From 22d7368dfb384e7698faad6d2891b4aaceab3d7c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Dec 2015 02:34:31 +0600 Subject: [PATCH] [bbc] Extract _ID_REGEX and ad one more video id pattern (Closes #7724) --- youtube_dl/extractor/bbc.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 33b296eaf..5f7265a06 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -22,7 +22,8 @@ class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|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 @@ -465,7 +466,7 @@ def _real_extract(self, url): 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) @@ -780,8 +781,9 @@ def _real_extract(self, url): # 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: @@ -816,7 +818,7 @@ def extract_all(pattern): # 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')