X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/b8d8e13c1f9e4d3cdd7d41c5c9d711a36dd5f9c3..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/radiocanada.py diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index 3b40002..a28b1a2 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -4,131 +4,120 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( - xpath_text, - find_xpath_attr, determine_ext, + ExtractorError, int_or_none, unified_strdate, - xpath_element, - ExtractorError, - determine_protocol, - unsmuggle_url, ) class RadioCanadaIE(InfoExtractor): IE_NAME = 'radiocanada' _VALID_URL = r'(?:radiocanada:|https?://ici\.radio-canada\.ca/widgets/mediaconsole/)(?P[^:/]+)[:/](?P[0-9]+)' - _TEST = { - 'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272', - 'info_dict': { - 'id': '7184272', - 'ext': 'mp4', - 'title': 'Le parcours du tireur capté sur vidéo', - 'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa', - 'upload_date': '20141023', + _TESTS = [ + { + 'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272', + 'info_dict': { + 'id': '7184272', + 'ext': 'mp4', + 'title': 'Le parcours du tireur capté sur vidéo', + 'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa', + 'upload_date': '20141023', + }, + 'params': { + # m3u8 download + 'skip_download': True, + } }, - 'params': { - # m3u8 download - 'skip_download': True, + { + # empty Title + 'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7754998/', + 'info_dict': { + 'id': '7754998', + 'ext': 'mp4', + 'title': 'letelejournal22h', + 'description': 'INTEGRALE WEB 22H-TJ', + 'upload_date': '20170720', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, - } - - def _real_extract(self, url): - url, smuggled_data = unsmuggle_url(url, {}) - app_code, video_id = re.match(self._VALID_URL, url).groups() + { + # with protectionType but not actually DRM protected + 'url': 'radiocanada:toutv:140872', + 'info_dict': { + 'id': '140872', + 'title': 'Épisode 1', + 'series': 'District 31', + }, + 'only_matching': True, + } + ] + _GEO_COUNTRIES = ['CA'] + _access_token = None + _claims = None - metadata = self._download_xml( - 'http://api.radio-canada.ca/metaMedia/v1/index.ashx', - video_id, note='Downloading metadata XML', query={ + def _call_api(self, path, video_id=None, app_code=None, query=None): + if not query: + query = {} + query.update({ + 'client_key': '773aea60-0e80-41bb-9c7f-e6d7c3ad17fb', + 'output': 'json', + }) + if video_id: + query.update({ 'appCode': app_code, 'idMedia': video_id, }) + if self._access_token: + query['access_token'] = self._access_token + try: + return self._download_json( + 'https://services.radio-canada.ca/media/' + path, video_id, query=query) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 422): + data = self._parse_json(e.cause.read().decode(), None) + error = data.get('error_description') or data['errorMessage']['text'] + raise ExtractorError(error, expected=True) + raise + + def _extract_info(self, app_code, video_id): + metas = self._call_api('meta/v1/index.ashx', video_id, app_code)['Metas'] def get_meta(name): - el = find_xpath_attr(metadata, './/Meta', 'name', name) - return el.text if el is not None else None + for meta in metas: + if meta.get('name') == name: + text = meta.get('text') + if text: + return text + # protectionType does not necessarily mean the video is DRM protected (see + # https://github.com/ytdl-org/youtube-dl/pull/18609). if get_meta('protectionType'): - raise ExtractorError('This video is DRM protected.', expected=True) - - device_types = ['ipad'] - if not smuggled_data: - device_types.append('flash') - device_types.append('android') + self.report_warning('This video is probably DRM protected.') - formats = [] - # TODO: extract f4m formats - # f4m formats can be extracted using flashhd device_type but they produce unplayable file - for device_type in device_types: - validation_url = 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx' - query = { - 'appCode': app_code, - 'idMedia': video_id, - 'connectionType': 'broadband', - 'multibitrate': 'true', - 'deviceType': device_type, - } - if smuggled_data: - validation_url = 'https://services.radio-canada.ca/media/validation/v2/' - query.update(smuggled_data) - else: - query.update({ - # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction - 'paysJ391wsHjbOJwvCs26toz': 'CA', - 'bypasslock': 'NZt5K62gRqfc', - }) - v_data = self._download_xml(validation_url, video_id, note='Downloading %s XML' % device_type, query=query, fatal=False) - v_url = xpath_text(v_data, 'url') - if not v_url: - continue - if v_url == 'null': - raise ExtractorError('%s said: %s' % ( - self.IE_NAME, xpath_text(v_data, 'message')), expected=True) - ext = determine_ext(v_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - v_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) - elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - v_url, video_id, f4m_id='hds', fatal=False)) - else: - ext = determine_ext(v_url) - bitrates = xpath_element(v_data, 'bitrates') - for url_e in bitrates.findall('url'): - tbr = int_or_none(url_e.get('bitrate')) - if not tbr: - continue - f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url) - protocol = determine_protocol({'url': f_url}) - f = { - 'format_id': '%s-%d' % (protocol, tbr), - 'url': f_url, - 'ext': 'flv' if protocol == 'rtmp' else ext, - 'protocol': protocol, - 'width': int_or_none(url_e.get('width')), - 'height': int_or_none(url_e.get('height')), - 'tbr': tbr, - } - mobj = re.match(r'(?Prtmp://[^/]+/[^/]+)/(?P[^?]+)(?P\?.+)', f_url) - if mobj: - f.update({ - 'url': mobj.group('url') + mobj.group('auth'), - 'play_path': mobj.group('playpath'), - }) - formats.append(f) - if protocol == 'rtsp': - base_url = self._search_regex( - r'rtsp://([^?]+)', f_url, 'base url', default=None) - if base_url: - base_url = 'http://' + base_url - formats.extend(self._extract_m3u8_formats( - base_url + '/playlist.m3u8', video_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False)) - formats.extend(self._extract_f4m_formats( - base_url + '/manifest.f4m', video_id, - f4m_id='hds', fatal=False)) + query = { + 'connectionType': 'hd', + 'deviceType': 'ipad', + 'multibitrate': 'true', + } + if self._claims: + query['claims'] = self._claims + v_data = self._call_api('validation/v2/', video_id, app_code, query) + v_url = v_data.get('url') + if not v_url: + error = v_data['message'] + if error == "Le contenu sélectionné n'est pas disponible dans votre pays": + raise self.raise_geo_restricted(error, self._GEO_COUNTRIES) + if error == 'Le contenu sélectionné est disponible seulement en premium': + self.raise_login_required(error) + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, error), expected=True) + formats = self._extract_m3u8_formats(v_url, video_id, 'mp4') self._sort_formats(formats) subtitles = {} @@ -141,7 +130,7 @@ class RadioCanadaIE(InfoExtractor): return { 'id': video_id, - 'title': get_meta('Title'), + 'title': get_meta('Title') or get_meta('AV-nomEmission'), 'description': get_meta('Description') or get_meta('ShortDescription'), 'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'), 'duration': int_or_none(get_meta('length')), @@ -153,11 +142,14 @@ class RadioCanadaIE(InfoExtractor): 'formats': formats, } + def _real_extract(self, url): + return self._extract_info(*re.match(self._VALID_URL, url).groups()) + class RadioCanadaAudioVideoIE(InfoExtractor): - 'radiocanada:audiovideo' - _VALID_URL = r'https?://ici\.radio-canada\.ca/audio-video/media-(?P[0-9]+)' - _TEST = { + IE_NAME = 'radiocanada:audiovideo' + _VALID_URL = r'https?://ici\.radio-canada\.ca/([^/]+/)*media-(?P[0-9]+)' + _TESTS = [{ 'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam', 'info_dict': { 'id': '7527184', @@ -170,7 +162,10 @@ class RadioCanadaAudioVideoIE(InfoExtractor): # m3u8 download 'skip_download': True, }, - } + }, { + 'url': 'https://ici.radio-canada.ca/info/videos/media-7527184/barack-obama-au-vietnam', + 'only_matching': True, + }] def _real_extract(self, url): return self.url_result('radiocanada:medianet:%s' % self._match_id(url))