HTML tags and unescapes entities.
        """
        res = self._search_regex(pattern, string, name, default, fatal, flags, group)
        if res:
            return clean_html(res).strip()
        else:
            return res

if cc_json:
            for closed_caption in cc_json:
                lang = closed_caption['lang']
                if lang not in subtitles:
                    subtitles[lang] = []
                subtitles[lang].append({
                    'url': closed_caption['url'],
                    'ext': mimetype2ext(closed_caption['content_type']),
                })

        return {
            'id': video_id,
            'display_id': display_id,
            'title': unescapeHTML(meta['title']),
            'formats': formats,
            'description': clean_html(meta['description']),
            'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage),
            'duration': int_or_none(meta.get('duration')),
            'subtitles': subtitles,
        }

post_id = self._match_id(url)

        wall_url = 'https://vk.com/wall%s' % post_id

        post_id = remove_start(post_id, '-')

        webpage = self._download_webpage(wall_url, post_id)

        error = self._html_search_regex(
            r'>Error\s*]+class=["\']body["\'][^>]*>([^<]+)',
            webpage, 'error', default=None)
        if error:
            raise ExtractorError('VK said: %s' % error, expected=True)

        description = clean_html(get_element_by_class('wall_post_text', webpage))
        uploader = clean_html(get_element_by_class('author', webpage))
        thumbnail = self._og_search_thumbnail(webpage)

        entries = []

        audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage)
        if audio_ids:
            al_audio = self._download_webpage(
                'https://vk.com/al_audio.php', post_id,
                note='Downloading audio info', fatal=False,
                data=urlencode_postdata({
                    'act': 'reload_audio',
                    'al': '1',
                    'ids': ','.join(audio_ids)
                }))
            if al_audio:
                Audio = collections.namedtuple(

def _real_extract(self, url):
        album_id = self._match_id(url)

        webpage = self._download_webpage(
            url, album_id, note='Download album info',
            errnote='Unable to get album info')

        album_name = self._html_search_regex(
            r']+class="comm"[^<]+]+title="([^"]+)"', webpage,
            'album name')
        album_intro = remove_start(
            clean_html(get_element_by_id('intro', webpage)),
            '%s简介：' % album_name)

        entries = [
            self.url_result(song_url, 'Kuwo') for song_url in re.findall(
                r']+class="listen">]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
                webpage)
        ]
        return self.playlist_result(entries, album_id, album_name, album_intro)

login_form.update({
            'username': username,
            'password': password,
        })

        post_url = urljoin(self._LOGIN_URL, self._search_regex(
            r']+action=(["\'])(?P.+?)\1', login_page,
            'post url', default=self._LOGIN_URL, group='url'))

        response, urlh = self._download_webpage_handle(
            post_url, None, 'Logging in', data=urlencode_postdata(login_form),
            headers={'Referer': self._LOGIN_URL})

        if self._LOGIN_URL in urlh.geturl():
            error = clean_html(get_element_by_class('form-message', response))
            if error:
                raise ExtractorError(
                    'Unable to login: %s' % error, expected=True)
            raise ExtractorError('Unable to log in')

video_title = self._html_search_regex(
            r']*class="uiHeaderTitle"[^>]*>([^<]*)', webpage,
            'title', default=None)
        if not video_title:
            video_title = self._html_search_regex(
                r'(?s)<span class="fbPhotosPhotoCaption"><span class="hasCaption">(.*?)</span>',
                webpage, 'alternative title', default=None)
        if not video_title:
            video_title = self._html_search_meta(
                'description', webpage, 'title', default=None)
        if video_title:
            video_title = limit_length(video_title, 80)
        else:
            video_title = 'Facebook video #%s' % video_id
        uploader = clean_html(get_element_by_id(
            'fbPhotoPageAuthorName', webpage)) or self._search_regex(
            r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
        timestamp = int_or_none(self._search_regex(
            r']+data-utime=["\'](\d+)', webpage,
            'timestamp', default=None))
        thumbnail = self._og_search_thumbnail(webpage)

        info_dict = {
            'id': video_id,
            'title': video_title,
            'formats': formats,
            'uploader': uploader,
            'timestamp': timestamp,
            'thumbnail': thumbnail,
        }
</span>

if subtitle:
            title += ' - %s' % subtitle
        title = title.strip()

        subtitles = {}
        subtitles_list = [{
            'url': subformat['url'],
            'ext': subformat.get('format'),
        } for subformat in info.get('subtitles', []) if subformat.get('url')]
        if subtitles_list:
            subtitles['fr'] = subtitles_list

        return {
            'id': video_id,
            'title': self._live_title(title) if is_live else title,
            'description': clean_html(info['synopsis']),
            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
            'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
            'timestamp': int_or_none(info['diffusion']['timestamp']),
            'is_live': is_live,
            'formats': formats,
            'subtitles': subtitles,
        }