X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=1d774b91e7d0ea6fb3a409ad04acfb375d35b3ba;hb=55c05398724f8bbb58db1b5ea55ad22038155c36;hp=e5e8f41f06ca14673507ed26fc1f76dcdfcc98b3;hpb=15c8d83358a964e8e5d12f1d0c55fe96fc111a01;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index e5e8f41f0..1d774b91e 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1072,8 +1072,8 @@ class VimeoIE(InfoExtractor): self.report_extraction(video_id) # Extract the config JSON - config = webpage.split(' = {config:')[1].split(',assets:')[0] try: + config = webpage.split(' = {config:')[1].split(',assets:')[0] config = json.loads(config) except: self._downloader.trouble(u'ERROR: unable to extract info section') @@ -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=(.+?)&([^&"]+&)*list=.*?%s' _MORE_PAGES_INDICATOR = r'yt-uix-pager-next' @@ -2262,7 +2262,7 @@ class BlipTVIE(InfoExtractor): else: cchar = '?' json_url = url + cchar + 'skin=json&version=2&no_wrap=1' - request = compat_urllib_request.Request(json_url.encode('utf-8')) + request = compat_urllib_request.Request(json_url) self.report_extraction(mobj.group(1)) info = None try: @@ -2287,7 +2287,8 @@ class BlipTVIE(InfoExtractor): return if info is None: # Regular URL try: - json_code = urlh.read() + json_code_bytes = urlh.read() + json_code = json_code_bytes.decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err)) return @@ -2803,13 +2804,13 @@ 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) @@ -2823,61 +2824,42 @@ class SoundcloudIE(InfoExtractor): 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_bytes = compat_urllib_request.urlopen(request).read() - webpage = webpage_bytes.decode('utf-8') + 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) - 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">

(.*?)

', webpage) - if mobj: - description = mobj.group(1) - - # upload date - upload_date = None - mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)", 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, + 'id': info['id'], 'url': mediaURL, - 'uploader': uploader, - 'upload_date': upload_date, - 'title': title, + 'uploader': info['user']['username'], + 'upload_date': info['created_at'], + 'title': info['title'], 'ext': u'mp3', - 'description': description + 'description': info['description'], }]