diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-08-21 01:37:43 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-08-21 01:37:43 +0800 |
commit | c687ac745b3c94b2fd246214e78c92a31bd9fc0f (patch) | |
tree | c97803d9238a144b597aaf2e10db5032820b0e03 /youtube_dl/extractor | |
parent | 912e0b7e46d795df3ec1866f9b0ff071cca8d550 (diff) |
[theplatform] Use subtitles from SMIL, too
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/theplatform.py | 17 |
1 files changed, 13 insertions, 4 deletions
diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index ba05ada39..25edc3100 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -28,7 +28,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns}) class ThePlatformBaseIE(InfoExtractor): - def _extract_theplatform_smil_formats(self, smil_url, video_id, note='Downloading SMIL data'): + def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'): meta = self._download_xml(smil_url, video_id, note=note) try: error_msg = next( @@ -54,7 +54,9 @@ class ThePlatformBaseIE(InfoExtractor): self._sort_formats(formats) - return formats + subtitles = self._parse_smil_subtitles(meta, default_ns) + + return formats, subtitles def get_metadata(self, path, video_id): info_url = 'http://link.theplatform.com/s/%s?format=preview' % path @@ -208,12 +210,14 @@ class ThePlatformIE(ThePlatformBaseIE): if sig: smil_url = self._sign_url(smil_url, sig['key'], sig['secret']) - formats = self._extract_theplatform_smil_formats(smil_url, video_id) + formats, subtitles = self._extract_theplatform_smil(smil_url, video_id) ret = self.get_metadata(path, video_id) + combined_subtitles = self._merge_subtitles(ret.get('subtitles', {}), subtitles) ret.update({ 'id': video_id, 'formats': formats, + 'subtitles': combined_subtitles, }) return ret @@ -251,6 +255,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): entry = feed['entries'][0] formats = [] + subtitles = {} first_video_id = None duration = None for item in entry['media$content']: @@ -259,7 +264,9 @@ class ThePlatformFeedIE(ThePlatformBaseIE): if first_video_id is None: first_video_id = cur_video_id duration = float_or_none(item.get('plfile$duration')) - formats.extend(self._extract_theplatform_smil_formats(smil_url, video_id, 'Downloading SMIL data for %s' % cur_video_id)) + cur_formats, cur_subtitles = self._extract_theplatform_smil(smil_url, video_id, 'Downloading SMIL data for %s' % cur_video_id) + formats.extend(cur_formats) + subtitles = self._merge_subtitles(subtitles, cur_subtitles) self._sort_formats(formats) @@ -273,9 +280,11 @@ class ThePlatformFeedIE(ThePlatformBaseIE): categories = [item['media$name'] for item in entry.get('media$categories', [])] ret = self.get_metadata('%s/%s' % (provider_id, first_video_id), video_id) + subtitles = self._merge_subtitles(subtitles, ret['subtitles']) ret.update({ 'id': video_id, 'formats': formats, + 'subtitles': subtitles, 'thumbnails': thumbnails, 'duration': duration, 'timestamp': timestamp, |