X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9fb40a4e5f59ba243dee2edad23a2c5555338113..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/bbc.py diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 8a2ed0a..002c39c 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -1,22 +1,28 @@ # coding: utf-8 from __future__ import unicode_literals -import re import itertools +import re from .common import InfoExtractor from ..utils import ( + clean_html, dict_get, ExtractorError, float_or_none, + get_element_by_class, int_or_none, + js_to_json, parse_duration, parse_iso8601, try_get, unescapeHTML, + url_or_none, + urlencode_postdata, + urljoin, ) from ..compat import ( - compat_etree_fromstring, + compat_etree_Element, compat_HTTPError, compat_urlparse, ) @@ -25,19 +31,24 @@ from ..compat import ( class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _ID_REGEX = r'[pb][\da-z]{7}' + _ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})' _VALID_URL = r'''(?x) https?:// (?:www\.)?bbc\.co\.uk/ (?: programmes/(?!articles/)| iplayer(?:/[^/]+)?/(?:episode/|playlist/)| - music/clips[/#]| - radio/player/ + music/(?:clips|audiovideo/popular)[/#]| + radio/player/| + sounds/play/| + events/[^/]+/play/[^/]+/ ) (?P%s)(?!/(?:episodes|broadcasts|clips)) ''' % _ID_REGEX + _LOGIN_URL = 'https://account.bbc.com/signin' + _NETRC_MACHINE = 'bbc' + _MEDIASELECTOR_URLS = [ # Provides HQ HLS streams with even better quality that pc mediaset but fails # with geolocation in some cases when it's even not geo restricted at all (e.g. @@ -60,7 +71,7 @@ class BBCCoUkIE(InfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4', + 'title': 'Kaleidoscope, Leonard Cohen', 'description': 'The Canadian poet and songwriter reflects on his musical career.', }, 'params': { @@ -198,7 +209,7 @@ class BBCCoUkIE(InfoExtractor): }, 'skip': 'Now it\'s really geo-restricted', }, { - # compact player (https://github.com/rg3/youtube-dl/issues/8147) + # compact player (https://github.com/ytdl-org/youtube-dl/issues/8147) 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player', 'info_dict': { 'id': 'p028bfkj', @@ -210,6 +221,20 @@ class BBCCoUkIE(InfoExtractor): # rtmp download 'skip_download': True, }, + }, { + 'url': 'https://www.bbc.co.uk/sounds/play/m0007jzb', + 'note': 'Audio', + 'info_dict': { + 'id': 'm0007jz9', + 'ext': 'mp4', + 'title': 'BBC Proms, 2019, Prom 34: West–Eastern Divan Orchestra', + 'description': "Live BBC Proms. West–Eastern Divan Orchestra with Daniel Barenboim and Martha Argerich.", + 'duration': 9840, + }, + 'params': { + # rtmp download + 'skip_download': True, + } }, { 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', 'only_matching': True, @@ -222,11 +247,55 @@ class BBCCoUkIE(InfoExtractor): }, { 'url': 'http://www.bbc.co.uk/radio/player/p03cchwf', 'only_matching': True, - } - ] + }, { + 'url': 'https://www.bbc.co.uk/music/audiovideo/popular#p055bc55', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/programmes/w3csv1y9', + 'only_matching': True, + }, { + 'url': 'https://www.bbc.co.uk/programmes/m00005xn', + 'only_matching': True, + }, { + 'url': 'https://www.bbc.co.uk/programmes/w172w4dww1jqt5s', + 'only_matching': True, + }] _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8' + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading signin page') + + login_form = self._hidden_inputs(login_page) + + 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') + + def _real_initialize(self): + self._login() + class MediaSelectionError(Exception): def __init__(self, id): self.id = id @@ -258,7 +327,13 @@ class BBCCoUkIE(InfoExtractor): def _get_subtitles(self, media, programme_id): subtitles = {} for connection in self._extract_connections(media): - captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') + cc_url = url_or_none(connection.get('href')) + if not cc_url: + continue + captions = self._download_xml( + cc_url, programme_id, 'Downloading captions', fatal=False) + if not isinstance(captions, compat_etree_Element): + continue lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') subtitles[lang] = [ { @@ -287,14 +362,9 @@ class BBCCoUkIE(InfoExtractor): self._raise_extractor_error(last_exception) 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 + media_selection = self._download_xml( + url, programme_id, 'Downloading media selection XML', + expected_status=(403, 404)) return self._process_media_selector(media_selection, programme_id) def _process_media_selector(self, media_selection, programme_id): @@ -361,7 +431,7 @@ class BBCCoUkIE(InfoExtractor): fmt.update({ 'width': width, 'height': height, - 'vbr': bitrate, + 'tbr': bitrate, 'vcodec': encoding, }) else: @@ -370,7 +440,7 @@ class BBCCoUkIE(InfoExtractor): 'acodec': encoding, 'vcodec': 'none', }) - if protocol == 'http': + if protocol in ('http', 'https'): # Direct link fmt.update({ 'url': href, @@ -389,6 +459,8 @@ class BBCCoUkIE(InfoExtractor): 'rtmp_live': False, 'ext': 'flv', }) + else: + continue formats.append(fmt) elif kind == 'captions': subtitles = self.extract_subtitles(media, programme_id) @@ -407,7 +479,7 @@ class BBCCoUkIE(InfoExtractor): description = smp_config['summary'] for item in smp_config['items']: kind = item['kind'] - if kind != 'programme' and kind != 'radioProgramme': + if kind not in ('programme', 'radioProgramme'): continue programme_id = item.get('vpid') duration = int_or_none(item.get('duration')) @@ -448,7 +520,7 @@ class BBCCoUkIE(InfoExtractor): for item in self._extract_items(playlist): kind = item.get('kind') - if kind != 'programme' and kind != 'radioProgramme': + if kind not in ('programme', 'radioProgramme'): continue title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS) @@ -456,7 +528,7 @@ class BBCCoUkIE(InfoExtractor): def get_programme_id(item): def get_from_attributes(item): - for p in('identifier', 'group'): + for p in ('identifier', 'group'): value = item.get(p) if value and re.match(r'^[pb][\da-z]{7}$', value): return value @@ -481,6 +553,12 @@ class BBCCoUkIE(InfoExtractor): webpage = self._download_webpage(url, group_id, 'Downloading video page') + error = self._search_regex( + r']+\bclass=["\']smp__message delta["\'][^>]*>([^<]+)<', + webpage, 'error', default=None) + if error: + raise ExtractorError(error, expected=True) + programme_id = None duration = None @@ -546,7 +624,7 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.com/news/world-europe-32668511', 'info_dict': { 'id': 'world-europe-32668511', - 'title': 'Russia stages massive WW2 parade despite Western boycott', + 'title': 'Russia stages massive WW2 parade', 'description': 'md5:00ff61976f6081841f759a08bf78cc9c', }, 'playlist_count': 2, @@ -718,6 +796,37 @@ class BBCIE(BBCCoUkIE): # single video article embedded with data-media-vpid 'url': 'http://www.bbc.co.uk/sport/rowing/35908187', 'only_matching': True, + }, { + 'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1', + 'info_dict': { + 'id': 'p06556y7', + 'ext': 'mp4', + 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?', + 'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd', + }, + 'params': { + 'skip_download': True, + } + }, { + # window.__PRELOADED_STATE__ + 'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl', + 'info_dict': { + 'id': 'b0b9z4vz', + 'ext': 'mp4', + 'title': 'Prom 6: An American in Paris and Turangalila', + 'description': 'md5:51cf7d6f5c8553f197e58203bc78dff8', + 'uploader': 'Radio 3', + 'uploader_id': 'bbc_radio_three', + }, + }, { + 'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227', + 'info_dict': { + 'id': 'p06w9tws', + 'ext': 'mp4', + 'title': 'md5:2fabf12a726603193a2879a055f72514', + 'description': 'Learn English words and phrases from this story', + }, + 'add_ie': [BBCCoUkIE.ie_key()], }] @classmethod @@ -868,6 +977,15 @@ class BBCIE(BBCCoUkIE): if entries: return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) + # http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227 + group_id = self._search_regex( + r']+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX, + webpage, 'group id', default=None) + if playlist_id: + return self.url_result( + 'https://www.bbc.co.uk/programmes/%s' % group_id, + ie=BBCCoUkIE.ie_key()) + # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) programme_id = self._search_regex( [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX, @@ -940,6 +1058,66 @@ class BBCIE(BBCCoUkIE): 'subtitles': subtitles, } + preload_state = self._parse_json(self._search_regex( + r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage, + 'preload state', default='{}'), playlist_id, fatal=False) + if preload_state: + current_programme = preload_state.get('programmes', {}).get('current') or {} + programme_id = current_programme.get('id') + if current_programme and programme_id and current_programme.get('type') == 'playable_item': + title = current_programme.get('titles', {}).get('tertiary') or playlist_title + formats, subtitles = self._download_media_selector(programme_id) + self._sort_formats(formats) + synopses = current_programme.get('synopses') or {} + network = current_programme.get('network') or {} + duration = int_or_none( + current_programme.get('duration', {}).get('value')) + thumbnail = None + image_url = current_programme.get('image_url') + if image_url: + thumbnail = image_url.replace('{recipe}', '1920x1920') + return { + 'id': programme_id, + 'title': title, + 'description': dict_get(synopses, ('long', 'medium', 'short')), + 'thumbnail': thumbnail, + 'duration': duration, + 'uploader': network.get('short_title'), + 'uploader_id': network.get('id'), + 'formats': formats, + 'subtitles': subtitles, + } + + bbc3_config = self._parse_json( + self._search_regex( + r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage, + 'bbcthree config', default='{}'), + playlist_id, transform_source=js_to_json, fatal=False) + if bbc3_config: + bbc3_playlist = try_get( + bbc3_config, lambda x: x['payload']['content']['bbcMedia']['playlist'], + dict) + if bbc3_playlist: + playlist_title = bbc3_playlist.get('title') or playlist_title + thumbnail = bbc3_playlist.get('holdingImageURL') + entries = [] + for bbc3_item in bbc3_playlist['items']: + programme_id = bbc3_item.get('versionID') + if not programme_id: + continue + formats, subtitles = self._download_media_selector(programme_id) + self._sort_formats(formats) + entries.append({ + 'id': programme_id, + 'title': playlist_title, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'formats': formats, + 'subtitles': subtitles, + }) + return self.playlist_result( + entries, playlist_id, playlist_title, playlist_description) + def extract_all(pattern): return list(filter(None, map( lambda s: self._parse_json(s, playlist_id, fatal=False),