pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-04-14 19:14:51 +09:00
Code Issues Projects Releases Wiki Activity

corrected HypemIE and added tests for hypem.com

Browse Source
This commit is contained in:
M.Yasoob Khalid 2013-06-05 22:06:25 +05:00
parent 40e4fcf910
commit 90e48f573d
2 changed files with 22 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
test/tests.json
View File

@ -491,5 +491,14 @@
"info_dict":{ "info_dict":{
"title":"FemaleAgent Shy beauty takes the bait" "title":"FemaleAgent Shy beauty takes the bait"
} }
},
{
"name": "Hypem",
"url": "http://hypem.com/track/1v6ga/BODYWORK+-+TAME",
"file": "1v6ga.mp3",
"md5": "b9cc91b5af8995e9f0c1cee04c575828",
"info_dict":{
"title":"TAME"
}
} }
] ]

28
youtube_dl/InfoExtractors.py
View File

@ -19,6 +19,7 @@ import operator
import hashlib import hashlib
import binascii import binascii
import urllib import urllib
import urllib2
from .utils import * from .utils import *
@ -4487,22 +4488,17 @@ class HypemIE(InfoExtractor):
"""Information Extractor for hypem""" """Information Extractor for hypem"""
_VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
def removeDisallowedFilenameChars(filename):
validFilenameChars = "-_.() %s%s" % (string.ascii_letters, string.digits)
cleanedFilename = unicodedata.normalize('NFKD', filename).encode('ASCII', 'ignore')
return ''.join(c for c in cleanedFilename if c in validFilenameChars)
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: if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError(u'Invalid URL: %s' % url)
data = {'ax':1 , data = {'ax':1 ,
'ts': time() 'ts': time.time()
} }
data_encoded = urllib.urlencode(data) data_encoded = urllib.urlencode(data)
complete_url = url + "?"+data_encoded complete_url = url + "?"+data_encoded
request = urllib2.Request(complete_url) request = compat_urllib_request.Request(complete_url)
response = urllib2.urlopen(request) response = compat_urllib_request.urlopen(request)
#save our cookie #save our cookie
cookie = response.headers.get('Set-Cookie') cookie = response.headers.get('Set-Cookie')
#grab the HTML #grab the HTML
@ -4523,15 +4519,16 @@ class HypemIE(InfoExtractor):
for track in tracks: for track in tracks:
key = track[u"key"] key = track[u"key"]
id = track[u"id"] id = track[u"id"]
artist = removeDisallowedFilenameChars(track[u"artist"]) artist = track[u"artist"]
title = removeDisallowedFilenameChars(track[u"song"]) title = track[u"song"]
type = track[u"type"] type = track[u"type"]
if type is False: if type is False:
continue continue
serve_url = "http://hypem.com/serve/source/{}/{}".format(id, key) serve_url = "http://hypem.com/serve/source/%s/%s"%(str(id), str(key))
request = urllib2.Request(serve_url, "" , {'Content-Type': 'application/json'}) self.report_extraction(id)
request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
request.add_header('cookie', cookie) request.add_header('cookie', cookie)
response = urllib2.urlopen(request) response = compat_urllib_request.urlopen(request)
song_data_json = response.read() song_data_json = response.read()
response.close() response.close()
song_data = json.loads(song_data_json) song_data = json.loads(song_data_json)
@ -4544,6 +4541,7 @@ class HypemIE(InfoExtractor):
'artist': artist, 'artist': artist,
}] }]
def gen_extractors(): def gen_extractors():
""" Return a list of an instance of every supported extractor. """ Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL. The order does matter; the first extractor matched is the one handling the URL.