mirrors/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-15 18:34:22 +00:00
Code Issues Projects Releases Wiki Activity

[hypem] Modernize and extract more metadata(closes #15320)

Browse Source
This commit is contained in:
Remita Amine 2019-03-11 09:43:06 +01:00
parent 197cf8b794
commit f517c0c0a7
1 changed files with 17 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
youtube_dl/extractor/hypem.py
View File

@ -1,18 +1,11 @@
from __future__ import unicode_literals
import json
import time
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
from ..utils import (
ExtractorError,
sanitized_Request,
)
from ..utils import int_or_none
class HypemIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/'
_VALID_URL = r'https?://(?:www\.)?hypem\.com/track/(?P<id>[0-9a-z]{5})'
_TEST = {
'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
@ -21,41 +14,36 @@ class HypemIE(InfoExtractor):
'ext': 'mp3',
'title': 'Tame',
'uploader': 'BODYWORK',
'timestamp': 1371810457,
'upload_date': '20130621',
}
}
def _real_extract(self, url):
track_id = self._match_id(url)
data = {'ax': 1, 'ts': time.time()}
request = sanitized_Request(url + '?' + compat_urllib_parse_urlencode(data))
response, urlh = self._download_webpage_handle(
request, track_id, 'Downloading webpage with the url')
response = self._download_webpage(url, track_id)
html_tracks = self._html_search_regex(
r'(?ms)<script type="application/json" id="displayList-data">(.+?)</script>',
response, 'tracks')
try:
track_list = json.loads(html_tracks)
track = track_list['tracks'][0]
except ValueError:
raise ExtractorError('Hypemachine contained invalid JSON.')
track = self._parse_json(self._html_search_regex(
r'(?s)<script\s+type="application/json"\s+id="displayList-data">(.+?)</script>',
response, 'tracks'), track_id)['tracks'][0]
key = track['key']
track_id = track['id']
title = track['song']
request = sanitized_Request(
'http://hypem.com/serve/source/%s/%s' % (track_id, key),
'', {'Content-Type': 'application/json'})
song_data = self._download_json(request, track_id, 'Downloading metadata')
final_url = song_data['url']
artist = track.get('artist')
final_url = self._download_json(
'http://hypem.com/serve/source/%s/%s' % (track_id, track['key']),
track_id, 'Downloading metadata', headers={
'Content-Type': 'application/json'
})['url']
return {
'id': track_id,
'url': final_url,
'ext': 'mp3',
'title': title,
'uploader': artist,
'uploader': track.get('artist'),
'duration': int_or_none(track.get('time')),
'timestamp': int_or_none(track.get('ts')),
'track': title,
}