diff options
Diffstat (limited to 'hypervideo_dl/extractor/naver.py')
| -rw-r--r-- | hypervideo_dl/extractor/naver.py | 35 |
1 files changed, 18 insertions, 17 deletions
diff --git a/hypervideo_dl/extractor/naver.py b/hypervideo_dl/extractor/naver.py index e2e6e97..d79caf5 100644 --- a/hypervideo_dl/extractor/naver.py +++ b/hypervideo_dl/extractor/naver.py @@ -21,6 +21,23 @@ from ..utils import ( class NaverBaseIE(InfoExtractor): _CAPTION_EXT_RE = r'\.(?:ttml|vtt)' + @staticmethod # NB: Used in VLiveWebArchiveIE, WeverseIE + def process_subtitles(vod_data, process_url): + ret = {'subtitles': {}, 'automatic_captions': {}} + for caption in traverse_obj(vod_data, ('captions', 'list', ...)): + caption_url = caption.get('source') + if not caption_url: + continue + type_ = 'automatic_captions' if caption.get('type') == 'auto' else 'subtitles' + lang = caption.get('locale') or join_nonempty('language', 'country', from_dict=caption) or 'und' + if caption.get('type') == 'fan': + lang += '_fan%d' % next(i for i in itertools.count(1) if f'{lang}_fan{i}' not in ret[type_]) + ret[type_].setdefault(lang, []).extend({ + 'url': sub_url, + 'name': join_nonempty('label', 'fanName', from_dict=caption, delim=' - '), + } for sub_url in process_url(caption_url)) + return ret + def _extract_video_info(self, video_id, vid, key): video_data = self._download_json( 'http://play.rmcnmv.naver.com/vod/play/v2.0/' + vid, @@ -79,34 +96,18 @@ class NaverBaseIE(InfoExtractor): ] return [caption_url] - automatic_captions = {} - subtitles = {} - for caption in get_list('caption'): - caption_url = caption.get('source') - if not caption_url: - continue - sub_dict = automatic_captions if caption.get('type') == 'auto' else subtitles - lang = caption.get('locale') or join_nonempty('language', 'country', from_dict=caption) or 'und' - if caption.get('type') == 'fan': - lang += '_fan%d' % next(i for i in itertools.count(1) if f'{lang}_fan{i}' not in sub_dict) - sub_dict.setdefault(lang, []).extend({ - 'url': sub_url, - 'name': join_nonempty('label', 'fanName', from_dict=caption, delim=' - '), - } for sub_url in get_subs(caption_url)) - user = meta.get('user', {}) return { 'id': video_id, 'title': title, 'formats': formats, - 'subtitles': subtitles, - 'automatic_captions': automatic_captions, 'thumbnail': try_get(meta, lambda x: x['cover']['source']), 'view_count': int_or_none(meta.get('count')), 'uploader_id': user.get('id'), 'uploader': user.get('name'), 'uploader_url': user.get('url'), + **self.process_subtitles(video_data, get_subs), } |