X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=ae17acd5dcd67e5dc10046174a17611924c1b187;hb=4c21c56bfe661f469ae4bea63c4dc78083e3179d;hp=71b6a136eb13e3d2d0d1d462f08b6ff369009998;hpb=633b4a5ff6bf100659695f9f932dd000919a2630;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 71b6a136e..ae17acd5d 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') @@ -1674,7 +1674,7 @@ class YoutubePlaylistIE(InfoExtractor): _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' + _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}" IE_NAME = u'youtube:playlist' def __init__(self, downloader=None): @@ -1713,7 +1713,7 @@ class YoutubePlaylistIE(InfoExtractor): url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum) request = compat_urllib_request.Request(url) try: - page = compat_urllib_request.urlopen(request).read() + page = compat_urllib_request.urlopen(request).read().decode('utf8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return @@ -1725,10 +1725,12 @@ class YoutubePlaylistIE(InfoExtractor): ids_in_page.append(mobj.group(1)) video_ids.extend(ids_in_page) - if re.search(self._MORE_PAGES_INDICATOR, page) is None: + if self._MORE_PAGES_INDICATOR not in page: break pagenum = pagenum + 1 + total = len(video_ids) + playliststart = self._downloader.params.get('playliststart', 1) - 1 playlistend = self._downloader.params.get('playlistend', -1) if playlistend == -1: @@ -1736,6 +1738,11 @@ class YoutubePlaylistIE(InfoExtractor): else: video_ids = video_ids[playliststart:playlistend] + if len(video_ids) == total: + self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total)) + else: + self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(video_ids))) + for id in video_ids: self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) return @@ -1746,7 +1753,7 @@ class YoutubeChannelIE(InfoExtractor): _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$" _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' - _MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO + _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}" IE_NAME = u'youtube:channel' def report_download_page(self, channel_id, pagenum): @@ -1770,7 +1777,7 @@ class YoutubeChannelIE(InfoExtractor): url = self._TEMPLATE_URL % (channel_id, pagenum) request = compat_urllib_request.Request(url) try: - page = compat_urllib_request.urlopen(request).read() + page = compat_urllib_request.urlopen(request).read().decode('utf8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return @@ -1782,10 +1789,12 @@ class YoutubeChannelIE(InfoExtractor): ids_in_page.append(mobj.group(1)) video_ids.extend(ids_in_page) - if re.search(self._MORE_PAGES_INDICATOR, page) is None: + if self._MORE_PAGES_INDICATOR not in page: break pagenum = pagenum + 1 + self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) + for id in video_ids: self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) return @@ -2262,7 +2271,7 @@ 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 +2296,8 @@ 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 @@ -2799,18 +2809,17 @@ class SoundcloudIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' IE_NAME = u'soundcloud' - _WORKING = False 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) @@ -2824,65 +2833,42 @@ 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)) - url = 'https://soundcloud.com/%s/%s' % (uploader, slug_title) - request = compat_urllib_request.Request(url) + 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: - urlo = 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) - else: - self._downloader.trouble(u'ERROR: unable to find video ID in Soundcloud file') + 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 - # 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)) - - # 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'], }]