From 77c4beab8a0c13e158bad8af4e014d57766f1940 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Thu, 20 Dec 2012 16:28:16 +0100 Subject: [PATCH] new info_dict field: uploader_id --- README.md | 19 ++++++++++--------- test/tests.json | 1 + youtube_dl/InfoExtractors.py | 18 +++++++++++++++--- youtube_dl/__init__.py | 2 +- 4 files changed, 27 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index 2ca021125..9dffd99ab 100644 --- a/README.md +++ b/README.md @@ -46,15 +46,16 @@ ## Filesystem Options: -A, --auto-number number downloaded files starting from 00000 -o, --output TEMPLATE 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' . + %(uploader_id)s for the uploader nickname if + different, %(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/%(upl + oader)s/%(title)s-%(id)s.%(ext)s' . --restrict-filenames Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames -a, --batch-file FILE file containing URLs to download ('-' for stdin) diff --git a/test/tests.json b/test/tests.json index 4f8f68f38..83afda985 100644 --- a/test/tests.json +++ b/test/tests.json @@ -6,6 +6,7 @@ "info_dict": { "title": "youtube-dl test video \"'/\\ä↭𝕐", "uploader": "Philipp Hagemeister", + "uploader_id": "phihag", "upload_date": "20121002", "description": "test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ." } diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 6201ccad7..3eb070d4a 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -32,7 +32,7 @@ class InfoExtractor(object): id: Video identifier. url: Final video URL. - uploader: Nickname of the video uploader, unescaped. + uploader: Full name of the video uploader, unescaped. upload_date: Video upload date (YYYYMMDD). title: Video title, unescaped. ext: Video filename extension. @@ -42,6 +42,7 @@ class InfoExtractor(object): format: The video format, defaults to ext (used for --get-format) thumbnail: Full URL to a video thumbnail image. description: One-line video description. + uploader_id: Nickname or id of the video uploader. player_url: SWF Player URL (used for rtmpdump). subtitles: The .srt file contents. urlhandle: [internal] The urlHandle to be used to download the file, @@ -384,10 +385,18 @@ def _real_extract(self, url): # uploader if 'author' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + self._downloader.trouble(u'ERROR: unable to extract uploader name') return video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) + # uploader_id + video_uploader_id = None + mobj = re.search(r'', video_webpage) + if mobj is not None: + video_uploader_id = mobj.group(1) + else: + self._downloader.trouble(u'WARNING: unable to extract uploader nickname') + # title if 'title' not in video_info: self._downloader.trouble(u'ERROR: unable to extract video title') @@ -495,6 +504,7 @@ def _real_extract(self, url): 'id': video_id, 'url': video_real_url, 'uploader': video_uploader, + 'uploader_id': video_uploader_id, 'upload_date': upload_date, 'title': video_title, 'ext': video_extension, @@ -994,8 +1004,9 @@ def _real_extract(self, url, new_video=True): # Extract title video_title = config["video"]["title"] - # Extract uploader + # Extract uploader and uploader_id video_uploader = config["video"]["owner"]["name"] + video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] # Extract video thumbnail video_thumbnail = config["video"]["thumbnail"] @@ -1047,6 +1058,7 @@ def _real_extract(self, url, new_video=True): 'id': video_id, 'url': video_url, 'uploader': video_uploader, + 'uploader_id': video_uploader_id, 'upload_date': video_upload_date, 'title': video_title, 'ext': video_extension, diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 9b25ab3a2..1102b2fce 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -307,7 +307,7 @@ def _find_term_columns(): 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. Can also be used to download to a different directory, for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .') + dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, %(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)