aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ted.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-11-10 11:54:18 +0100
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-11-10 11:54:18 +0100
commit231516b6c983561cdfb7d58a07bb78a5fa132e10 (patch)
tree9700b60833718b12a8bb620752bdd7b8b0de9329 /youtube_dl/extractor/ted.py
parentfb53d58dcf5e407f39ac79f05d838a20e00823c1 (diff)
parent4ed3e51080dea651b3db8889b0c8f2e40d261075 (diff)
Merge pull request #1705 from iemejia/master
[ted] support for subtitles
Diffstat (limited to 'youtube_dl/extractor/ted.py')
-rw-r--r--youtube_dl/extractor/ted.py34
1 files changed, 31 insertions, 3 deletions
diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py
index dfa1176a3..1b006bc9b 100644
--- a/youtube_dl/extractor/ted.py
+++ b/youtube_dl/extractor/ted.py
@@ -1,10 +1,14 @@
import json
import re
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
+from ..utils import (
+ compat_str,
+ RegexNotFoundError,
+)
-class TEDIE(InfoExtractor):
+class TEDIE(SubtitlesInfoExtractor):
_VALID_URL=r'''http://www\.ted\.com/
(
((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
@@ -82,11 +86,21 @@ class TEDIE(InfoExtractor):
'url': stream['file'],
'format': stream['id']
} for stream in info['htmlStreams']]
+
+ video_id = info['id']
+
+ # subtitles
+ video_subtitles = self.extract_subtitles(video_id, webpage)
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, webpage)
+ return
+
info = {
- 'id': info['id'],
+ 'id': video_id,
'title': title,
'thumbnail': thumbnail,
'description': desc,
+ 'subtitles': video_subtitles,
'formats': formats,
}
@@ -94,3 +108,17 @@ class TEDIE(InfoExtractor):
info.update(info['formats'][-1])
return info
+
+ def _get_available_subtitles(self, video_id, webpage):
+ try:
+ options = self._search_regex(r'(?:<select name="subtitles_language_select" id="subtitles_language_select">)(.*?)(?:</select>)', webpage, 'subtitles_language_select', flags=re.DOTALL)
+ languages = re.findall(r'(?:<option value=")(\S+)"', options)
+ 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
+ return sub_lang_list
+ except RegexNotFoundError as err:
+ self._downloader.report_warning(u'video doesn\'t have subtitles')
+ return {}