depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-23 02:32:16 +00:00
Code Issues Releases Wiki Activity

[bbccouk] Improve extraction (Closes #5530)

Browse source
This commit is contained in:
Sergey M․ 2015-05-01 03:59:13 +06:00
parent 1dbd717eb4
commit 8683b4d8d9
1 changed files with 26 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
youtube_dl/extractor/bbccouk.py
View file

@ -3,7 +3,10 @@ from __future__ import unicode_literals
import xml.etree.ElementTree import xml.etree.ElementTree
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ExtractorError from ..utils import (
ExtractorError,
int_or_none,
)
from ..compat import compat_HTTPError from ..compat import compat_HTTPError
@ -326,16 +329,29 @@ class BBCCoUkIE(InfoExtractor):
webpage = self._download_webpage(url, group_id, 'Downloading video page') webpage = self._download_webpage(url, group_id, 'Downloading video page')
programme_id = self._search_regex( thumbnail = self._og_search_thumbnail(webpage)
r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
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: 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) formats, subtitles = self._download_media_selector(programme_id)
title = self._og_search_title(webpage)
description = self._search_regex(
r'<p class="medium-description">([^<]+)</p>',
webpage, 'description', fatal=False)
else: else:
programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
@ -345,6 +361,7 @@ class BBCCoUkIE(InfoExtractor):
'id': programme_id, 'id': programme_id,
'title': title, 'title': title,
'description': description, 'description': description,
'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,