From 9e982f9e4eff4219f8c10df7529280b7eab16236 Mon Sep 17 00:00:00 2001 From: Jeff Crouse Date: Tue, 22 Jan 2013 00:50:42 -0500 Subject: [PATCH] Added "min-filesize" and "max-filesize" options --- README.md | 2 ++ youtube_dl/FileDownloader.py | 11 +++++++++++ youtube_dl/__init__.py | 16 ++++++++++++++++ 3 files changed, 29 insertions(+) diff --git a/README.md b/README.md index 71bad017d..f637e0b1b 100644 --- a/README.md +++ b/README.md @@ -38,6 +38,8 @@ ## Video Selection: --reject-title REGEX skip download for matching titles (regex or caseless sub-string) --max-downloads NUMBER Abort after downloading NUMBER files + --min-filesize SIZE Do not download any videos smaller than SIZE (e.g. 50k or 44.6m) + --max-filesize SIZE Do not download any videos larger than SIZE (e.g. 50k or 44.6m) ## Filesystem Options: -t, --title use title in file name diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index e3131bbe6..49b032a1b 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -82,6 +82,8 @@ class FileDownloader(object): subtitleslang: Language of the subtitles to download test: Download only first bytes to test the downloader. keepvideo: Keep the video file after post-processing + min_filesize: Skip files smaller than this size + max_filesize: Skip files larger than this size """ params = None @@ -712,6 +714,15 @@ def _do_download(self, filename, info_dict): data_len = data.info().get('Content-length', None) if data_len is not None: data_len = int(data_len) + resume_len + min_data_len = self.params.get("min_filesize", None) + max_data_len = self.params.get("max_filesize", None) + if min_data_len is not None and data_len < min_data_len: + self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len)) + return False + if max_data_len is not None and data_len > max_data_len: + self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len)) + return False + data_len_str = self.format_bytes(data_len) byte_counter = 0 + resume_len block_size = self.params.get('buffersize', 1024) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 10e9c8b8c..bdab38a4e 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -151,6 +151,10 @@ def _find_term_columns(): selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None) + selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Skip files smaller than this size", default=None) + selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Skip files larger than this size", default=None) + + authentication.add_option('-u', '--username', dest='username', metavar='USERNAME', help='account username') authentication.add_option('-p', '--password', @@ -349,6 +353,16 @@ def _real_main(): if numeric_limit is None: parser.error(u'invalid rate limit specified') opts.ratelimit = numeric_limit + if opts.min_filesize is not None: + numeric_limit = FileDownloader.parse_bytes(opts.min_filesize) + if numeric_limit is None: + parser.error(u'invalid min_filesize specified') + opts.min_filesize = numeric_limit + if opts.max_filesize is not None: + numeric_limit = FileDownloader.parse_bytes(opts.max_filesize) + if numeric_limit is None: + parser.error(u'invalid max_filesize specified') + opts.max_filesize = numeric_limit if opts.retries is not None: try: opts.retries = int(opts.retries) @@ -438,6 +452,8 @@ def _real_main(): 'verbose': opts.verbose, 'test': opts.test, 'keepvideo': opts.keepvideo, + 'min_filesize': opts.min_filesize, + 'max_filesize': opts.max_filesize }) if opts.verbose: