diff options
author | Jesús <heckyel@hyperbola.info> | 2021-06-09 17:54:27 -0500 |
---|---|---|
committer | Jesús <heckyel@hyperbola.info> | 2021-06-09 17:54:27 -0500 |
commit | 27fe903c511691c078942bef5ee9a05a43b15c8f (patch) | |
tree | 50f30ab2ec749b965869518c0a28651f8677f0d3 /hypervideo_dl/extractor/hitrecord.py | |
download | hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.tar.lz hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.tar.xz hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.zip |
initial
Diffstat (limited to 'hypervideo_dl/extractor/hitrecord.py')
-rw-r--r-- | hypervideo_dl/extractor/hitrecord.py | 68 |
1 files changed, 68 insertions, 0 deletions
diff --git a/hypervideo_dl/extractor/hitrecord.py b/hypervideo_dl/extractor/hitrecord.py new file mode 100644 index 0000000..fd5dc29 --- /dev/null +++ b/hypervideo_dl/extractor/hitrecord.py @@ -0,0 +1,68 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + clean_html, + float_or_none, + int_or_none, + try_get, +) + + +class HitRecordIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hitrecord\.org/records/(?P<id>\d+)' + _TEST = { + 'url': 'https://hitrecord.org/records/2954362', + 'md5': 'fe1cdc2023bce0bbb95c39c57426aa71', + 'info_dict': { + 'id': '2954362', + 'ext': 'mp4', + 'title': 'A Very Different World (HITRECORD x ACLU)', + 'description': 'md5:e62defaffab5075a5277736bead95a3d', + 'duration': 139.327, + 'timestamp': 1471557582, + 'upload_date': '20160818', + 'uploader': 'Zuzi.C12', + 'uploader_id': '362811', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'tags': list, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_json( + 'https://hitrecord.org/api/web/records/%s' % video_id, video_id) + + title = video['title'] + video_url = video['source_url']['mp4_url'] + + tags = None + tags_list = try_get(video, lambda x: x['tags'], list) + if tags_list: + tags = [ + t['text'] + for t in tags_list + if isinstance(t, dict) and t.get('text') + and isinstance(t['text'], compat_str)] + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': clean_html(video.get('body')), + 'duration': float_or_none(video.get('duration'), 1000), + 'timestamp': int_or_none(video.get('created_at_i')), + 'uploader': try_get( + video, lambda x: x['user']['username'], compat_str), + 'uploader_id': try_get( + video, lambda x: compat_str(x['user']['id'])), + 'view_count': int_or_none(video.get('total_views_count')), + 'like_count': int_or_none(video.get('hearts_count')), + 'comment_count': int_or_none(video.get('comments_count')), + 'tags': tags, + } |