X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9d6a3ba754469c85b7f0f88714203f99ac69087a..acbcfdb2cbb57cd2ab6a5d73341cd077fa71f6c9:/youtube_dl/extractor/bbc.py?ds=sidebyside diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 30a63a2..e765079 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -1,8 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals -import re import itertools +import re from .common import InfoExtractor from ..utils import ( @@ -17,11 +17,12 @@ from ..utils import ( parse_iso8601, try_get, unescapeHTML, + url_or_none, urlencode_postdata, urljoin, ) from ..compat import ( - compat_etree_fromstring, + compat_etree_Element, compat_HTTPError, compat_urlparse, ) @@ -30,7 +31,7 @@ from ..compat import ( class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _ID_REGEX = r'[pbw][\da-z]{7}' + _ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})' _VALID_URL = r'''(?x) https?:// (?:www\.)?bbc\.co\.uk/ @@ -207,7 +208,7 @@ 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', @@ -237,6 +238,12 @@ class BBCCoUkIE(InfoExtractor): }, { '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' @@ -305,7 +312,13 @@ 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] = [ { @@ -334,14 +347,9 @@ 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): @@ -784,6 +792,26 @@ class BBCIE(BBCCoUkIE): '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 @@ -934,6 +962,15 @@ 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'