From 82c18e2a53a14cf88bc15a1d0b0f4342d2dc5db8 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Sun, 13 Sep 2015 19:18:57 +0600 Subject: [PATCH] [nowness] Simplify --- youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/nowness.py | 107 ++++++++++++++++--------------- 2 files changed, 57 insertions(+), 52 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 99da52d96..74b7df463 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -408,7 +408,7 @@ from .novamov import NovaMovIE from .nowness import ( NownessIE, NownessPlaylistIE, - NownessSerieIE, + NownessSeriesIE, ) from .nowtv import NowTVIE from .nowvideo import NowVideoIE diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index 9a0e46917..9fb916c18 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -4,11 +4,14 @@ from __future__ import unicode_literals from .brightcove import BrightcoveIE from .common import InfoExtractor from ..utils import ExtractorError -from ..compat import compat_urllib_request +from ..compat import ( + compat_str, + compat_urllib_request, +) class NownessBaseIE(InfoExtractor): - def extract_url_result(self, post): + def _extract_url_result(self, post): if post['type'] == 'video': for media in post['media']: if media['type'] == 'video': @@ -18,7 +21,7 @@ class NownessBaseIE(InfoExtractor): player_code = self._download_webpage( 'http://www.nowness.com/iframe?id=%s' % video_id, video_id, note='Downloading player JavaScript', - errnote='Player download failed') + errnote='Unable to download player JavaScript') bc_url = BrightcoveIE._extract_brightcove_url(player_code) if bc_url is None: raise ExtractorError('Could not find player definition') @@ -32,50 +35,46 @@ class NownessBaseIE(InfoExtractor): # return self.url_result('http://cinematique.com/embed/%s' % video_id, 'Cinematique') pass - def api_request(self, url, request_path): + def _api_request(self, url, request_path): display_id = self._match_id(url) - - lang = 'zh-cn' if 'cn.nowness.com' in url else 'en-us' - request = compat_urllib_request.Request('http://api.nowness.com/api/' + request_path % display_id, headers={ - 'X-Nowness-Language': lang, - }) - json_data = self._download_json(request, display_id) - return display_id, json_data + request = compat_urllib_request.Request( + 'http://api.nowness.com/api/' + request_path % display_id, + headers={ + 'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us', + }) + return display_id, self._download_json(request, display_id) class NownessIE(NownessBaseIE): IE_NAME = 'nowness' _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/(?:story|(?:series|category)/[^/]+)/(?P[^/]+?)(?:$|[?#])' - _TESTS = [ - { - 'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation', - 'md5': '068bc0202558c2e391924cb8cc470676', - 'info_dict': { - 'id': '2520295746001', - 'ext': 'mp4', - 'title': 'Candor: The Art of Gesticulation', - 'description': 'Candor: The Art of Gesticulation', - 'thumbnail': 're:^https?://.*\.jpg', - 'uploader': 'Nowness', - } - }, - { - 'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr', - 'md5': 'e79cf125e387216f86b2e0a5b5c63aa3', - 'info_dict': { - 'id': '3716354522001', - 'ext': 'mp4', - 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', - 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', - 'thumbnail': 're:^https?://.*\.jpg', - 'uploader': 'Nowness', - } - }, - ] + _TESTS = [{ + 'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation', + 'md5': '068bc0202558c2e391924cb8cc470676', + 'info_dict': { + 'id': '2520295746001', + 'ext': 'mp4', + 'title': 'Candor: The Art of Gesticulation', + 'description': 'Candor: The Art of Gesticulation', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, { + 'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr', + 'md5': 'e79cf125e387216f86b2e0a5b5c63aa3', + 'info_dict': { + 'id': '3716354522001', + 'ext': 'mp4', + 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }] def _real_extract(self, url): - display_id, post = self.api_request(url, 'post/getBySlug/%s') - return self.extract_url_result(post) + _, post = self._api_request(url, 'post/getBySlug/%s') + return self._extract_url_result(post) class NownessPlaylistIE(NownessBaseIE): @@ -83,33 +82,39 @@ class NownessPlaylistIE(NownessBaseIE): _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P\d+)' _TEST = { 'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues', - 'info_dict': - { + 'info_dict': { 'id': '3286', }, 'playlist_mincount': 8, } def _real_extract(self, url): - playlist_id, playlist = self.api_request(url, 'post?PlaylistId=%s') - entries = [self.extract_url_result(item) for item in playlist['items']] + playlist_id, playlist = self._api_request(url, 'post?PlaylistId=%s') + entries = [self._extract_url_result(item) for item in playlist['items']] return self.playlist_result(entries, playlist_id) -class NownessSerieIE(NownessBaseIE): - IE_NAME = 'nowness:serie' +class NownessSeriesIE(NownessBaseIE): + IE_NAME = 'nowness:series' _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P[^/]+?)(?:$|[?#])' _TEST = { 'url': 'https://www.nowness.com/series/60-seconds', - 'info_dict': - { + 'info_dict': { 'id': '60', + 'title': '60 Seconds', + 'description': 'One-minute wisdom in a new NOWNESS series', }, 'playlist_mincount': 4, } def _real_extract(self, url): - display_id, serie = self.api_request(url, 'series/getBySlug/%s') - serie_id = str(serie['id']) - entries = [self.extract_url_result(post) for post in serie['posts']] - return self.playlist_result(entries, serie_id) + display_id, series = self._api_request(url, 'series/getBySlug/%s') + entries = [self._extract_url_result(post) for post in series['posts']] + series_title = None + series_description = None + translations = series.get('translations', []) + if translations: + series_title = translations[0].get('title') or translations[0]['seoTitle'] + series_description = translations[0].get('seoDescription') + return self.playlist_result( + entries, compat_str(series['id']), series_title, series_description) -- 2.22.2