From 69bb54ebf9dc01b8b50922f9b325c60c21f63c4c Mon Sep 17 00:00:00 2001 From: "Sergey M." Date: Sat, 1 Mar 2014 16:34:38 +0700 Subject: [PATCH] [mailru] Add support for mail.ru video --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/mailru.py | 66 ++++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) create mode 100644 youtube_dl/extractor/mailru.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2f8fcb8c9..25045390e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -134,6 +134,7 @@ from .lynda import ( ) from .m6 import M6IE from .macgamestore import MacGameStoreIE +from .mailru import MailRuIE from .malemotion import MalemotionIE from .mdr import MDRIE from .metacafe import MetacafeIE diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py new file mode 100644 index 000000000..f819c09b3 --- /dev/null +++ b/youtube_dl/extractor/mailru.py @@ -0,0 +1,66 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re +import datetime + +from .common import InfoExtractor + + +class MailRuIE(InfoExtractor): + IE_NAME = 'mailru' + IE_DESC = 'Видео@Mail.Ru' + _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/video/.*#video=/?(?P[^/]+/[^/]+/[^/]+/\d+)' + + _TEST = { + 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', + 'md5': 'dea205f03120046894db4ebb6159879a', + 'info_dict': { + 'id': '46301138', + 'ext': 'mp4', + 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', + 'upload_date': '20140224', + 'uploader': 'sonypicturesrus', + 'uploader_id': 'sonypicturesrus@mail.ru', + 'duration': 184, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + video_data = self._download_json( + 'http://videoapi.my.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON') + + author = video_data['author'] + uploader = author['name'] + uploader_id = author['id'] + + movie = video_data['movie'] + content_id = str(movie['contentId']) + title = movie['title'] + thumbnail = movie['poster'] + duration = movie['duration'] + + upload_date = datetime.datetime.fromtimestamp(video_data['timestamp']).strftime('%Y%m%d') + view_count = video_data['views_count'] + + formats = [ + { + 'url': video['url'], + 'format_id': video['name'], + } for video in video_data['videos'] + ] + + return { + 'id': content_id, + 'title': title, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + } \ No newline at end of file -- 2.39.5