X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/feb5020b37d7d3ba4005a8bac6f4efece4ce4b8c..0433503f78928c1f0c76a8d66ef236dc35ff23df:/youtube_dl/extractor/hypem.py diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py index ab2b591..f7c9130 100644 --- a/youtube_dl/extractor/hypem.py +++ b/youtube_dl/extractor/hypem.py @@ -1,71 +1,61 @@ +from __future__ import unicode_literals + import json -import re import time from .common import InfoExtractor +from ..compat import compat_urllib_parse_urlencode from ..utils import ( - compat_str, - compat_urllib_parse, - compat_urllib_request, - ExtractorError, + sanitized_Request, ) class HypemIE(InfoExtractor): - """Information Extractor for hypem""" - _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' + _VALID_URL = r'https?://(?:www\.)?hypem\.com/track/(?P[^/]+)/' _TEST = { - u'url': u'http://hypem.com/track/1v6ga/BODYWORK+-+TAME', - u'file': u'1v6ga.mp3', - u'md5': u'b9cc91b5af8995e9f0c1cee04c575828', - u'info_dict': { - u"title": u"Tame" + 'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME', + 'md5': 'b9cc91b5af8995e9f0c1cee04c575828', + 'info_dict': { + 'id': '1v6ga', + 'ext': 'mp3', + 'title': 'Tame', + 'uploader': 'BODYWORK', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - track_id = mobj.group(1) - - data = { 'ax': 1, 'ts': time.time() } - data_encoded = compat_urllib_parse.urlencode(data) - complete_url = url + "?" + data_encoded - request = compat_urllib_request.Request(complete_url) - response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url') - cookie = urlh.headers.get('Set-Cookie', '') + track_id = self._match_id(url) - self.report_extraction(track_id) + 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') - html_tracks = self._html_search_regex(r'', - response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip() + html_tracks = self._html_search_regex( + r'(?ms)', + response, 'tracks') try: track_list = json.loads(html_tracks) - track = track_list[u'tracks'][0] + track = track_list['tracks'][0] except ValueError: - raise ExtractorError(u'Hypemachine contained invalid JSON.') - - key = track[u"key"] - track_id = track[u"id"] - artist = track[u"artist"] - title = track[u"song"] - - serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key)) - request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'}) - request.add_header('cookie', cookie) - song_data_json = self._download_webpage(request, track_id, u'Downloading metadata') - try: - song_data = json.loads(song_data_json) - except ValueError: - raise ExtractorError(u'Hypemachine contained invalid JSON.') - final_url = song_data[u"url"] - - return [{ - 'id': track_id, - 'url': final_url, - 'ext': "mp3", - 'title': title, - 'artist': artist, - }] \ No newline at end of file + raise ExtractorError('Hypemachine contained invalid JSON.') + + 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') + + return { + 'id': track_id, + 'url': final_url, + 'ext': 'mp3', + 'title': title, + 'uploader': artist, + }