How to use youtube_dl - 10 common examples

'vcodec': 'none',
                    'ext': ext,
                })
            else:
                height = int_or_none(source.get('height'))
                if height is None:
                    # Often no height is provided but there is a label in
                    # format like "1080p", "720p SD", or 1080.
                    height = int_or_none(self._search_regex(
                        r'^(\d{3,4})[pP]?(?:\b|$)', compat_str(source.get('label') or ''),
                        'height', default=None))
                a_format = {
                    'url': source_url,
                    'width': int_or_none(source.get('width')),
                    'height': height,
                    'tbr': int_or_none(source.get('bitrate')),
                    'ext': ext,
                }
                if source_url.startswith('rtmp'):
                    a_format['ext'] = 'flv'
                    # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
                    # of jwplayer.flash.swf
                    rtmp_url_parts = re.split(
                        r'((?:mp4|mp3|flv):)', source_url, 1)
                    if len(rtmp_url_parts) == 3:
                        rtmp_url, prefix, play_path = rtmp_url_parts
                        a_format.update({
                            'url': rtmp_url,
                            'play_path': prefix + play_path,
                        })
                    if rtmp_params:
                        a_format.update(rtmp_params)

try_get,
)
from .dailymotion import DailymotionIE


class FranceTVBaseInfoExtractor(InfoExtractor):
    def _make_url_result(self, video_or_full_id, catalog=None):
        full_id = 'francetv:%s' % video_or_full_id
        if '@' not in video_or_full_id and catalog:
            full_id += '@%s' % catalog
        return self.url_result(
            full_id, ie=FranceTVIE.ie_key(),
            video_id=video_or_full_id.split('@')[0])


class FranceTVIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                    (?:
                        https?://
                            sivideo\.webservices\.francetelevisions\.fr/tools/getInfosOeuvre/v2/\?
                            .*?\bidDiffusion=[^&]+|
                        (?:
                            https?://videos\.francetv\.fr/video/|
                            francetv:
                        )
                        (?P[^@]+)(?:@(?P.+))?
                    )
                    '''

    _TESTS = [{
        # without catalog
        'url': 'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=162311093&callback=_jsonp_loader_callback_request_0',

def _extract_from_json_url(self, json_url, video_id, lang, title=None):
        info = self._download_json(json_url, video_id)
        player_info = info['videoJsonPlayer']

        vsr = try_get(player_info, lambda x: x['VSR'], dict)
        if not vsr:
            error = None
            if try_get(player_info, lambda x: x['custom_msg']['type']) == 'error':
                error = try_get(
                    player_info, lambda x: x['custom_msg']['msg'], compat_str)
            if not error:
                error = 'Video %s is not available' % player_info.get('VID') or video_id
            raise ExtractorError(error, expected=True)

        upload_date_str = player_info.get('shootingDate')
        if not upload_date_str:
            upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]

        title = (player_info.get('VTI') or title or player_info['VID']).strip()
        subtitle = player_info.get('VSU', '').strip()
        if subtitle:
            title += ' - %s' % subtitle

        info_dict = {
            'id': player_info['VID'],
            'title': title,

'description': xpath_text(item, 'description'),
                'timestamp': timestamp,
                'duration': int_or_none(content.get('duration')),
                'age_limit': parse_age_limit(xpath_text(item, _add_ns('media:rating'))),
                'episode': xpath_text(item, _add_ns('clearleap:episode')),
                'episode_number': int_or_none(xpath_text(item, _add_ns('clearleap:episodeInSeason'))),
                'series': xpath_text(item, _add_ns('clearleap:series')),
                'season_number': int_or_none(xpath_text(item, _add_ns('clearleap:season'))),
                'thumbnails': thumbnails,
                'ie_key': 'CBCWatchVideo',
            })

        return self.playlist_result(
            entries, xpath_text(channel, 'guid'),
            xpath_text(channel, 'title'),
            xpath_text(channel, 'description'))

media_url = None
                # @href is introduced in 2.0, see section 11.6 of F4M spec
                if manifest_version == '2.0':
                    media_url = media_el.attrib.get('href')
                if media_url is None:
                    media_url = media_el.attrib.get('url')
                if not media_url:
                    continue
                manifest_url = (
                    media_url if media_url.startswith('http://') or media_url.startswith('https://')
                    else ((manifest_base_url or '/'.join(manifest_url.split('/')[:-1])) + '/' + media_url))
                # If media_url is itself a f4m manifest do the recursive extraction
                # since bitrates in parent manifest (this one) and media_url manifest
                # may differ leading to inability to resolve the format by requested
                # bitrate in f4m downloader
                ext = determine_ext(manifest_url)
                if ext == 'f4m':
                    f4m_formats = self._extract_f4m_formats(
                        manifest_url, video_id, preference=preference, f4m_id=f4m_id,
                        transform_source=transform_source, fatal=fatal)
                    # Sometimes stream-level manifest contains single media entry that
                    # does not contain any quality metadata (e.g. http://matchtv.ru/#live-player).
                    # At the same time parent's media entry in set-level manifest may
                    # contain it. We will copy it from parent in such cases.
                    if len(f4m_formats) == 1:
                        f = f4m_formats[0]
                        f.update({
                            'tbr': f.get('tbr') or tbr,
                            'width': f.get('width') or width,
                            'height': f.get('height') or height,
                            'format_id': f.get('format_id') if not tbr else format_id,
                            'vcodec': vcodec,

})
                formats.append(fmt)

        if not formats and video.get('is_geo_blocked'):
            self.raise_geo_restricted(
                'This content might not be available in your country due to copyright reasons')

        self._sort_formats(formats)

        # TODO: webvtt in m3u8
        subtitles = {}
        sami_path = video.get('sami_path')
        if sami_path:
            lang = self._search_regex(
                r'_([a-z]{2})\.xml', sami_path, 'lang',
                default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
            subtitles[lang] = [{
                'url': sami_path,
            }]

        series = video.get('format_title')
        episode_number = int_or_none(video.get('format_position', {}).get('episode'))
        season = video.get('_embedded', {}).get('season', {}).get('title')
        season_number = int_or_none(video.get('format_position', {}).get('season'))

        return {
            'id': video_id,
            'title': title,
            'description': video.get('description'),
            'series': series,
            'episode_number': episode_number,
            'season': season,

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 _extract_video_formats(self, mdoc, mtvn_id, video_id):
        if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None:
            if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
                self.to_screen('The normal version is not available from your '
                               'country, trying with the mobile version')
                return self._extract_mobile_video_formats(mtvn_id)
            raise ExtractorError('This video is not available from your country.',
                                 expected=True)

        formats = []
        for rendition in mdoc.findall('.//rendition'):
            if rendition.get('method') == 'hls':
                hls_url = rendition.find('./src').text
                formats.extend(self._extract_m3u8_formats(
                    hls_url, video_id, ext='mp4', entry_protocol='m3u8_native',
                    m3u8_id='hls', fatal=False))
            else:
                # fms
                try:
                    _, _, ext = rendition.attrib['type'].partition('/')
                    rtmp_video_url = rendition.find('./src').text
                    if 'error_not_available.swf' in rtmp_video_url:
                        raise ExtractorError(

def _check_error(json_string, key_or_keys):
        keys = [key_or_keys] if isinstance(key_or_keys, compat_str) else key_or_keys
        for key in keys:
            error = json_string.get(key)
            if error:
                raise ExtractorError('Unable to login: %s' % error, expected=True)

def _download_media_selector_url(self, url, programme_id=None):
        try:
            media_selection = self._download_xml(
                url, programme_id, 'Downloading media selection XML')
        except ExtractorError as ee:
            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
                media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
            else:
                raise
        return self._process_media_selector(media_selection, programme_id)