from __future__ import absolute_import
+import errno
import io
import os
import re
logtostderr: Log messages to stderr instead of stdout.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
+ writeannotations: Write the video annotations to a .annotations.xml file
writethumbnail: Write the thumbnail image to a file
writesubtitles: Write the video subtitles to a file
writeautomaticsub: Write the automatic subtitles to a file
allsubtitles: Downloads all the subtitles of the video
+ (requires writesubtitles or writeautomaticsub)
listsubtitles: Lists all available subtitles for the video
subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt)
subtitleslangs: List of languages of the subtitles to download
keepvideo: Keep the video file after post-processing
daterange: A DateRange object, download only if the upload_date is in the range.
skip_download: Skip the actual download of the video file
+ cachedir: Location of the cache files in the filesystem.
+ None to disable filesystem cache.
+ noplaylist: Download single video instead of a playlist if in doubt.
+ age_limit: An integer representing the user's age in years.
+ Unsuitable videos for the given age are skipped.
+ downloadarchive: File name of a file where all downloads are recorded.
+ Videos already present in the file are not downloaded
+ again.
The following parameters are not used by YoutubeDL itself, they are used by
the FileDownloader:
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._ies = []
+ self._ies_instances = {}
self._pps = []
self._progress_hooks = []
self._download_retcode = 0
self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
+
+ if (sys.version_info >= (3,) and sys.platform != 'win32' and
+ sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
+ and not params['restrictfilenames']):
+ # On Python 3, the Unicode filesystem API will throw errors (#1474)
+ self.report_warning(
+ u'Assuming --restrict-filenames since file system encoding '
+ u'cannot encode all charactes. '
+ u'Set the LC_ALL environment variable to fix this.')
+ params['restrictfilenames'] = True
+
self.params = params
self.fd = FileDownloader(self, self.params)
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
+ self._ies_instances[ie.ie_key()] = ie
ie.set_downloader(self)
+ def get_info_extractor(self, ie_key):
+ """
+ Get an instance of an IE with name ie_key, it will try to get one from
+ the _ies list, if there's no instance it will create a new one and add
+ it to the extractor list.
+ """
+ ie = self._ies_instances.get(ie_key)
+ if ie is None:
+ ie = get_info_extractor(ie_key)()
+ self.add_info_extractor(ie)
+ return ie
+
def add_default_info_extractors(self):
"""
Add the InfoExtractors returned by gen_extractors to the end of the list
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()
+ write_string(output, self._screen_file)
def to_stderr(self, message):
"""Print message to stderr."""
""" Report that the metadata file has been written """
self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
+ def report_writeannotations(self, annofn):
+ """ Report that the annotations file has been written. """
+ self.to_screen(u'[info] Writing video annotations to: ' + annofn)
+
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
dateRange = self.params.get('daterange', DateRange())
if date not in dateRange:
return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
+ age_limit = self.params.get('age_limit')
+ if age_limit is not None:
+ if age_limit < info_dict.get('age_limit', 0):
+ return u'Skipping "' + title + '" because it is age restricted'
+ if self.in_download_archive(info_dict):
+ return (u'%(title)s has already been recorded in archive'
+ % info_dict)
return None
def extract_info(self, url, download=True, ie_key=None, extra_info={}):
'''
if ie_key:
- ie = get_info_extractor(ie_key)()
- ie.set_downloader(self)
- ies = [ie]
+ ies = [self.get_info_extractor(ie_key)]
else:
ies = self._ies
result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
if result_type == 'video':
ie_result.update(extra_info)
- if 'playlist' not in ie_result:
- # It isn't part of a playlist
- ie_result['playlist'] = None
- ie_result['playlist_index'] = None
- if download:
- self.process_info(ie_result)
- return ie_result
+ return self.process_video_result(ie_result)
elif result_type == 'url':
# We have to add extra_info to the results because it may be
# contained in a playlist
else:
raise Exception('Invalid result type: %s' % result_type)
+ def process_video_result(self, info_dict, download=True):
+ assert info_dict.get('_type', 'video') == 'video'
+
+ if 'playlist' not in info_dict:
+ # It isn't part of a playlist
+ info_dict['playlist'] = None
+ info_dict['playlist_index'] = None
+
+ # This extractors handle format selection themselves
+ if info_dict['extractor'] in [u'youtube', u'Youku', u'YouPorn', u'mixcloud']:
+ self.process_info(info_dict)
+ return info_dict
+
+ # We now pick which formats have to be downloaded
+ if info_dict.get('formats') is None:
+ # There's only one format available
+ formats = [info_dict]
+ else:
+ formats = info_dict['formats']
+
+ # We check that all the formats have the format and format_id fields
+ for (i, format) in enumerate(formats):
+ if format.get('format') is None:
+ if format.get('height') is not None:
+ if format.get('width') is not None:
+ format_desc = u'%sx%s' % (format['width'], format['height'])
+ else:
+ format_desc = u'%sp' % format['height']
+ else:
+ format_desc = '???'
+ format['format'] = format_desc
+ if format.get('format_id') is None:
+ format['format_id'] = compat_str(i)
+
+ if self.params.get('listformats', None):
+ self.list_formats(info_dict)
+ return
+
+ format_limit = self.params.get('format_limit', None)
+ if format_limit:
+ formats = [f for f in formats if f['format_id'] <= format_limit]
+ if self.params.get('prefer_free_formats'):
+ def _free_formats_key(f):
+ try:
+ ext_ord = [u'flv', u'mp4', u'webm'].index(f['ext'])
+ except ValueError:
+ ext_ord = -1
+ # We only compare the extension if they have the same height and width
+ return (f.get('height'), f.get('width'), ext_ord)
+ formats = sorted(formats, key=_free_formats_key)
+
+ req_format = self.params.get('format', 'best')
+ formats_to_download = []
+ if req_format == 'best' or req_format is None:
+ formats_to_download = [formats[-1]]
+ elif req_format == 'worst':
+ formats_to_download = [formats[0]]
+ # The -1 is for supporting YoutubeIE
+ elif req_format in ('-1', 'all'):
+ formats_to_download = formats
+ else:
+ # We can accept formats requestd in the format: 34/10/5, we pick
+ # the first that is availble, starting from left
+ req_formats = req_format.split('/')
+ for rf in req_formats:
+ matches = filter(lambda f:f['format_id'] == rf ,formats)
+ if matches:
+ formats_to_download = [matches[0]]
+ break
+ if not formats_to_download:
+ raise ExtractorError(u'requested format not available')
+
+ if download:
+ if len(formats_to_download) > 1:
+ self.to_screen(u'[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download)))
+ for format in formats_to_download:
+ new_info = dict(info_dict)
+ new_info.update(format)
+ self.process_info(new_info)
+ # We update the info dict with the best quality format (backwards compatibility)
+ info_dict.update(formats_to_download[-1])
+ return info_dict
+
def process_info(self, info_dict):
"""Process a single resolved IE result."""
if self.params.get('forceid', False):
compat_print(info_dict['id'])
if self.params.get('forceurl', False):
- compat_print(info_dict['url'])
+ # For RTMP URLs, also include the playpath
+ compat_print(info_dict['url'] + info_dict.get('play_path', u''))
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:
self.report_writedescription(descfn)
with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
descfile.write(info_dict['description'])
+ except (KeyError, TypeError):
+ self.report_warning(u'There\'s no description to write.')
except (OSError, IOError):
self.report_error(u'Cannot write description file ' + descfn)
return
+ if self.params.get('writeannotations', False):
+ try:
+ annofn = filename + u'.annotations.xml'
+ self.report_writeannotations(annofn)
+ with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
+ annofile.write(info_dict['annotations'])
+ except (KeyError, TypeError):
+ self.report_warning(u'There are no annotations to write.')
+ except (OSError, IOError):
+ self.report_error(u'Cannot write annotations file: ' + annofn)
+ return
+
subtitles_are_requested = any([self.params.get('writesubtitles', False),
- self.params.get('writeautomaticsub'),
- self.params.get('allsubtitles', False)])
+ self.params.get('writeautomaticsub')])
if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']:
# subtitles download errors are already managed as troubles in relevant IE
thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
(info_dict['extractor'], info_dict['id']))
- uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
- with open(thumb_filename, 'wb') as thumbf:
- shutil.copyfileobj(uf, thumbf)
- self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
- (info_dict['extractor'], info_dict['id'], thumb_filename))
+ try:
+ uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
+ with open(thumb_filename, 'wb') as thumbf:
+ shutil.copyfileobj(uf, thumbf)
+ self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
+ (info_dict['extractor'], info_dict['id'], thumb_filename))
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self.report_warning(u'Unable to download thumbnail "%s": %s' %
+ (info_dict['thumbnail'], compat_str(err)))
if not self.params.get('skip_download', False):
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
else:
try:
success = self.fd._do_download(filename, info_dict)
- except (OSError, IOError) as err:
- raise UnavailableVideoError(err)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_error(u'unable to download video data: %s' % str(err))
return
+ except (OSError, IOError) as err:
+ raise UnavailableVideoError(err)
except (ContentTooShortError, ) as err:
self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
self.report_error(u'postprocessing: %s' % str(err))
return
+ self.record_download_archive(info_dict)
+
def download(self, url_list):
"""Download a given list of URLs."""
if len(url_list) > 1 and self.fixed_template():
os.remove(encodeFilename(filename))
except (IOError, OSError):
self.report_warning(u'Unable to remove downloaded video file')
+
+ def in_download_archive(self, info_dict):
+ fn = self.params.get('download_archive')
+ if fn is None:
+ return False
+ vid_id = info_dict['extractor'] + u' ' + info_dict['id']
+ try:
+ with locked_file(fn, 'r', encoding='utf-8') as archive_file:
+ for line in archive_file:
+ if line.strip() == vid_id:
+ return True
+ except IOError as ioe:
+ if ioe.errno != errno.ENOENT:
+ raise
+ return False
+
+ def record_download_archive(self, info_dict):
+ fn = self.params.get('download_archive')
+ if fn is None:
+ return
+ vid_id = info_dict['extractor'] + u' ' + info_dict['id']
+ with locked_file(fn, 'a', encoding='utf-8') as archive_file:
+ archive_file.write(vid_id + u'\n')
+
+ def list_formats(self, info_dict):
+ formats_s = []
+ for format in info_dict.get('formats', [info_dict]):
+ formats_s.append("%s\t:\t%s\t[%s]" % (format['format_id'],
+ format['ext'],
+ format.get('format', '???'),
+ )
+ )
+ if len(formats_s) != 1:
+ formats_s[0] += ' (worst)'
+ formats_s[-1] += ' (best)'
+ formats_s = "\n".join(formats_s)
+ self.to_screen(u"[info] Available formats for %s:\nformat code\textension\n%s" % (info_dict['id'], formats_s))
projects / youtube-dl / blobdiff