X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/4e090bc3ceacc4e3cd464d12ea97700e3acad37d..b6db0e9853c4704fd25a056749ab237cc74bcd00:/youtube_dl/extractor/bbc.py diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 8a2ed0a..30a63a2 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -6,14 +6,19 @@ import itertools 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, + urlencode_postdata, + urljoin, ) from ..compat import ( compat_etree_fromstring, @@ -25,19 +30,23 @@ 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'[pbw][\da-z]{7}' _VALID_URL = r'''(?x) https?:// (?:www\.)?bbc\.co\.uk/ (?: programmes/(?!articles/)| iplayer(?:/[^/]+)?/(?:episode/|playlist/)| - music/clips[/#]| - radio/player/ + music/(?:clips|audiovideo/popular)[/#]| + radio/player/| + 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. @@ -222,11 +231,49 @@ 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, + }] _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 @@ -361,7 +408,7 @@ class BBCCoUkIE(InfoExtractor): fmt.update({ 'width': width, 'height': height, - 'vbr': bitrate, + 'tbr': bitrate, 'vcodec': encoding, }) else: @@ -370,7 +417,7 @@ class BBCCoUkIE(InfoExtractor): 'acodec': encoding, 'vcodec': 'none', }) - if protocol == 'http': + if protocol in ('http', 'https'): # Direct link fmt.update({ 'url': href, @@ -389,6 +436,8 @@ 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 +456,7 @@ 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 +497,7 @@ 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) @@ -481,6 +530,12 @@ 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 @@ -718,6 +773,17 @@ 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, + } }] @classmethod @@ -940,6 +1006,36 @@ class BBCIE(BBCCoUkIE): '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),