From a1f03c7b06d0a811d18499cb2ef09405c52a5db9 Mon Sep 17 00:00:00 2001 From: Nevar Angelo Date: Tue, 30 Nov 2010 18:51:00 +0200 Subject: [PATCH 01/36] Reworked 'upload_date' code for output sequence in YoutubeIE. Reverted to previous version of 'upload_date' and fixed a mistake that prevented the code from working properly. --- youtube-dl | 35 ++++++++--------------------------- 1 file changed, 8 insertions(+), 27 deletions(-) diff --git a/youtube-dl b/youtube-dl index 24722d292..4cea2e85e 100755 --- a/youtube-dl +++ b/youtube-dl @@ -5,6 +5,7 @@ # Author: Benjamin Johnson # License: Public domain code import cookielib +import datetime import htmlentitydefs import httplib import locale @@ -36,21 +37,6 @@ std_headers = { simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') -month_name_to_number = { - 'January': '01', - 'February': '02', - 'March': '03', - 'April': '04', - 'May': '05', - 'June': '06', - 'July': '07', - 'August': '08', - 'September': '09', - 'October': '10', - 'November': '11', - 'December': '12', -} - def preferredencoding(): """Get preferred encoding. @@ -913,18 +899,13 @@ class YoutubeIE(InfoExtractor): upload_date = u'NA' mobj = re.search(r'id="eow-date".*?>(.*?)', video_webpage, re.DOTALL) if mobj is not None: - try: - if ',' in mobj.group(1): - # Month Day, Year - m, d, y = mobj.group(1).replace(',', '').split() - else: - # Day Month Year, we'll suppose - d, m, y = mobj.group(1).split() - m = month_name_to_number[m] - d = '%02d' % (long(d)) - upload_date = '%s%s%s' % (y, m, d) - except: - upload_date = u'NA' + upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) + format_expressions = ['%d %B %Y', '%B %d %Y'] + for expression in format_expressions: + try: + upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') + except: + pass # description video_description = 'No description available.' From 62cf7aaf9a3b9b74ba90d1c17303eb5cabd3f52c Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Sat, 4 Dec 2010 10:38:53 +0100 Subject: [PATCH 02/36] Use a temporary filename to download files --- youtube-dl | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) diff --git a/youtube-dl b/youtube-dl index 4cea2e85e..22dd230ee 100755 --- a/youtube-dl +++ b/youtube-dl @@ -235,6 +235,11 @@ class FileDownloader(object): if not os.path.exists(dir): os.mkdir(dir) + @staticmethod + def temp_name(filename): + """Returns a temporary filename for the given filename.""" + return filename + '.part' + @staticmethod def format_bytes(bytes): if bytes is None: @@ -353,6 +358,12 @@ class FileDownloader(object): speed = float(byte_counter) / elapsed if speed > rate_limit: time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def try_rename(self, old_filename, new_filename): + try: + os.rename(old_filename, new_filename) + except (IOError, OSError), err: + self.trouble(u'ERROR: unable to rename file') def report_destination(self, filename): """Report destination filename.""" @@ -484,6 +495,7 @@ class FileDownloader(object): def _download_with_rtmpdump(self, filename, url, player_url): self.report_destination(filename) + tmpfilename = self.temp_name(filename) # Check for rtmpdump first try: @@ -495,36 +507,43 @@ class FileDownloader(object): # Download using rtmpdump. rtmpdump returns exit code 2 when # the connection was interrumpted and resuming appears to be # possible. This is part of rtmpdump's normal usage, AFAIK. - basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename] + basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]) while retval == 2 or retval == 1: - prevsize = os.path.getsize(filename) + prevsize = os.path.getsize(tmpfilename) self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) time.sleep(5.0) # This seems to be needed retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) - cursize = os.path.getsize(filename) + cursize = os.path.getsize(tmpfilename) if prevsize == cursize and retval == 1: break if retval == 0: - self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename)) + self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename)) + self.try_rename(tmpfilename, filename) return True else: self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) return False def _do_download(self, filename, url, player_url): + # Check file already present + if self.params.get('continuedl', False) and os.path.isfile(filename): + self.report_file_already_downloaded(filename) + return True + # Attempt to download using rtmpdump if url.startswith('rtmp'): return self._download_with_rtmpdump(filename, url, player_url) + tmpfilename = self.temp_name(filename) stream = None open_mode = 'wb' basic_request = urllib2.Request(url, None, std_headers) request = urllib2.Request(url, None, std_headers) # Establish possible resume length - if os.path.isfile(filename): - resume_len = os.path.getsize(filename) + if os.path.isfile(tmpfilename): + resume_len = os.path.getsize(tmpfilename) else: resume_len = 0 @@ -566,6 +585,7 @@ class FileDownloader(object): # completely downloaded if the file size differs less than 100 bytes from # the one in the hard drive. self.report_file_already_downloaded(filename) + self.try_rename(tmpfilename, filename) return True else: # The length does not match, we start the download over @@ -599,7 +619,7 @@ class FileDownloader(object): # Open file just in time if stream is None: try: - (stream, filename) = sanitize_open(filename, open_mode) + (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) self.report_destination(filename) except (OSError, IOError), err: self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) @@ -623,6 +643,7 @@ class FileDownloader(object): self.report_finish() if data_len is not None and str(byte_counter) != data_len: raise ContentTooShortError(byte_counter, long(data_len)) + self.try_rename(tmpfilename, filename) return True class InfoExtractor(object): From a9806fd83d7efc4cc1dcd11174c839f637d0c105 Mon Sep 17 00:00:00 2001 From: Vasyl' Vavrychuk Date: Sun, 5 Dec 2010 20:48:22 +0200 Subject: [PATCH 03/36] report_extraction was never called for GenericIE --- youtube-dl | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube-dl b/youtube-dl index 22dd230ee..d0584a312 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1619,6 +1619,7 @@ class GenericIE(InfoExtractor): self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) return + self.report_extraction(video_id) # Start with something easy: JW Player in SWFObject mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if mobj is None: From 6f0ff3bab9f213790817e3344bb5025a7fbea1e4 Mon Sep 17 00:00:00 2001 From: Vasyl' Vavrychuk Date: Sun, 5 Dec 2010 20:57:46 +0200 Subject: [PATCH 04/36] Fixed failure of os.rename after receiving file finished due to file not being closed. Following error happen while at the end of _do_download called try_rename WindowsError: [Error 32] The process cannot access the file because it is being used by another process --- youtube-dl | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube-dl b/youtube-dl index d0584a312..6b5f5693d 100755 --- a/youtube-dl +++ b/youtube-dl @@ -640,6 +640,7 @@ class FileDownloader(object): # Apply rate limit self.slow_down(start, byte_counter) + stream.close() self.report_finish() if data_len is not None and str(byte_counter) != data_len: raise ContentTooShortError(byte_counter, long(data_len)) From 27179cfdba64c40607ec089f53ed754efceff64a Mon Sep 17 00:00:00 2001 From: Vasyl' Vavrychuk Date: Sun, 5 Dec 2010 21:09:14 +0200 Subject: [PATCH 05/36] Implemented depositfiles.com support --- youtube-dl | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 81 insertions(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index 6b5f5693d..0e9699807 100755 --- a/youtube-dl +++ b/youtube-dl @@ -110,7 +110,6 @@ def sanitize_open(filename, open_mode): stream = open(filename, open_mode) return (stream, filename) - class DownloadError(Exception): """Download Error exception. @@ -2077,6 +2076,85 @@ class YoutubeUserIE(InfoExtractor): self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return +class DepositFilesIE(InfoExtractor): + """Information extractor for depositfiles.com""" + + _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + @staticmethod + def suitable(url): + return (re.match(DepositFilesIE._VALID_URL, url) is not None) + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) + + def _real_initialize(self): + return + + def _real_extract(self, url): + # At this point we have a new file + self._downloader.increment_downloads() + + file_id = url.split('/')[-1] + # Rebuild url in english locale + url = 'http://depositfiles.com/en/files/' + file_id + + # Retrieve file webpage with 'Free download' button pressed + free_download_indication = { 'gateway_result' : '1' } + request = urllib2.Request(url, urllib.urlencode(free_download_indication), std_headers) + try: + self.report_download_webpage(file_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err)) + return + + # Search for the real file URL + mobj = re.search(r'
(Attention.*?)', webpage, re.DOTALL) + if (mobj is not None) and (mobj.group(1) is not None): + restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() + self._downloader.trouble(u'ERROR: %s' % restriction_message) + else: + self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) + return + + file_url = mobj.group(1) + file_extension = os.path.splitext(file_url)[1][1:] + + # Search for file title + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + file_title = mobj.group(1).decode('utf-8') + + try: + # Process file information + self._downloader.process_info({ + 'id': file_id.decode('utf-8'), + 'url': file_url.decode('utf-8'), + 'uploader': u'NA', + 'upload_date': u'NA', + 'title': file_title, + 'stitle': file_title, + 'ext': file_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'ERROR: unable to download file') + class PostProcessor(object): """Post Processor class. @@ -2310,6 +2388,7 @@ if __name__ == '__main__': photobucket_ie = PhotobucketIE() yahoo_ie = YahooIE() yahoo_search_ie = YahooSearchIE(yahoo_ie) + deposit_files_ie = DepositFilesIE() generic_ie = GenericIE() # File downloader @@ -2356,6 +2435,7 @@ if __name__ == '__main__': fd.add_info_extractor(photobucket_ie) fd.add_info_extractor(yahoo_ie) fd.add_info_extractor(yahoo_search_ie) + fd.add_info_extractor(deposit_files_ie) # This must come last since it's the # fallback if none of the others work From e567ef93d8833a566f063bab9f9ee2310a131ab1 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Wed, 8 Dec 2010 11:04:22 +0100 Subject: [PATCH 06/36] Add Vasyl' Vavrychuk to the list of authors --- youtube-dl | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube-dl b/youtube-dl index 0e9699807..d60fa60c9 100755 --- a/youtube-dl +++ b/youtube-dl @@ -3,6 +3,7 @@ # Author: Ricardo Garcia Gonzalez # Author: Danny Colligan # Author: Benjamin Johnson +# Author: Vasyl' Vavrychuk # License: Public domain code import cookielib import datetime From d157d2597a5fe99db60304fe1e89523de78b7981 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Thu, 9 Dec 2010 19:22:32 +0100 Subject: [PATCH 07/36] Fix YoutubeIE after recent YouTube changes (closes #34) --- youtube-dl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube-dl b/youtube-dl index d60fa60c9..415cf7073 100755 --- a/youtube-dl +++ b/youtube-dl @@ -955,9 +955,9 @@ class YoutubeIE(InfoExtractor): self._downloader.trouble(u'ERROR: no known formats available for video') return if requested_format is None: - video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality + video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality elif requested_format == '-1': - video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats + video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats else: video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format From 7d950ca1d6543d51d066eaceb9ea1d5ac96d92f4 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Thu, 9 Dec 2010 19:33:04 +0100 Subject: [PATCH 08/36] Improve temporary filename handling of special cases --- youtube-dl | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index 415cf7073..64c590fbf 100755 --- a/youtube-dl +++ b/youtube-dl @@ -238,7 +238,9 @@ class FileDownloader(object): @staticmethod def temp_name(filename): """Returns a temporary filename for the given filename.""" - return filename + '.part' + if filename == u'-' or (os.path.exists(filename) and not os.path.isfile(filename)): + return filename + return filename + u'.part' @staticmethod def format_bytes(bytes): @@ -361,6 +363,8 @@ class FileDownloader(object): def try_rename(self, old_filename, new_filename): try: + if old_filename == new_filename: + return os.rename(old_filename, new_filename) except (IOError, OSError), err: self.trouble(u'ERROR: unable to rename file') From f148ea4473697a1e6666e789b0bfae8f0b4804e4 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Thu, 9 Dec 2010 19:37:07 +0100 Subject: [PATCH 09/36] Bump version number --- LATEST_VERSION | 2 +- youtube-dl | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/LATEST_VERSION b/LATEST_VERSION index 4f8405c40..a1c4173c8 100644 --- a/LATEST_VERSION +++ b/LATEST_VERSION @@ -1 +1 @@ -2010.11.19 +2010.12.09 diff --git a/youtube-dl b/youtube-dl index 64c590fbf..e6177e363 100755 --- a/youtube-dl +++ b/youtube-dl @@ -2232,7 +2232,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2010.11.19', + version='2010.12.09', conflict_handler='resolve', ) From f83ae7816b64ff23fbef602d7ade3fd00b57e5aa Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Thu, 9 Dec 2010 19:57:39 +0100 Subject: [PATCH 10/36] Fix problem when requesting an existing format explicitly with -f --- youtube-dl | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/youtube-dl b/youtube-dl index e6177e363..a8e3bd36c 100755 --- a/youtube-dl +++ b/youtube-dl @@ -944,7 +944,7 @@ class YoutubeIE(InfoExtractor): video_token = urllib.unquote_plus(video_info['token'][0]) # Decide which formats to download - requested_format = self._downloader.params.get('format', None) + req_format = self._downloader.params.get('format', None) get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token) if 'fmt_url_map' in video_info: @@ -958,12 +958,15 @@ class YoutubeIE(InfoExtractor): if len(existing_formats) == 0: self._downloader.trouble(u'ERROR: no known formats available for video') return - if requested_format is None: + if req_format is None: video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality - elif requested_format == '-1': + elif req_format == '-1': video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats else: - video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format + if req_format in url_map: + video_url_list = [(req_format, url_map[req_format])] # Specific format + else: + video_url_list = [(req_format, get_video_template % req_format)] # Specific format elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): self.report_rtmp_download() From 106d091e80f609802d3f6dcc3512525458900042 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Sat, 11 Dec 2010 11:32:13 +0100 Subject: [PATCH 11/36] Do not use 0% as the starting point in resumed downloads (closes #40) --- youtube-dl | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index a8e3bd36c..22b9eba17 100755 --- a/youtube-dl +++ b/youtube-dl @@ -606,8 +606,10 @@ class FileDownloader(object): return False data_len = data.info().get('Content-length', None) + if data_len is not None: + data_len = long(data_len) + resume_len data_len_str = self.format_bytes(data_len) - byte_counter = 0 + byte_counter = 0 + resume_len block_size = 1024 start = time.time() while True: From 5c1327931a91fbc2f621b7f107255463bdf698b9 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Sat, 11 Dec 2010 11:34:10 +0100 Subject: [PATCH 12/36] Stop attempting to use get_video and detect missing formats ourselves --- youtube-dl | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/youtube-dl b/youtube-dl index 22b9eba17..8f895a5cb 100755 --- a/youtube-dl +++ b/youtube-dl @@ -947,7 +947,6 @@ class YoutubeIE(InfoExtractor): # Decide which formats to download req_format = self._downloader.params.get('format', None) - get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token) if 'fmt_url_map' in video_info: url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(',')) @@ -965,10 +964,11 @@ class YoutubeIE(InfoExtractor): elif req_format == '-1': video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats else: - if req_format in url_map: - video_url_list = [(req_format, url_map[req_format])] # Specific format - else: - video_url_list = [(req_format, get_video_template % req_format)] # Specific format + # Specific format + if req_format not in url_map: + self._downloader.trouble(u'ERROR: requested format not available') + return + video_url_list = [(req_format, url_map[req_format])] # Specific format elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): self.report_rtmp_download() @@ -1002,7 +1002,7 @@ class YoutubeIE(InfoExtractor): 'player_url': player_url, }) except UnavailableVideoError, err: - self._downloader.trouble(u'ERROR: unable to download video (format may not be available)') + self._downloader.trouble(u'ERROR: unable to download video') class MetacafeIE(InfoExtractor): From ef4f4544a24633655a9347176ed475322e6dacf0 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Sat, 11 Dec 2010 11:35:28 +0100 Subject: [PATCH 13/36] Remove deprecated -b option and nonworking -m option (closes #39) --- youtube-dl | 6 ------ 1 file changed, 6 deletions(-) diff --git a/youtube-dl b/youtube-dl index 8f895a5cb..4cb84b22a 100755 --- a/youtube-dl +++ b/youtube-dl @@ -2270,14 +2270,10 @@ if __name__ == '__main__': video_format = optparse.OptionGroup(parser, 'Video Format Options') video_format.add_option('-f', '--format', action='store', dest='format', metavar='FORMAT', help='video format code') - video_format.add_option('-m', '--mobile-version', - action='store_const', dest='format', help='alias for -f 17', const='17') video_format.add_option('--all-formats', action='store_const', dest='format', help='download all available video formats', const='-1') video_format.add_option('--max-quality', action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') - video_format.add_option('-b', '--best-quality', - action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)') parser.add_option_group(video_format) verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') @@ -2351,8 +2347,6 @@ if __name__ == '__main__': all_urls = batchurls + args # Conflicting, missing and erroneous options - if opts.bestquality: - print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n' if opts.usenetrc and (opts.username is not None or opts.password is not None): parser.error(u'using .netrc conflicts with giving username/password') if opts.password is not None and opts.username is None: From b905e5f583d06678ab0a54b53a227208de7c35ee Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Sun, 12 Dec 2010 19:21:09 +0100 Subject: [PATCH 14/36] Fix erroneous "content too short" error message --- youtube-dl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index 4cb84b22a..7d4344ae0 100755 --- a/youtube-dl +++ b/youtube-dl @@ -648,7 +648,7 @@ class FileDownloader(object): stream.close() self.report_finish() - if data_len is not None and str(byte_counter) != data_len: + if data_len is not None and byte_counter != data_len: raise ContentTooShortError(byte_counter, long(data_len)) self.try_rename(tmpfilename, filename) return True From 975a91d0ac950f8558067810ba64adb2fb4feada Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Wed, 15 Dec 2010 21:42:11 +0100 Subject: [PATCH 15/36] Take into account resume_len when calculating speed and ETA --- youtube-dl | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/youtube-dl b/youtube-dl index 7d4344ae0..cf0e9fcb8 100755 --- a/youtube-dl +++ b/youtube-dl @@ -617,10 +617,9 @@ class FileDownloader(object): before = time.time() data_block = data.read(block_size) after = time.time() - data_block_len = len(data_block) - if data_block_len == 0: + if len(data_block) == 0: break - byte_counter += data_block_len + byte_counter += len(data_block) # Open file just in time if stream is None: @@ -635,16 +634,16 @@ class FileDownloader(object): except (IOError, OSError), err: self.trouble(u'\nERROR: unable to write data: %s' % str(err)) return False - block_size = self.best_block_size(after - before, data_block_len) + block_size = self.best_block_size(after - before, len(data_block)) # Progress message percent_str = self.calc_percent(byte_counter, data_len) - eta_str = self.calc_eta(start, time.time(), data_len, byte_counter) - speed_str = self.calc_speed(start, time.time(), byte_counter) + eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) + speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) self.report_progress(percent_str, data_len_str, speed_str, eta_str) # Apply rate limit - self.slow_down(start, byte_counter) + self.slow_down(start, byte_counter - resume_len) stream.close() self.report_finish() From a57ed21f6df916188229870fdfbcec5c58c89b0e Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Thu, 16 Dec 2010 07:09:58 +0100 Subject: [PATCH 16/36] Request page compression by default, like Firefox does --- youtube-dl | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube-dl b/youtube-dl index cf0e9fcb8..a0b5577d5 100755 --- a/youtube-dl +++ b/youtube-dl @@ -33,6 +33,7 @@ std_headers = { 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', + 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'en-us,en;q=0.5', } From 09cc744c90ccff8d6f52cbea8c4bcb864b897cbb Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Mon, 3 Jan 2011 11:22:49 +0100 Subject: [PATCH 17/36] Print new line before a few error messages --- youtube-dl | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/youtube-dl b/youtube-dl index a0b5577d5..87e0375c4 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1002,7 +1002,7 @@ class YoutubeIE(InfoExtractor): 'player_url': player_url, }) except UnavailableVideoError, err: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class MetacafeIE(InfoExtractor): @@ -1147,7 +1147,7 @@ class MetacafeIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class DailymotionIE(InfoExtractor): @@ -1236,7 +1236,7 @@ class DailymotionIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class GoogleIE(InfoExtractor): """Information extractor for video.google.com.""" @@ -1346,7 +1346,7 @@ class GoogleIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class PhotobucketIE(InfoExtractor): @@ -1428,7 +1428,7 @@ class PhotobucketIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class YahooIE(InfoExtractor): @@ -1586,7 +1586,7 @@ class YahooIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class GenericIE(InfoExtractor): @@ -1687,7 +1687,7 @@ class GenericIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError, err: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class YoutubeSearchIE(InfoExtractor): From e7cf18cb6b5c5c679583636d5b057d328655c7a6 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Mon, 3 Jan 2011 11:47:23 +0100 Subject: [PATCH 18/36] Add --dump-user-agent option (patch provided by Benjamin Johnson) --- youtube-dl | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube-dl b/youtube-dl index 87e0375c4..614f20c59 100755 --- a/youtube-dl +++ b/youtube-dl @@ -2257,6 +2257,8 @@ if __name__ == '__main__': dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) parser.add_option('--playlist-end', dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) + parser.add_option('--dump-user-agent', + action='store_true', dest='dump_user_agent', help='display the current browser identification', default=False) authentication = optparse.OptionGroup(parser, 'Authentication Options') authentication.add_option('-u', '--username', @@ -2325,6 +2327,11 @@ if __name__ == '__main__': except (IOError, OSError), err: sys.exit(u'ERROR: unable to open cookie file') + # Dump user agent + if opts.dump_user_agent: + print std_headers['User-Agent'] + sys.exit(0) + # General configuration cookie_processor = urllib2.HTTPCookieProcessor(jar) urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) From ccbd296bee952961aa09eae700dd4670fef11d7e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mantas=20Mikul=C4=97nas?= Date: Mon, 3 Jan 2011 16:14:19 +0200 Subject: [PATCH 19/36] Added --console-title to display download progress in console window title. This uses SetConsoleTitle() Win32 API for Windows Console, and Xterm escape sequence otherwise. --- youtube-dl | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/youtube-dl b/youtube-dl index 614f20c59..d6aeceabc 100755 --- a/youtube-dl +++ b/youtube-dl @@ -6,6 +6,7 @@ # Author: Vasyl' Vavrychuk # License: Public domain code import cookielib +import ctypes import datetime import htmlentitydefs import httplib @@ -208,6 +209,7 @@ class FileDownloader(object): playliststart: Playlist item to start at. playlistend: Playlist item to end at. logtostderr: Log messages to stderr instead of stdout. + consoletitle: Display progress in console window's titlebar. """ params = None @@ -332,6 +334,17 @@ class FileDownloader(object): """Print message to stderr.""" print >>sys.stderr, message.encode(preferredencoding()) + def to_cons_title(self, message): + """Set console/terminal window title to message.""" + if not self.params.get('consoletitle', False): + return + if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): + # c_wchar_p() might not be necessary if `message` is + # already of type unicode() + ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) + elif 'TERM' in os.environ: + sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) + def fixed_template(self): """Checks if the output template is fixed.""" return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) @@ -380,6 +393,8 @@ class FileDownloader(object): return self.to_screen(u'\r[download] %s of %s at %s ETA %s' % (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % + (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) def report_resuming_byte(self, resume_len): """Report attempt to resume at given byte.""" @@ -2293,6 +2308,8 @@ if __name__ == '__main__': action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False) verbosity.add_option('--no-progress', action='store_true', dest='noprogress', help='do not print progress bar', default=False) + verbosity.add_option('--console-title', + action='store_true', dest='consoletitle', help='display progress in console titlebar', default=False) parser.add_option_group(verbosity) filesystem = optparse.OptionGroup(parser, 'Filesystem Options') @@ -2434,6 +2451,7 @@ if __name__ == '__main__': 'playliststart': opts.playliststart, 'playlistend': opts.playlistend, 'logtostderr': opts.outtmpl == '-', + 'consoletitle': opts.consoletitle, }) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie) From d3975459d15e0e3c8e695d36990860b16ad1b97e Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Fri, 7 Jan 2011 10:22:01 +0100 Subject: [PATCH 20/36] Remove trailing whitespace --- youtube-dl | 82 +++++++++++++++++++++++++++--------------------------- 1 file changed, 41 insertions(+), 41 deletions(-) diff --git a/youtube-dl b/youtube-dl index d6aeceabc..6a648e723 100755 --- a/youtube-dl +++ b/youtube-dl @@ -58,7 +58,7 @@ def preferredencoding(): def htmlentity_transform(matchobj): """Transforms an HTML entity to a Unicode character. - + This function receives a match object and is intended to be used with the re.sub() function. """ @@ -115,7 +115,7 @@ def sanitize_open(filename, open_mode): class DownloadError(Exception): """Download Error exception. - + This exception may be thrown by FileDownloader objects if they are not configured to continue on errors. They will contain the appropriate error message. @@ -227,7 +227,7 @@ class FileDownloader(object): self._num_downloads = 0 self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] self.params = params - + @staticmethod def pmkdir(filename): """Create directory components in filename. Similar to Unix "mkdir -p".""" @@ -313,12 +313,12 @@ class FileDownloader(object): """Add an InfoExtractor object to the end of the list.""" self._ies.append(ie) ie.set_downloader(self) - + def add_post_processor(self, pp): """Add a PostProcessor object to the end of the chain.""" self._pps.append(pp) pp.set_downloader(self) - + def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False): """Print message to stdout if not in quiet mode.""" try: @@ -329,11 +329,11 @@ class FileDownloader(object): except (UnicodeEncodeError), err: if not ignore_encoding_errors: raise - + def to_stderr(self, message): """Print message to stderr.""" print >>sys.stderr, message.encode(preferredencoding()) - + def to_cons_title(self, message): """Set console/terminal window title to message.""" if not self.params.get('consoletitle', False): @@ -386,7 +386,7 @@ class FileDownloader(object): def report_destination(self, filename): """Report destination filename.""" self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) - + def report_progress(self, percent_str, data_len_str, speed_str, eta_str): """Report download progress.""" if self.params.get('noprogress', False): @@ -399,29 +399,29 @@ class FileDownloader(object): def report_resuming_byte(self, resume_len): """Report attempt to resume at given byte.""" self.to_screen(u'[download] Resuming download at byte %s' % resume_len) - + def report_retry(self, count, retries): """Report retry in case of HTTP error 5xx""" self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) - + def report_file_already_downloaded(self, file_name): """Report file has already been fully downloaded.""" try: self.to_screen(u'[download] %s has already been downloaded' % file_name) except (UnicodeEncodeError), err: self.to_screen(u'[download] The file has already been downloaded') - + def report_unable_to_resume(self): """Report it was impossible to resume download.""" self.to_screen(u'[download] Unable to resume') - + def report_finish(self): """Report download finished.""" if self.params.get('noprogress', False): self.to_screen(u'[download] Download completed') else: self.to_screen(u'') - + def increment_downloads(self): """Increment the ordinal that assigns a number to each file.""" self._num_downloads += 1 @@ -441,7 +441,7 @@ class FileDownloader(object): print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') return - + try: template_dict = dict(info_dict) template_dict['epoch'] = unicode(long(time.time())) @@ -512,7 +512,7 @@ class FileDownloader(object): info = pp.run(info) if info is None: break - + def _download_with_rtmpdump(self, filename, url, player_url): self.report_destination(filename) tmpfilename = self.temp_name(filename) @@ -730,7 +730,7 @@ class InfoExtractor(object): def set_downloader(self, downloader): """Sets the downloader for this IE.""" self._downloader = downloader - + def _real_initialize(self): """Real initialization process. Redefine in subclasses.""" pass @@ -771,31 +771,31 @@ class YoutubeIE(InfoExtractor): def report_login(self): """Report attempt to log in.""" self._downloader.to_screen(u'[youtube] Logging in') - + def report_age_confirmation(self): """Report attempt to confirm age.""" self._downloader.to_screen(u'[youtube] Confirming age') - + def report_video_webpage_download(self, video_id): """Report attempt to download video webpage.""" self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) - + def report_video_info_webpage_download(self, video_id): """Report attempt to download video info webpage.""" self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) - + def report_information_extraction(self, video_id): """Report attempt to extract video information.""" self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) - + def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) - + def report_rtmp_download(self): """Indicate the download will use the RTMP protocol.""" self._downloader.to_screen(u'[youtube] RTMP download detected') - + def _real_initialize(self): if self._downloader is None: return @@ -851,7 +851,7 @@ class YoutubeIE(InfoExtractor): except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) return - + # Confirm age age_form = { 'next_url': '/', @@ -1043,11 +1043,11 @@ class MetacafeIE(InfoExtractor): def report_age_confirmation(self): """Report attempt to confirm age.""" self._downloader.to_screen(u'[metacafe] Confirming age') - + def report_download_webpage(self, video_id): """Report webpage download.""" self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) - + def report_extraction(self, video_id): """Report information extraction.""" self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) @@ -1074,7 +1074,7 @@ class MetacafeIE(InfoExtractor): except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) return - + def _real_extract(self, url): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) @@ -1110,7 +1110,7 @@ class MetacafeIE(InfoExtractor): if mobj is not None: mediaURL = urllib.unquote(mobj.group(1)) video_extension = mediaURL[-3:] - + # Extract gdaKey if available mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) if mobj is None: @@ -1180,7 +1180,7 @@ class DailymotionIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) - + def report_extraction(self, video_id): """Report information extraction.""" self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) @@ -1717,7 +1717,7 @@ class YoutubeSearchIE(InfoExtractor): def __init__(self, youtube_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._youtube_ie = youtube_ie - + @staticmethod def suitable(url): return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None) @@ -1729,7 +1729,7 @@ class YoutubeSearchIE(InfoExtractor): def _real_initialize(self): self._youtube_ie.initialize() - + def _real_extract(self, query): mobj = re.match(self._VALID_QUERY, query) if mobj is None: @@ -1808,7 +1808,7 @@ class GoogleSearchIE(InfoExtractor): def __init__(self, google_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._google_ie = google_ie - + @staticmethod def suitable(url): return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None) @@ -1820,7 +1820,7 @@ class GoogleSearchIE(InfoExtractor): def _real_initialize(self): self._google_ie.initialize() - + def _real_extract(self, query): mobj = re.match(self._VALID_QUERY, query) if mobj is None: @@ -1899,7 +1899,7 @@ class YahooSearchIE(InfoExtractor): def __init__(self, yahoo_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._yahoo_ie = yahoo_ie - + @staticmethod def suitable(url): return (re.match(YahooSearchIE._VALID_QUERY, url) is not None) @@ -1911,7 +1911,7 @@ class YahooSearchIE(InfoExtractor): def _real_initialize(self): self._yahoo_ie.initialize() - + def _real_extract(self, query): mobj = re.match(self._VALID_QUERY, query) if mobj is None: @@ -1990,7 +1990,7 @@ class YoutubePlaylistIE(InfoExtractor): def __init__(self, youtube_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._youtube_ie = youtube_ie - + @staticmethod def suitable(url): return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None) @@ -2001,7 +2001,7 @@ class YoutubePlaylistIE(InfoExtractor): def _real_initialize(self): self._youtube_ie.initialize() - + def _real_extract(self, url): # Extract playlist id mobj = re.match(self._VALID_URL, url) @@ -2053,7 +2053,7 @@ class YoutubeUserIE(InfoExtractor): def __init__(self, youtube_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._youtube_ie = youtube_ie - + @staticmethod def suitable(url): return (re.match(YoutubeUserIE._VALID_URL, url) is not None) @@ -2064,7 +2064,7 @@ class YoutubeUserIE(InfoExtractor): def _real_initialize(self): self._youtube_ie.initialize() - + def _real_extract(self, url): # Extract username mobj = re.match(self._VALID_URL, url) @@ -2205,7 +2205,7 @@ class PostProcessor(object): def set_downloader(self, downloader): """Sets the downloader for this PP.""" self._downloader = downloader - + def run(self, information): """Run the PostProcessor. @@ -2225,7 +2225,7 @@ class PostProcessor(object): it was called from. """ return information # by default, do nothing - + ### MAIN PROGRAM ### if __name__ == '__main__': try: From 3fb2c487c05cb9998a7ae6fb1dc8ca2c4d25a9aa Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Fri, 7 Jan 2011 10:23:18 +0100 Subject: [PATCH 21/36] Add --no-part option (closes #48) --- youtube-dl | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/youtube-dl b/youtube-dl index 6a648e723..b2ef1251a 100755 --- a/youtube-dl +++ b/youtube-dl @@ -210,6 +210,7 @@ class FileDownloader(object): playlistend: Playlist item to end at. logtostderr: Log messages to stderr instead of stdout. consoletitle: Display progress in console window's titlebar. + nopart: Do not use temporary .part files. """ params = None @@ -237,14 +238,7 @@ class FileDownloader(object): for dir in aggregate: if not os.path.exists(dir): os.mkdir(dir) - - @staticmethod - def temp_name(filename): - """Returns a temporary filename for the given filename.""" - if filename == u'-' or (os.path.exists(filename) and not os.path.isfile(filename)): - return filename - return filename + u'.part' - + @staticmethod def format_bytes(bytes): if bytes is None: @@ -374,7 +368,14 @@ class FileDownloader(object): speed = float(byte_counter) / elapsed if speed > rate_limit: time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) - + + def temp_name(self, filename): + """Returns a temporary filename for the given filename.""" + if self.params.get('nopart', False) or filename == u'-' or \ + (os.path.exists(filename) and not os.path.isfile(filename)): + return filename + return filename + u'.part' + def try_rename(self, old_filename, new_filename): try: if old_filename == new_filename: @@ -547,7 +548,7 @@ class FileDownloader(object): def _do_download(self, filename, url, player_url): # Check file already present - if self.params.get('continuedl', False) and os.path.isfile(filename): + if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False): self.report_file_already_downloaded(filename) return True @@ -2329,6 +2330,8 @@ if __name__ == '__main__': action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False) filesystem.add_option('--cookies', dest='cookiefile', metavar='FILE', help='file to dump cookie jar to') + filesystem.add_option('--no-part', + action='store_true', dest='nopart', help='do not use .part files', default=False) parser.add_option_group(filesystem) (opts, args) = parser.parse_args() @@ -2452,6 +2455,7 @@ if __name__ == '__main__': 'playlistend': opts.playlistend, 'logtostderr': opts.outtmpl == '-', 'consoletitle': opts.consoletitle, + 'nopart': opts.nopart, }) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie) From aac3fe0f4adaad809d25e335c17711c23d51eec0 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Mon, 10 Jan 2011 12:54:14 +0100 Subject: [PATCH 22/36] Fix bug in regular expression for youtu.be links --- youtube-dl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index b2ef1251a..a09b498ba 100755 --- a/youtube-dl +++ b/youtube-dl @@ -743,7 +743,7 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' From 1987c2325a9764e24104fa8da23b467a5e33cf49 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Wed, 12 Jan 2011 20:20:37 +0100 Subject: [PATCH 23/36] Add proper support for "gzip" and "deflate" encodings --- youtube-dl | 89 +++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 72 insertions(+), 17 deletions(-) diff --git a/youtube-dl b/youtube-dl index a09b498ba..13d42765b 100755 --- a/youtube-dl +++ b/youtube-dl @@ -8,6 +8,7 @@ import cookielib import ctypes import datetime +import gzip import htmlentitydefs import httplib import locale @@ -18,11 +19,13 @@ import os.path import re import socket import string +import StringIO import subprocess import sys import time import urllib import urllib2 +import zlib # parse_qs was moved from the cgi module to the urlparse module recently. try: @@ -161,6 +164,56 @@ class ContentTooShortError(Exception): self.downloaded = downloaded self.expected = expected +class YoutubeDLHandler(urllib2.HTTPHandler): + """Handler for HTTP requests and responses. + + This class, when installed with an OpenerDirector, automatically adds + the standard headers to every HTTP request and handles gzipped and + deflated responses from web servers. If compression is to be avoided in + a particular request, the original request in the program code only has + to include the HTTP header "Youtubedl-No-Compression", which will be + removed before making the real request. + + Part of this code was copied from: + + http://techknack.net/python-urllib2-handlers/ + + Andrew Rowls, the author of that code, agreed to release it to the + public domain. + """ + + @staticmethod + def deflate(data): + try: + return zlib.decompress(data, -zlib.MAX_WBITS) + except zlib.error: + return zlib.decompress(data) + + def http_request(self, req): + for h in std_headers: + if h in req.headers: + del req.headers[h] + req.add_header(h, std_headers[h]) + if 'Youtubedl-no-compression' in req.headers: + if 'Accept-encoding' in req.headers: + del req.headers['Accept-encoding'] + del req.headers['Youtubedl-no-compression'] + return req + + def http_response(self, req, resp): + old_resp = resp + # gzip + if resp.headers.get('Content-encoding', '') == 'gzip': + gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') + resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code) + resp.msg = old_resp.msg + # deflate + if resp.headers.get('Content-encoding', '') == 'deflate': + gz = StringIO.StringIO(self.deflate(resp.read())) + resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code) + resp.msg = old_resp.msg + return resp + class FileDownloader(object): """File Downloader class. @@ -559,8 +612,11 @@ class FileDownloader(object): tmpfilename = self.temp_name(filename) stream = None open_mode = 'wb' - basic_request = urllib2.Request(url, None, std_headers) - request = urllib2.Request(url, None, std_headers) + + # Do not include the Accept-Encoding header + headers = {'Youtubedl-no-compression': 'True'} + basic_request = urllib2.Request(url, None, headers) + request = urllib2.Request(url, None, headers) # Establish possible resume length if os.path.isfile(tmpfilename): @@ -822,7 +878,7 @@ class YoutubeIE(InfoExtractor): return # Set language - request = urllib2.Request(self._LANG_URL, None, std_headers) + request = urllib2.Request(self._LANG_URL) try: self.report_lang() urllib2.urlopen(request).read() @@ -842,7 +898,7 @@ class YoutubeIE(InfoExtractor): 'username': username, 'password': password, } - request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers) + request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) try: self.report_login() login_results = urllib2.urlopen(request).read() @@ -858,7 +914,7 @@ class YoutubeIE(InfoExtractor): 'next_url': '/', 'action_confirm': 'Confirm', } - request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers) + request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form)) try: self.report_age_confirmation() age_results = urllib2.urlopen(request).read() @@ -876,7 +932,7 @@ class YoutubeIE(InfoExtractor): # Get video webpage self.report_video_webpage_download(video_id) - request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id, None, std_headers) + request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) try: video_webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -895,7 +951,7 @@ class YoutubeIE(InfoExtractor): for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' % (video_id, el_type)) - request = urllib2.Request(video_info_url, None, std_headers) + request = urllib2.Request(video_info_url) try: video_info_webpage = urllib2.urlopen(request).read() video_info = parse_qs(video_info_webpage) @@ -1055,7 +1111,7 @@ class MetacafeIE(InfoExtractor): def _real_initialize(self): # Retrieve disclaimer - request = urllib2.Request(self._DISCLAIMER, None, std_headers) + request = urllib2.Request(self._DISCLAIMER) try: self.report_disclaimer() disclaimer = urllib2.urlopen(request).read() @@ -1068,7 +1124,7 @@ class MetacafeIE(InfoExtractor): 'filters': '0', 'submit': "Continue - I'm over 18", } - request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers) + request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form)) try: self.report_age_confirmation() disclaimer = urllib2.urlopen(request).read() @@ -1771,7 +1827,7 @@ class YoutubeSearchIE(InfoExtractor): while True: self.report_download_page(query, pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) - request = urllib2.Request(result_url, None, std_headers) + request = urllib2.Request(result_url) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -1862,7 +1918,7 @@ class GoogleSearchIE(InfoExtractor): while True: self.report_download_page(query, pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) - request = urllib2.Request(result_url, None, std_headers) + request = urllib2.Request(result_url) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -1953,7 +2009,7 @@ class YahooSearchIE(InfoExtractor): while True: self.report_download_page(query, pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) - request = urllib2.Request(result_url, None, std_headers) + request = urllib2.Request(result_url) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -2017,7 +2073,7 @@ class YoutubePlaylistIE(InfoExtractor): while True: self.report_download_page(playlist_id, pagenum) - request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers) + request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum)) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -2079,7 +2135,7 @@ class YoutubeUserIE(InfoExtractor): pagenum = 1 self.report_download_page(username) - request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers) + request = urllib2.Request(self._TEMPLATE_URL % (username)) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -2135,7 +2191,7 @@ class DepositFilesIE(InfoExtractor): # Retrieve file webpage with 'Free download' button pressed free_download_indication = { 'gateway_result' : '1' } - request = urllib2.Request(url, urllib.urlencode(free_download_indication), std_headers) + request = urllib2.Request(url, urllib.urlencode(free_download_indication)) try: self.report_download_webpage(file_id) webpage = urllib2.urlopen(request).read() @@ -2354,8 +2410,7 @@ if __name__ == '__main__': # General configuration cookie_processor = urllib2.HTTPCookieProcessor(jar) - urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) - urllib2.install_opener(urllib2.build_opener(cookie_processor)) + urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())) socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) # Batch file verification From 8cc42e7c1a5bc05a6ca753c0f92732c04ac48ab7 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Wed, 12 Jan 2011 20:21:43 +0100 Subject: [PATCH 24/36] Fix "unable to rename file" Windows error (closes #56) --- youtube-dl | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/youtube-dl b/youtube-dl index 13d42765b..c49c1b064 100755 --- a/youtube-dl +++ b/youtube-dl @@ -429,6 +429,11 @@ class FileDownloader(object): return filename return filename + u'.part' + def undo_temp_name(self, filename): + if filename.endswith(u'.part'): + return filename[:-len(u'.part')] + return filename + def try_rename(self, old_filename, new_filename): try: if old_filename == new_filename: @@ -698,6 +703,7 @@ class FileDownloader(object): if stream is None: try: (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) + filename = self.undo_temp_name(tmpfilename) self.report_destination(filename) except (OSError, IOError), err: self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) From 0d8d9877ad7dc7ba893f7e37382add01a01c3d0a Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Wed, 12 Jan 2011 20:22:37 +0100 Subject: [PATCH 25/36] Add support for embedded YouTube playist URLs (closes #54) --- youtube-dl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index c49c1b064..32e334ce4 100755 --- a/youtube-dl +++ b/youtube-dl @@ -2044,7 +2044,7 @@ class YahooSearchIE(InfoExtractor): class YoutubePlaylistIE(InfoExtractor): """Information Extractor for YouTube playlists.""" - _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*' + _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/|p/)([^&]+).*' _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' From 0fe64c04f8ae57ace54404a8b8bfb5deff552e2d Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Wed, 12 Jan 2011 21:07:56 +0100 Subject: [PATCH 26/36] Make the self-updating function a bit more robust --- youtube-dl | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/youtube-dl b/youtube-dl index 32e334ce4..443bb211b 100755 --- a/youtube-dl +++ b/youtube-dl @@ -2296,20 +2296,26 @@ if __name__ == '__main__': import getpass import optparse - # Function to update the program file with the latest version from bitbucket.org + # Function to update the program file with the latest version from the repository. def update_self(downloader, filename): # Note: downloader only used for options - if not os.access (filename, os.W_OK): + if not os.access(filename, os.W_OK): sys.exit('ERROR: no write permissions on %s' % filename) downloader.to_screen('Updating to latest stable version...') - latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' - latest_version = urllib.urlopen(latest_url).read().strip() - prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version - newcontent = urllib.urlopen(prog_url).read() - stream = open(filename, 'w') - stream.write(newcontent) - stream.close() + try: + latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' + latest_version = urllib.urlopen(latest_url).read().strip() + prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version + newcontent = urllib.urlopen(prog_url).read() + except (IOError, OSError), err: + sys.exit('ERROR: unable to download latest version') + try: + stream = open(filename, 'w') + stream.write(newcontent) + stream.close() + except (IOError, OSError), err: + sys.exit('ERROR: unable to overwrite current version') downloader.to_screen('Updated to version %s' % latest_version) # Parse command line From 0d14e225fa031f37c34242551565b6dadbfa51af Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Tue, 18 Jan 2011 19:16:42 +0100 Subject: [PATCH 27/36] Omit code argument in addinfourl for Python 2.4 --- youtube-dl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube-dl b/youtube-dl index 443bb211b..8bdde1704 100755 --- a/youtube-dl +++ b/youtube-dl @@ -205,12 +205,12 @@ class YoutubeDLHandler(urllib2.HTTPHandler): # gzip if resp.headers.get('Content-encoding', '') == 'gzip': gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') - resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code) + resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url) resp.msg = old_resp.msg # deflate if resp.headers.get('Content-encoding', '') == 'deflate': gz = StringIO.StringIO(self.deflate(resp.read())) - resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code) + resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url) resp.msg = old_resp.msg return resp From 7b531c0be61b84884302b564a9fc89edde2cfc67 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Tue, 18 Jan 2011 20:52:37 +0100 Subject: [PATCH 28/36] Wrap call to addinfourl for compatibility with Python 2.4 --- youtube-dl | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube-dl b/youtube-dl index 8bdde1704..1b20025e7 100755 --- a/youtube-dl +++ b/youtube-dl @@ -189,6 +189,12 @@ class YoutubeDLHandler(urllib2.HTTPHandler): except zlib.error: return zlib.decompress(data) + @staticmethod + def addinfourl_wrapper(stream, headers, url, code): + if hasattr(urllib2.addinfourl, 'getcode'): + return urllib2.addinfourl(stream, headers, url, code) + return urllib2.addinfourl(stream, headers, url) + def http_request(self, req): for h in std_headers: if h in req.headers: @@ -205,12 +211,12 @@ class YoutubeDLHandler(urllib2.HTTPHandler): # gzip if resp.headers.get('Content-encoding', '') == 'gzip': gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') - resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url) + resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) resp.msg = old_resp.msg # deflate if resp.headers.get('Content-encoding', '') == 'deflate': gz = StringIO.StringIO(self.deflate(resp.read())) - resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url) + resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) resp.msg = old_resp.msg return resp From 0f6b00b587e9b47919555f9c250b753419063b46 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Thu, 20 Jan 2011 20:36:42 +0100 Subject: [PATCH 29/36] Improve addinfourl_wrapper for compatibility with older Python versions --- youtube-dl | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index 1b20025e7..103189b21 100755 --- a/youtube-dl +++ b/youtube-dl @@ -193,7 +193,9 @@ class YoutubeDLHandler(urllib2.HTTPHandler): def addinfourl_wrapper(stream, headers, url, code): if hasattr(urllib2.addinfourl, 'getcode'): return urllib2.addinfourl(stream, headers, url, code) - return urllib2.addinfourl(stream, headers, url) + ret = urllib2.addinfourl(stream, headers, url) + ret.code = code + return ret def http_request(self, req): for h in std_headers: From c02d8e404019975060b195b7c7b6fb39944e321b Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Fri, 21 Jan 2011 18:16:33 +0100 Subject: [PATCH 30/36] Fix dailymotion support (closes #60) --- youtube-dl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index 103189b21..869a32b0a 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1302,7 +1302,7 @@ class DailymotionIE(InfoExtractor): video_title = mobj.group(1).decode('utf-8') video_title = sanitize_title(video_title) - mobj = re.search(r'(?im)
.*?(.+?)', webpage) + mobj = re.search(r'(?im)(.+?)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return From 0f7099a59b0d39ee94ae0351c6091c31819d9b36 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Fri, 21 Jan 2011 18:18:48 +0100 Subject: [PATCH 31/36] Fix omission of Witold Baryluk as the Dailymotion InfoExtractor author --- youtube-dl | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube-dl b/youtube-dl index 869a32b0a..99c9afe0a 100755 --- a/youtube-dl +++ b/youtube-dl @@ -4,6 +4,7 @@ # Author: Danny Colligan # Author: Benjamin Johnson # Author: Vasyl' Vavrychuk +# Author: Witold Baryluk # License: Public domain code import cookielib import ctypes From b940c84a245c27199b78956e283e6e2832bd51b4 Mon Sep 17 00:00:00 2001 From: Lionel Elie Mamane Date: Tue, 25 Jan 2011 08:37:08 +0100 Subject: [PATCH 32/36] Support for youtube.com/embed/XXXXX URLs (closes #63) --- youtube-dl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube-dl b/youtube-dl index 99c9afe0a..640c8777d 100755 --- a/youtube-dl +++ b/youtube-dl @@ -814,7 +814,7 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' From 9f7963468bf7f19e0cd2e11ed3ed2829f5c68b78 Mon Sep 17 00:00:00 2001 From: Gergely Imreh Date: Tue, 25 Jan 2011 11:03:16 +0800 Subject: [PATCH 33/36] New option --get-filename to print output filename When using youtube-dl within scripts, it is very useful to know what will be the final output filename with all the title settings and filename templates applied. Add option to the quiet mode operations to print that info. For this I had to move the filename-generation into its own function. As much as I can tell it should work almost always well, ie. not to break things if one not actually interested in the title, like in case of other forced printing. That is, unless there's an invalid system charset or the user specified a wrong output template. In that case probably could be assumed that the user does have a problem (the former) or did want to mess with the filename (the latter). Signed-off-by: Gergely Imreh --- youtube-dl | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/youtube-dl b/youtube-dl index 640c8777d..be859a5a1 100755 --- a/youtube-dl +++ b/youtube-dl @@ -258,6 +258,7 @@ class FileDownloader(object): forcetitle: Force printing title. forcethumbnail: Force printing thumbnail URL. forcedescription: Force printing description. + forcefilename: Force printing final filename. simulate: Do not download the video files. format: Video format code. format_limit: Highest quality format to try. @@ -494,8 +495,21 @@ class FileDownloader(object): """Increment the ordinal that assigns a number to each file.""" self._num_downloads += 1 + def prepare_filename(self, info_dict): + """Generate the output filename.""" + try: + template_dict = dict(info_dict) + template_dict['epoch'] = unicode(long(time.time())) + template_dict['autonumber'] = unicode('%05d' % self._num_downloads) + filename = self.params['outtmpl'] % template_dict + return filename + except (ValueError, KeyError), err: + self.trouble(u'ERROR: invalid system charset or erroneous output template') + return None + def process_info(self, info_dict): """Process a single dictionary returned by an InfoExtractor.""" + filename = self.prepare_filename(info_dict) # Do nothing else if in simulate mode if self.params.get('simulate', False): # Forced printings @@ -507,16 +521,12 @@ class FileDownloader(object): print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') if self.params.get('forcedescription', False) and 'description' in info_dict: print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forcefilename', False) and filename is not None: + print filename.encode(preferredencoding(), 'xmlcharrefreplace') return - try: - template_dict = dict(info_dict) - template_dict['epoch'] = unicode(long(time.time())) - template_dict['autonumber'] = unicode('%05d' % self._num_downloads) - filename = self.params['outtmpl'] % template_dict - except (ValueError, KeyError), err: - self.trouble(u'ERROR: invalid system charset or erroneous output template') + if filename is None: return if self.params.get('nooverwrites', False) and os.path.exists(filename): self.to_stderr(u'WARNING: file exists and will be skipped') @@ -2384,6 +2394,8 @@ if __name__ == '__main__': action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False) verbosity.add_option('--get-description', action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False) + verbosity.add_option('--get-filename', + action='store_true', dest='getfilename', help='simulate, quiet but print output filename', default=False) verbosity.add_option('--no-progress', action='store_true', dest='noprogress', help='do not print progress bar', default=False) verbosity.add_option('--console-title', @@ -2503,12 +2515,13 @@ if __name__ == '__main__': 'usenetrc': opts.usenetrc, 'username': opts.username, 'password': opts.password, - 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription), + 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename), 'forceurl': opts.geturl, 'forcetitle': opts.gettitle, 'forcethumbnail': opts.getthumbnail, 'forcedescription': opts.getdescription, - 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription), + 'forcefilename': opts.getfilename, + 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename), 'format': opts.format, 'format_limit': opts.format_limit, 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) From 09bd408c284771224db5665d937b62d6c36759fb Mon Sep 17 00:00:00 2001 From: Gergely Imreh Date: Thu, 27 Jan 2011 13:02:51 +0800 Subject: [PATCH 34/36] Set downloaded file's time stamp from last-modified header This file stamp setting is very relaxed. If there's any problem along the way (no last-modified header, bad time string format, no time set privileges,...) or if nothing is downloaded (e.g. using resumed download but the file was already complete) then nothing is done. --- youtube-dl | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/youtube-dl b/youtube-dl index be859a5a1..e28788e3c 100755 --- a/youtube-dl +++ b/youtube-dl @@ -9,6 +9,7 @@ import cookielib import ctypes import datetime +import email.utils import gzip import htmlentitydefs import httplib @@ -117,6 +118,14 @@ def sanitize_open(filename, open_mode): stream = open(filename, open_mode) return (stream, filename) +def timeconvert(timestr): + """Convert RFC 2822 defined time string into system timestamp""" + timestamp = None + timetuple = email.utils.parsedate_tz(timestr) + if timetuple is not None: + timestamp = email.utils.mktime_tz(timetuple) + return timestamp + class DownloadError(Exception): """Download Error exception. @@ -748,6 +757,15 @@ class FileDownloader(object): if data_len is not None and byte_counter != data_len: raise ContentTooShortError(byte_counter, long(data_len)) self.try_rename(tmpfilename, filename) + # Update file modification time + timestr = data.info().get('last-modified', None) + if timestr is not None: + filetime = timeconvert(timestr) + if filetime is not None: + try: + os.utime(filename,(time.time(), filetime)) + except: + pass return True class InfoExtractor(object): From e30189021db82c98019a9c055b9d81e4a7417b81 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Fri, 28 Jan 2011 19:59:18 +0100 Subject: [PATCH 35/36] Make the file timestamp feature optional --- youtube-dl | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) diff --git a/youtube-dl b/youtube-dl index e28788e3c..05869004b 100755 --- a/youtube-dl +++ b/youtube-dl @@ -283,6 +283,7 @@ class FileDownloader(object): logtostderr: Log messages to stderr instead of stdout. consoletitle: Display progress in console window's titlebar. nopart: Do not use temporary .part files. + updatetime: Use the Last-modified header to set output file timestamps. """ params = None @@ -460,6 +461,23 @@ class FileDownloader(object): os.rename(old_filename, new_filename) except (IOError, OSError), err: self.trouble(u'ERROR: unable to rename file') + + def try_utime(self, filename, last_modified_hdr): + """Try to set the last-modified time of the given file.""" + if last_modified_hdr is None: + return + if not os.path.isfile(filename): + return + timestr = last_modified_hdr + if timestr is None: + return + filetime = timeconvert(timestr) + if filetime is None: + return + try: + os.utime(filename,(time.time(), filetime)) + except: + pass def report_destination(self, filename): """Report destination filename.""" @@ -757,15 +775,11 @@ class FileDownloader(object): if data_len is not None and byte_counter != data_len: raise ContentTooShortError(byte_counter, long(data_len)) self.try_rename(tmpfilename, filename) + # Update file modification time - timestr = data.info().get('last-modified', None) - if timestr is not None: - filetime = timeconvert(timestr) - if filetime is not None: - try: - os.utime(filename,(time.time(), filetime)) - except: - pass + if self.params.get('updatetime', True): + self.try_utime(filename, data.info().get('last-modified', None)) + return True class InfoExtractor(object): @@ -2439,6 +2453,9 @@ if __name__ == '__main__': dest='cookiefile', metavar='FILE', help='file to dump cookie jar to') filesystem.add_option('--no-part', action='store_true', dest='nopart', help='do not use .part files', default=False) + filesystem.add_option('--no-mtime', + action='store_false', dest='updatetime', + help='do not use the Last-modified header to set the file modification time', default=True) parser.add_option_group(filesystem) (opts, args) = parser.parse_args() @@ -2563,6 +2580,7 @@ if __name__ == '__main__': 'logtostderr': opts.outtmpl == '-', 'consoletitle': opts.consoletitle, 'nopart': opts.nopart, + 'updatetime': opts.updatetime, }) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie) From 6025795d952958391a2325dbdcf41a6baae8d8f4 Mon Sep 17 00:00:00 2001 From: Ricardo Garcia Date: Fri, 28 Jan 2011 19:59:47 +0100 Subject: [PATCH 36/36] Split some long lines --- youtube-dl | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/youtube-dl b/youtube-dl index 05869004b..8dd03daf3 100755 --- a/youtube-dl +++ b/youtube-dl @@ -2393,7 +2393,8 @@ if __name__ == '__main__': parser.add_option('--playlist-end', dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) parser.add_option('--dump-user-agent', - action='store_true', dest='dump_user_agent', help='display the current browser identification', default=False) + action='store_true', dest='dump_user_agent', + help='display the current browser identification', default=False) authentication = optparse.OptionGroup(parser, 'Authentication Options') authentication.add_option('-u', '--username', @@ -2423,15 +2424,19 @@ if __name__ == '__main__': verbosity.add_option('-e', '--get-title', action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) verbosity.add_option('--get-thumbnail', - action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False) + action='store_true', dest='getthumbnail', + help='simulate, quiet but print thumbnail URL', default=False) verbosity.add_option('--get-description', - action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False) + action='store_true', dest='getdescription', + help='simulate, quiet but print video description', default=False) verbosity.add_option('--get-filename', - action='store_true', dest='getfilename', help='simulate, quiet but print output filename', default=False) + action='store_true', dest='getfilename', + help='simulate, quiet but print output filename', default=False) verbosity.add_option('--no-progress', action='store_true', dest='noprogress', help='do not print progress bar', default=False) verbosity.add_option('--console-title', - action='store_true', dest='consoletitle', help='display progress in console titlebar', default=False) + action='store_true', dest='consoletitle', + help='display progress in console titlebar', default=False) parser.add_option_group(verbosity) filesystem = optparse.OptionGroup(parser, 'Filesystem Options') @@ -2440,7 +2445,8 @@ if __name__ == '__main__': filesystem.add_option('-l', '--literal', action='store_true', dest='useliteral', help='use literal title in file name', default=False) filesystem.add_option('-A', '--auto-number', - action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False) + 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') filesystem.add_option('-a', '--batch-file',