[mixcloud] Rewrite extractor (fixes #278)

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-09-14 14:26:42 +02:00
parent 0b7f31184d
commit 19e1d35989
2 changed files with 46 additions and 83 deletions

View file

@ -5,34 +5,27 @@ import socket
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_http_client, compat_http_client,
compat_str,
compat_urllib_error, compat_urllib_error,
compat_urllib_request, compat_urllib_request,
unified_strdate,
ExtractorError,
) )
class MixcloudIE(InfoExtractor): class MixcloudIE(InfoExtractor):
_WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
IE_NAME = u'mixcloud' IE_NAME = u'mixcloud'
def report_download_json(self, file_id): _TEST = {
"""Report JSON download.""" u'url': u'http://www.mixcloud.com/dholbach/cryptkeeper/',
self.to_screen(u'Downloading json') u'file': u'dholbach-cryptkeeper.mp3',
u'info_dict': {
def get_urls(self, jsonData, fmt, bitrate='best'): u'title': u'Cryptkeeper',
"""Get urls from 'audio_formats' section in json""" u'description': u'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
try: u'uploader': u'Daniel Holbach',
bitrate_list = jsonData[fmt] u'uploader_id': u'dholbach',
if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: u'upload_date': u'20111115',
bitrate = max(bitrate_list) # select highest },
}
url_list = jsonData[fmt][bitrate]
except TypeError: # we have no bitrate info.
url_list = jsonData[fmt]
return url_list
def check_urls(self, url_list): def check_urls(self, url_list):
"""Returns 1st active url from list""" """Returns 1st active url from list"""
@ -45,71 +38,32 @@ class MixcloudIE(InfoExtractor):
return None return None
def _print_formats(self, formats):
print('Available formats:')
for fmt in formats.keys():
for b in formats[fmt]:
try:
ext = formats[fmt][b][0]
print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
except TypeError: # we have no bitrate info
ext = formats[fmt][0]
print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
break
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)
# extract uploader & filename from url
uploader = mobj.group(1).decode('utf-8')
file_id = uploader + "-" + mobj.group(2).decode('utf-8')
# construct API request uploader = mobj.group(1)
file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' cloudcast_name = mobj.group(2)
# retrieve .json file with links to files track_id = '-'.join((uploader, cloudcast_name))
request = compat_urllib_request.Request(file_url) api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
try: webpage = self._download_webpage(url, track_id)
self.report_download_json(file_url) json_data = self._download_webpage(api_url, track_id,
jsonData = compat_urllib_request.urlopen(request).read() u'Downloading cloudcast info')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: info = json.loads(json_data)
raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err))
# parse JSON preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
json_data = json.loads(jsonData) song_url = preview_url.replace('/previews/', '/cloudcasts/originals/')
player_url = json_data['player_swf_url'] template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
formats = dict(json_data['audio_formats']) final_song_url = self.check_urls(template_url % i for i in range(30))
req_format = self._downloader.params.get('format', None) return {
'id': track_id,
if self._downloader.params.get('listformats', None): 'title': info['name'],
self._print_formats(formats) 'url': final_song_url,
return 'ext': 'mp3',
'description': info['description'],
if req_format is None or req_format == 'best': 'thumbnail': info['pictures'].get('extra_large'),
for format_param in formats.keys(): 'uploader': info['user']['name'],
url_list = self.get_urls(formats, format_param) 'uploader_id': info['user']['username'],
# check urls 'upload_date': unified_strdate(info['created_time']),
file_url = self.check_urls(url_list) 'view_count': info['play_count'],
if file_url is not None: }
break # got it!
else:
if req_format not in formats:
raise ExtractorError(u'Format is not available')
url_list = self.get_urls(formats, req_format)
file_url = self.check_urls(url_list)
format_param = req_format
return [{
'id': file_id.decode('utf-8'),
'url': file_url.decode('utf-8'),
'uploader': uploader.decode('utf-8'),
'upload_date': None,
'title': json_data['name'],
'ext': file_url.split('.')[-1].decode('utf-8'),
'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
'thumbnail': json_data['thumbnail_url'],
'description': json_data['description'],
'player_url': player_url.decode('utf-8'),
}]

View file

@ -700,7 +700,16 @@ def unified_strdate(date_str):
date_str = date_str.replace(',',' ') date_str = date_str.replace(',',' ')
# %z (UTC offset) is only supported in python>=3.2 # %z (UTC offset) is only supported in python>=3.2
date_str = re.sub(r' (\+|-)[\d]*$', '', date_str) date_str = re.sub(r' (\+|-)[\d]*$', '', date_str)
format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S', '%d.%m.%Y %H:%M'] format_expressions = [
'%d %B %Y',
'%B %d %Y',
'%b %d %Y',
'%Y-%m-%d',
'%d/%m/%Y',
'%Y/%m/%d %H:%M:%S',
'%d.%m.%Y %H:%M',
'%Y-%m-%dT%H:%M:%SZ',
]
for expression in format_expressions: for expression in format_expressions:
try: try:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d') upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')