w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[hypem] Modernize

Browse source
This commit is contained in:
Philipp Hagemeister 2014-06-09 22:30:57 +02:00
parent 2b88feedf7
commit 2656f4eb6a
1 changed files with 33 additions and 35 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

68
youtube_dl/extractor/hypem.py
View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import json import json
import re import re
import time import time
@ -13,59 +15,55 @@ from ..utils import (
class HypemIE(InfoExtractor): class HypemIE(InfoExtractor):
"""Information Extractor for hypem""" _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
_VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
_TEST = { _TEST = {
u'url': u'http://hypem.com/track/1v6ga/BODYWORK+-+TAME', 'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
u'file': u'1v6ga.mp3', 'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
u'md5': u'b9cc91b5af8995e9f0c1cee04c575828', 'info_dict': {
u'info_dict': { 'id': '1v6ga',
u"title": u"Tame" 'ext': 'mp3',
'title': 'Tame',
'uploader': 'BODYWORK',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
track_id = mobj.group(1) track_id = mobj.group(1)
data = {'ax': 1, 'ts': time.time()} data = {'ax': 1, 'ts': time.time()}
data_encoded = compat_urllib_parse.urlencode(data) data_encoded = compat_urllib_parse.urlencode(data)
complete_url = url + "?" + data_encoded complete_url = url + "?" + data_encoded
request = compat_urllib_request.Request(complete_url) request = compat_urllib_request.Request(complete_url)
response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url') response, urlh = self._download_webpage_handle(
request, track_id, 'Downloading webpage with the url')
cookie = urlh.headers.get('Set-Cookie', '') cookie = urlh.headers.get('Set-Cookie', '')
self.report_extraction(track_id) html_tracks = self._html_search_regex(
r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>', response, 'tracks')
response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
try: try:
track_list = json.loads(html_tracks) track_list = json.loads(html_tracks)
track = track_list[u'tracks'][0] track = track_list['tracks'][0]
except ValueError: except ValueError:
raise ExtractorError(u'Hypemachine contained invalid JSON.') raise ExtractorError('Hypemachine contained invalid JSON.')
key = track[u"key"] key = track['key']
track_id = track[u"id"] track_id = track['id']
artist = track[u"artist"] artist = track['artist']
title = track[u"song"] title = track['song']
serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key)) serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'}) request = compat_urllib_request.Request(
serve_url, '', {'Content-Type': 'application/json'})
request.add_header('cookie', cookie) request.add_header('cookie', cookie)
song_data_json = self._download_webpage(request, track_id, u'Downloading metadata') song_data = self._download_json(request, track_id, 'Downloading metadata')
try: final_url = song_data["url"]
song_data = json.loads(song_data_json)
except ValueError:
raise ExtractorError(u'Hypemachine contained invalid JSON.')
final_url = song_data[u"url"]
return [{ return {
'id': track_id, 'id': track_id,
'url': final_url, 'url': final_url,
'ext': "mp3", 'ext': 'mp3',
'title': title, 'title': title,
'artist': artist, 'uploader': artist,
}] }