[theplatform] Extract captions (Closes #4495)

This commit is contained in:
Sergey M․ 2014-12-17 20:20:40 +06:00
parent e54a3a2f01
commit 748ec66725

View file

@ -3,7 +3,7 @@
import re import re
import json import json
from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor
from ..compat import ( from ..compat import (
compat_str, compat_str,
) )
@ -16,7 +16,7 @@
_x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'}) _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'})
class ThePlatformIE(InfoExtractor): class ThePlatformIE(SubtitlesInfoExtractor):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
(?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/ (?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/
(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)? (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
@ -66,6 +66,20 @@ def _real_extract(self, url):
info_json = self._download_webpage(info_url, video_id) info_json = self._download_webpage(info_url, video_id)
info = json.loads(info_json) info = json.loads(info_json)
subtitles = {}
captions = info.get('captions')
if isinstance(captions, list):
for caption in captions:
lang, src = caption.get('lang'), caption.get('src')
if lang and src:
subtitles[lang] = src
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id, subtitles)
return
subtitles = self.extract_subtitles(video_id, subtitles)
head = meta.find(_x('smil:head')) head = meta.find(_x('smil:head'))
body = meta.find(_x('smil:body')) body = meta.find(_x('smil:body'))
@ -117,6 +131,7 @@ def _real_extract(self, url):
return { return {
'id': video_id, 'id': video_id,
'title': info['title'], 'title': info['title'],
'subtitles': subtitles,
'formats': formats, 'formats': formats,
'description': info['description'], 'description': info['description'],
'thumbnail': info['defaultThumbnailUrl'], 'thumbnail': info['defaultThumbnailUrl'],