From 8683b4d8d91a7c6b72ca4a12bf6b538cbb4b2a68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 1 May 2015 03:59:13 +0600 Subject: [PATCH] [bbccouk] Improve extraction (Closes #5530) --- youtube_dl/extractor/bbccouk.py | 35 ++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py index abc34a576..22c2843be 100644 --- a/youtube_dl/extractor/bbccouk.py +++ b/youtube_dl/extractor/bbccouk.py @@ -3,7 +3,10 @@ import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, +) from ..compat import compat_HTTPError @@ -326,16 +329,29 @@ def _real_extract(self, url): webpage = self._download_webpage(url, group_id, 'Downloading video page') - programme_id = self._search_regex( - r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) + thumbnail = self._og_search_thumbnail(webpage) + + programme_id = None + + tviplayer = self._search_regex( + r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', + webpage, 'player', default=None) + + if tviplayer: + player = self._parse_json(tviplayer, group_id).get('player', {}) + duration = int_or_none(player.get('duration')) + programme_id = player.get('vpid') + + if not programme_id: + programme_id = self._search_regex( + r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) + if programme_id: - player = self._download_json( - 'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id, - group_id)['jsConf']['player'] - title = player['title'] - description = player['subtitle'] - duration = player['duration'] formats, subtitles = self._download_media_selector(programme_id) + title = self._og_search_title(webpage) + description = self._search_regex( + r'

([^<]+)

', + webpage, 'description', fatal=False) else: programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) @@ -345,6 +361,7 @@ def _real_extract(self, url): 'id': programme_id, 'title': title, 'description': description, + 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, 'subtitles': subtitles,