From df4d817bc3802e776c5056c3288953aa0ff817b1 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Wed, 22 Aug 2018 02:19:30 +0700 Subject: [PATCH] [kinopoisk] Add extractor (closes #17283) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/kinopoisk.py | 70 ++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) create mode 100644 youtube_dl/extractor/kinopoisk.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d8e86c277..9fc1cfa70 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -520,6 +520,7 @@ from .keezmovies import KeezMoviesIE from .ketnet import KetnetIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE +from .kinopoisk import KinoPoiskIE from .keek import KeekIE from .konserthusetplay import KonserthusetPlayIE from .kontrtube import KontrTubeIE diff --git a/youtube_dl/extractor/kinopoisk.py b/youtube_dl/extractor/kinopoisk.py new file mode 100644 index 000000000..9e8d01f53 --- /dev/null +++ b/youtube_dl/extractor/kinopoisk.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + dict_get, + int_or_none, +) + + +class KinoPoiskIE(InfoExtractor): + _GEO_COUNTRIES = ['RU'] + _VALID_URL = r'https?://(?:www\.)?kinopoisk\.ru/film/(?P\d+)' + _TESTS = [{ + 'url': 'https://www.kinopoisk.ru/film/81041/watch/', + 'md5': '4f71c80baea10dfa54a837a46111d326', + 'info_dict': { + 'id': '81041', + 'ext': 'mp4', + 'title': 'Алеша попович и тугарин змей', + 'description': 'md5:43787e673d68b805d0aa1df5a5aea701', + 'thumbnail': r're:^https?://.*', + 'duration': 4533, + 'age_limit': 12, + }, + 'params': { + 'format': 'bestvideo', + }, + }, { + 'url': 'https://www.kinopoisk.ru/film/81041', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'https://ott-widget.kinopoisk.ru/v1/kp/', video_id, + query={'kpId': video_id}) + + data = self._parse_json( + self._search_regex( + r'(?s)]+\btype=["\']application/json[^>]+>(.+?)<', + webpage, 'data'), + video_id)['models'] + + film = data['filmStatus'] + title = film.get('title') or film['originalTitle'] + + formats = self._extract_m3u8_formats( + data['playlistEntity']['uri'], video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') + self._sort_formats(formats) + + description = dict_get( + film, ('descriptscription', 'description', + 'shortDescriptscription', 'shortDescription')) + thumbnail = film.get('coverUrl') or film.get('posterUrl') + duration = int_or_none(film.get('duration')) + age_limit = int_or_none(film.get('restrictionAge')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': age_limit, + 'formats': formats, + } -- 2.22.2