aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/FileDownloader.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/FileDownloader.py')
-rw-r--r--youtube_dl/FileDownloader.py133
1 files changed, 74 insertions, 59 deletions
diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py
index 14e872a98..d7d5b1521 100644
--- a/youtube_dl/FileDownloader.py
+++ b/youtube_dl/FileDownloader.py
@@ -13,7 +13,7 @@ import urllib2
if os.name == 'nt':
import ctypes
-
+
from utils import *
@@ -44,37 +44,40 @@ class FileDownloader(object):
Available options:
- username: Username for authentication purposes.
- password: Password for authentication purposes.
- usenetrc: Use netrc for authentication instead.
- quiet: Do not print messages to stdout.
- forceurl: Force printing final URL.
- 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.
- outtmpl: Template for output names.
- ignoreerrors: Do not stop on download errors.
- ratelimit: Download speed limit, in bytes/sec.
- nooverwrites: Prevent overwriting files.
- retries: Number of times to retry for HTTP error 5xx
- continuedl: Try to continue downloads if possible.
- noprogress: Do not print the progress bar.
- playliststart: Playlist item to start at.
- playlistend: Playlist item to end at.
- matchtitle: Download only matching titles.
- rejecttitle: Reject downloads for matching titles.
- 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.
- writedescription: Write the video description to a .description file
- writeinfojson: Write the video description to a .info.json file
- writesubtitles: Write the video subtitles to a .srt file
- subtitleslang: Language of the subtitles to download
+ username: Username for authentication purposes.
+ password: Password for authentication purposes.
+ usenetrc: Use netrc for authentication instead.
+ quiet: Do not print messages to stdout.
+ forceurl: Force printing final URL.
+ 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.
+ outtmpl: Template for output names.
+ restrictfilenames: Do not allow "&" and spaces in file names
+ ignoreerrors: Do not stop on download errors.
+ ratelimit: Download speed limit, in bytes/sec.
+ nooverwrites: Prevent overwriting files.
+ retries: Number of times to retry for HTTP error 5xx
+ buffersize: Size of download buffer in bytes.
+ noresizebuffer: Do not automatically resize the download buffer.
+ continuedl: Try to continue downloads if possible.
+ noprogress: Do not print the progress bar.
+ playliststart: Playlist item to start at.
+ playlistend: Playlist item to end at.
+ matchtitle: Download only matching titles.
+ rejecttitle: Reject downloads for matching titles.
+ 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.
+ writedescription: Write the video description to a .description file
+ writeinfojson: Write the video description to a .info.json file
+ writesubtitles: Write the video subtitles to a .srt file
+ subtitleslang: Language of the subtitles to download
"""
params = None
@@ -93,6 +96,9 @@ class FileDownloader(object):
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self.params = params
+ if '%(stitle)s' in self.params['outtmpl']:
+ self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
+
@staticmethod
def format_bytes(bytes):
if bytes is None:
@@ -139,23 +145,23 @@ 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 long(new_max)
+ return int(new_max)
rate = bytes / elapsed_time
if rate > new_max:
- return long(new_max)
+ return int(new_max)
if rate < new_min:
- return long(new_min)
- return long(rate)
+ return int(new_min)
+ return int(rate)
@staticmethod
def parse_bytes(bytestr):
- """Parse a string indicating a byte quantity into a long integer."""
+ """Parse a string indicating a byte quantity into an integer."""
matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
if matchobj is None:
return None
number = float(matchobj.group(1))
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
- return long(round(number * multiplier))
+ return int(round(number * multiplier))
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
@@ -173,7 +179,6 @@ class FileDownloader(object):
if not self.params.get('quiet', False):
terminator = [u'\n', u''][skip_eol]
output = message + terminator
-
if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
output = output.encode(preferredencoding(), 'ignore')
self._screen_file.write(output)
@@ -181,7 +186,8 @@ class FileDownloader(object):
def to_stderr(self, message):
"""Print message to stderr."""
- print >>sys.stderr, message.encode(preferredencoding())
+ assert type(message) == type(u'')
+ sys.stderr.write((message + u'\n').encode(preferredencoding()))
def to_cons_title(self, message):
"""Set console/terminal window title to message."""
@@ -321,8 +327,10 @@ class FileDownloader(object):
"""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)
+ template_dict['epoch'] = int(time.time())
+ template_dict['autonumber'] = u'%05d' % self._num_downloads
+
+ template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items())
filename = self.params['outtmpl'] % template_dict
return filename
except (ValueError, KeyError), err:
@@ -334,17 +342,22 @@ class FileDownloader(object):
title = info_dict['title']
matchtitle = self.params.get('matchtitle', False)
- if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
- return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+ if matchtitle:
+ matchtitle = matchtitle.decode('utf8')
+ if not re.search(matchtitle, title, re.IGNORECASE):
+ return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
rejecttitle = self.params.get('rejecttitle', False)
- if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
- return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+ if rejecttitle:
+ rejecttitle = rejecttitle.decode('utf8')
+ if re.search(rejecttitle, title, re.IGNORECASE):
+ return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
return None
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
- info_dict['stitle'] = sanitize_filename(info_dict['title'])
+ # Keep for backwards compatibility
+ info_dict['stitle'] = info_dict['title']
reason = self._match_entry(info_dict)
if reason is not None:
@@ -357,20 +370,20 @@ class FileDownloader(object):
raise MaxDownloadsReached()
filename = self.prepare_filename(info_dict)
-
+
# Forced printings
if self.params.get('forcetitle', False):
- print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+ print(info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace'))
if self.params.get('forceurl', False):
- print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
+ print(info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace'))
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
- print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
+ 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')
+ print(info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace'))
if self.params.get('forcefilename', False) and filename is not None:
- print filename.encode(preferredencoding(), 'xmlcharrefreplace')
+ print(filename.encode(preferredencoding(), 'xmlcharrefreplace'))
if self.params.get('forceformat', False):
- print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
+ print(info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace'))
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
@@ -399,10 +412,10 @@ class FileDownloader(object):
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write description file ' + descfn)
return
-
+
if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
# subtitles download errors are already managed as troubles in relevant IE
- # that way it will silently go on when used with unsupporting IE
+ # that way it will silently go on when used with unsupporting IE
try:
srtfn = filename.rsplit('.', 1)[0] + u'.srt'
self.report_writesubtitles(srtfn)
@@ -448,7 +461,7 @@ class FileDownloader(object):
except (ContentTooShortError, ), err:
self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
-
+
if success:
try:
self.post_process(filename, info_dict)
@@ -474,6 +487,7 @@ class FileDownloader(object):
# Extract information from URL and process it
videos = ie.extract(url)
for video in videos or []:
+ video['extractor'] = ie.IE_NAME
try:
self.increment_downloads()
self.process_info(video)
@@ -633,7 +647,7 @@ class FileDownloader(object):
data_len = long(data_len) + resume_len
data_len_str = self.format_bytes(data_len)
byte_counter = 0 + resume_len
- block_size = 1024
+ block_size = self.params.get('buffersize', 1024)
start = time.time()
while True:
# Download and write
@@ -659,7 +673,8 @@ 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, len(data_block))
+ if not self.params.get('noresizebuffer', False):
+ block_size = self.best_block_size(after - before, len(data_block))
# Progress message
speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)