aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ted.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2015-02-15 18:03:41 +0100
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2015-02-16 21:51:03 +0100
commita504ced097e703a9bc6c18b6e31bcafb4783ed80 (patch)
tree1d520371df47be5f2c62aaee78dbced5d6b05d08 /youtube_dl/extractor/ted.py
parent8fb474fb17a64ff2aa9f6315ebbc99ae7938c4e1 (diff)
Improve subtitles support
For each language the extractor builds a list with the available formats sorted (like for video formats), then YoutubeDL selects one of them using the '--sub-format' option which now allows giving the format preferences (for example 'ass/srt/best'). For each format the 'url' field can be set so that we only download the contents if needed, or if the contents needs to be processed (like in crunchyroll) the 'data' field can be used. The reasons for this change are: * We weren't checking that the format given with '--sub-format' was available, checking it in each extractor would be repetitive. * It allows to easily support giving a format preference. * The subtitles were automatically downloaded in the extractor, but I think that if you use for example the '--dump-json' option you want to finish as fast as possible. Currently only the ted extractor has been updated, but the old system still works.
Diffstat (limited to 'youtube_dl/extractor/ted.py')
-rw-r--r--youtube_dl/extractor/ted.py18
1 files changed, 10 insertions, 8 deletions
diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py
index 10b3b706a..1809eaae4 100644
--- a/youtube_dl/extractor/ted.py
+++ b/youtube_dl/extractor/ted.py
@@ -3,14 +3,14 @@ from __future__ import unicode_literals
import json
import re
-from .subtitles import SubtitlesInfoExtractor
+from .common import InfoExtractor
from ..compat import (
compat_str,
)
-class TEDIE(SubtitlesInfoExtractor):
+class TEDIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?P<proto>https?://)
(?P<type>www|embed(?:-ssl)?)(?P<urlmain>\.ted\.com/
@@ -165,9 +165,6 @@ class TEDIE(SubtitlesInfoExtractor):
video_id = compat_str(talk_info['id'])
# subtitles
video_subtitles = self.extract_subtitles(video_id, talk_info)
- if self._downloader.params.get('listsubtitles', False):
- self._list_available_subtitles(video_id, talk_info)
- return
thumbnail = talk_info['thumb']
if not thumbnail.startswith('http'):
@@ -183,13 +180,18 @@ class TEDIE(SubtitlesInfoExtractor):
'duration': talk_info.get('duration'),
}
- def _get_available_subtitles(self, video_id, talk_info):
+ def _get_subtitles(self, video_id, talk_info):
languages = [lang['languageCode'] for lang in talk_info.get('languages', [])]
if languages:
sub_lang_list = {}
for l in languages:
- url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l)
- sub_lang_list[l] = url
+ sub_lang_list[l] = [
+ {
+ 'url': 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/%s' % (video_id, l, ext),
+ 'ext': ext,
+ }
+ for ext in ['ted', 'srt']
+ ]
return sub_lang_list
else:
self._downloader.report_warning('video doesn\'t have subtitles')