From 8af2804a5d09e08d8916e7a7d2eab40864e9ecd8 Mon Sep 17 00:00:00 2001 From: remitamine Date: Fri, 1 Jan 2016 21:53:19 +0100 Subject: [PATCH] [testtube] Remove Extractor --- youtube_dl/extractor/revision3.py | 30 +++++++++-- youtube_dl/extractor/testtube.py | 90 ------------------------------- 2 files changed, 27 insertions(+), 93 deletions(-) delete mode 100644 youtube_dl/extractor/testtube.py diff --git a/youtube_dl/extractor/revision3.py b/youtube_dl/extractor/revision3.py index 25fe4ef16..b1b8800b9 100644 --- a/youtube_dl/extractor/revision3.py +++ b/youtube_dl/extractor/revision3.py @@ -9,6 +9,7 @@ from ..utils import ( int_or_none, parse_iso8601, unescapeHTML, + qualities, ) @@ -19,12 +20,15 @@ class Revision3IE(InfoExtractor): 'md5': 'd94a72d85d0a829766de4deb8daaf7df', 'info_dict': { 'id': '73034', + 'display_id': 'technobuffalo/5-google-predictions-for-2016', 'ext': 'webm', 'title': '5 Google Predictions for 2016', 'description': 'Google had a great 2015, but it\'s already time to look ahead. Here are our five predictions for 2016.', 'upload_date': '20151228', 'timestamp': 1451325600, 'duration': 187, + 'uploader': 'TechnoBuffalo', + 'uploader_id': 'technobuffalo', } }, { 'url': 'http://testtube.com/brainstuff', @@ -34,6 +38,20 @@ class Revision3IE(InfoExtractor): 'description': 'Whether the topic is popcorn or particle physics, you can count on the HowStuffWorks team to explore-and explain-the everyday science in the world around us on BrainStuff.', }, 'playlist_mincount': 93, + }, { + 'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial', + 'info_dict': { + 'id': '60163', + 'display_id': 'dnews/5-weird-ways-plants-can-eat-animals', + 'duration': 275, + 'ext': 'webm', + 'title': '5 Weird Ways Plants Can Eat Animals', + 'description': 'Why have some plants evolved to eat meat?', + 'upload_date': '20150120', + 'timestamp': 1421763300, + 'uploader': 'DNews', + 'uploader_id': 'dnews', + }, }] _PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s' _API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62' @@ -51,7 +69,7 @@ class Revision3IE(InfoExtractor): video_id)['items'][0] formats = [] - for media_type, media in video_data['media'].items(): + for vcodec, media in video_data['media'].items(): for quality_id, quality in media.items(): if quality_id == 'hls': formats.extend(self._extract_m3u8_formats( @@ -60,22 +78,28 @@ class Revision3IE(InfoExtractor): else: formats.append({ 'url': quality['url'], - 'format_id': '%s-%s' % (media_type, quality_id), + 'format_id': '%s-%s' % (vcodec, quality_id), 'tbr': int_or_none(quality.get('bitrate')), + 'vcodec': vcodec, }) self._sort_formats(formats) + preference = qualities(['mini', 'small', 'medium', 'large']) thumbnails = [{ 'url': image_url, 'id': image_id, + 'preference': preference(image_id) } for image_id, image_url in video_data.get('images', {}).items()] return { 'id': video_id, + 'display_id': display_id, 'title': unescapeHTML(video_data['title']), 'description': unescapeHTML(video_data.get('summary')), 'timestamp': parse_iso8601(episode_data.get('publishTime'), ' '), 'author': episode_data.get('author'), + 'uploader': video_data.get('show', {}).get('name'), + 'uploader_id': video_data.get('show', {}).get('slug'), 'duration': int_or_none(video_data.get('duration')), 'thumbnails': thumbnails, 'formats': formats, @@ -89,7 +113,7 @@ class Revision3IE(InfoExtractor): page_num = 1 while True: entries.extend([self.url_result( - url + '/%s' % episode['slug']) for episode in episodes_data]) + 'http://%s/%s/%s' % (domain, display_id, episode['slug'])) for episode in episodes_data]) processed_episodes += len(episodes_data) if processed_episodes == num_episodes: break diff --git a/youtube_dl/extractor/testtube.py b/youtube_dl/extractor/testtube.py deleted file mode 100644 index 26655d690..000000000 --- a/youtube_dl/extractor/testtube.py +++ /dev/null @@ -1,90 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - qualities, -) - - -class TestTubeIE(InfoExtractor): - _VALID_URL = r'https?://testtube\.com/[^/?#]+/(?P[^/?#]+)' - _TESTS = [{ - 'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial', - 'info_dict': { - 'id': '60163', - 'display_id': '5-weird-ways-plants-can-eat-animals', - 'duration': 275, - 'ext': 'webm', - 'title': '5 Weird Ways Plants Can Eat Animals', - 'description': 'Why have some plants evolved to eat meat?', - 'thumbnail': 're:^https?://.*\.jpg$', - 'uploader': 'DNews', - 'uploader_id': 'dnews', - }, - }, { - 'url': 'https://testtube.com/iflscience/insane-jet-ski-flipping', - 'info_dict': { - 'id': 'fAGfJ4YjVus', - 'ext': 'mp4', - 'title': 'Flipping Jet-Ski Skills | Outrageous Acts of Science', - 'uploader': 'Science Channel', - 'uploader_id': 'ScienceChannel', - 'upload_date': '20150203', - 'description': 'md5:e61374030015bae1d2e22f096d4769d6', - } - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - youtube_url = self._html_search_regex( - r']+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"', - webpage, 'youtube iframe', default=None) - if youtube_url: - return self.url_result(youtube_url, 'Youtube', video_id=display_id) - - video_id = self._search_regex( - r"player\.loadRevision3Item\('video_id',\s*([0-9]+)\);", - webpage, 'video ID') - - all_info = self._download_json( - 'https://testtube.com/api/getPlaylist.json?api_key=ba9c741bce1b9d8e3defcc22193f3651b8867e62&codecs=h264,vp8,theora&video_id=%s' % video_id, - video_id) - info = all_info['items'][0] - - formats = [] - for vcodec, fdatas in info['media'].items(): - for name, fdata in fdatas.items(): - formats.append({ - 'format_id': '%s-%s' % (vcodec, name), - 'url': fdata['url'], - 'vcodec': vcodec, - 'tbr': fdata.get('bitrate'), - }) - self._sort_formats(formats) - - duration = int_or_none(info.get('duration')) - images = info.get('images') - thumbnails = None - preference = qualities(['mini', 'small', 'medium', 'large']) - if images: - thumbnails = [{ - 'id': thumbnail_id, - 'url': img_url, - 'preference': preference(thumbnail_id) - } for thumbnail_id, img_url in images.items()] - - return { - 'id': video_id, - 'display_id': display_id, - 'title': info['title'], - 'description': info.get('summary'), - 'thumbnails': thumbnails, - 'uploader': info.get('show', {}).get('name'), - 'uploader_id': info.get('show', {}).get('slug'), - 'duration': duration, - 'formats': formats, - }