From: kaspi Date: Sun, 18 Oct 2015 03:27:03 +0000 (-0400) Subject: [npr] Add extractor X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=76048b23e8a4aac93a33a96356fe64a9bcf78421;p=youtube-dl [npr] Add extractor removed md5 from _TEST moved from xml data to json test changed _TEST url to one that will not expire, so tests would not be failing --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 19cea5e99..c46e19eae 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -473,6 +473,7 @@ from .npo import ( VPROIE, WNLIE ) +from .npr import NprIE from .nrk import ( NRKIE, NRKPlaylistIE, diff --git a/youtube_dl/extractor/npr.py b/youtube_dl/extractor/npr.py new file mode 100644 index 000000000..a823bc096 --- /dev/null +++ b/youtube_dl/extractor/npr.py @@ -0,0 +1,71 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import os.path +import re + +from ..compat import compat_urllib_parse_unquote +from ..utils import url_basename +from .common import InfoExtractor + +class NprIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?npr\.org/player/v2/mediaPlayer.html?.*id=(?P[0-9]+)' + _TEST = { + 'url': 'http://www.npr.org/player/v2/mediaPlayer.html?id=449974205', + 'info_dict': { + 'id': '449974205', + 'ext': 'mp4', + 'title': 'New Music From Beach House, Chairlift, CMJ Discoveries And More' + } +} + + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage_url = 'http://www.npr.org/player/v2/mediaPlayer.html?id=' + video_id + webpage = self._download_webpage(webpage_url, video_id) + key = 'MDAzMzQ2MjAyMDEyMzk4MTU1MDg3ZmM3MQ010' + xml_url = 'http://api.npr.org/query?id=%s&apiKey=%s' % (video_id, key) + json_url = 'http://api.npr.org/query?id=%s&apiKey=%s&format=json' % (video_id, key) + + formats = [] + entries = [] + + config = self._download_json(json_url, video_id) + + content = config["list"]["story"] + + album_title = config["list"]["story"][0]['song'][0]['album']['albumTitle'] + print album_title['$text'] + + for key in content: + if "audio" in key: + for x in key['audio']: + if x['type'] == 'standard': + playlist = True + song_duration = x["duration"]['$text'] + song_title = x["title"]["$text"] + song_id = x["id"] + + for k in x["format"]: + if type(x["format"][k]) is list: + for z in x["format"][k]: + formats.append({ 'format': z['type'], + 'url' : z['$text'] + }) + else: + formats.append({ 'format': k, + 'url' : x["format"][k]['$text'] + }) + + entries.append({ "title":song_title, + "id":song_id, + "duration": song_duration , + "formats":formats}) + formats = [] + + return { '_type': 'playlist', + 'id' : video_id, + 'title' : album_title, + 'entries': entries }