aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
authorFilippo Valsorda <filippo.valsorda@gmail.com>2012-12-08 01:57:43 +0100
committerFilippo Valsorda <filippo.valsorda@gmail.com>2012-12-08 01:57:43 +0100
commit3c6ffbaedbbae8734f6b86fea1169413b656abf3 (patch)
tree27edbd964e1411e0228900b1c36612058cca7954 /youtube_dl
parentc7287a3cafba65b700b64633d76aa016f5cbc95d (diff)
parent863baa16eca7a98c38fb29c5e54f76df224f2351 (diff)
Merge 'rg3/master' into fork_master
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/FileDownloader.py7
-rw-r--r--youtube_dl/InfoExtractors.py76
-rw-r--r--youtube_dl/__init__.py2
-rw-r--r--youtube_dl/utils.py23
4 files changed, 49 insertions, 59 deletions
diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py
index 48c8eb126..c471cc160 100644
--- a/youtube_dl/FileDownloader.py
+++ b/youtube_dl/FileDownloader.py
@@ -334,8 +334,11 @@ class FileDownloader(object):
template_dict['epoch'] = int(time.time())
template_dict['autonumber'] = u'%05d' % self._num_downloads
- template_dict = dict((key, u'NA' if val is None else val) for key, val in template_dict.items())
- template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items())
+ sanitize = lambda k,v: sanitize_filename(
+ u'NA' if v is None else compat_str(v),
+ restricted=self.params.get('restrictfilenames'),
+ is_id=(k==u'id'))
+ template_dict = dict((k, sanitize(k, v)) for k,v in template_dict.items())
filename = self.params['outtmpl'] % template_dict
return filename
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 925dabc96..49976c25b 100644
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -1671,7 +1671,7 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+ _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([0-9A-Za-z_-]+))?.*'
_TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;([^&"]+&amp;)*list=.*?%s'
_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
@@ -2803,13 +2803,13 @@ class SoundcloudIE(InfoExtractor):
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- def report_webpage(self, video_id):
+ def report_resolve(self, video_id):
"""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):
"""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):
mobj = re.match(self._VALID_URL, url)
@@ -2818,65 +2818,47 @@ class SoundcloudIE(InfoExtractor):
return
# extract uploader (which is in the url)
- uploader = mobj.group(1).decode('utf-8')
+ uploader = mobj.group(1)
# extract simple title (uploader + slug of song title)
- slug_title = mobj.group(2).decode('utf-8')
+ slug_title = mobj.group(2)
simple_title = uploader + u'-' + slug_title
- self.report_webpage('%s/%s' % (uploader, slug_title))
+ self.report_resolve('%s/%s' % (uploader, slug_title))
- request = compat_urllib_request.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
+ url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
+ resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+ request = compat_urllib_request.Request(resolv_url)
try:
- webpage = compat_urllib_request.urlopen(request).read()
+ info_json_bytes = compat_urllib_request.urlopen(request).read()
+ info_json = info_json_bytes.decode('utf-8')
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))
return
+ info = json.loads(info_json)
+ video_id = info['id']
self.report_extraction('%s/%s' % (uploader, slug_title))
- # extract uid and stream token that soundcloud hands out for access
- mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
- if mobj:
- video_id = mobj.group(1)
- stream_token = mobj.group(2)
-
- # extract unsimplified title
- mobj = re.search('"title":"(.*?)",', webpage)
- if mobj:
- title = mobj.group(1).decode('utf-8')
- else:
- title = simple_title
-
- # construct media url (with uid/token)
- mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
- mediaURL = mediaURL % (video_id, stream_token)
-
- # description
- description = u'No description available'
- mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
- if mobj:
- description = mobj.group(1)
-
- # upload date
- upload_date = None
- mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
- if mobj:
- try:
- upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
- except Exception as err:
- self._downloader.to_stderr(compat_str(err))
+ streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+ request = compat_urllib_request.Request(streams_url)
+ try:
+ stream_json_bytes = compat_urllib_request.urlopen(request).read()
+ stream_json = stream_json_bytes.decode('utf-8')
+ 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))
+ return
- # for soundcloud, a request to a cross domain is required for cookies
- request = compat_urllib_request.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
+ streams = json.loads(stream_json)
+ mediaURL = streams['http_mp3_128_url']
return [{
- 'id': video_id.decode('utf-8'),
+ 'id': info['id'],
'url': mediaURL,
- 'uploader': uploader.decode('utf-8'),
- 'upload_date': upload_date,
- 'title': title,
+ 'uploader': info['user']['username'],
+ 'upload_date': info['created_at'],
+ 'title': info['title'],
'ext': u'mp3',
- 'description': description.decode('utf-8')
+ 'description': info['description'],
}]
diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index f953f1fb9..8e46dfea9 100644
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -305,7 +305,7 @@ def parseOpts():
action='store_true', dest='autonumber',
help='number downloaded files starting from 00000', default=False)
filesystem.add_option('-o', '--output',
- dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout.')
+ dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')
filesystem.add_option('--restrict-filenames',
action='store_true', dest='restrictfilenames',
help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 7f73b8476..44f939053 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -317,9 +317,10 @@ def timeconvert(timestr):
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
-def sanitize_filename(s, restricted=False):
+def sanitize_filename(s, restricted=False, is_id=False):
"""Sanitizes a string so it could be used as part of a filename.
If restricted is set, use a stricter subset of allowed characters.
+ Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
"""
def replace_insane(char):
if char == '?' or ord(char) < 32 or ord(char) == 127:
@@ -337,14 +338,15 @@ def sanitize_filename(s, restricted=False):
return char
result = u''.join(map(replace_insane, s))
- while '__' in result:
- result = result.replace('__', '_')
- result = result.strip('_')
- # Common case of "Foreign band name - English song title"
- if restricted and result.startswith('-_'):
- result = result[2:]
- if not result:
- result = '_'
+ if not is_id:
+ while '__' in result:
+ result = result.replace('__', '_')
+ result = result.strip('_')
+ # Common case of "Foreign band name - English song title"
+ if restricted and result.startswith('-_'):
+ result = result[2:]
+ if not result:
+ result = '_'
return result
def orderedSet(iterable):
@@ -504,3 +506,6 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
return resp
+
+ https_request = http_request
+ https_response = http_response