From cf1a8668e8e47a56c834fb567d227787d7480d08 Mon Sep 17 00:00:00 2001 From: Joost Verdoorn Date: Thu, 19 Nov 2020 17:26:53 +0100 Subject: [PATCH] [Amara] Add new extractor (#20618) * [Amara] Add new extractor --- youtube_dl/extractor/amara.py | 76 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 77 insertions(+) create mode 100644 youtube_dl/extractor/amara.py diff --git a/youtube_dl/extractor/amara.py b/youtube_dl/extractor/amara.py new file mode 100644 index 000000000..b222154bd --- /dev/null +++ b/youtube_dl/extractor/amara.py @@ -0,0 +1,76 @@ +# coding: utf-8 +from __future__ import unicode_literals +from .common import InfoExtractor + + +class AmaraIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?amara\.org/(?:\w+/)?videos/(?P\w+)' + _TESTS = [ + { + 'url': 'https://amara.org/en/videos/jVx79ZKGK1ky/info/why-jury-trials-are-becoming-less-common/?tab=video', + 'md5': 'ea10daf2b6154b8c1ecf9922aca5e8ae', + 'info_dict': { + 'id': 'h6ZuVdvYnfE', + 'ext': 'mp4', + 'title': 'Why jury trials are becoming less common', + 'description': 'md5:a61811c319943960b6ab1c23e0cbc2c1', + 'thumbnail': r're:^https?://.*\.jpg$', + 'subtitles': dict, + 'upload_date': '20160813', + 'uploader': 'PBS NewsHour', + 'uploader_id': 'PBSNewsHour' + } + }, + { + 'url': 'https://amara.org/en/videos/kYkK1VUTWW5I/info/vimeo-at-ces-2011', + 'md5': '99392c75fa05d432a8f11df03612195e', + 'info_dict': { + 'id': '18622084', + 'ext': 'mov', + 'title': 'Vimeo at CES 2011!', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'subtitles': dict, + 'timestamp': 1294649110, + 'upload_date': '20110110', + 'uploader': 'Sam Morrill', + 'uploader_id': 'sammorrill' + } + }, + { + 'url': 'https://amara.org/en/videos/s8KL7I3jLmh6/info/the-danger-of-a-single-story/', + 'md5': 'd3970f08512738ee60c5807311ff5d3f', + 'info_dict': { + 'id': 'ChimamandaAdichie_2009G-transcript', + 'ext': 'mp4', + 'title': 'The danger of a single story', + 'description': 'md5:d769b31139c3b8bb5be9177f62ea3f23', + 'thumbnail': r're:^https?://.*\.jpg$', + 'subtitles': dict, + 'upload_date': '20131206' + } + } + ] + + def get_subtitles_for_language(self, language): + return [{ + 'ext': type, + 'url': language['subtitles_uri'].replace('format=json', 'format=' + type) + } for type in ['vtt', 'srt', 'json']] + + def _real_extract(self, url): + video_id = self._match_id(url) + meta = self._download_json('https://amara.org/api/videos/%s/' % video_id, video_id, query={'format': 'json'}) + + video_url = meta.get('all_urls')[0] + subtitles = dict([(language['code'], self.get_subtitles_for_language(language)) for language in meta.get('languages', []) if language['published']]) + + return { + '_type': 'url_transparent', + 'url': video_url, + 'id': video_id, + 'subtitles': subtitles, + 'title': meta['title'], + 'description': meta.get('description'), + 'thumbnail': meta.get('thumbnail') + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 088800eb9..183050e07 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -36,6 +36,7 @@ from .afreecatv import AfreecaTVIE from .airmozilla import AirMozillaIE from .aljazeera import AlJazeeraIE from .alphaporno import AlphaPornoIE +from .amara import AmaraIE from .amcnetworks import AMCNetworksIE from .americastestkitchen import AmericasTestKitchenIE from .animeondemand import AnimeOnDemandIE