From f0a6c3d2bc3a7d84c9a25d8ed96e6549f3ebdacb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 7 Jun 2014 20:32:23 +0700 Subject: [PATCH] [teachertube] Add support for audios --- youtube_dl/extractor/teachertube.py | 36 ++++++++++++++++++----------- 1 file changed, 22 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index 4740f3d562..6d52763f95 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -4,13 +4,17 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + qualities, + determine_ext, +) class TeacherTubeIE(InfoExtractor): IE_NAME = 'teachertube' IE_DESC = 'teachertube.com videos' - _VALID_URL = r'https?://(?:www\.)?teachertube\.com/viewVideo\.php\?video_id=(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=)(?P\d+)' _TESTS = [{ 'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997', @@ -32,6 +36,15 @@ class TeacherTubeIE(InfoExtractor): 'description': 'md5:2ca52b20cd727773d1dc418b3d6bd07b', 'thumbnail': 're:http://.*\.jpg', }, + }, { + 'url': 'http://www.teachertube.com/music.php?music_id=8805', + 'md5': '01e8352006c65757caf7b961f6050e21', + 'info_dict': { + 'id': '8805', + 'ext': 'mp3', + 'title': 'PER ASPERA AD ASTRA', + 'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNIČKE ŠKOLE PER ASPERA AD ASTRA', + }, }] def _real_extract(self, url): @@ -40,19 +53,14 @@ class TeacherTubeIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - url = self._html_search_meta('twitter:player:stream', webpage, 'twitter player') - - formats = [{ - 'format_id': 'flv', - 'url': url.replace('mp4v', 'flv').replace('.mp4', '.flv'), - 'quality': 0, - 'ext': 'flv', - }, { - 'format_id': 'mp4', - 'url': url, - 'quality': 1, - 'ext': 'mp4', - }] + quality = qualities(['mp3', 'flv', 'mp4']) + + formats = [ + { + 'url': media_url, + 'quality': quality(determine_ext(media_url)) + } for media_url in set(zip(*re.findall(r'([\'"])file\1\s*:\s*"([^"]+)"', webpage))[1]) + ] self._sort_formats(formats)