-from __future__ import absolute_import
-
-import math
-import os
-import re
-import socket
-import subprocess
-import sys
-import time
-import traceback
-
-if os.name == 'nt':
- import ctypes
-
-from .utils import *
-
-
-class FileDownloader(object):
- """File Downloader class.
-
- File downloader objects are the ones responsible of downloading the
- actual video file and writing it to disk if the user has requested
- it, among some other tasks. In most cases there should be one per
- program. As, given a video URL, the downloader doesn't know how to
- extract all the needed information, task that InfoExtractors do, it
- has to pass the URL to one of them.
-
- For this, file downloader objects have a method that allows
- InfoExtractors to be registered in a given order. When it is passed
- a URL, the file downloader handles it to the first InfoExtractor it
- finds that reports being able to handle it. The InfoExtractor extracts
- all the information about the video or videos the URL refers to, and
- asks the FileDownloader to process the video information, possibly
- downloading the video.
-
- File downloaders accept a lot of parameters. In order not to saturate
- the object constructor with arguments, it receives a dictionary of
- options instead. These options are available through the params
- attribute for the InfoExtractors to use. The FileDownloader also
- registers itself as the downloader in charge for the InfoExtractors
- that are added to it, so this is a "mutual registration".
-
- 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.
- 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
- test: Download only first bytes to test the downloader.
- """
-
- params = None
- _ies = []
- _pps = []
- _download_retcode = None
- _num_downloads = None
- _screen_file = None
-
- def __init__(self, params):
- """Create a FileDownloader object with the given options."""
- self._ies = []
- self._pps = []
- self._download_retcode = 0
- self._num_downloads = 0
- 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:
- return 'N/A'
- if type(bytes) is str:
- bytes = float(bytes)
- if bytes == 0.0:
- exponent = 0
- else:
- exponent = int(math.log(bytes, 1024.0))
- suffix = 'bkMGTPEZY'[exponent]
- converted = float(bytes) / float(1024 ** exponent)
- return '%.2f%s' % (converted, suffix)
-
- @staticmethod
- def calc_percent(byte_counter, data_len):
- if data_len is None:
- return '---.-%'
- return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
-
- @staticmethod
- def calc_eta(start, now, total, current):
- if total is None:
- return '--:--'
- dif = now - start
- if current == 0 or dif < 0.001: # One millisecond
- return '--:--'
- rate = float(current) / dif
- eta = int((float(total) - float(current)) / rate)
- (eta_mins, eta_secs) = divmod(eta, 60)
- if eta_mins > 99:
- return '--:--'
- return '%02d:%02d' % (eta_mins, eta_secs)
-
- @staticmethod
- def calc_speed(start, now, bytes):
- dif = now - start
- if bytes == 0 or dif < 0.001: # One millisecond
- return '%10s' % '---b/s'
- return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
-
- @staticmethod
- def best_block_size(elapsed_time, bytes):
- 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)
- rate = bytes / elapsed_time
- if rate > new_max:
- return int(new_max)
- if rate < new_min:
- return int(new_min)
- return int(rate)
-
- @staticmethod
- def parse_bytes(bytestr):
- """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 int(round(number * multiplier))
-
- def add_info_extractor(self, ie):
- """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):
- """Print message to stdout if not in quiet mode."""
- assert type(message) == type(u'')
- if not self.params.get('quiet', False):
- terminator = [u'\n', u''][skip_eol]
- output = message + terminator
- if 'b' in getattr(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)
- self._screen_file.flush()
-
- def to_stderr(self, message):
- """Print message to stderr."""
- assert type(message) == type(u'')
- output = message + u'\n'
- if 'b' in getattr(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())
- sys.stderr.write(output)
-
- 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(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None)
-
- def trouble(self, message=None):
- """Determine action to take when a download problem appears.
-
- Depending on if the downloader has been configured to ignore
- download errors or not, this method may throw an exception or
- not when errors are found, after printing the message.
- """
- if message is not None:
- self.to_stderr(message)
- if self.params.get('verbose'):
- self.to_stderr(u''.join(traceback.format_list(traceback.extract_stack())))
- if not self.params.get('ignoreerrors', False):
- raise DownloadError(message)
- self._download_retcode = 1
-
- def slow_down(self, start_time, byte_counter):
- """Sleep if the download speed is over the rate limit."""
- rate_limit = self.params.get('ratelimit', None)
- if rate_limit is None or byte_counter == 0:
- return
- now = time.time()
- elapsed = now - start_time
- if elapsed <= 0.0:
- return
- 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(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
- 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:
- return
- os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
- except (IOError, OSError) as 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(encodeFilename(filename)):
- return
- timestr = last_modified_hdr
- if timestr is None:
- return
- filetime = timeconvert(timestr)
- if filetime is None:
- return filetime
- try:
- os.utime(filename, (time.time(), filetime))
- except:
- pass
- return filetime
-
- def report_writedescription(self, descfn):
- """ Report that the description file is being written """
- self.to_screen(u'[info] Writing video description to: ' + descfn)
-
- def report_writesubtitles(self, srtfn):
- """ Report that the subtitles file is being written """
- self.to_screen(u'[info] Writing video subtitles to: ' + srtfn)
-
- def report_writeinfojson(self, infofn):
- """ Report that the metadata file has been written """
- self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
-
- def report_destination(self, filename):
- """Report destination filename."""
- self.to_screen(u'[download] Destination: ' + filename)
-
- def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
- """Report download progress."""
- if self.params.get('noprogress', False):
- 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."""
- 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) as 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
-
- def prepare_filename(self, info_dict):
- """Generate the output filename."""
- try:
- template_dict = dict(info_dict)
-
- template_dict['epoch'] = int(time.time())
- template_dict['autonumber'] = u'%05d' % self._num_downloads
-
- sanitize = lambda k,v: sanitize_filename(
- u'NA' if v is None else compat_str(v),
- restricted=self.params.get('restrictfilenames'),
- is_id=(k==u'id'))
- template_dict = dict((k, sanitize(k, v)) for k,v in template_dict.items())
-
- filename = self.params['outtmpl'] % template_dict
- return filename
- except (ValueError, KeyError) as err:
- self.trouble(u'ERROR: invalid system charset or erroneous output template')
- return None
-
- def _match_entry(self, info_dict):
- """ Returns None iff the file should be downloaded """
-
- title = info_dict['title']
- matchtitle = self.params.get('matchtitle', False)
- 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:
- 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."""
-
- # Keep for backwards compatibility
- info_dict['stitle'] = info_dict['title']
-
- if not 'format' in info_dict:
- info_dict['format'] = info_dict['ext']
-
- reason = self._match_entry(info_dict)
- if reason is not None:
- self.to_screen(u'[download] ' + reason)
- return
-
- max_downloads = self.params.get('max_downloads')
- if max_downloads is not None:
- if self._num_downloads > int(max_downloads):
- raise MaxDownloadsReached()
-
- filename = self.prepare_filename(info_dict)
-
- # Forced printings
- if self.params.get('forcetitle', False):
- compat_print(info_dict['title'])
- if self.params.get('forceurl', False):
- compat_print(info_dict['url'])
- if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
- compat_print(info_dict['thumbnail'])
- if self.params.get('forcedescription', False) and 'description' in info_dict:
- compat_print(info_dict['description'])
- if self.params.get('forcefilename', False) and filename is not None:
- compat_print(filename)
- if self.params.get('forceformat', False):
- compat_print(info_dict['format'])
-
- # Do nothing else if in simulate mode
- if self.params.get('simulate', False):
- return
-
- if filename is None:
- return
-
- try:
- dn = os.path.dirname(encodeFilename(filename))
- if dn != '' and not os.path.exists(dn): # dn is already encoded
- os.makedirs(dn)
- except (OSError, IOError) as err:
- self.trouble(u'ERROR: unable to create directory ' + compat_str(err))
- return
-
- if self.params.get('writedescription', False):
- try:
- descfn = filename + u'.description'
- self.report_writedescription(descfn)
- descfile = open(encodeFilename(descfn), 'wb')
- try:
- descfile.write(info_dict['description'].encode('utf-8'))
- finally:
- descfile.close()
- 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
- try:
- srtfn = filename.rsplit('.', 1)[0] + u'.srt'
- self.report_writesubtitles(srtfn)
- srtfile = open(encodeFilename(srtfn), 'wb')
- try:
- srtfile.write(info_dict['subtitles'].encode('utf-8'))
- finally:
- srtfile.close()
- except (OSError, IOError):
- self.trouble(u'ERROR: Cannot write subtitles file ' + descfn)
- return
-
- if self.params.get('writeinfojson', False):
- infofn = filename + u'.info.json'
- self.report_writeinfojson(infofn)
- try:
- json.dump
- except (NameError,AttributeError):
- self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
- return
- try:
- infof = open(encodeFilename(infofn), 'wb')
- try:
- json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
- json.dump(json_info_dict, infof)
- finally:
- infof.close()
- except (OSError, IOError):
- self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
- return
-
- if not self.params.get('skip_download', False):
- if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
- success = True
- else:
- try:
- success = self._do_download(filename, info_dict)
- except (OSError, IOError) as err:
- raise UnavailableVideoError()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self.trouble(u'ERROR: unable to download video data: %s' % str(err))
- return
- except (ContentTooShortError, ) as 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)
- except (PostProcessingError) as err:
- self.trouble(u'ERROR: postprocessing: %s' % str(err))
- return
-
- def download(self, url_list):
- """Download a given list of URLs."""
- if len(url_list) > 1 and self.fixed_template():
- raise SameFileError(self.params['outtmpl'])
-
- for url in url_list:
- suitable_found = False
- for ie in self._ies:
- # Go to next InfoExtractor if not suitable
- if not ie.suitable(url):
- continue
-
- # Warn if the _WORKING attribute is False
- if not ie.working():
- self.trouble(u'WARNING: the program functionality for this site has been marked as broken, '
- u'and will probably not work. If you want to go on, use the -i option.')
-
- # Suitable InfoExtractor found
- suitable_found = True
-
- # 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)
- except UnavailableVideoError:
- self.trouble(u'\nERROR: unable to download video')
-
- # Suitable InfoExtractor had been found; go to next URL
- break
-
- if not suitable_found:
- self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
-
- return self._download_retcode
-
- def post_process(self, filename, ie_info):
- """Run the postprocessing chain on the given file."""
- info = dict(ie_info)
- info['filepath'] = filename
- for pp in self._pps:
- 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)
-
- # Check for rtmpdump first
- try:
- subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
- except (OSError, IOError):
- self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
- return False
-
- # 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', tmpfilename]
- args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
- if self.params.get('verbose', False):
- try:
- import pipes
- shell_quote = lambda args: ' '.join(map(pipes.quote, args))
- except ImportError:
- shell_quote = repr
- self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args))
- retval = subprocess.call(args)
- while retval == 2 or retval == 1:
- prevsize = os.path.getsize(encodeFilename(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(encodeFilename(tmpfilename))
- if prevsize == cursize and retval == 1:
- break
- # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
- if prevsize == cursize and retval == 2 and cursize > 1024:
- self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
- retval = 0
- break
- if retval == 0:
- self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(encodeFilename(tmpfilename)))
- self.try_rename(tmpfilename, filename)
- return True
- else:
- self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
- return False
Rapsys Git / youtubedl / blobdiff