Compare commits

...

12 Commits

Author SHA1 Message Date
Ricardo Garcia
8b07dec5f6 Bump version number 2010-10-31 11:24:40 +01:00
Ricardo Garcia
113e5266cc Modify "more pages" check in YouTube playlist (fixes issue #29) 2010-10-31 11:24:40 +01:00
Ricardo Garcia
55e7c75e12 Delay opening file until there is data to write
Fixes issue #19.
2010-10-31 11:24:40 +01:00
Ricardo Garcia
ff21a710ae Restore INTERNAL version number 2010-10-31 11:24:36 +01:00
Ricardo Garcia
7374795552 Bump version number 2010-10-31 11:24:36 +01:00
Ricardo Garcia
0cd61126fc Document new "continuedl" FileDownloader option 2010-10-31 11:24:36 +01:00
Ricardo Garcia
e1f18b8a84 Remove integer casts and replace them with long integer casts 2010-10-31 11:24:36 +01:00
Ricardo Garcia
6a0015a7e0 Fix missing cast preventing detection of already downloaded file 2010-10-31 11:24:36 +01:00
Ricardo Garcia
7db85b2c70 Tweaks to ivanov's code 2010-10-31 11:24:36 +01:00
Paul Ivanov
f76c2df64e Added -c option (--continue)
interrupted downloads will properly resume and append to the previously downloaded data, instead of overwriting the file.

There's some error checking - if the length of the file to be download matches the length of the previously downloaded data, we report that this file has already been downloaded and do nothing.

If there is some other HTTP 416 'Requested range not satisfiable' error, we simply re-download the whole file (reverting to the original functionality)

All other HTTP errors are simply raised.

Resuming does not override -w (--nooverwrite), since it is not clear what should happen if file on disk is larger than file to be downloaded.

Thus, -c does nothing if -w is present.
2010-10-31 11:24:36 +01:00
Ricardo Garcia
daa88ccc2e Fix TypeError when using the -f option (fixes issue #24) 2010-10-31 11:24:36 +01:00
Ricardo Garcia
eb5d184157 Restore INTERNAL version number 2010-10-31 11:24:36 +01:00
2 changed files with 80 additions and 35 deletions

View File

@@ -1 +1 @@
2009.05.25
2009.06.29

View File

@@ -114,6 +114,7 @@ class FileDownloader(object):
ignoreerrors: Do not stop on download errors.
ratelimit: Download speed limit, in bytes/sec.
nooverwrites: Prevent overwriting files.
continuedl: Try to continue downloads if possible.
"""
params = None
@@ -182,13 +183,13 @@ class FileDownloader(object):
new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001:
return int(new_max)
return long(new_max)
rate = bytes / elapsed_time
if rate > new_max:
return int(new_max)
return long(new_max)
if rate < new_min:
return int(new_min)
return int(rate)
return long(new_min)
return long(rate)
@staticmethod
def parse_bytes(bytestr):
@@ -266,6 +267,18 @@ class FileDownloader(object):
"""Report download progress."""
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
def report_resuming_byte(self, resume_len):
"""Report attemtp to resume at given byte."""
self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
self.to_stdout(u'[download] %s has already been downloaded' % file_name)
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
self.to_stdout(u'[download] Unable to resume')
def report_finish(self):
"""Report download finished."""
@@ -292,7 +305,6 @@ class FileDownloader(object):
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
filename = self.params['outtmpl'] % template_dict
self.report_destination(filename)
except (ValueError, KeyError), err:
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
if self.params['nooverwrites'] and os.path.exists(filename):
@@ -306,17 +318,8 @@ class FileDownloader(object):
return
try:
outstream = open(filename, 'wb')
success = self._do_download(filename, info_dict['url'])
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
return
try:
self._do_download(outstream, info_dict['url'])
outstream.close()
except (OSError, IOError), err:
outstream.close()
os.remove(filename)
raise UnavailableFormatError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble('ERROR: unable to download video data: %s' % str(err))
@@ -325,11 +328,12 @@ class FileDownloader(object):
self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
self.trouble('ERROR: postprocessing: %s' % str(err))
return
if success:
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
self.trouble('ERROR: postprocessing: %s' % str(err))
return
def download(self, url_list):
"""Download a given list of URLs."""
@@ -366,21 +370,43 @@ class FileDownloader(object):
if info is None:
break
def _do_download(self, stream, url):
def _do_download(self, filename, url):
stream = None
open_mode = 'ab'
basic_request = urllib2.Request(url, None, std_headers)
request = urllib2.Request(url, None, std_headers)
data = urllib2.urlopen(request)
# Attempt to resume download with "continuedl" option
if os.path.isfile(filename):
resume_len = os.path.getsize(filename)
else:
resume_len = 0
if self.params['continuedl'] and resume_len != 0:
self.report_resuming_byte(resume_len)
request.add_header('Range','bytes=%d-' % resume_len)
# Establish connection
try:
data = urllib2.urlopen(request)
except (urllib2.HTTPError, ), err:
if err.code != 416: # 416 is 'Requested range not satisfiable'
raise
data = urllib2.urlopen(basic_request)
content_length = data.info()['Content-Length']
if content_length is not None and long(content_length) == resume_len:
self.report_file_already_downloaded(filename)
return True
else:
self.report_unable_to_resume()
open_mode = 'wb'
data_len = data.info().get('Content-length', None)
data_len_str = self.format_bytes(data_len)
byte_counter = 0
block_size = 1024
start = time.time()
while True:
# 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)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Download and write
before = time.time()
data_block = data.read(block_size)
@@ -389,15 +415,31 @@ class FileDownloader(object):
if data_block_len == 0:
break
byte_counter += data_block_len
# Open file just in time
if stream is None:
try:
stream = open(filename, open_mode)
self.report_destination(filename)
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
return False
stream.write(data_block)
block_size = self.best_block_size(after - before, data_block_len)
# 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)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Apply rate limit
self.slow_down(start, byte_counter)
self.report_finish()
if data_len is not None and str(byte_counter) != data_len:
raise ContentTooShortError(byte_counter, long(data_len))
return True
class InfoExtractor(object):
"""Information Extractor class.
@@ -859,7 +901,7 @@ class YoutubeSearchIE(InfoExtractor):
return
else:
try:
n = int(prefix)
n = long(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
@@ -868,7 +910,7 @@ class YoutubeSearchIE(InfoExtractor):
n = self._max_youtube_results
self._download_n_results(query, n)
return
except ValueError: # parsing prefix as int fails
except ValueError: # parsing prefix as integer fails
self._download_n_results(query, 1)
return
@@ -914,7 +956,7 @@ class YoutubePlaylistIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?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'/view_play_list?p=%s&amp;page=%s'
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
@@ -960,7 +1002,7 @@ class YoutubePlaylistIE(InfoExtractor):
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
if (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page:
break
pagenum = pagenum + 1
@@ -1029,7 +1071,7 @@ if __name__ == '__main__':
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
version='2009.05.25',
version='2009.06.29',
conflict_handler='resolve',
)
@@ -1053,7 +1095,7 @@ if __name__ == '__main__':
video_format = optparse.OptionGroup(parser, 'Video Format Options')
video_format.add_option('-f', '--format',
action='append', dest='format', metavar='FMT', help='video format code')
action='store', dest='format', metavar='FMT', help='video format code')
video_format.add_option('-b', '--best-quality',
action='store_const', dest='format', help='download the best quality video possible', const='0')
video_format.add_option('-m', '--mobile-version',
@@ -1084,6 +1126,8 @@ if __name__ == '__main__':
dest='batchfile', metavar='F', help='file containing URLs to download')
filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue',
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
parser.add_option_group(filesystem)
(opts, args) = parser.parse_args()
@@ -1141,6 +1185,7 @@ if __name__ == '__main__':
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
'continuedl': opts.continue_dl,
})
fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie)