X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fbbc.py;h=691aecc0dbb2a9c8c49b75f6e6fc377519752eb3;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=ea67e3f2dd0ebc47cc36315eb999fec6fc29cd94;hpb=7033bc1a5117068c493931cb736d53e68d50f9a1;p=youtube-dl diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index ea67e3f2d..691aecc0d 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -14,18 +13,22 @@ from ..utils import ( remove_end, unescapeHTML, ) -from ..compat import compat_HTTPError +from ..compat import ( + compat_etree_fromstring, + compat_HTTPError, +) class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P[\da-z]{8})' + _ID_REGEX = r'[pb][\da-z]{7}' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P%s)' % _ID_REGEX _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. - # http://www.bbc.co.uk/programmes/b06bp7lf) + # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable. 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s', 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s', ] @@ -44,9 +47,8 @@ class BBCCoUkIE(InfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Kaleidoscope, Leonard Cohen', + 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4', 'description': 'The Canadian poet and songwriter reflects on his musical career.', - 'duration': 1740, }, 'params': { # rtmp download @@ -109,7 +111,8 @@ class BBCCoUkIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'Episode is no longer available on BBC iPlayer Radio', }, { 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', 'note': 'Audio', @@ -332,7 +335,7 @@ class BBCCoUkIE(InfoExtractor): return self._download_media_selector_url( mediaselector_url % programme_id, programme_id) except BBCCoUkIE.MediaSelectionError as e: - if e.id in ('notukerror', 'geolocation'): + if e.id in ('notukerror', 'geolocation', 'selectionunavailable'): last_exception = e continue self._raise_extractor_error(e) @@ -343,8 +346,8 @@ class BBCCoUkIE(InfoExtractor): 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 == 403: - media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) + 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) @@ -451,6 +454,7 @@ class BBCCoUkIE(InfoExtractor): webpage = self._download_webpage(url, group_id, 'Downloading video page') programme_id = None + duration = None tviplayer = self._search_regex( r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', @@ -463,14 +467,16 @@ class BBCCoUkIE(InfoExtractor): if not programme_id: programme_id = self._search_regex( - r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) + r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None) if programme_id: formats, subtitles = self._download_media_selector(programme_id) title = self._og_search_title(webpage) description = self._search_regex( r'

([^<]+)

', - webpage, 'description', fatal=False) + webpage, 'description', default=None) + if not description: + description = self._html_search_meta('description', webpage) else: programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) @@ -584,6 +590,7 @@ class BBCIE(BBCCoUkIE): 'ext': 'mp4', 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', 'duration': 56, + 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', }, 'params': { 'skip_download': True, @@ -652,7 +659,7 @@ class BBCIE(BBCCoUkIE): @classmethod def suitable(cls, url): - return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url) + return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url) def _extract_from_media_meta(self, media_meta, video_id): # Direct links to media in media metadata (e.g. @@ -726,6 +733,7 @@ class BBCIE(BBCCoUkIE): # article with multiple videos embedded with playlist.sxml (e.g. # http://www.bbc.com/sport/0/football/34475836) playlists = re.findall(r']+name="playlist"[^>]+value="([^"]+)"', webpage) + playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage)) if playlists: entries = [ self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp) @@ -778,8 +786,9 @@ class BBCIE(BBCCoUkIE): # 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-vpid="([\da-z]{8})"', - r']+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], + [r'data-video-player-vpid="(%s)"' % self._ID_REGEX, + r']+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX, + r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX], webpage, 'vpid', default=None) if programme_id: @@ -814,7 +823,7 @@ class BBCIE(BBCCoUkIE): # Multiple video article (e.g. # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460) - EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?' + EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX entries = [] for match in extract_all(r'new\s+SMP\(({.+?})\)'): embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') @@ -903,3 +912,33 @@ class BBCIE(BBCCoUkIE): }) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) + + +class BBCCoUkArticleIE(InfoExtractor): + _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P[a-zA-Z0-9]+)' + IE_NAME = 'bbc.co.uk:article' + IE_DESC = 'BBC articles' + + _TEST = { + 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer', + 'info_dict': { + 'id': '3jNQLTMrPlYGTBn0WV6M2MS', + 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four', + 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.', + }, + 'playlist_count': 4, + 'add_ie': ['BBCCoUk'], + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage).strip() + + entries = [self.url_result(programme_url) for programme_url in re.findall( + r']+typeof="Clip"[^>]+resource="([^"]+)"', webpage)] + + return self.playlist_result(entries, playlist_id, title, description)