fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

More work on soundcloud IE

This commit is contained in:
Philipp Hagemeister 2012-12-07 01:24:51 +01:00
parent f9b2f2b955
commit 8fd3afd56c
1 changed files with 23 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
youtube_dl/InfoExtractors.py
View File

@ -2799,18 +2799,17 @@ class SoundcloudIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
IE_NAME = u'soundcloud' IE_NAME = u'soundcloud'
_WORKING = False
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
def report_webpage(self, video_id): def report_resolve(self, video_id):
"""Report information extraction.""" """Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id))
def report_extraction(self, video_id): def report_extraction(self, video_id):
"""Report information extraction.""" """Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id))
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -2824,28 +2823,36 @@ class SoundcloudIE(InfoExtractor):
slug_title = mobj.group(2) slug_title = mobj.group(2)
simple_title = uploader + u'-' + slug_title simple_title = uploader + u'-' + slug_title
self.report_webpage('%s/%s' % (uploader, slug_title)) self.report_resolve('%s/%s' % (uploader, slug_title))
url = 'https://soundcloud.com/%s/%s' % (uploader, slug_title) url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
request = compat_urllib_request.Request(url) resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
request = compat_urllib_request.Request(resolv_url)
try: try:
webpage_bytes = compat_urllib_request.urlopen(request).read() info_json_bytes = compat_urllib_request.urlopen(request).read()
webpage = webpage_bytes.decode('utf-8') info_json = info_json_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
return return
info = json.loads(info_json)
video_id = info['id']
self.report_extraction('%s/%s' % (uploader, slug_title)) self.report_extraction('%s/%s' % (uploader, slug_title))
# extract uid and stream token that soundcloud hands out for access streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage) request = compat_urllib_request.Request(resolv_url)
if mobj: try:
video_id = mobj.group(1) stream_json_bytes = compat_urllib_request.urlopen(request).read()
stream_token = mobj.group(2) stream_json = stream_json_bytes.decode('utf-8')
else: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to find video ID in Soundcloud file') self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
return return
streams = json.loads(stream_json)
print('\n\n\n' + repr(streams))
assert "http_mp3_128_url" in streams
# TODO get title etc. from info
# extract unsimplified title # extract unsimplified title
mobj = re.search('"title":"(.*?)",', webpage) mobj = re.search('"title":"(.*?)",', webpage)
if mobj: if mobj: