mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-10 00:58:17 +02:00
[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
This commit is contained in:
parent
f20756fb10
commit
76048b23e8
@ -473,6 +473,7 @@
|
||||
VPROIE,
|
||||
WNLIE
|
||||
)
|
||||
from .npr import NprIE
|
||||
from .nrk import (
|
||||
NRKIE,
|
||||
NRKPlaylistIE,
|
||||
|
71
youtube_dl/extractor/npr.py
Normal file
71
youtube_dl/extractor/npr.py
Normal file
@ -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<id>[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 }
|
Loading…
Reference in New Issue
Block a user