depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-22 16:57:40 +00:00
Code Issues Releases Wiki Activity

Prepare widespread unicode literal use

Browse source
This commit is contained in:
Philipp Hagemeister 2014-01-05 01:52:03 +01:00
parent a7c26e7338
commit 6febd1c1df
3 changed files with 158 additions and 118 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
setup.py
View file

@ -1,7 +1,7 @@
#!/usr/bin/env python #!/usr/bin/env python
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import print_function from __future__ import print_function, unicode_literals
import pkg_resources import pkg_resources
import sys import sys

40
test/test_unicode_literals.py Normal file
View file

@ -0,0 +1,40 @@
from __future__ import unicode_literals
import io
import os
import re
import unittest
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
class TestUnicodeLiterals(unittest.TestCase):
def test_all_files(self):
print('Skipping this test (not yet fully implemtned)')
return
for dirpath, _, filenames in os.walk(rootDir):
for basename in filenames:
if not basename.endswith('.py'):
continue
fn = os.path.join(dirpath, basename)
with io.open(fn, encoding='utf-8') as inf:
code = inf.read()
if "'" not in code and '"' not in code:
continue
imps = 'from __future__ import unicode_literals'
self.assertTrue(
imps in code,
' %s missing in %s' % (imps, fn))
m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code)
if m is not None:
self.assertTrue(
m is None,
'u present in %s, around %s' % (
fn, code[m.start() - 10:m.end() + 10]))
if __name__ == '__main__':
unittest.main()

234
youtube_dl/YoutubeDL.py
View file

@ -1,7 +1,7 @@
#!/usr/bin/env python #!/usr/bin/env python
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import from __future__ import absolute_import, unicode_literals
import collections import collections
import errno import errno
@ -200,7 +200,7 @@ class YoutubeDL(object):
self._output_channel = os.fdopen(master, 'rb') self._output_channel = os.fdopen(master, 'rb')
except OSError as ose: except OSError as ose:
if ose.errno == 2: if ose.errno == 2:
self.report_warning(u'Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.') self.report_warning('Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.')
else: else:
raise raise
@ -209,13 +209,13 @@ class YoutubeDL(object):
and not params['restrictfilenames']): and not params['restrictfilenames']):
# On Python 3, the Unicode filesystem API will throw errors (#1474) # On Python 3, the Unicode filesystem API will throw errors (#1474)
self.report_warning( self.report_warning(
u'Assuming --restrict-filenames since file system encoding ' 'Assuming --restrict-filenames since file system encoding '
u'cannot encode all charactes. ' 'cannot encode all charactes. '
u'Set the LC_ALL environment variable to fix this.') 'Set the LC_ALL environment variable to fix this.')
self.params['restrictfilenames'] = True self.params['restrictfilenames'] = True
if '%(stitle)s' in self.params.get('outtmpl', ''): if '%(stitle)s' in self.params.get('outtmpl', ''):
self.report_warning(u'%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
self._setup_opener() self._setup_opener()
@ -258,13 +258,13 @@ class YoutubeDL(object):
return message return message
assert hasattr(self, '_output_process') assert hasattr(self, '_output_process')
assert type(message) == type(u'') assert type(message) == type('')
line_count = message.count(u'\n') + 1 line_count = message.count('\n') + 1
self._output_process.stdin.write((message + u'\n').encode('utf-8')) self._output_process.stdin.write((message + '\n').encode('utf-8'))
self._output_process.stdin.flush() self._output_process.stdin.flush()
res = u''.join(self._output_channel.readline().decode('utf-8') res = ''.join(self._output_channel.readline().decode('utf-8')
for _ in range(line_count)) for _ in range(line_count))
return res[:-len(u'\n')] return res[:-len('\n')]
def to_screen(self, message, skip_eol=False): def to_screen(self, message, skip_eol=False):
"""Print message to stdout if not in quiet mode.""" """Print message to stdout if not in quiet mode."""
@ -276,19 +276,19 @@ class YoutubeDL(object):
self.params['logger'].debug(message) self.params['logger'].debug(message)
elif not check_quiet or not self.params.get('quiet', False): elif not check_quiet or not self.params.get('quiet', False):
message = self._bidi_workaround(message) message = self._bidi_workaround(message)
terminator = [u'\n', u''][skip_eol] terminator = ['\n', ''][skip_eol]
output = message + terminator output = message + terminator
write_string(output, self._screen_file) write_string(output, self._screen_file)
def to_stderr(self, message): def to_stderr(self, message):
"""Print message to stderr.""" """Print message to stderr."""
assert type(message) == type(u'') assert type(message) == type('')
if self.params.get('logger'): if self.params.get('logger'):
self.params['logger'].error(message) self.params['logger'].error(message)
else: else:
message = self._bidi_workaround(message) message = self._bidi_workaround(message)
output = message + u'\n' output = message + '\n'
write_string(output, self._err_file) write_string(output, self._err_file)
def to_console_title(self, message): def to_console_title(self, message):
@ -299,21 +299,21 @@ class YoutubeDL(object):
# already of type unicode() # already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
elif 'TERM' in os.environ: elif 'TERM' in os.environ:
write_string(u'\033]0;%s\007' % message, self._screen_file) write_string('\033]0;%s\007' % message, self._screen_file)
def save_console_title(self): def save_console_title(self):
if not self.params.get('consoletitle', False): if not self.params.get('consoletitle', False):
return return
if 'TERM' in os.environ: if 'TERM' in os.environ:
# Save the title on stack # Save the title on stack
write_string(u'\033[22;0t', self._screen_file) write_string('\033[22;0t', self._screen_file)
def restore_console_title(self): def restore_console_title(self):
if not self.params.get('consoletitle', False): if not self.params.get('consoletitle', False):
return return
if 'TERM' in os.environ: if 'TERM' in os.environ:
# Restore the title from stack # Restore the title from stack
write_string(u'\033[23;0t', self._screen_file) write_string('\033[23;0t', self._screen_file)
def __enter__(self): def __enter__(self):
self.save_console_title() self.save_console_title()
@ -339,13 +339,13 @@ class YoutubeDL(object):
if self.params.get('verbose'): if self.params.get('verbose'):
if tb is None: if tb is None:
if sys.exc_info()[0]: # if .trouble has been called from an except block if sys.exc_info()[0]: # if .trouble has been called from an except block
tb = u'' tb = ''
if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
tb += u''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info))
tb += compat_str(traceback.format_exc()) tb += compat_str(traceback.format_exc())
else: else:
tb_data = traceback.format_list(traceback.extract_stack()) tb_data = traceback.format_list(traceback.extract_stack())
tb = u''.join(tb_data) tb = ''.join(tb_data)
self.to_stderr(tb) self.to_stderr(tb)
if not self.params.get('ignoreerrors', False): if not self.params.get('ignoreerrors', False):
if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
@ -361,10 +361,10 @@ class YoutubeDL(object):
If stderr is a tty file the 'WARNING:' will be colored If stderr is a tty file the 'WARNING:' will be colored
''' '''
if self._err_file.isatty() and os.name != 'nt': if self._err_file.isatty() and os.name != 'nt':
_msg_header = u'\033[0;33mWARNING:\033[0m' _msg_header = '\033[0;33mWARNING:\033[0m'
else: else:
_msg_header = u'WARNING:' _msg_header = 'WARNING:'
warning_message = u'%s %s' % (_msg_header, message) warning_message = '%s %s' % (_msg_header, message)
self.to_stderr(warning_message) self.to_stderr(warning_message)
def report_error(self, message, tb=None): def report_error(self, message, tb=None):
@ -373,18 +373,18 @@ class YoutubeDL(object):
in red if stderr is a tty file. in red if stderr is a tty file.
''' '''
if self._err_file.isatty() and os.name != 'nt': if self._err_file.isatty() and os.name != 'nt':
_msg_header = u'\033[0;31mERROR:\033[0m' _msg_header = '\033[0;31mERROR:\033[0m'
else: else:
_msg_header = u'ERROR:' _msg_header = 'ERROR:'
error_message = u'%s %s' % (_msg_header, message) error_message = '%s %s' % (_msg_header, message)
self.trouble(error_message, tb) self.trouble(error_message, tb)
def report_file_already_downloaded(self, file_name): def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded.""" """Report file has already been fully downloaded."""
try: try:
self.to_screen(u'[download] %s has already been downloaded' % file_name) self.to_screen('[download] %s has already been downloaded' % file_name)
except UnicodeEncodeError: except UnicodeEncodeError:
self.to_screen(u'[download] The file has already been downloaded') self.to_screen('[download] The file has already been downloaded')
def increment_downloads(self): def increment_downloads(self):
"""Increment the ordinal that assigns a number to each file.""" """Increment the ordinal that assigns a number to each file."""
@ -399,61 +399,61 @@ class YoutubeDL(object):
autonumber_size = self.params.get('autonumber_size') autonumber_size = self.params.get('autonumber_size')
if autonumber_size is None: if autonumber_size is None:
autonumber_size = 5 autonumber_size = 5
autonumber_templ = u'%0' + str(autonumber_size) + u'd' autonumber_templ = '%0' + str(autonumber_size) + 'd'
template_dict['autonumber'] = autonumber_templ % self._num_downloads template_dict['autonumber'] = autonumber_templ % self._num_downloads
if template_dict.get('playlist_index') is not None: if template_dict.get('playlist_index') is not None:
template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index'] template_dict['playlist_index'] = '%05d' % template_dict['playlist_index']
sanitize = lambda k, v: sanitize_filename( sanitize = lambda k, v: sanitize_filename(
compat_str(v), compat_str(v),
restricted=self.params.get('restrictfilenames'), restricted=self.params.get('restrictfilenames'),
is_id=(k == u'id')) is_id=(k == 'id'))
template_dict = dict((k, sanitize(k, v)) template_dict = dict((k, sanitize(k, v))
for k, v in template_dict.items() for k, v in template_dict.items()
if v is not None) if v is not None)
template_dict = collections.defaultdict(lambda: u'NA', template_dict) template_dict = collections.defaultdict(lambda: 'NA', template_dict)
tmpl = os.path.expanduser(self.params['outtmpl']) tmpl = os.path.expanduser(self.params['outtmpl'])
filename = tmpl % template_dict filename = tmpl % template_dict
return filename return filename
except ValueError as err: except ValueError as err:
self.report_error(u'Error in output template: ' + str(err) + u' (encoding: ' + repr(preferredencoding()) + ')') self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
return None return None
def _match_entry(self, info_dict): def _match_entry(self, info_dict):
""" Returns None iff the file should be downloaded """ """ Returns None iff the file should be downloaded """
video_title = info_dict.get('title', info_dict.get('id', u'video')) video_title = info_dict.get('title', info_dict.get('id', 'video'))
if 'title' in info_dict: if 'title' in info_dict:
# This can happen when we're just evaluating the playlist # This can happen when we're just evaluating the playlist
title = info_dict['title'] title = info_dict['title']
matchtitle = self.params.get('matchtitle', False) matchtitle = self.params.get('matchtitle', False)
if matchtitle: if matchtitle:
if not re.search(matchtitle, title, re.IGNORECASE): if not re.search(matchtitle, title, re.IGNORECASE):
return u'"' + title + '" title did not match pattern "' + matchtitle + '"' return '"' + title + '" title did not match pattern "' + matchtitle + '"'
rejecttitle = self.params.get('rejecttitle', False) rejecttitle = self.params.get('rejecttitle', False)
if rejecttitle: if rejecttitle:
if re.search(rejecttitle, title, re.IGNORECASE): if re.search(rejecttitle, title, re.IGNORECASE):
return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' return '"' + title + '" title matched reject pattern "' + rejecttitle + '"'
date = info_dict.get('upload_date', None) date = info_dict.get('upload_date', None)
if date is not None: if date is not None:
dateRange = self.params.get('daterange', DateRange()) dateRange = self.params.get('daterange', DateRange())
if date not in dateRange: if date not in dateRange:
return u'%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
view_count = info_dict.get('view_count', None) view_count = info_dict.get('view_count', None)
if view_count is not None: if view_count is not None:
min_views = self.params.get('min_views') min_views = self.params.get('min_views')
if min_views is not None and view_count < min_views: if min_views is not None and view_count < min_views:
return u'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views) return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views)
max_views = self.params.get('max_views') max_views = self.params.get('max_views')
if max_views is not None and view_count > max_views: if max_views is not None and view_count > max_views:
return u'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
age_limit = self.params.get('age_limit') age_limit = self.params.get('age_limit')
if age_limit is not None: if age_limit is not None:
if age_limit < info_dict.get('age_limit', 0): if age_limit < info_dict.get('age_limit', 0):
return u'Skipping "' + title + '" because it is age restricted' return 'Skipping "' + title + '" because it is age restricted'
if self.in_download_archive(info_dict): if self.in_download_archive(info_dict):
return u'%s has already been recorded in archive' % video_title return '%s has already been recorded in archive' % video_title
return None return None
@staticmethod @staticmethod
@ -480,8 +480,8 @@ class YoutubeDL(object):
continue continue
if not ie.working(): if not ie.working():
self.report_warning(u'The program functionality for this site has been marked as broken, ' self.report_warning('The program functionality for this site has been marked as broken, '
u'and will probably not work.') 'and will probably not work.')
try: try:
ie_result = ie.extract(url) ie_result = ie.extract(url)
@ -514,7 +514,7 @@ class YoutubeDL(object):
else: else:
raise raise
else: else:
self.report_error(u'no suitable InfoExtractor: %s' % url) self.report_error('no suitable InfoExtractor: %s' % url)
def process_ie_result(self, ie_result, download=True, extra_info={}): def process_ie_result(self, ie_result, download=True, extra_info={}):
""" """
@ -565,7 +565,7 @@ class YoutubeDL(object):
elif result_type == 'playlist': elif result_type == 'playlist':
# We process each entry in the playlist # We process each entry in the playlist
playlist = ie_result.get('title', None) or ie_result.get('id', None) playlist = ie_result.get('title', None) or ie_result.get('id', None)
self.to_screen(u'[download] Downloading playlist: %s' % playlist) self.to_screen('[download] Downloading playlist: %s' % playlist)
playlist_results = [] playlist_results = []
@ -580,11 +580,11 @@ class YoutubeDL(object):
n_entries = len(entries) n_entries = len(entries)
self.to_screen( self.to_screen(
u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" % "[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
(ie_result['extractor'], playlist, n_all_entries, n_entries)) (ie_result['extractor'], playlist, n_all_entries, n_entries))
for i, entry in enumerate(entries, 1): for i, entry in enumerate(entries, 1):
self.to_screen(u'[download] Downloading video #%s of %s' % (i, n_entries)) self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries))
extra = { extra = {
'playlist': playlist, 'playlist': playlist,
'playlist_index': i + playliststart, 'playlist_index': i + playliststart,
@ -596,7 +596,7 @@ class YoutubeDL(object):
reason = self._match_entry(entry) reason = self._match_entry(entry)
if reason is not None: if reason is not None:
self.to_screen(u'[download] ' + reason) self.to_screen('[download] ' + reason)
continue continue
entry_result = self.process_ie_result(entry, entry_result = self.process_ie_result(entry,
@ -629,7 +629,7 @@ class YoutubeDL(object):
elif format_spec == 'worst': elif format_spec == 'worst':
return available_formats[0] return available_formats[0]
else: else:
extensions = [u'mp4', u'flv', u'webm', u'3gp'] extensions = ['mp4', 'flv', 'webm', '3gp']
if format_spec in extensions: if format_spec in extensions:
filter_f = lambda f: f['ext'] == format_spec filter_f = lambda f: f['ext'] == format_spec
else: else:
@ -648,7 +648,7 @@ class YoutubeDL(object):
info_dict['playlist_index'] = None info_dict['playlist_index'] = None
# This extractors handle format selection themselves # This extractors handle format selection themselves
if info_dict['extractor'] in [u'Youku']: if info_dict['extractor'] in ['Youku']:
if download: if download:
self.process_info(info_dict) self.process_info(info_dict)
return info_dict return info_dict
@ -665,10 +665,10 @@ class YoutubeDL(object):
if format.get('format_id') is None: if format.get('format_id') is None:
format['format_id'] = compat_str(i) format['format_id'] = compat_str(i)
if format.get('format') is None: if format.get('format') is None:
format['format'] = u'{id} - {res}{note}'.format( format['format'] = '{id} - {res}{note}'.format(
id=format['format_id'], id=format['format_id'],
res=self.format_resolution(format), res=self.format_resolution(format),
note=u' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '', note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '',
) )
# Automatically determine file extension if missing # Automatically determine file extension if missing
if 'ext' not in format: if 'ext' not in format:
@ -709,12 +709,12 @@ class YoutubeDL(object):
formats_to_download = [selected_format] formats_to_download = [selected_format]
break break
if not formats_to_download: if not formats_to_download:
raise ExtractorError(u'requested format not available', raise ExtractorError('requested format not available',
expected=True) expected=True)
if download: if download:
if len(formats_to_download) > 1: if len(formats_to_download) > 1:
self.to_screen(u'[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download))) self.to_screen('[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download)))
for format in formats_to_download: for format in formats_to_download:
new_info = dict(info_dict) new_info = dict(info_dict)
new_info.update(format) new_info.update(format)
@ -732,7 +732,7 @@ class YoutubeDL(object):
info_dict['fulltitle'] = info_dict['title'] info_dict['fulltitle'] = info_dict['title']
if len(info_dict['title']) > 200: if len(info_dict['title']) > 200:
info_dict['title'] = info_dict['title'][:197] + u'...' info_dict['title'] = info_dict['title'][:197] + '...'
# Keep for backwards compatibility # Keep for backwards compatibility
info_dict['stitle'] = info_dict['title'] info_dict['stitle'] = info_dict['title']
@ -742,7 +742,7 @@ class YoutubeDL(object):
reason = self._match_entry(info_dict) reason = self._match_entry(info_dict)
if reason is not None: if reason is not None:
self.to_screen(u'[download] ' + reason) self.to_screen('[download] ' + reason)
return return
max_downloads = self.params.get('max_downloads') max_downloads = self.params.get('max_downloads')
@ -759,7 +759,7 @@ class YoutubeDL(object):
self.to_stdout(info_dict['id']) self.to_stdout(info_dict['id'])
if self.params.get('forceurl', False): if self.params.get('forceurl', False):
# For RTMP URLs, also include the playpath # For RTMP URLs, also include the playpath
self.to_stdout(info_dict['url'] + info_dict.get('play_path', u'')) self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:
self.to_stdout(info_dict['thumbnail']) self.to_stdout(info_dict['thumbnail'])
if self.params.get('forcedescription', False) and info_dict.get('description') is not None: if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
@ -786,37 +786,37 @@ class YoutubeDL(object):
if dn != '' and not os.path.exists(dn): if dn != '' and not os.path.exists(dn):
os.makedirs(dn) os.makedirs(dn)
except (OSError, IOError) as err: except (OSError, IOError) as err:
self.report_error(u'unable to create directory ' + compat_str(err)) self.report_error('unable to create directory ' + compat_str(err))
return return
if self.params.get('writedescription', False): if self.params.get('writedescription', False):
descfn = filename + u'.description' descfn = filename + '.description'
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)): if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
self.to_screen(u'[info] Video description is already present') self.to_screen('[info] Video description is already present')
else: else:
try: try:
self.to_screen(u'[info] Writing video description to: ' + descfn) self.to_screen('[info] Writing video description to: ' + descfn)
with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
descfile.write(info_dict['description']) descfile.write(info_dict['description'])
except (KeyError, TypeError): except (KeyError, TypeError):
self.report_warning(u'There\'s no description to write.') self.report_warning('There\'s no description to write.')
except (OSError, IOError): except (OSError, IOError):
self.report_error(u'Cannot write description file ' + descfn) self.report_error('Cannot write description file ' + descfn)
return return
if self.params.get('writeannotations', False): if self.params.get('writeannotations', False):
annofn = filename + u'.annotations.xml' annofn = filename + '.annotations.xml'
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)): if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)):
self.to_screen(u'[info] Video annotations are already present') self.to_screen('[info] Video annotations are already present')
else: else:
try: try:
self.to_screen(u'[info] Writing video annotations to: ' + annofn) self.to_screen('[info] Writing video annotations to: ' + annofn)
with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
annofile.write(info_dict['annotations']) annofile.write(info_dict['annotations'])
except (KeyError, TypeError): except (KeyError, TypeError):
self.report_warning(u'There are no annotations to write.') self.report_warning('There are no annotations to write.')
except (OSError, IOError): except (OSError, IOError):
self.report_error(u'Cannot write annotations file: ' + annofn) self.report_error('Cannot write annotations file: ' + annofn)
return return
subtitles_are_requested = any([self.params.get('writesubtitles', False), subtitles_are_requested = any([self.params.get('writesubtitles', False),
@ -834,45 +834,45 @@ class YoutubeDL(object):
try: try:
sub_filename = subtitles_filename(filename, sub_lang, sub_format) sub_filename = subtitles_filename(filename, sub_lang, sub_format)
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
self.to_screen(u'[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format)) self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format))
else: else:
self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename) self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
subfile.write(sub) subfile.write(sub)
except (OSError, IOError): except (OSError, IOError):
self.report_error(u'Cannot write subtitles file ' + descfn) self.report_error('Cannot write subtitles file ' + descfn)
return return
if self.params.get('writeinfojson', False): if self.params.get('writeinfojson', False):
infofn = os.path.splitext(filename)[0] + u'.info.json' infofn = os.path.splitext(filename)[0] + '.info.json'
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)): if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
self.to_screen(u'[info] Video description metadata is already present') self.to_screen('[info] Video description metadata is already present')
else: else:
self.to_screen(u'[info] Writing video description metadata as JSON to: ' + infofn) self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
try: try:
write_json_file(info_dict, encodeFilename(infofn)) write_json_file(info_dict, encodeFilename(infofn))
except (OSError, IOError): except (OSError, IOError):
self.report_error(u'Cannot write metadata to JSON file ' + infofn) self.report_error('Cannot write metadata to JSON file ' + infofn)
return return
if self.params.get('writethumbnail', False): if self.params.get('writethumbnail', False):
if info_dict.get('thumbnail') is not None: if info_dict.get('thumbnail') is not None:
thumb_format = determine_ext(info_dict['thumbnail'], u'jpg') thumb_format = determine_ext(info_dict['thumbnail'], 'jpg')
thumb_filename = os.path.splitext(filename)[0] + u'.' + thumb_format thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)): if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
self.to_screen(u'[%s] %s: Thumbnail is already present' % self.to_screen('[%s] %s: Thumbnail is already present' %
(info_dict['extractor'], info_dict['id'])) (info_dict['extractor'], info_dict['id']))
else: else:
self.to_screen(u'[%s] %s: Downloading thumbnail ...' % self.to_screen('[%s] %s: Downloading thumbnail ...' %
(info_dict['extractor'], info_dict['id'])) (info_dict['extractor'], info_dict['id']))
try: try:
uf = compat_urllib_request.urlopen(info_dict['thumbnail']) uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
with open(thumb_filename, 'wb') as thumbf: with open(thumb_filename, 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf) shutil.copyfileobj(uf, thumbf)
self.to_screen(u'[%s] %s: Writing thumbnail to: %s' % self.to_screen('[%s] %s: Writing thumbnail to: %s' %
(info_dict['extractor'], info_dict['id'], thumb_filename)) (info_dict['extractor'], info_dict['id'], thumb_filename))
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_warning(u'Unable to download thumbnail "%s": %s' % self.report_warning('Unable to download thumbnail "%s": %s' %
(info_dict['thumbnail'], compat_str(err))) (info_dict['thumbnail'], compat_str(err)))
if not self.params.get('skip_download', False): if not self.params.get('skip_download', False):
@ -885,19 +885,19 @@ class YoutubeDL(object):
fd.add_progress_hook(ph) fd.add_progress_hook(ph)
success = fd.download(filename, info_dict) success = fd.download(filename, info_dict)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as 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)) self.report_error('unable to download video data: %s' % str(err))
return return
except (OSError, IOError) as err: except (OSError, IOError) as err:
raise UnavailableVideoError(err) raise UnavailableVideoError(err)
except (ContentTooShortError, ) as err: except (ContentTooShortError, ) as err:
self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return return
if success: if success:
try: try:
self.post_process(filename, info_dict) self.post_process(filename, info_dict)
except (PostProcessingError) as err: except (PostProcessingError) as err:
self.report_error(u'postprocessing: %s' % str(err)) self.report_error('postprocessing: %s' % str(err))
return return
self.record_download_archive(info_dict) self.record_download_archive(info_dict)
@ -914,9 +914,9 @@ class YoutubeDL(object):
#It also downloads the videos #It also downloads the videos
self.extract_info(url) self.extract_info(url)
except UnavailableVideoError: except UnavailableVideoError:
self.report_error(u'unable to download video') self.report_error('unable to download video')
except MaxDownloadsReached: except MaxDownloadsReached:
self.to_screen(u'[info] Maximum number of downloaded files reached.') self.to_screen('[info] Maximum number of downloaded files reached.')
raise raise
return self._download_retcode return self._download_retcode
@ -929,7 +929,7 @@ class YoutubeDL(object):
except DownloadError: except DownloadError:
webpage_url = info.get('webpage_url') webpage_url = info.get('webpage_url')
if webpage_url is not None: if webpage_url is not None:
self.report_warning(u'The info failed to download, trying with "%s"' % webpage_url) self.report_warning('The info failed to download, trying with "%s"' % webpage_url)
return self.download([webpage_url]) return self.download([webpage_url])
else: else:
raise raise
@ -953,10 +953,10 @@ class YoutubeDL(object):
self.report_error(e.msg) self.report_error(e.msg)
if keep_video is False and not self.params.get('keepvideo', False): if keep_video is False and not self.params.get('keepvideo', False):
try: try:
self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename) self.to_screen('Deleting original file %s (pass -k to keep)' % filename)
os.remove(encodeFilename(filename)) os.remove(encodeFilename(filename))
except (IOError, OSError): except (IOError, OSError):
self.report_warning(u'Unable to remove downloaded video file') self.report_warning('Unable to remove downloaded video file')
def _make_archive_id(self, info_dict): def _make_archive_id(self, info_dict):
# Future-proof against any change in case # Future-proof against any change in case
@ -967,7 +967,7 @@ class YoutubeDL(object):
extractor = info_dict.get('ie_key') # key in a playlist extractor = info_dict.get('ie_key') # key in a playlist
if extractor is None: if extractor is None:
return None # Incomplete video information return None # Incomplete video information
return extractor.lower() + u' ' + info_dict['id'] return extractor.lower() + ' ' + info_dict['id']
def in_download_archive(self, info_dict): def in_download_archive(self, info_dict):
fn = self.params.get('download_archive') fn = self.params.get('download_archive')
@ -995,7 +995,7 @@ class YoutubeDL(object):
vid_id = self._make_archive_id(info_dict) vid_id = self._make_archive_id(info_dict)
assert vid_id assert vid_id
with locked_file(fn, 'a', encoding='utf-8') as archive_file: with locked_file(fn, 'a', encoding='utf-8') as archive_file:
archive_file.write(vid_id + u'\n') archive_file.write(vid_id + '\n')
@staticmethod @staticmethod
def format_resolution(format, default='unknown'): def format_resolution(format, default='unknown'):
@ -1005,49 +1005,49 @@ class YoutubeDL(object):
return format['resolution'] return format['resolution']
if format.get('height') is not None: if format.get('height') is not None:
if format.get('width') is not None: if format.get('width') is not None:
res = u'%sx%s' % (format['width'], format['height']) res = '%sx%s' % (format['width'], format['height'])
else: else:
res = u'%sp' % format['height'] res = '%sp' % format['height']
elif format.get('width') is not None: elif format.get('width') is not None:
res = u'?x%d' % format['width'] res = '?x%d' % format['width']
else: else:
res = default res = default
return res return res
def list_formats(self, info_dict): def list_formats(self, info_dict):
def format_note(fdict): def format_note(fdict):
res = u'' res = ''
if fdict.get('ext') in ['f4f', 'f4m']: if fdict.get('ext') in ['f4f', 'f4m']:
res += u'(unsupported) ' res += '(unsupported) '
if fdict.get('format_note') is not None: if fdict.get('format_note') is not None:
res += fdict['format_note'] + u' ' res += fdict['format_note'] + ' '
if fdict.get('tbr') is not None: if fdict.get('tbr') is not None:
res += u'%4dk ' % fdict['tbr'] res += '%4dk ' % fdict['tbr']
if (fdict.get('vcodec') is not None and if (fdict.get('vcodec') is not None and
fdict.get('vcodec') != 'none'): fdict.get('vcodec') != 'none'):
res += u'%-5s@' % fdict['vcodec'] res += '%-5s@' % fdict['vcodec']
elif fdict.get('vbr') is not None and fdict.get('abr') is not None: elif fdict.get('vbr') is not None and fdict.get('abr') is not None:
res += u'video@' res += 'video@'
if fdict.get('vbr') is not None: if fdict.get('vbr') is not None:
res += u'%4dk' % fdict['vbr'] res += '%4dk' % fdict['vbr']
if fdict.get('acodec') is not None: if fdict.get('acodec') is not None:
if res: if res:
res += u', ' res += ', '
res += u'%-5s' % fdict['acodec'] res += '%-5s' % fdict['acodec']
elif fdict.get('abr') is not None: elif fdict.get('abr') is not None:
if res: if res:
res += u', ' res += ', '
res += 'audio' res += 'audio'
if fdict.get('abr') is not None: if fdict.get('abr') is not None:
res += u'@%3dk' % fdict['abr'] res += '@%3dk' % fdict['abr']
if fdict.get('filesize') is not None: if fdict.get('filesize') is not None:
if res: if res:
res += u', ' res += ', '
res += format_bytes(fdict['filesize']) res += format_bytes(fdict['filesize'])
return res return res
def line(format, idlen=20): def line(format, idlen=20):
return ((u'%-' + compat_str(idlen + 1) + u's%-10s%-12s%s') % ( return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % (
format['format_id'], format['format_id'],
format['ext'], format['ext'],
self.format_resolution(format), self.format_resolution(format),
@ -1055,7 +1055,7 @@ class YoutubeDL(object):
)) ))
formats = info_dict.get('formats', [info_dict]) formats = info_dict.get('formats', [info_dict])
idlen = max(len(u'format code'), idlen = max(len('format code'),
max(len(f['format_id']) for f in formats)) max(len(f['format_id']) for f in formats))
formats_s = [line(f, idlen) for f in formats] formats_s = [line(f, idlen) for f in formats]
if len(formats) > 1: if len(formats) > 1:
@ -1063,10 +1063,10 @@ class YoutubeDL(object):
formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)' formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)'
header_line = line({ header_line = line({
'format_id': u'format code', 'ext': u'extension', 'format_id': 'format code', 'ext': 'extension',
'resolution': u'resolution', 'format_note': u'note'}, idlen=idlen) 'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen)
self.to_screen(u'[info] Available formats for %s:\n%s\n%s' % self.to_screen('[info] Available formats for %s:\n%s\n%s' %
(info_dict['id'], header_line, u"\n".join(formats_s))) (info_dict['id'], header_line, '\n'.join(formats_s)))
def urlopen(self, req): def urlopen(self, req):
""" Start an HTTP download """ """ Start an HTTP download """
@ -1075,7 +1075,7 @@ class YoutubeDL(object):
def print_debug_header(self): def print_debug_header(self):
if not self.params.get('verbose'): if not self.params.get('verbose'):
return return
write_string(u'[debug] youtube-dl version ' + __version__ + u'\n') write_string('[debug] youtube-dl version ' + __version__ + '\n')
try: try:
sp = subprocess.Popen( sp = subprocess.Popen(
['git', 'rev-parse', '--short', 'HEAD'], ['git', 'rev-parse', '--short', 'HEAD'],
@ -1084,20 +1084,20 @@ class YoutubeDL(object):
out, err = sp.communicate() out, err = sp.communicate()
out = out.decode().strip() out = out.decode().strip()
if re.match('[0-9a-f]+', out): if re.match('[0-9a-f]+', out):
write_string(u'[debug] Git HEAD: ' + out + u'\n') write_string('[debug] Git HEAD: ' + out + '\n')
except: except:
try: try:
sys.exc_clear() sys.exc_clear()
except: except:
pass pass
write_string(u'[debug] Python version %s - %s' % write_string('[debug] Python version %s - %s' %
(platform.python_version(), platform_name()) + u'\n') (platform.python_version(), platform_name()) + '\n')
proxy_map = {} proxy_map = {}
for handler in self._opener.handlers: for handler in self._opener.handlers:
if hasattr(handler, 'proxies'): if hasattr(handler, 'proxies'):
proxy_map.update(handler.proxies) proxy_map.update(handler.proxies)
write_string(u'[debug] Proxy map: ' + compat_str(proxy_map) + u'\n') write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n')
def _setup_opener(self): def _setup_opener(self):
timeout_val = self.params.get('socket_timeout') timeout_val = self.params.get('socket_timeout')