1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 08:27:43 +00:00
youtube-dl/youtube_dl/extractor/npr.py

125 lines
4.9 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
from .common import InfoExtractor
2016-01-06 19:57:36 +00:00
from ..utils import (
int_or_none,
qualities,
url_or_none,
2016-01-06 19:57:36 +00:00
)
2016-01-06 19:57:36 +00:00
class NprIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?npr\.org/(?:sections/[^/]+/)?\d{4}/\d{2}/\d{2}/(?P<id>\d+)'
2016-01-06 19:57:36 +00:00
_TESTS = [{
'url': 'https://www.npr.org/sections/allsongs/2015/10/21/449974205/new-music-from-beach-house-chairlift-cmj-discoveries-and-more',
2016-01-06 19:57:36 +00:00
'info_dict': {
'id': '449974205',
'title': 'New Music From Beach House, Chairlift, CMJ Discoveries And More'
},
'playlist_count': 7,
}, {
'url': 'https://www.npr.org/sections/deceptivecadence/2015/10/09/446928052/music-from-the-shadows-ancient-armenian-hymns-and-piano-jazz',
2016-01-06 19:57:36 +00:00
'info_dict': {
'id': '446928052',
'title': "Songs We Love: Tigran Hamasyan, 'Your Mercy is Boundless'"
},
'playlist': [{
'md5': '12fa60cb2d3ed932f53609d4aeceabf1',
'info_dict': {
'id': '446929930',
'ext': 'mp3',
'title': 'Your Mercy is Boundless (Bazum en Qo gtutyunqd)',
'duration': 402,
},
}],
}, {
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 15:00:05 +00:00
# multimedia, not media title
'url': 'https://www.npr.org/2017/06/19/533198237/tigers-jaw-tiny-desk-concert',
'info_dict': {
'id': '533198237',
'title': 'Tigers Jaw: Tiny Desk Concert',
},
'playlist': [{
'md5': '12fa60cb2d3ed932f53609d4aeceabf1',
'info_dict': {
'id': '533201718',
'ext': 'mp4',
'title': 'Tigers Jaw: Tiny Desk Concert',
'duration': 402,
},
}],
'expected_warnings': ['Failed to download m3u8 information'],
}, {
# multimedia, no formats, stream
'url': 'https://www.npr.org/2020/02/14/805476846/laura-stevenson-tiny-desk-concert',
'only_matching': True,
2016-01-06 19:57:36 +00:00
}]
def _real_extract(self, url):
2016-01-06 19:57:36 +00:00
playlist_id = self._match_id(url)
story = self._download_json(
'http://api.npr.org/query', playlist_id, query={
2016-01-06 19:57:36 +00:00
'id': playlist_id,
'fields': 'audio,multimedia,title',
2016-01-06 19:57:36 +00:00
'format': 'json',
'apiKey': 'MDAzMzQ2MjAyMDEyMzk4MTU1MDg3ZmM3MQ010',
})['list']['story'][0]
playlist_title = story.get('title', {}).get('$text')
KNOWN_FORMATS = ('threegp', 'm3u8', 'smil', 'mp4', 'mp3')
2016-01-06 19:57:36 +00:00
quality = qualities(KNOWN_FORMATS)
2016-01-06 19:57:36 +00:00
entries = []
for media in story.get('audio', []) + story.get('multimedia', []):
media_id = media['id']
2016-01-06 19:57:36 +00:00
formats = []
for format_id, formats_entry in media.get('format', {}).items():
2016-01-06 19:57:36 +00:00
if not formats_entry:
continue
if isinstance(formats_entry, list):
formats_entry = formats_entry[0]
format_url = formats_entry.get('$text')
if not format_url:
continue
if format_id in KNOWN_FORMATS:
if format_id == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, media_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif format_id == 'smil':
smil_formats = self._extract_smil_formats(
format_url, media_id, transform_source=lambda s: s.replace(
'rtmp://flash.npr.org/ondemand/', 'https://ondemand.npr.org/'))
self._check_formats(smil_formats, media_id)
formats.extend(smil_formats)
else:
formats.append({
'url': format_url,
'format_id': format_id,
'quality': quality(format_id),
})
for stream_id, stream_entry in media.get('stream', {}).items():
if not isinstance(stream_entry, dict):
continue
if stream_id != 'hlsUrl':
continue
stream_url = url_or_none(stream_entry.get('$text'))
if not stream_url:
continue
formats.extend(self._extract_m3u8_formats(
stream_url, stream_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
2016-01-06 19:57:36 +00:00
self._sort_formats(formats)
2016-01-06 19:57:36 +00:00
entries.append({
'id': media_id,
'title': media.get('title', {}).get('$text') or playlist_title,
'thumbnail': media.get('altImageUrl', {}).get('$text'),
'duration': int_or_none(media.get('duration', {}).get('$text')),
2016-01-06 19:57:36 +00:00
'formats': formats,
})
2016-01-06 19:57:36 +00:00
return self.playlist_result(entries, playlist_id, playlist_title)