*.vtt
*.flv
*.mp4
+*.m4a
+*.m4v
*.part
test/testdata
.tox
empty string (--proxy "") for direct connection
--no-check-certificate Suppress HTTPS certificate validation.
--cache-dir DIR Location in the filesystem where youtube-dl can
- store downloaded information permanently. By
+ store some downloaded information permanently. By
default $XDG_CACHE_HOME/youtube-dl or ~/.cache
- /youtube-dl .
+ /youtube-dl . At the moment, only YouTube player
+ files (for videos with obfuscated signatures) are
+ cached, but that may change.
--no-cache-dir Disable filesystem caching
--bidi-workaround Work around terminals that lack bidirectional
text support. Requires bidiv or fribidi
### Is anyone going to need the feature?
Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
+
+### Is your question about youtube-dl?
+
+It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
#!/usr/bin/env python
# -*- coding: utf-8 -*-
-from __future__ import print_function
+from __future__ import print_function, unicode_literals
import pkg_resources
import sys
BandcampAlbumIE,
SmotriCommunityIE,
SmotriUserIE,
- IviCompilationIE
+ IviCompilationIE,
+ ImdbListIE,
)
self.assertEqual(result['id'], u'dezhurnyi_angel/season2')
self.assertEqual(result['title'], u'Дежурный ангел (2010 - 2012) 2 сезон')
self.assertTrue(len(result['entries']) >= 20)
+
+ def test_imdb_list(self):
+ dl = FakeYDL()
+ ie = ImdbListIE(dl)
+ result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['id'], u'sMjedvGDd8U')
+ self.assertEqual(result['title'], u'Animated and Family Films')
+ self.assertTrue(len(result['entries']) >= 48)
if __name__ == '__main__':
--- /dev/null
+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 implemented)')
+ 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()
PostProcessingError,
shell_quote,
subtitles_filename,
+ prepend_extension,
)
files_cmd = []
for path in input_paths:
- files_cmd.extend(['-i', encodeFilename(path)])
+ files_cmd.extend(['-i', encodeFilename(path, True)])
cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y'] + files_cmd
+ opts +
- [encodeFilename(self._ffmpeg_filename_argument(out_path))])
+ [encodeFilename(self._ffmpeg_filename_argument(out_path), True)])
if self._downloader.params.get('verbose', False):
self._downloader.to_screen(u'[debug] ffmpeg command line: %s' % shell_quote(cmd))
if not self._exes['ffprobe'] and not self._exes['avprobe']:
raise PostProcessingError(u'ffprobe or avprobe not found. Please install one.')
try:
- cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', encodeFilename(self._ffmpeg_filename_argument(path))]
+ cmd = [
+ self._exes['avprobe'] or self._exes['ffprobe'],
+ '-show_streams',
+ encodeFilename(self._ffmpeg_filename_argument(path), True)]
handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE)
output = handle.communicate()[0]
if handle.wait() != 0:
return True, info
filename = info['filepath']
- ext = os.path.splitext(filename)[1][1:]
- temp_filename = filename + u'.temp'
+ temp_filename = prepend_extension(filename, 'temp')
options = ['-c', 'copy']
for (name, value) in metadata.items():
options.extend(['-metadata', '%s=%s' % (name, value)])
- options.extend(['-f', ext])
self._downloader.to_screen(u'[ffmpeg] Adding metadata to \'%s\'' % filename)
self.run_ffmpeg(filename, temp_filename, options)
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
return True, info
+
+
+class FFmpegMergerPP(FFmpegPostProcessor):
+ def run(self, info):
+ filename = info['filepath']
+ args = ['-c', 'copy']
+ self.run_ffmpeg_multiple_files(info['__files_to_merge'], filename, args)
+ return True, info
#!/usr/bin/env python
# -*- coding: utf-8 -*-
-from __future__ import absolute_import
+from __future__ import absolute_import, unicode_literals
import collections
import errno
write_json_file,
write_string,
YoutubeDLHandler,
+ prepend_extension,
)
from .extractor import get_info_extractor, gen_extractors
from .downloader import get_suitable_downloader
+from .PostProcessor import FFmpegMergerPP
from .version import __version__
socket_timeout: Time to wait for unresponsive hosts, in seconds
bidi_workaround: Work around buggy terminals without bidirectional text
support, using fridibi
+ debug_printtraffic:Print out sent and received HTTP traffic
The following parameters are not used by YoutubeDL itself, they are used by
the FileDownloader:
def __init__(self, params=None):
"""Create a FileDownloader object with the given options."""
+ if params is None:
+ params = {}
self._ies = []
self._ies_instances = {}
self._pps = []
self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self._err_file = sys.stderr
- self.params = {} if params is None else params
+ self.params = params
if params.get('bidi_workaround', False):
try:
self._output_channel = os.fdopen(master, 'rb')
except OSError as ose:
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:
raise
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.')
+ 'Assuming --restrict-filenames since file system encoding '
+ 'cannot encode all charactes. '
+ 'Set the LC_ALL environment variable to fix this.')
self.params['restrictfilenames'] = True
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()
return message
assert hasattr(self, '_output_process')
- assert type(message) == type(u'')
- line_count = message.count(u'\n') + 1
- self._output_process.stdin.write((message + u'\n').encode('utf-8'))
+ assert type(message) == type('')
+ line_count = message.count('\n') + 1
+ self._output_process.stdin.write((message + '\n').encode('utf-8'))
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))
- return res[:-len(u'\n')]
+ return res[:-len('\n')]
def to_screen(self, message, skip_eol=False):
"""Print message to stdout if not in quiet mode."""
self.params['logger'].debug(message)
elif not check_quiet or not self.params.get('quiet', False):
message = self._bidi_workaround(message)
- terminator = [u'\n', u''][skip_eol]
+ terminator = ['\n', ''][skip_eol]
output = message + terminator
write_string(output, self._screen_file)
def to_stderr(self, message):
"""Print message to stderr."""
- assert type(message) == type(u'')
+ assert type(message) == type('')
if self.params.get('logger'):
self.params['logger'].error(message)
else:
message = self._bidi_workaround(message)
- output = message + u'\n'
+ output = message + '\n'
write_string(output, self._err_file)
def to_console_title(self, message):
# already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
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):
if not self.params.get('consoletitle', False):
return
if 'TERM' in os.environ:
# 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):
if not self.params.get('consoletitle', False):
return
if 'TERM' in os.environ:
# 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):
self.save_console_title()
if self.params.get('verbose'):
if tb is None:
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]:
- 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())
else:
tb_data = traceback.format_list(traceback.extract_stack())
- tb = u''.join(tb_data)
+ tb = ''.join(tb_data)
self.to_stderr(tb)
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 stderr is a tty file the 'WARNING:' will be colored
'''
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:
- _msg_header = u'WARNING:'
- warning_message = u'%s %s' % (_msg_header, message)
+ _msg_header = 'WARNING:'
+ warning_message = '%s %s' % (_msg_header, message)
self.to_stderr(warning_message)
def report_error(self, message, tb=None):
in red if stderr is a tty file.
'''
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:
- _msg_header = u'ERROR:'
- error_message = u'%s %s' % (_msg_header, message)
+ _msg_header = 'ERROR:'
+ error_message = '%s %s' % (_msg_header, message)
self.trouble(error_message, tb)
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)
+ self.to_screen('[download] %s has already been downloaded' % file_name)
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):
"""Increment the ordinal that assigns a number to each file."""
autonumber_size = self.params.get('autonumber_size')
if autonumber_size is None:
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
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(
compat_str(v),
restricted=self.params.get('restrictfilenames'),
- is_id=(k == u'id'))
+ is_id=(k == 'id'))
template_dict = dict((k, sanitize(k, v))
for k, v in template_dict.items()
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'])
filename = tmpl % template_dict
return filename
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
def _match_entry(self, info_dict):
""" 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:
# This can happen when we're just evaluating the playlist
title = info_dict['title']
matchtitle = self.params.get('matchtitle', False)
if matchtitle:
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)
if rejecttitle:
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)
if date is not None:
dateRange = self.params.get('daterange', 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)
if view_count is not None:
min_views = self.params.get('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')
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')
if age_limit is not None:
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):
- return u'%s has already been recorded in archive' % video_title
+ return '%s has already been recorded in archive' % video_title
return None
@staticmethod
continue
if not ie.working():
- self.report_warning(u'The program functionality for this site has been marked as broken, '
- u'and will probably not work.')
+ self.report_warning('The program functionality for this site has been marked as broken, '
+ 'and will probably not work.')
try:
ie_result = ie.extract(url)
else:
raise
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={}):
"""
elif result_type == 'playlist':
# We process each entry in the playlist
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 = []
n_entries = len(entries)
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))
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 = {
'playlist': playlist,
'playlist_index': i + playliststart,
reason = self._match_entry(entry)
if reason is not None:
- self.to_screen(u'[download] ' + reason)
+ self.to_screen('[download] ' + reason)
continue
entry_result = self.process_ie_result(entry,
elif format_spec == 'worst':
return available_formats[0]
else:
- extensions = [u'mp4', u'flv', u'webm', u'3gp']
+ extensions = ['mp4', 'flv', 'webm', '3gp']
if format_spec in extensions:
filter_f = lambda f: f['ext'] == format_spec
else:
info_dict['playlist_index'] = None
# This extractors handle format selection themselves
- if info_dict['extractor'] in [u'Youku']:
+ if info_dict['extractor'] in ['Youku']:
if download:
self.process_info(info_dict)
return info_dict
if format.get('format_id') is None:
format['format_id'] = compat_str(i)
if format.get('format') is None:
- format['format'] = u'{id} - {res}{note}'.format(
+ format['format'] = '{id} - {res}{note}'.format(
id=format['format_id'],
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
if 'ext' not in format:
if req_format in ('-1', 'all'):
formats_to_download = formats
else:
- # We can accept formats requestd in the format: 34/5/best, we pick
+ # We can accept formats requested in the format: 34/5/best, we pick
# the first that is available, starting from left
req_formats = req_format.split('/')
for rf in req_formats:
- selected_format = self.select_format(rf, formats)
+ if re.match(r'.+?\+.+?', rf) is not None:
+ # Two formats have been requested like '137+139'
+ format_1, format_2 = rf.split('+')
+ formats_info = (self.select_format(format_1, formats),
+ self.select_format(format_2, formats))
+ if all(formats_info):
+ selected_format = {
+ 'requested_formats': formats_info,
+ 'format': rf,
+ 'ext': formats_info[0]['ext'],
+ }
+ else:
+ selected_format = None
+ else:
+ selected_format = self.select_format(rf, formats)
if selected_format is not None:
formats_to_download = [selected_format]
break
if not formats_to_download:
- raise ExtractorError(u'requested format not available',
+ raise ExtractorError('requested format not available',
expected=True)
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)))
+ self.to_screen('[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)
info_dict['fulltitle'] = info_dict['title']
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
info_dict['stitle'] = info_dict['title']
reason = self._match_entry(info_dict)
if reason is not None:
- self.to_screen(u'[download] ' + reason)
+ self.to_screen('[download] ' + reason)
return
max_downloads = self.params.get('max_downloads')
self.to_stdout(info_dict['id'])
if self.params.get('forceurl', False):
# 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:
self.to_stdout(info_dict['thumbnail'])
if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
if dn != '' and not os.path.exists(dn):
os.makedirs(dn)
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
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)):
- self.to_screen(u'[info] Video description is already present')
+ self.to_screen('[info] Video description is already present')
else:
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:
descfile.write(info_dict['description'])
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):
- self.report_error(u'Cannot write description file ' + descfn)
+ self.report_error('Cannot write description file ' + descfn)
return
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)):
- self.to_screen(u'[info] Video annotations are already present')
+ self.to_screen('[info] Video annotations are already present')
else:
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:
annofile.write(info_dict['annotations'])
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):
- self.report_error(u'Cannot write annotations file: ' + annofn)
+ self.report_error('Cannot write annotations file: ' + annofn)
return
subtitles_are_requested = any([self.params.get('writesubtitles', False),
try:
sub_filename = subtitles_filename(filename, sub_lang, sub_format)
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:
- 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:
subfile.write(sub)
except (OSError, IOError):
- self.report_error(u'Cannot write subtitles file ' + descfn)
+ self.report_error('Cannot write subtitles file ' + descfn)
return
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)):
- self.to_screen(u'[info] Video description metadata is already present')
+ self.to_screen('[info] Video description metadata is already present')
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:
write_json_file(info_dict, encodeFilename(infofn))
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
if self.params.get('writethumbnail', False):
if info_dict.get('thumbnail') is not None:
- thumb_format = determine_ext(info_dict['thumbnail'], u'jpg')
- thumb_filename = os.path.splitext(filename)[0] + u'.' + thumb_format
+ thumb_format = determine_ext(info_dict['thumbnail'], 'jpg')
+ thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format
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']))
else:
- self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
+ self.to_screen('[%s] %s: Downloading thumbnail ...' %
(info_dict['extractor'], info_dict['id']))
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' %
+ self.to_screen('[%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' %
+ self.report_warning('Unable to download thumbnail "%s": %s' %
(info_dict['thumbnail'], compat_str(err)))
if not self.params.get('skip_download', False):
success = True
else:
try:
- fd = get_suitable_downloader(info_dict)(self, self.params)
- for ph in self._progress_hooks:
- fd.add_progress_hook(ph)
- success = fd.download(filename, info_dict)
+ def dl(name, info):
+ fd = get_suitable_downloader(info)(self, self.params)
+ for ph in self._progress_hooks:
+ fd.add_progress_hook(ph)
+ return fd.download(name, info)
+ if info_dict.get('requested_formats') is not None:
+ downloaded = []
+ success = True
+ for f in info_dict['requested_formats']:
+ new_info = dict(info_dict)
+ new_info.update(f)
+ fname = self.prepare_filename(new_info)
+ fname = prepend_extension(fname, 'f%s' % f['format_id'])
+ downloaded.append(fname)
+ partial_success = dl(fname, new_info)
+ success = success and partial_success
+ info_dict['__postprocessors'] = [FFmpegMergerPP(self)]
+ info_dict['__files_to_merge'] = downloaded
+ else:
+ # Just a single file
+ success = dl(filename, info_dict)
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
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))
+ self.report_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.report_error(u'postprocessing: %s' % str(err))
+ self.report_error('postprocessing: %s' % str(err))
return
self.record_download_archive(info_dict)
#It also downloads the videos
self.extract_info(url)
except UnavailableVideoError:
- self.report_error(u'unable to download video')
+ self.report_error('unable to download video')
except MaxDownloadsReached:
- self.to_screen(u'[info] Maximum number of downloaded files reached.')
+ self.to_screen('[info] Maximum number of downloaded files reached.')
raise
return self._download_retcode
except DownloadError:
webpage_url = info.get('webpage_url')
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])
else:
raise
info = dict(ie_info)
info['filepath'] = filename
keep_video = None
- for pp in self._pps:
+ pps_chain = []
+ if ie_info.get('__postprocessors') is not None:
+ pps_chain.extend(ie_info['__postprocessors'])
+ pps_chain.extend(self._pps)
+ for pp in pps_chain:
try:
keep_video_wish, new_info = pp.run(info)
if keep_video_wish is not None:
self.report_error(e.msg)
if keep_video is False and not self.params.get('keepvideo', False):
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))
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):
# Future-proof against any change in case
extractor = info_dict.get('ie_key') # key in a playlist
if extractor is None:
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):
fn = self.params.get('download_archive')
vid_id = self._make_archive_id(info_dict)
assert vid_id
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
def format_resolution(format, default='unknown'):
return format['resolution']
if format.get('height') 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:
- res = u'%sp' % format['height']
+ res = '%sp' % format['height']
elif format.get('width') is not None:
- res = u'?x%d' % format['width']
+ res = '?x%d' % format['width']
else:
res = default
return res
def list_formats(self, info_dict):
def format_note(fdict):
- res = u''
- if f.get('ext') in ['f4f', 'f4m']:
- res += u'(unsupported) '
+ res = ''
+ if fdict.get('ext') in ['f4f', 'f4m']:
+ res += '(unsupported) '
if fdict.get('format_note') is not None:
- res += fdict['format_note'] + u' '
+ res += fdict['format_note'] + ' '
if fdict.get('tbr') is not None:
- res += u'%4dk ' % fdict['tbr']
+ res += '%4dk ' % fdict['tbr']
if (fdict.get('vcodec') is not None and
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:
- res += u'video@'
+ res += 'video@'
if fdict.get('vbr') is not None:
- res += u'%4dk' % fdict['vbr']
+ res += '%4dk' % fdict['vbr']
if fdict.get('acodec') is not None:
if res:
- res += u', '
- res += u'%-5s' % fdict['acodec']
+ res += ', '
+ res += '%-5s' % fdict['acodec']
elif fdict.get('abr') is not None:
if res:
- res += u', '
+ res += ', '
res += 'audio'
if fdict.get('abr') is not None:
- res += u'@%3dk' % fdict['abr']
+ res += '@%3dk' % fdict['abr']
if fdict.get('filesize') is not None:
if res:
- res += u', '
+ res += ', '
res += format_bytes(fdict['filesize'])
return res
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['ext'],
self.format_resolution(format),
))
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))
formats_s = [line(f, idlen) for f in formats]
if len(formats) > 1:
formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)'
header_line = line({
- 'format_id': u'format code', 'ext': u'extension',
- 'resolution': u'resolution', 'format_note': u'note'}, idlen=idlen)
- self.to_screen(u'[info] Available formats for %s:\n%s\n%s' %
- (info_dict['id'], header_line, u"\n".join(formats_s)))
+ 'format_id': 'format code', 'ext': 'extension',
+ 'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen)
+ self.to_screen('[info] Available formats for %s:\n%s\n%s' %
+ (info_dict['id'], header_line, '\n'.join(formats_s)))
def urlopen(self, req):
""" Start an HTTP download """
def print_debug_header(self):
if not self.params.get('verbose'):
return
- write_string(u'[debug] youtube-dl version ' + __version__ + u'\n')
+ write_string('[debug] youtube-dl version ' + __version__ + '\n')
try:
sp = subprocess.Popen(
['git', 'rev-parse', '--short', 'HEAD'],
out, err = sp.communicate()
out = out.decode().strip()
if re.match('[0-9a-f]+', out):
- write_string(u'[debug] Git HEAD: ' + out + u'\n')
+ write_string('[debug] Git HEAD: ' + out + '\n')
except:
try:
sys.exc_clear()
except:
pass
- write_string(u'[debug] Python version %s - %s' %
- (platform.python_version(), platform_name()) + u'\n')
+ write_string('[debug] Python version %s - %s' %
+ (platform.python_version(), platform_name()) + '\n')
proxy_map = {}
for handler in self._opener.handlers:
if hasattr(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):
timeout_val = self.params.get('socket_timeout')
if 'http' in proxies and 'https' not in proxies:
proxies['https'] = proxies['http']
proxy_handler = compat_urllib_request.ProxyHandler(proxies)
+
+ debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(
- self.params.get('nocheckcertificate', False))
+ self.params.get('nocheckcertificate', False), debuglevel=debuglevel)
+ ydlh = YoutubeDLHandler(debuglevel=debuglevel)
opener = compat_urllib_request.build_opener(
- https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
+ https_handler, proxy_handler, cookie_processor, ydlh)
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play
# (See https://github.com/rg3/youtube-dl/issues/1309 for details)
general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
general.add_option(
'--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
- help='Location in the filesystem where youtube-dl can store downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl .')
+ help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
general.add_option(
'--no-cache-dir', action='store_const', const=None, dest='cachedir',
help='Disable filesystem caching')
verbosity.add_option('--youtube-print-sig-code',
action='store_true', dest='youtube_print_sig_code', default=False,
help=optparse.SUPPRESS_HELP)
-
+ verbosity.add_option('--print-traffic',
+ dest='debug_printtraffic', action='store_true', default=False,
+ help=optparse.SUPPRESS_HELP)
filesystem.add_option('-t', '--title',
action='store_true', dest='usetitle', help='use title in file name (default)', default=False)
'proxy': opts.proxy,
'socket_timeout': opts.socket_timeout,
'bidi_workaround': opts.bidi_workaround,
+ 'debug_printtraffic': opts.debug_printtraffic,
}
with YoutubeDL(ydl_opts) as ydl:
return False
try:
stream.write(data_block)
- except (IOError, OSError):
+ except (IOError, OSError) as err:
self.to_stderr(u"\n")
self.report_error(u'unable to write data: %s' % str(err))
return False
from .cinemassacre import CinemassacreIE
from .clipfish import ClipfishIE
from .clipsyndicate import ClipsyndicateIE
+from .cmt import CMTIE
from .cnn import CNNIE
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .howcast import HowcastIE
from .hypem import HypemIE
from .ign import IGNIE, OneUPIE
-from .imdb import ImdbIE
+from .imdb import (
+ ImdbIE,
+ ImdbListIE
+)
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE
from .jeuxvideo import JeuxVideoIE
from .jukebox import JukeboxIE
from .justintv import JustinTVIE
+from .jpopsukitv import JpopsukiIE
from .kankan import KankanIE
from .keezmovies import KeezMoviesIE
from .kickstarter import KickStarterIE
from .keek import KeekIE
from .liveleak import LiveLeakIE
from .livestream import LivestreamIE, LivestreamOriginalIE
+from .lynda import (
+ LyndaIE,
+ LyndaCourseIE
+)
+from .macgamestore import MacGameStoreIE
from .mdr import MDRIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
+from __future__ import unicode_literals
+
import datetime
import json
import re
"""Information extractor for blip.tv"""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
- _URL_EXT = r'^.*\.([a-z0-9]+)$'
- IE_NAME = u'blip.tv'
+
_TEST = {
- u'url': u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
- u'file': u'5779306.m4v',
- u'md5': u'80baf1ec5c3d2019037c1c707d676b9f',
- u'info_dict': {
- u"upload_date": u"20111205",
- u"description": u"md5:9bc31f227219cde65e47eeec8d2dc596",
- u"uploader": u"Comic Book Resources - CBR TV",
- u"title": u"CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3"
+ 'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
+ 'file': '5779306.mov',
+ 'md5': 'c6934ad0b6acf2bd920720ec888eb812',
+ 'info_dict': {
+ 'upload_date': '20111205',
+ 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
+ 'uploader': 'Comic Book Resources - CBR TV',
+ 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
}
}
def report_direct_download(self, title):
"""Report information extraction."""
- self.to_screen(u'%s: Direct download detected' % title)
+ self.to_screen('%s: Direct download detected' % title)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError('Invalid URL: %s' % url)
# See https://github.com/rg3/youtube-dl/issues/857
embed_mobj = re.search(r'^(?:https?://)?(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
if embed_mobj:
info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1)
info_page = self._download_webpage(info_url, embed_mobj.group(1))
- video_id = self._search_regex(r'data-episode-id="(\d+)', info_page, u'video_id')
- return self.url_result('http://blip.tv/a/a-'+video_id, 'BlipTV')
+ video_id = self._search_regex(r'data-episode-id="(\d+)', info_page, 'video_id')
+ return self.url_result('http://blip.tv/a/a-' + video_id, 'BlipTV')
if '?' in url:
cchar = '&'
request.add_header('User-Agent', 'iTunes/10.6.1')
self.report_extraction(mobj.group(1))
urlh = self._request_webpage(request, None, False,
- u'unable to download video info webpage')
+ 'unable to download video info webpage')
try:
json_code_bytes = urlh.read()
json_code = json_code_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err))
+ raise ExtractorError('Unable to read video info webpage: %s' % compat_str(err))
try:
json_data = json.loads(json_code)
data = json_data
upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+ formats = []
if 'additionalMedia' in data:
- formats = sorted(data['additionalMedia'], key=lambda f: int(f['media_height']))
- best_format = formats[-1]
- video_url = best_format['url']
+ for f in sorted(data['additionalMedia'], key=lambda f: int(f['media_height'])):
+ if not int(f['media_width']): # filter m3u8
+ continue
+ formats.append({
+ 'url': f['url'],
+ 'format_id': f['role'],
+ 'width': int(f['media_width']),
+ 'height': int(f['media_height']),
+ })
else:
- video_url = data['media']['url']
- umobj = re.match(self._URL_EXT, video_url)
- if umobj is None:
- raise ValueError('Can not determine filename extension')
- ext = umobj.group(1)
+ formats.append({
+ 'url': data['media']['url'],
+ 'width': int(data['media']['width']),
+ 'height': int(data['media']['height']),
+ })
+
+ self._sort_formats(formats)
return {
'id': compat_str(data['item_id']),
- 'url': video_url,
'uploader': data['display_name'],
'upload_date': upload_date,
'title': data['title'],
- 'ext': ext,
- 'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
'description': data['description'],
- 'player_url': data['embedUrl'],
'user_agent': 'iTunes/10.6.1',
+ 'formats': formats,
}
except (ValueError, KeyError) as err:
- raise ExtractorError(u'Unable to parse video information: %s' % repr(err))
+ raise ExtractorError('Unable to parse video information: %s' % repr(err))
class BlipTVUserIE(InfoExtractor):
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
_PAGE_SIZE = 12
- IE_NAME = u'blip.tv:user'
+ IE_NAME = 'blip.tv:user'
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError('Invalid URL: %s' % url)
username = mobj.group(1)
page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
- page = self._download_webpage(url, username, u'Downloading user page')
+ page = self._download_webpage(url, username, 'Downloading user page')
mobj = re.search(r'data-users-id="([^"]+)"', page)
page_base = page_base % mobj.group(1)
while True:
url = page_base + "&page=" + str(pagenum)
page = self._download_webpage(url, username,
- u'Downloading video ids from page %d' % pagenum)
+ 'Downloading video ids from page %d' % pagenum)
# Extract video identifiers
ids_in_page = []
pagenum += 1
- urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids]
+ urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
return [self.playlist_result(url_entries, playlist_title = username)]
--- /dev/null
+from .mtv import MTVIE
+
+class CMTIE(MTVIE):
+ IE_NAME = u'cmt.com'
+ _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml'
+ _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
+
+ _TESTS = [
+ {
+ u'url': u'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
+ u'md5': u'e6b7ef3c4c45bbfae88061799bbba6c2',
+ u'info_dict': {
+ u'id': u'989124',
+ u'ext': u'mp4',
+ u'title': u'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
+ u'description': u'Blame It All On My Roots',
+ },
+ },
+ ]
+from __future__ import unicode_literals
+
+import json
import re
from .common import InfoExtractor
-from ..utils import (
- compat_urllib_parse_urlparse,
- determine_ext,
-
- ExtractorError,
-)
class CollegeHumorIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
_TESTS = [{
- u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
- u'file': u'6902724.mp4',
- u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
- u'info_dict': {
- u'title': u'Comic-Con Cosplay Catastrophe',
- u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.',
+ 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
+ 'file': '6902724.mp4',
+ 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
+ 'info_dict': {
+ 'title': 'Comic-Con Cosplay Catastrophe',
+ 'description': 'Fans get creative this year at San Diego. Too',
+ 'age_limit': 13,
},
},
{
- u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
- u'file': u'3505939.mp4',
- u'md5': u'c51ca16b82bb456a4397987791a835f5',
- u'info_dict': {
- u'title': u'Font Conference',
- u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
+ 'url': 'http://www.collegehumor.com/video/3505939/font-conference',
+ 'file': '3505939.mp4',
+ 'md5': '72fa701d8ef38664a4dbb9e2ab721816',
+ 'info_dict': {
+ 'title': 'Font Conference',
+ 'description': 'This video wasn\'t long enough, so we made it double-spaced.',
+ 'age_limit': 10,
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
- info = {
- 'id': video_id,
- 'uploader': None,
- 'upload_date': None,
- }
-
- self.report_extraction(video_id)
- xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
- mdoc = self._download_xml(xmlUrl, video_id,
- u'Downloading info XML',
- u'Unable to download video info XML')
+ jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json'
+ data = json.loads(self._download_webpage(
+ jsonUrl, video_id, 'Downloading info JSON'))
+ vdata = data['video']
- try:
- videoNode = mdoc.findall('./video')[0]
- youtubeIdNode = videoNode.find('./youtubeID')
- if youtubeIdNode is not None:
- return self.url_result(youtubeIdNode.text, 'Youtube')
- info['description'] = videoNode.findall('./description')[0].text
- info['title'] = videoNode.findall('./caption')[0].text
- info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
- next_url = videoNode.findall('./file')[0].text
- except IndexError:
- raise ExtractorError(u'Invalid metadata XML file')
-
- if next_url.endswith(u'manifest.f4m'):
- manifest_url = next_url + '?hdcore=2.10.3'
- adoc = self._download_xml(manifest_url, video_id,
- u'Downloading XML manifest',
- u'Unable to download video info XML')
-
- try:
- video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
- except IndexError:
- raise ExtractorError(u'Invalid manifest file')
- url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
- info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
- info['ext'] = 'mp4'
+ AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
+ rating = vdata.get('rating')
+ if rating:
+ age_limit = AGE_LIMITS.get(rating.lower())
else:
- # Old-style direct links
- info['url'] = next_url
- info['ext'] = determine_ext(info['url'])
+ age_limit = None # None = No idea
+
+ PREFS = {'high_quality': 2, 'low_quality': 0}
+ formats = []
+ for format_key in ('mp4', 'webm'):
+ for qname, qurl in vdata[format_key].items():
+ formats.append({
+ 'format_id': format_key + '_' + qname,
+ 'url': qurl,
+ 'format': format_key,
+ 'preference': PREFS.get(qname),
+ })
+ self._sort_formats(formats)
- return info
+ return {
+ 'id': video_id,
+ 'title': vdata['title'],
+ 'description': vdata.get('description'),
+ 'thumbnail': vdata.get('thumbnail'),
+ 'formats': formats,
+ 'age_limit': age_limit,
+ }
class ComedyCentralIE(MTVServicesInfoExtractor):
- _VALID_URL = r'https?://(?:www.)?comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
+ _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/
+ (video-clips|episodes|cc-studios|video-collections)
+ /(?P<title>.*)'''
_FEED_URL = u'http://comedycentral.com/feeds/mrss/'
_TEST = {
download, lower-case.
"http", "https", "rtsp", "rtmp" or so.
* preference Order number of this format. If this field is
- present, the formats get sorted by this field.
+ present and not None, the formats get sorted
+ by this field.
-1 for default (order by other properties),
-2 or smaller for less than default.
url: Final video URL.
@staticmethod
def _og_regexes(prop):
content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
- property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop)
+ property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
template = r'<meta[^>]+?%s[^>]+?%s'
return [
template % (property_re, content_re),
class DreiSatIE(InfoExtractor):
IE_NAME = '3sat'
- _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/index\.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+ _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
_TEST = {
u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
- u'file': u'36983.webm',
- u'md5': u'57c97d0469d71cf874f6815aa2b7c944',
+ u'file': u'36983.mp4',
+ u'md5': u'9dcfe344732808dbfcc901537973c922',
u'info_dict': {
u"title": u"Kaffeeland Schweiz",
u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...",
return self.url_result('http://' + url)
video_id = os.path.splitext(url.split('/')[-1])[0]
+ self.to_screen(u'%s: Requesting header' % video_id)
+
try:
response = self._send_head(url)
'description': descr,
'thumbnail': format_info['slate'],
}
+
+class ImdbListIE(InfoExtractor):
+ IE_NAME = u'imdb:list'
+ IE_DESC = u'Internet Movie Database lists'
+ _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ list_id = mobj.group('id')
+
+ # RSS XML is sometimes malformed
+ rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, u'Downloading list RSS')
+ list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, u'list title')
+
+ # Export is independent of actual author_id, but returns 404 if no author_id is provided.
+ # However, passing dummy author_id seems to be enough.
+ csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id,
+ list_id, u'Downloading list CSV')
+
+ entries = []
+ for item in csv.split('\n')[1:]:
+ cols = item.split(',')
+ if len(cols) < 2:
+ continue
+ item_id = cols[1][1:-1]
+ if item_id.startswith('vi'):
+ entries.append(self.url_result('http://www.imdb.com/video/imdb/%s' % item_id, 'Imdb'))
+
+ return self.playlist_result(entries, list_id, list_title)
\ No newline at end of file
--- /dev/null
+# coding=utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ unified_strdate,
+)
+
+
+class JpopsukiIE(InfoExtractor):
+ IE_NAME = 'jpopsuki.tv'
+ _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)'
+
+ _TEST = {
+ 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
+ 'md5': '88018c0c1a9b1387940e90ec9e7e198e',
+ 'file': '00be659d23b0b40508169cdee4545771.mp4',
+ 'info_dict': {
+ 'id': '00be659d23b0b40508169cdee4545771',
+ 'title': 'ayumi hamasaki - evolution',
+ 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution',
+ 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
+ 'uploader': 'plama_chan',
+ 'uploader_id': '404',
+ 'upload_date': '20121101'
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
+ r'<source src="(.*?)" type', webpage, 'video url')
+
+ video_title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+ uploader = self._html_search_regex(
+ r'<li>from: <a href="/user/view/user/(.*?)/uid/',
+ webpage, 'video uploader', fatal=False)
+ uploader_id = self._html_search_regex(
+ r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)',
+ webpage, 'video uploader_id', fatal=False)
+ upload_date = self._html_search_regex(
+ r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date',
+ fatal=False)
+ if upload_date is not None:
+ upload_date = unified_strdate(upload_date)
+ view_count_str = self._html_search_regex(
+ r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count',
+ fatal=False)
+ comment_count_str = self._html_search_regex(
+ r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count',
+ fatal=False)
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'upload_date': upload_date,
+ 'view_count': int_or_none(view_count_str),
+ 'comment_count': int_or_none(comment_count_str),
+ }
--- /dev/null
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class LyndaIE(InfoExtractor):
+ IE_NAME = 'lynda'
+ IE_DESC = 'lynda.com videos'
+ _VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html'
+
+ _TEST = {
+ 'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
+ 'file': '114408.mp4',
+ 'md5': 'ecfc6862da89489161fb9cd5f5a6fac1',
+ u"info_dict": {
+ 'title': 'Using the exercise files',
+ 'duration': 68
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1)
+
+ page = self._download_webpage('http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id,
+ video_id, 'Downloading video JSON')
+ video_json = json.loads(page)
+
+ if 'Status' in video_json and video_json['Status'] == 'NotFound':
+ raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+ if video_json['HasAccess'] is False:
+ raise ExtractorError('Video %s is only available for members' % video_id, expected=True)
+
+ video_id = video_json['ID']
+ duration = video_json['DurationInSeconds']
+ title = video_json['Title']
+
+ formats = [{'url': fmt['Url'],
+ 'ext': fmt['Extension'],
+ 'width': fmt['Width'],
+ 'height': fmt['Height'],
+ 'filesize': fmt['FileSize'],
+ 'format_id': fmt['Resolution']
+ } for fmt in video_json['Formats']]
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'duration': duration,
+ 'formats': formats
+ }
+
+
+class LyndaCourseIE(InfoExtractor):
+ IE_NAME = 'lynda:course'
+ IE_DESC = 'lynda.com online courses'
+
+ # Course link equals to welcome/introduction video link of same course
+ # We will recognize it as course link
+ _VALID_URL = r'https?://(?:www|m)\.lynda\.com/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ course_path = mobj.group('coursepath')
+ course_id = mobj.group('courseid')
+
+ page = self._download_webpage('http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
+ course_id, 'Downloading course JSON')
+ course_json = json.loads(page)
+
+ if 'Status' in course_json and course_json['Status'] == 'NotFound':
+ raise ExtractorError('Course %s does not exist' % course_id, expected=True)
+
+ unaccessible_videos = 0
+ videos = []
+
+ for chapter in course_json['Chapters']:
+ for video in chapter['Videos']:
+ if video['HasAccess'] is not True:
+ unaccessible_videos += 1
+ continue
+ videos.append(video['ID'])
+
+ if unaccessible_videos > 0:
+ self._downloader.report_warning('%s videos are only available for members and will not be downloaded' % unaccessible_videos)
+
+ entries = [
+ self.url_result('http://www.lynda.com/%s/%s-4.html' %
+ (course_path, video_id),
+ 'Lynda')
+ for video_id in videos]
+
+ course_title = course_json['Title']
+
+ return self.playlist_result(entries, course_id, course_title)
--- /dev/null
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class MacGameStoreIE(InfoExtractor):
+ IE_NAME = 'macgamestore'
+ IE_DESC = 'MacGameStore trailers'
+ _VALID_URL = r'https?://www\.macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
+
+ _TEST = {
+ 'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',
+ 'file': '2450.m4v',
+ 'md5': '8649b8ea684b6666b4c5be736ecddc61',
+ 'info_dict': {
+ 'title': 'Crow',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id, 'Downloading trailer page')
+
+ if re.search(r'>Missing Media<', webpage) is not None:
+ raise ExtractorError('Trailer %s does not exist' % video_id, expected=True)
+
+ video_title = self._html_search_regex(
+ r'<title>MacGameStore: (.*?) Trailer</title>', webpage, 'title')
+
+ video_url = self._html_search_regex(
+ r'(?s)<div\s+id="video-player".*?href="([^"]+)"\s*>',
+ webpage, 'video URL')
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title
+ }
info = json.loads(json_data)
preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
- song_url = preview_url.replace('/previews/', '/cloudcasts/originals/')
+ song_url = preview_url.replace('/previews/', '/c/originals/')
template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
final_song_url = self._get_url(template_url)
if final_song_url is None:
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
- uri = mobj.group('mgid')
+ uri = mobj.groupdict().get('mgid')
if uri is None:
webpage = self._download_webpage(url, video_id)
class PornHdIE(InfoExtractor):
- _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+ _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
_TEST = {
u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
u'file': u'1962.flv',
(?!sets/)(?P<title>[\w\d-]+)/?
(?P<token>[^?]+?)?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
- |(?P<widget>w\.soundcloud\.com/player/?.*?url=.*)
+ |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
)
'''
IE_NAME = u'soundcloud'
if track_id is not None:
info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
full_title = track_id
- elif mobj.group('widget'):
+ elif mobj.group('player'):
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
return self.url_result(query['url'][0], ie='Soundcloud')
else:
'height': a['height'],
'filesize': a['size'],
'ext': a['ext'],
+ 'preference': 1 if atype == 'original' else None,
})
self._sort_formats(formats)
'137': {'ext': 'mp4', 'height': 1080, 'resolution': '1080p', 'format_note': 'DASH video', 'preference': -40},
'138': {'ext': 'mp4', 'height': 1081, 'resolution': '>1080p', 'format_note': 'DASH video', 'preference': -40},
'160': {'ext': 'mp4', 'height': 192, 'resolution': '192p', 'format_note': 'DASH video', 'preference': -40},
+ '264': {'ext': 'mp4', 'height': 1080, 'resolution': '1080p', 'format_note': 'DASH video', 'preference': -40},
# Dash mp4 audio
'139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50},
result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s)
return result
-def encodeFilename(s):
+
+def encodeFilename(s, for_subprocess=False):
"""
@param s The name of the file
"""
- assert type(s) == type(u'')
+ assert type(s) == compat_str
# Python 3 has a Unicode API
if sys.version_info >= (3, 0):
# Pass u'' directly to use Unicode APIs on Windows 2000 and up
# (Detecting Windows NT 4 is tricky because 'major >= 4' would
# match Windows 9x series as well. Besides, NT 4 is obsolete.)
- return s
+ if not for_subprocess:
+ return s
+ else:
+ # For subprocess calls, encode with locale encoding
+ # Refer to http://stackoverflow.com/a/9951851/35070
+ encoding = preferredencoding()
else:
encoding = sys.getfilesystemencoding()
- if encoding is None:
- encoding = 'utf-8'
- return s.encode(encoding, 'ignore')
+ if encoding is None:
+ encoding = 'utf-8'
+ return s.encode(encoding, 'ignore')
+
def decodeOption(optval):
if optval is None:
else:
return '%d' % secs
-def make_HTTPS_handler(opts_no_check_certificate):
+
+def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
if sys.version_info < (3, 2):
import httplib
class HTTPSHandlerV3(compat_urllib_request.HTTPSHandler):
def https_open(self, req):
return self.do_open(HTTPSConnectionV3, req)
- return HTTPSHandlerV3()
+ return HTTPSHandlerV3(**kwargs)
else:
context = ssl.SSLContext(ssl.PROTOCOL_SSLv3)
context.verify_mode = (ssl.CERT_NONE
context.load_default_certs()
except AttributeError:
pass # Python < 3.4
- return compat_urllib_request.HTTPSHandler(context=context)
+ return compat_urllib_request.HTTPSHandler(context=context, **kwargs)
class ExtractorError(Exception):
"""Error during info extraction."""
def write_string(s, out=None):
if out is None:
out = sys.stderr
- assert type(s) == type(u'')
+ assert type(s) == compat_str
if ('b' in getattr(out, 'mode', '') or
sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
s = s.encode(preferredencoding(), 'ignore')
- out.write(s)
+ try:
+ out.write(s)
+ except UnicodeEncodeError:
+ # In Windows shells, this can fail even when the codec is just charmap!?
+ # See https://wiki.python.org/moin/PrintFails#Issue
+ if sys.platform == 'win32' and hasattr(out, 'encoding'):
+ s = s.encode(out.encoding, 'ignore').decode(out.encoding)
+ out.write(s)
+ else:
+ raise
+
out.flush()
def setproctitle(title):
- assert isinstance(title, type(u''))
+ assert isinstance(title, compat_str)
try:
libc = ctypes.cdll.LoadLibrary("libc.so.6")
except OSError:
if m.group('hours'):
res += int(m.group('hours')) * 60 * 60
return res
+
+
+def prepend_extension(filename, ext):
+ name, real_ext = os.path.splitext(filename)
+ return u'{0}.{1}{2}'.format(name, ext, real_ext)
-__version__ = '2013.12.26'
+__version__ = '2014.01.03'
projects / youtube-dl / commitdiff