Compare commits
36 Commits
2011.11.23
...
2012.01.08
Author | SHA1 | Date | |
---|---|---|---|
|
38ffbc0222 | ||
|
fefb166c52 | ||
|
dcb3c22e0b | ||
|
47a53c9e46 | ||
|
1413cd87eb | ||
|
c92e184f75 | ||
|
3906e6ce60 | ||
|
c7d3c3db0d | ||
|
d6639d05c2 | ||
|
633cf7cbad | ||
|
a5647b79ce | ||
|
ba5059dd66 | ||
|
bb8abbbbae | ||
|
561504fffa | ||
|
23e6b8adc8 | ||
|
3e0ea7d07a | ||
|
94fd3201b2 | ||
|
0b3f3e1ad9 | ||
|
a05d2a0c05 | ||
|
0b14e0b367 | ||
|
66e8777769 | ||
|
348486ced4 | ||
|
f1f300e629 | ||
|
dd17922afc | ||
|
40fd4cb86a | ||
|
9e9b75ae4d | ||
|
8abf76ddb9 | ||
|
c95da745bc | ||
|
0cd235eef6 | ||
|
77315556f1 | ||
|
c379c181e0 | ||
|
31a2ec2d88 | ||
|
b88a52504e | ||
|
a95567af99 | ||
|
849edab8ec | ||
|
b158a1d946 |
3
.gitignore
vendored
Normal file
3
.gitignore
vendored
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
*.pyc
|
||||||
|
*.pyo
|
||||||
|
*~
|
@@ -1 +1 @@
|
|||||||
2011.11.23
|
2012.01.08
|
||||||
|
6
Makefile
6
Makefile
@@ -10,9 +10,11 @@ update-readme:
|
|||||||
header=$$(sed -e '/.*## OPTIONS/,$$ d' README.md) && \
|
header=$$(sed -e '/.*## OPTIONS/,$$ d' README.md) && \
|
||||||
footer=$$(sed -e '1,/.*## FAQ/ d' README.md) && \
|
footer=$$(sed -e '1,/.*## FAQ/ d' README.md) && \
|
||||||
echo "$${header}" > README.md && \
|
echo "$${header}" > README.md && \
|
||||||
echo -e '\n## OPTIONS' >> README.md && \
|
echo >> README.md && \
|
||||||
|
echo '## OPTIONS' >> README.md && \
|
||||||
echo "$${options}" >> README.md&& \
|
echo "$${options}" >> README.md&& \
|
||||||
echo -e '\n## FAQ' >> README.md && \
|
echo >> README.md && \
|
||||||
|
echo '## FAQ' >> README.md && \
|
||||||
echo "$${footer}" >> README.md
|
echo "$${footer}" >> README.md
|
||||||
|
|
||||||
compile:
|
compile:
|
||||||
|
12
README.md
12
README.md
@@ -28,6 +28,7 @@ which means you can modify it, redistribute it or use it however you like.
|
|||||||
sub-string)
|
sub-string)
|
||||||
--reject-title REGEX skip download for matching titles (regex or
|
--reject-title REGEX skip download for matching titles (regex or
|
||||||
caseless sub-string)
|
caseless sub-string)
|
||||||
|
--max-downloads NUMBER Abort after downloading NUMBER files
|
||||||
|
|
||||||
### Filesystem Options:
|
### Filesystem Options:
|
||||||
-t, --title use title in file name
|
-t, --title use title in file name
|
||||||
@@ -36,8 +37,10 @@ which means you can modify it, redistribute it or use it however you like.
|
|||||||
-o, --output TEMPLATE output filename template. Use %(stitle)s to get the
|
-o, --output TEMPLATE output filename template. Use %(stitle)s to get the
|
||||||
title, %(uploader)s for the uploader name,
|
title, %(uploader)s for the uploader name,
|
||||||
%(autonumber)s to get an automatically incremented
|
%(autonumber)s to get an automatically incremented
|
||||||
number, %(ext)s for the filename extension, and %%
|
number, %(ext)s for the filename extension,
|
||||||
for a literal percent
|
%(upload_date)s for the upload date (YYYYMMDD), and
|
||||||
|
%% for a literal percent. Use - to output to
|
||||||
|
stdout.
|
||||||
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
|
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
|
||||||
-w, --no-overwrites do not overwrite files
|
-w, --no-overwrites do not overwrite files
|
||||||
-c, --continue resume partially downloaded files
|
-c, --continue resume partially downloaded files
|
||||||
@@ -67,6 +70,8 @@ which means you can modify it, redistribute it or use it however you like.
|
|||||||
### Video Format Options:
|
### Video Format Options:
|
||||||
-f, --format FORMAT video format code
|
-f, --format FORMAT video format code
|
||||||
--all-formats download all available video formats
|
--all-formats download all available video formats
|
||||||
|
--prefer-free-formats prefer free video formats unless a specific one is
|
||||||
|
requested
|
||||||
--max-quality FORMAT highest quality format to download
|
--max-quality FORMAT highest quality format to download
|
||||||
-F, --list-formats list all available formats (currently youtube only)
|
-F, --list-formats list all available formats (currently youtube only)
|
||||||
|
|
||||||
@@ -78,7 +83,8 @@ which means you can modify it, redistribute it or use it however you like.
|
|||||||
### Post-processing Options:
|
### Post-processing Options:
|
||||||
--extract-audio convert video files to audio-only files (requires
|
--extract-audio convert video files to audio-only files (requires
|
||||||
ffmpeg and ffprobe)
|
ffmpeg and ffprobe)
|
||||||
--audio-format FORMAT "best", "aac", "vorbis" or "mp3"; best by default
|
--audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", or "wav";
|
||||||
|
best by default
|
||||||
--audio-quality QUALITY ffmpeg audio bitrate specification, 128k by default
|
--audio-quality QUALITY ffmpeg audio bitrate specification, 128k by default
|
||||||
-k, --keep-video keeps the video file on disk after the post-
|
-k, --keep-video keeps the video file on disk after the post-
|
||||||
processing; the video is erased by default
|
processing; the video is erased by default
|
||||||
|
6
devscripts/posix-locale.sh
Normal file
6
devscripts/posix-locale.sh
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
|
||||||
|
# source this file in your shell to get a POSIX locale (which will break many programs, but that's kind of the point)
|
||||||
|
|
||||||
|
export LC_ALL=POSIX
|
||||||
|
export LANG=POSIX
|
||||||
|
export LANGUAGE=POSIX
|
579
youtube-dl
579
youtube-dl
@@ -1,7 +1,7 @@
|
|||||||
#!/usr/bin/env python
|
#!/usr/bin/env python
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
__author__ = (
|
__authors__ = (
|
||||||
'Ricardo Garcia Gonzalez',
|
'Ricardo Garcia Gonzalez',
|
||||||
'Danny Colligan',
|
'Danny Colligan',
|
||||||
'Benjamin Johnson',
|
'Benjamin Johnson',
|
||||||
@@ -14,10 +14,11 @@ __author__ = (
|
|||||||
'Sören Schulze',
|
'Sören Schulze',
|
||||||
'Kevin Ngo',
|
'Kevin Ngo',
|
||||||
'Ori Avtalion',
|
'Ori Avtalion',
|
||||||
|
'shizeeg',
|
||||||
)
|
)
|
||||||
|
|
||||||
__license__ = 'Public Domain'
|
__license__ = 'Public Domain'
|
||||||
__version__ = '2011.11.23'
|
__version__ = '2012.01.08'
|
||||||
|
|
||||||
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
|
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
|
||||||
|
|
||||||
@@ -258,14 +259,14 @@ def sanitize_open(filename, open_mode):
|
|||||||
import msvcrt
|
import msvcrt
|
||||||
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
|
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
|
||||||
return (sys.stdout, filename)
|
return (sys.stdout, filename)
|
||||||
stream = open(filename, open_mode)
|
stream = open(_encodeFilename(filename), open_mode)
|
||||||
return (stream, filename)
|
return (stream, filename)
|
||||||
except (IOError, OSError), err:
|
except (IOError, OSError), err:
|
||||||
# In case of error, try to remove win32 forbidden chars
|
# In case of error, try to remove win32 forbidden chars
|
||||||
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
|
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
|
||||||
|
|
||||||
# An exception here should be caught in the caller
|
# An exception here should be caught in the caller
|
||||||
stream = open(filename, open_mode)
|
stream = open(_encodeFilename(filename), open_mode)
|
||||||
return (stream, filename)
|
return (stream, filename)
|
||||||
|
|
||||||
|
|
||||||
@@ -281,6 +282,31 @@ def _simplify_title(title):
|
|||||||
expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
|
expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
|
||||||
return expr.sub(u'_', title).strip(u'_')
|
return expr.sub(u'_', title).strip(u'_')
|
||||||
|
|
||||||
|
def _orderedSet(iterable):
|
||||||
|
""" Remove all duplicates from the input iterable """
|
||||||
|
res = []
|
||||||
|
for el in iterable:
|
||||||
|
if el not in res:
|
||||||
|
res.append(el)
|
||||||
|
return res
|
||||||
|
|
||||||
|
def _unescapeHTML(s):
|
||||||
|
"""
|
||||||
|
@param s a string (of type unicode)
|
||||||
|
"""
|
||||||
|
assert type(s) == type(u'')
|
||||||
|
|
||||||
|
htmlParser = HTMLParser.HTMLParser()
|
||||||
|
return htmlParser.unescape(s)
|
||||||
|
|
||||||
|
def _encodeFilename(s):
|
||||||
|
"""
|
||||||
|
@param s The name of the file (of type unicode)
|
||||||
|
"""
|
||||||
|
|
||||||
|
assert type(s) == type(u'')
|
||||||
|
return s.encode(sys.getfilesystemencoding(), 'ignore')
|
||||||
|
|
||||||
class DownloadError(Exception):
|
class DownloadError(Exception):
|
||||||
"""Download Error exception.
|
"""Download Error exception.
|
||||||
|
|
||||||
@@ -308,6 +334,10 @@ class PostProcessingError(Exception):
|
|||||||
"""
|
"""
|
||||||
pass
|
pass
|
||||||
|
|
||||||
|
class MaxDownloadsReached(Exception):
|
||||||
|
""" --max-downloads limit has been reached. """
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
class UnavailableVideoError(Exception):
|
class UnavailableVideoError(Exception):
|
||||||
"""Unavailable Format exception.
|
"""Unavailable Format exception.
|
||||||
@@ -541,16 +571,17 @@ class FileDownloader(object):
|
|||||||
self._pps.append(pp)
|
self._pps.append(pp)
|
||||||
pp.set_downloader(self)
|
pp.set_downloader(self)
|
||||||
|
|
||||||
def to_screen(self, message, skip_eol=False, ignore_encoding_errors=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."""
|
||||||
try:
|
assert type(message) == type(u'')
|
||||||
if not self.params.get('quiet', False):
|
if not self.params.get('quiet', False):
|
||||||
terminator = [u'\n', u''][skip_eol]
|
terminator = [u'\n', u''][skip_eol]
|
||||||
print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
|
output = message + terminator
|
||||||
|
|
||||||
|
if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
|
||||||
|
output = output.encode(preferredencoding(), 'ignore')
|
||||||
|
self._screen_file.write(output)
|
||||||
self._screen_file.flush()
|
self._screen_file.flush()
|
||||||
except (UnicodeEncodeError), err:
|
|
||||||
if not ignore_encoding_errors:
|
|
||||||
raise
|
|
||||||
|
|
||||||
def to_stderr(self, message):
|
def to_stderr(self, message):
|
||||||
"""Print message to stderr."""
|
"""Print message to stderr."""
|
||||||
@@ -600,7 +631,7 @@ class FileDownloader(object):
|
|||||||
def temp_name(self, filename):
|
def temp_name(self, filename):
|
||||||
"""Returns a temporary filename for the given filename."""
|
"""Returns a temporary filename for the given filename."""
|
||||||
if self.params.get('nopart', False) or filename == u'-' or \
|
if self.params.get('nopart', False) or filename == u'-' or \
|
||||||
(os.path.exists(filename) and not os.path.isfile(filename)):
|
(os.path.exists(_encodeFilename(filename)) and not os.path.isfile(_encodeFilename(filename))):
|
||||||
return filename
|
return filename
|
||||||
return filename + u'.part'
|
return filename + u'.part'
|
||||||
|
|
||||||
@@ -613,7 +644,7 @@ class FileDownloader(object):
|
|||||||
try:
|
try:
|
||||||
if old_filename == new_filename:
|
if old_filename == new_filename:
|
||||||
return
|
return
|
||||||
os.rename(old_filename, new_filename)
|
os.rename(_encodeFilename(old_filename), _encodeFilename(new_filename))
|
||||||
except (IOError, OSError), err:
|
except (IOError, OSError), err:
|
||||||
self.trouble(u'ERROR: unable to rename file')
|
self.trouble(u'ERROR: unable to rename file')
|
||||||
|
|
||||||
@@ -621,7 +652,7 @@ class FileDownloader(object):
|
|||||||
"""Try to set the last-modified time of the given file."""
|
"""Try to set the last-modified time of the given file."""
|
||||||
if last_modified_hdr is None:
|
if last_modified_hdr is None:
|
||||||
return
|
return
|
||||||
if not os.path.isfile(filename):
|
if not os.path.isfile(_encodeFilename(filename)):
|
||||||
return
|
return
|
||||||
timestr = last_modified_hdr
|
timestr = last_modified_hdr
|
||||||
if timestr is None:
|
if timestr is None:
|
||||||
@@ -637,15 +668,15 @@ class FileDownloader(object):
|
|||||||
|
|
||||||
def report_writedescription(self, descfn):
|
def report_writedescription(self, descfn):
|
||||||
""" Report that the description file is being written """
|
""" Report that the description file is being written """
|
||||||
self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
|
self.to_screen(u'[info] Writing video description to: ' + descfn)
|
||||||
|
|
||||||
def report_writeinfojson(self, infofn):
|
def report_writeinfojson(self, infofn):
|
||||||
""" Report that the metadata file has been written """
|
""" Report that the metadata file has been written """
|
||||||
self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
|
self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
|
||||||
|
|
||||||
def report_destination(self, filename):
|
def report_destination(self, filename):
|
||||||
"""Report destination filename."""
|
"""Report destination filename."""
|
||||||
self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
|
self.to_screen(u'[download] Destination: ' + filename)
|
||||||
|
|
||||||
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
|
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
|
||||||
"""Report download progress."""
|
"""Report download progress."""
|
||||||
@@ -698,8 +729,31 @@ class FileDownloader(object):
|
|||||||
self.trouble(u'ERROR: invalid system charset or erroneous output template')
|
self.trouble(u'ERROR: invalid system charset or erroneous output template')
|
||||||
return None
|
return None
|
||||||
|
|
||||||
|
def _match_entry(self, info_dict):
|
||||||
|
""" Returns None iff the file should be downloaded """
|
||||||
|
|
||||||
|
title = info_dict['title']
|
||||||
|
matchtitle = self.params.get('matchtitle', False)
|
||||||
|
if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
|
||||||
|
return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
|
||||||
|
rejecttitle = self.params.get('rejecttitle', False)
|
||||||
|
if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
|
||||||
|
return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
|
||||||
|
return None
|
||||||
|
|
||||||
def process_info(self, info_dict):
|
def process_info(self, info_dict):
|
||||||
"""Process a single dictionary returned by an InfoExtractor."""
|
"""Process a single dictionary returned by an InfoExtractor."""
|
||||||
|
|
||||||
|
reason = self._match_entry(info_dict)
|
||||||
|
if reason is not None:
|
||||||
|
self.to_screen(u'[download] ' + reason)
|
||||||
|
return
|
||||||
|
|
||||||
|
max_downloads = self.params.get('max_downloads')
|
||||||
|
if max_downloads is not None:
|
||||||
|
if self._num_downloads > int(max_downloads):
|
||||||
|
raise MaxDownloadsReached()
|
||||||
|
|
||||||
filename = self.prepare_filename(info_dict)
|
filename = self.prepare_filename(info_dict)
|
||||||
|
|
||||||
# Forced printings
|
# Forced printings
|
||||||
@@ -723,23 +777,9 @@ class FileDownloader(object):
|
|||||||
if filename is None:
|
if filename is None:
|
||||||
return
|
return
|
||||||
|
|
||||||
matchtitle=self.params.get('matchtitle',False)
|
|
||||||
rejecttitle=self.params.get('rejecttitle',False)
|
|
||||||
title=info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
|
|
||||||
if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
|
|
||||||
self.to_screen(u'[download] "%s" title did not match pattern "%s"' % (title, matchtitle))
|
|
||||||
return
|
|
||||||
if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
|
|
||||||
self.to_screen(u'[download] "%s" title matched reject pattern "%s"' % (title, rejecttitle))
|
|
||||||
return
|
|
||||||
|
|
||||||
if self.params.get('nooverwrites', False) and os.path.exists(filename):
|
|
||||||
self.to_stderr(u'WARNING: file exists and will be skipped')
|
|
||||||
return
|
|
||||||
|
|
||||||
try:
|
try:
|
||||||
dn = os.path.dirname(filename)
|
dn = os.path.dirname(_encodeFilename(filename))
|
||||||
if dn != '' and not os.path.exists(dn):
|
if dn != '' and not os.path.exists(dn): # dn is already encoded
|
||||||
os.makedirs(dn)
|
os.makedirs(dn)
|
||||||
except (OSError, IOError), err:
|
except (OSError, IOError), err:
|
||||||
self.trouble(u'ERROR: unable to create directory ' + unicode(err))
|
self.trouble(u'ERROR: unable to create directory ' + unicode(err))
|
||||||
@@ -747,9 +787,9 @@ class FileDownloader(object):
|
|||||||
|
|
||||||
if self.params.get('writedescription', False):
|
if self.params.get('writedescription', False):
|
||||||
try:
|
try:
|
||||||
descfn = filename + '.description'
|
descfn = filename + u'.description'
|
||||||
self.report_writedescription(descfn)
|
self.report_writedescription(descfn)
|
||||||
descfile = open(descfn, 'wb')
|
descfile = open(_encodeFilename(descfn), 'wb')
|
||||||
try:
|
try:
|
||||||
descfile.write(info_dict['description'].encode('utf-8'))
|
descfile.write(info_dict['description'].encode('utf-8'))
|
||||||
finally:
|
finally:
|
||||||
@@ -759,7 +799,7 @@ class FileDownloader(object):
|
|||||||
return
|
return
|
||||||
|
|
||||||
if self.params.get('writeinfojson', False):
|
if self.params.get('writeinfojson', False):
|
||||||
infofn = filename + '.info.json'
|
infofn = filename + u'.info.json'
|
||||||
self.report_writeinfojson(infofn)
|
self.report_writeinfojson(infofn)
|
||||||
try:
|
try:
|
||||||
json.dump
|
json.dump
|
||||||
@@ -767,7 +807,7 @@ class FileDownloader(object):
|
|||||||
self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
|
self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
|
||||||
return
|
return
|
||||||
try:
|
try:
|
||||||
infof = open(infofn, 'wb')
|
infof = open(_encodeFilename(infofn), 'wb')
|
||||||
try:
|
try:
|
||||||
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
|
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
|
||||||
json.dump(json_info_dict, infof)
|
json.dump(json_info_dict, infof)
|
||||||
@@ -778,6 +818,9 @@ class FileDownloader(object):
|
|||||||
return
|
return
|
||||||
|
|
||||||
if not self.params.get('skip_download', False):
|
if not self.params.get('skip_download', False):
|
||||||
|
if self.params.get('nooverwrites', False) and os.path.exists(_encodeFilename(filename)):
|
||||||
|
success = True
|
||||||
|
else:
|
||||||
try:
|
try:
|
||||||
success = self._do_download(filename, info_dict)
|
success = self._do_download(filename, info_dict)
|
||||||
except (OSError, IOError), err:
|
except (OSError, IOError), err:
|
||||||
@@ -848,11 +891,11 @@ class FileDownloader(object):
|
|||||||
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
|
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
|
||||||
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
|
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
|
||||||
while retval == 2 or retval == 1:
|
while retval == 2 or retval == 1:
|
||||||
prevsize = os.path.getsize(tmpfilename)
|
prevsize = os.path.getsize(_encodeFilename(tmpfilename))
|
||||||
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
|
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
|
||||||
time.sleep(5.0) # This seems to be needed
|
time.sleep(5.0) # This seems to be needed
|
||||||
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
|
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
|
||||||
cursize = os.path.getsize(tmpfilename)
|
cursize = os.path.getsize(_encodeFilename(tmpfilename))
|
||||||
if prevsize == cursize and retval == 1:
|
if prevsize == cursize and retval == 1:
|
||||||
break
|
break
|
||||||
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
|
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
|
||||||
@@ -861,7 +904,7 @@ class FileDownloader(object):
|
|||||||
retval = 0
|
retval = 0
|
||||||
break
|
break
|
||||||
if retval == 0:
|
if retval == 0:
|
||||||
self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
|
self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(_encodeFilename(tmpfilename)))
|
||||||
self.try_rename(tmpfilename, filename)
|
self.try_rename(tmpfilename, filename)
|
||||||
return True
|
return True
|
||||||
else:
|
else:
|
||||||
@@ -873,7 +916,7 @@ class FileDownloader(object):
|
|||||||
player_url = info_dict.get('player_url', None)
|
player_url = info_dict.get('player_url', None)
|
||||||
|
|
||||||
# Check file already present
|
# Check file already present
|
||||||
if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
|
if self.params.get('continuedl', False) and os.path.isfile(_encodeFilename(filename)) and not self.params.get('nopart', False):
|
||||||
self.report_file_already_downloaded(filename)
|
self.report_file_already_downloaded(filename)
|
||||||
return True
|
return True
|
||||||
|
|
||||||
@@ -890,8 +933,8 @@ class FileDownloader(object):
|
|||||||
request = urllib2.Request(url, None, headers)
|
request = urllib2.Request(url, None, headers)
|
||||||
|
|
||||||
# Establish possible resume length
|
# Establish possible resume length
|
||||||
if os.path.isfile(tmpfilename):
|
if os.path.isfile(_encodeFilename(tmpfilename)):
|
||||||
resume_len = os.path.getsize(tmpfilename)
|
resume_len = os.path.getsize(_encodeFilename(tmpfilename))
|
||||||
else:
|
else:
|
||||||
resume_len = 0
|
resume_len = 0
|
||||||
|
|
||||||
@@ -1095,6 +1138,7 @@ class YoutubeIE(InfoExtractor):
|
|||||||
_NETRC_MACHINE = 'youtube'
|
_NETRC_MACHINE = 'youtube'
|
||||||
# Listed in order of quality
|
# Listed in order of quality
|
||||||
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
|
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
|
||||||
|
_available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
|
||||||
_video_extensions = {
|
_video_extensions = {
|
||||||
'13': '3gp',
|
'13': '3gp',
|
||||||
'17': 'mp4',
|
'17': 'mp4',
|
||||||
@@ -1344,10 +1388,11 @@ class YoutubeIE(InfoExtractor):
|
|||||||
url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
|
url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
|
||||||
|
|
||||||
format_limit = self._downloader.params.get('format_limit', None)
|
format_limit = self._downloader.params.get('format_limit', None)
|
||||||
if format_limit is not None and format_limit in self._available_formats:
|
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
|
||||||
format_list = self._available_formats[self._available_formats.index(format_limit):]
|
if format_limit is not None and format_limit in available_formats:
|
||||||
|
format_list = available_formats[available_formats.index(format_limit):]
|
||||||
else:
|
else:
|
||||||
format_list = self._available_formats
|
format_list = available_formats
|
||||||
existing_formats = [x for x in format_list if x in url_map]
|
existing_formats = [x for x in format_list if x in url_map]
|
||||||
if len(existing_formats) == 0:
|
if len(existing_formats) == 0:
|
||||||
self._downloader.trouble(u'ERROR: no known formats available for video')
|
self._downloader.trouble(u'ERROR: no known formats available for video')
|
||||||
@@ -1573,7 +1618,6 @@ class DailymotionIE(InfoExtractor):
|
|||||||
self._downloader.increment_downloads()
|
self._downloader.increment_downloads()
|
||||||
video_id = mobj.group(1)
|
video_id = mobj.group(1)
|
||||||
|
|
||||||
simple_title = mobj.group(2).decode('utf-8')
|
|
||||||
video_extension = 'flv'
|
video_extension = 'flv'
|
||||||
|
|
||||||
# Retrieve video webpage to extract further information
|
# Retrieve video webpage to extract further information
|
||||||
@@ -1603,12 +1647,13 @@ class DailymotionIE(InfoExtractor):
|
|||||||
|
|
||||||
video_url = mediaURL
|
video_url = mediaURL
|
||||||
|
|
||||||
mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)
|
mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
self._downloader.trouble(u'ERROR: unable to extract title')
|
self._downloader.trouble(u'ERROR: unable to extract title')
|
||||||
return
|
return
|
||||||
video_title = mobj.group(1).decode('utf-8')
|
video_title = _unescapeHTML(mobj.group('title').decode('utf-8'))
|
||||||
video_title = sanitize_title(video_title)
|
video_title = sanitize_title(video_title)
|
||||||
|
simple_title = _simplify_title(video_title)
|
||||||
|
|
||||||
mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
|
mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
@@ -3122,7 +3167,7 @@ class ComedyCentralIE(InfoExtractor):
|
|||||||
return
|
return
|
||||||
epTitle = mobj.group('episode')
|
epTitle = mobj.group('episode')
|
||||||
|
|
||||||
mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"/>', html)
|
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html)
|
||||||
if len(mMovieParams) == 0:
|
if len(mMovieParams) == 0:
|
||||||
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
|
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
|
||||||
return
|
return
|
||||||
@@ -3608,6 +3653,339 @@ class InfoQIE(InfoExtractor):
|
|||||||
except UnavailableVideoError, err:
|
except UnavailableVideoError, err:
|
||||||
self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
|
self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
|
||||||
|
|
||||||
|
class MixcloudIE(InfoExtractor):
|
||||||
|
"""Information extractor for www.mixcloud.com"""
|
||||||
|
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
|
||||||
|
IE_NAME = u'mixcloud'
|
||||||
|
|
||||||
|
def __init__(self, downloader=None):
|
||||||
|
InfoExtractor.__init__(self, downloader)
|
||||||
|
|
||||||
|
def report_download_json(self, file_id):
|
||||||
|
"""Report JSON download."""
|
||||||
|
self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
|
||||||
|
|
||||||
|
def report_extraction(self, file_id):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
|
||||||
|
|
||||||
|
def get_urls(self, jsonData, fmt, bitrate='best'):
|
||||||
|
"""Get urls from 'audio_formats' section in json"""
|
||||||
|
file_url = None
|
||||||
|
try:
|
||||||
|
bitrate_list = jsonData[fmt]
|
||||||
|
if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
|
||||||
|
bitrate = max(bitrate_list) # select highest
|
||||||
|
|
||||||
|
url_list = jsonData[fmt][bitrate]
|
||||||
|
except TypeError: # we have no bitrate info.
|
||||||
|
url_list = jsonData[fmt]
|
||||||
|
|
||||||
|
return url_list
|
||||||
|
|
||||||
|
def check_urls(self, url_list):
|
||||||
|
"""Returns 1st active url from list"""
|
||||||
|
for url in url_list:
|
||||||
|
try:
|
||||||
|
urllib2.urlopen(url)
|
||||||
|
return url
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
url = None
|
||||||
|
|
||||||
|
return None
|
||||||
|
|
||||||
|
def _print_formats(self, formats):
|
||||||
|
print 'Available formats:'
|
||||||
|
for fmt in formats.keys():
|
||||||
|
for b in formats[fmt]:
|
||||||
|
try:
|
||||||
|
ext = formats[fmt][b][0]
|
||||||
|
print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])
|
||||||
|
except TypeError: # we have no bitrate info
|
||||||
|
ext = formats[fmt][0]
|
||||||
|
print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])
|
||||||
|
break
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||||
|
return
|
||||||
|
# extract uploader & filename from url
|
||||||
|
uploader = mobj.group(1).decode('utf-8')
|
||||||
|
file_id = uploader + "-" + mobj.group(2).decode('utf-8')
|
||||||
|
|
||||||
|
# construct API request
|
||||||
|
file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
|
||||||
|
# retrieve .json file with links to files
|
||||||
|
request = urllib2.Request(file_url)
|
||||||
|
try:
|
||||||
|
self.report_download_json(file_url)
|
||||||
|
jsonData = urllib2.urlopen(request).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
# parse JSON
|
||||||
|
json_data = json.loads(jsonData)
|
||||||
|
player_url = json_data['player_swf_url']
|
||||||
|
formats = dict(json_data['audio_formats'])
|
||||||
|
|
||||||
|
req_format = self._downloader.params.get('format', None)
|
||||||
|
bitrate = None
|
||||||
|
|
||||||
|
if self._downloader.params.get('listformats', None):
|
||||||
|
self._print_formats(formats)
|
||||||
|
return
|
||||||
|
|
||||||
|
if req_format is None or req_format == 'best':
|
||||||
|
for format_param in formats.keys():
|
||||||
|
url_list = self.get_urls(formats, format_param)
|
||||||
|
# check urls
|
||||||
|
file_url = self.check_urls(url_list)
|
||||||
|
if file_url is not None:
|
||||||
|
break # got it!
|
||||||
|
else:
|
||||||
|
if req_format not in formats.keys():
|
||||||
|
self._downloader.trouble(u'ERROR: format is not available')
|
||||||
|
return
|
||||||
|
|
||||||
|
url_list = self.get_urls(formats, req_format)
|
||||||
|
file_url = self.check_urls(url_list)
|
||||||
|
format_param = req_format
|
||||||
|
|
||||||
|
# We have audio
|
||||||
|
self._downloader.increment_downloads()
|
||||||
|
try:
|
||||||
|
# Process file information
|
||||||
|
self._downloader.process_info({
|
||||||
|
'id': file_id.decode('utf-8'),
|
||||||
|
'url': file_url.decode('utf-8'),
|
||||||
|
'uploader': uploader.decode('utf-8'),
|
||||||
|
'upload_date': u'NA',
|
||||||
|
'title': json_data['name'],
|
||||||
|
'stitle': _simplify_title(json_data['name']),
|
||||||
|
'ext': file_url.split('.')[-1].decode('utf-8'),
|
||||||
|
'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
|
||||||
|
'thumbnail': json_data['thumbnail_url'],
|
||||||
|
'description': json_data['description'],
|
||||||
|
'player_url': player_url.decode('utf-8'),
|
||||||
|
})
|
||||||
|
except UnavailableVideoError, err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download file')
|
||||||
|
|
||||||
|
class StanfordOpenClassroomIE(InfoExtractor):
|
||||||
|
"""Information extractor for Stanford's Open ClassRoom"""
|
||||||
|
|
||||||
|
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
|
||||||
|
IE_NAME = u'stanfordoc'
|
||||||
|
|
||||||
|
def report_download_webpage(self, objid):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid))
|
||||||
|
|
||||||
|
def report_extraction(self, video_id):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||||
|
return
|
||||||
|
|
||||||
|
if mobj.group('course') and mobj.group('video'): # A specific video
|
||||||
|
course = mobj.group('course')
|
||||||
|
video = mobj.group('video')
|
||||||
|
info = {
|
||||||
|
'id': _simplify_title(course + '_' + video),
|
||||||
|
}
|
||||||
|
|
||||||
|
self.report_extraction(info['id'])
|
||||||
|
baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
|
||||||
|
xmlUrl = baseUrl + video + '.xml'
|
||||||
|
try:
|
||||||
|
metaXml = urllib2.urlopen(xmlUrl).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err))
|
||||||
|
return
|
||||||
|
mdoc = xml.etree.ElementTree.fromstring(metaXml)
|
||||||
|
try:
|
||||||
|
info['title'] = mdoc.findall('./title')[0].text
|
||||||
|
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
|
||||||
|
except IndexError:
|
||||||
|
self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
|
||||||
|
return
|
||||||
|
info['stitle'] = _simplify_title(info['title'])
|
||||||
|
info['ext'] = info['url'].rpartition('.')[2]
|
||||||
|
info['format'] = info['ext']
|
||||||
|
self._downloader.increment_downloads()
|
||||||
|
try:
|
||||||
|
self._downloader.process_info(info)
|
||||||
|
except UnavailableVideoError, err:
|
||||||
|
self._downloader.trouble(u'\nERROR: unable to download video')
|
||||||
|
elif mobj.group('course'): # A course page
|
||||||
|
unescapeHTML = HTMLParser.HTMLParser().unescape
|
||||||
|
|
||||||
|
course = mobj.group('course')
|
||||||
|
info = {
|
||||||
|
'id': _simplify_title(course),
|
||||||
|
'type': 'playlist',
|
||||||
|
}
|
||||||
|
|
||||||
|
self.report_download_webpage(info['id'])
|
||||||
|
try:
|
||||||
|
coursepage = urllib2.urlopen(url).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
m = re.search('<h1>([^<]+)</h1>', coursepage)
|
||||||
|
if m:
|
||||||
|
info['title'] = unescapeHTML(m.group(1))
|
||||||
|
else:
|
||||||
|
info['title'] = info['id']
|
||||||
|
info['stitle'] = _simplify_title(info['title'])
|
||||||
|
|
||||||
|
m = re.search('<description>([^<]+)</description>', coursepage)
|
||||||
|
if m:
|
||||||
|
info['description'] = unescapeHTML(m.group(1))
|
||||||
|
|
||||||
|
links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
|
||||||
|
info['list'] = [
|
||||||
|
{
|
||||||
|
'type': 'reference',
|
||||||
|
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
|
||||||
|
}
|
||||||
|
for vpage in links]
|
||||||
|
|
||||||
|
for entry in info['list']:
|
||||||
|
assert entry['type'] == 'reference'
|
||||||
|
self.extract(entry['url'])
|
||||||
|
else: # Root page
|
||||||
|
unescapeHTML = HTMLParser.HTMLParser().unescape
|
||||||
|
|
||||||
|
info = {
|
||||||
|
'id': 'Stanford OpenClassroom',
|
||||||
|
'type': 'playlist',
|
||||||
|
}
|
||||||
|
|
||||||
|
self.report_download_webpage(info['id'])
|
||||||
|
rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
|
||||||
|
try:
|
||||||
|
rootpage = urllib2.urlopen(rootURL).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
info['title'] = info['id']
|
||||||
|
info['stitle'] = _simplify_title(info['title'])
|
||||||
|
|
||||||
|
links = _orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
|
||||||
|
info['list'] = [
|
||||||
|
{
|
||||||
|
'type': 'reference',
|
||||||
|
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
|
||||||
|
}
|
||||||
|
for cpage in links]
|
||||||
|
|
||||||
|
for entry in info['list']:
|
||||||
|
assert entry['type'] == 'reference'
|
||||||
|
self.extract(entry['url'])
|
||||||
|
|
||||||
|
class MTVIE(InfoExtractor):
|
||||||
|
"""Information extractor for MTV.com"""
|
||||||
|
|
||||||
|
_VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
|
||||||
|
IE_NAME = u'mtv'
|
||||||
|
|
||||||
|
def report_webpage(self, video_id):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
|
||||||
|
|
||||||
|
def report_extraction(self, video_id):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||||
|
return
|
||||||
|
if not mobj.group('proto'):
|
||||||
|
url = 'http://' + url
|
||||||
|
video_id = mobj.group('videoid')
|
||||||
|
self.report_webpage(video_id)
|
||||||
|
|
||||||
|
request = urllib2.Request(url)
|
||||||
|
try:
|
||||||
|
webpage = urllib2.urlopen(request).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to extract song name')
|
||||||
|
return
|
||||||
|
song_name = _unescapeHTML(mobj.group(1).decode('iso-8859-1'))
|
||||||
|
mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to extract performer')
|
||||||
|
return
|
||||||
|
performer = _unescapeHTML(mobj.group(1).decode('iso-8859-1'))
|
||||||
|
video_title = performer + ' - ' + song_name
|
||||||
|
|
||||||
|
mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to mtvn_uri')
|
||||||
|
return
|
||||||
|
mtvn_uri = mobj.group(1)
|
||||||
|
|
||||||
|
mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to extract content id')
|
||||||
|
return
|
||||||
|
content_id = mobj.group(1)
|
||||||
|
|
||||||
|
videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
|
||||||
|
self.report_extraction(video_id)
|
||||||
|
request = urllib2.Request(videogen_url)
|
||||||
|
try:
|
||||||
|
metadataXml = urllib2.urlopen(request).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
mdoc = xml.etree.ElementTree.fromstring(metadataXml)
|
||||||
|
renditions = mdoc.findall('.//rendition')
|
||||||
|
|
||||||
|
# For now, always pick the highest quality.
|
||||||
|
rendition = renditions[-1]
|
||||||
|
|
||||||
|
try:
|
||||||
|
_,_,ext = rendition.attrib['type'].partition('/')
|
||||||
|
format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
|
||||||
|
video_url = rendition.find('./src').text
|
||||||
|
except KeyError:
|
||||||
|
self._downloader.trouble('Invalid rendition field.')
|
||||||
|
return
|
||||||
|
|
||||||
|
self._downloader.increment_downloads()
|
||||||
|
info = {
|
||||||
|
'id': video_id,
|
||||||
|
'url': video_url,
|
||||||
|
'uploader': performer,
|
||||||
|
'title': video_title,
|
||||||
|
'stitle': _simplify_title(video_title),
|
||||||
|
'ext': ext,
|
||||||
|
'format': format,
|
||||||
|
}
|
||||||
|
|
||||||
|
try:
|
||||||
|
self._downloader.process_info(info)
|
||||||
|
except UnavailableVideoError, err:
|
||||||
|
self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
|
||||||
|
|
||||||
|
|
||||||
class PostProcessor(object):
|
class PostProcessor(object):
|
||||||
@@ -3656,6 +4034,9 @@ class PostProcessor(object):
|
|||||||
"""
|
"""
|
||||||
return information # by default, do nothing
|
return information # by default, do nothing
|
||||||
|
|
||||||
|
class AudioConversionError(BaseException):
|
||||||
|
def __init__(self, message):
|
||||||
|
self.message = message
|
||||||
|
|
||||||
class FFmpegExtractAudioPP(PostProcessor):
|
class FFmpegExtractAudioPP(PostProcessor):
|
||||||
|
|
||||||
@@ -3670,7 +4051,7 @@ class FFmpegExtractAudioPP(PostProcessor):
|
|||||||
@staticmethod
|
@staticmethod
|
||||||
def get_audio_codec(path):
|
def get_audio_codec(path):
|
||||||
try:
|
try:
|
||||||
cmd = ['ffprobe', '-show_streams', '--', path]
|
cmd = ['ffprobe', '-show_streams', '--', _encodeFilename(path)]
|
||||||
handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
|
handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
|
||||||
output = handle.communicate()[0]
|
output = handle.communicate()[0]
|
||||||
if handle.wait() != 0:
|
if handle.wait() != 0:
|
||||||
@@ -3687,12 +4068,23 @@ class FFmpegExtractAudioPP(PostProcessor):
|
|||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def run_ffmpeg(path, out_path, codec, more_opts):
|
def run_ffmpeg(path, out_path, codec, more_opts):
|
||||||
|
if codec is None:
|
||||||
|
acodec_opts = []
|
||||||
|
else:
|
||||||
|
acodec_opts = ['-acodec', codec]
|
||||||
|
cmd = ['ffmpeg', '-y', '-i', _encodeFilename(path), '-vn'] + acodec_opts + more_opts + ['--', _encodeFilename(out_path)]
|
||||||
try:
|
try:
|
||||||
cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
|
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||||
ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
|
stdout,stderr = p.communicate()
|
||||||
return (ret == 0)
|
|
||||||
except (IOError, OSError):
|
except (IOError, OSError):
|
||||||
return False
|
e = sys.exc_info()[1]
|
||||||
|
if isinstance(e, OSError) and e.errno == 2:
|
||||||
|
raise AudioConversionError('ffmpeg not found. Please install ffmpeg.')
|
||||||
|
else:
|
||||||
|
raise e
|
||||||
|
if p.returncode != 0:
|
||||||
|
msg = stderr.strip().split('\n')[-1]
|
||||||
|
raise AudioConversionError(msg)
|
||||||
|
|
||||||
def run(self, information):
|
def run(self, information):
|
||||||
path = information['filepath']
|
path = information['filepath']
|
||||||
@@ -3703,8 +4095,13 @@ class FFmpegExtractAudioPP(PostProcessor):
|
|||||||
return None
|
return None
|
||||||
|
|
||||||
more_opts = []
|
more_opts = []
|
||||||
if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
|
if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
|
||||||
if filecodec in ['aac', 'mp3', 'vorbis']:
|
if self._preferredcodec == 'm4a' and filecodec == 'aac':
|
||||||
|
# Lossless, but in another container
|
||||||
|
acodec = 'copy'
|
||||||
|
extension = self._preferredcodec
|
||||||
|
more_opts = ['-absf', 'aac_adtstoasc']
|
||||||
|
elif filecodec in ['aac', 'mp3', 'vorbis']:
|
||||||
# Lossless if possible
|
# Lossless if possible
|
||||||
acodec = 'copy'
|
acodec = 'copy'
|
||||||
extension = filecodec
|
extension = filecodec
|
||||||
@@ -3721,35 +4118,44 @@ class FFmpegExtractAudioPP(PostProcessor):
|
|||||||
more_opts += ['-ab', self._preferredquality]
|
more_opts += ['-ab', self._preferredquality]
|
||||||
else:
|
else:
|
||||||
# We convert the audio (lossy)
|
# We convert the audio (lossy)
|
||||||
acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
|
acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
|
||||||
extension = self._preferredcodec
|
extension = self._preferredcodec
|
||||||
more_opts = []
|
more_opts = []
|
||||||
if self._preferredquality is not None:
|
if self._preferredquality is not None:
|
||||||
more_opts += ['-ab', self._preferredquality]
|
more_opts += ['-ab', self._preferredquality]
|
||||||
if self._preferredcodec == 'aac':
|
if self._preferredcodec == 'aac':
|
||||||
more_opts += ['-f', 'adts']
|
more_opts += ['-f', 'adts']
|
||||||
|
if self._preferredcodec == 'm4a':
|
||||||
|
more_opts += ['-absf', 'aac_adtstoasc']
|
||||||
if self._preferredcodec == 'vorbis':
|
if self._preferredcodec == 'vorbis':
|
||||||
extension = 'ogg'
|
extension = 'ogg'
|
||||||
|
if self._preferredcodec == 'wav':
|
||||||
|
extension = 'wav'
|
||||||
|
more_opts += ['-f', 'wav']
|
||||||
|
|
||||||
(prefix, ext) = os.path.splitext(path)
|
prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
|
||||||
new_path = prefix + '.' + extension
|
new_path = prefix + sep + extension
|
||||||
self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path)
|
self._downloader.to_screen(u'[ffmpeg] Destination: ' + new_path)
|
||||||
status = self.run_ffmpeg(path, new_path, acodec, more_opts)
|
try:
|
||||||
|
self.run_ffmpeg(path, new_path, acodec, more_opts)
|
||||||
if not status:
|
except:
|
||||||
self._downloader.to_stderr(u'WARNING: error running ffmpeg')
|
etype,e,tb = sys.exc_info()
|
||||||
|
if isinstance(e, AudioConversionError):
|
||||||
|
self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message)
|
||||||
|
else:
|
||||||
|
self._downloader.to_stderr(u'ERROR: error running ffmpeg')
|
||||||
return None
|
return None
|
||||||
|
|
||||||
# Try to update the date time for extracted audio file.
|
# Try to update the date time for extracted audio file.
|
||||||
if information.get('filetime') is not None:
|
if information.get('filetime') is not None:
|
||||||
try:
|
try:
|
||||||
os.utime(new_path, (time.time(), information['filetime']))
|
os.utime(_encodeFilename(new_path), (time.time(), information['filetime']))
|
||||||
except:
|
except:
|
||||||
self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
|
self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
|
||||||
|
|
||||||
if not self._keepvideo:
|
if not self._keepvideo:
|
||||||
try:
|
try:
|
||||||
os.remove(path)
|
os.remove(_encodeFilename(path))
|
||||||
except (IOError, OSError):
|
except (IOError, OSError):
|
||||||
self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
|
self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
|
||||||
return None
|
return None
|
||||||
@@ -3795,6 +4201,20 @@ def parseOpts():
|
|||||||
# Deferred imports
|
# Deferred imports
|
||||||
import getpass
|
import getpass
|
||||||
import optparse
|
import optparse
|
||||||
|
import shlex
|
||||||
|
|
||||||
|
def _readOptions(filename_bytes):
|
||||||
|
try:
|
||||||
|
optionf = open(filename_bytes)
|
||||||
|
except IOError:
|
||||||
|
return [] # silently skip if file is not present
|
||||||
|
try:
|
||||||
|
res = []
|
||||||
|
for l in optionf:
|
||||||
|
res += shlex.split(l, comments=True)
|
||||||
|
finally:
|
||||||
|
optionf.close()
|
||||||
|
return res
|
||||||
|
|
||||||
def _format_option_string(option):
|
def _format_option_string(option):
|
||||||
''' ('-o', '--option') -> -o, --format METAVAR'''
|
''' ('-o', '--option') -> -o, --format METAVAR'''
|
||||||
@@ -3875,6 +4295,7 @@ def parseOpts():
|
|||||||
dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
|
dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
|
||||||
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
|
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
|
||||||
selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
|
selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
|
||||||
|
selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None)
|
||||||
|
|
||||||
authentication.add_option('-u', '--username',
|
authentication.add_option('-u', '--username',
|
||||||
dest='username', metavar='USERNAME', help='account username')
|
dest='username', metavar='USERNAME', help='account username')
|
||||||
@@ -3888,6 +4309,8 @@ def parseOpts():
|
|||||||
action='store', dest='format', metavar='FORMAT', help='video format code')
|
action='store', dest='format', metavar='FORMAT', help='video format code')
|
||||||
video_format.add_option('--all-formats',
|
video_format.add_option('--all-formats',
|
||||||
action='store_const', dest='format', help='download all available video formats', const='all')
|
action='store_const', dest='format', help='download all available video formats', const='all')
|
||||||
|
video_format.add_option('--prefer-free-formats',
|
||||||
|
action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested')
|
||||||
video_format.add_option('--max-quality',
|
video_format.add_option('--max-quality',
|
||||||
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
|
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
|
||||||
video_format.add_option('-F', '--list-formats',
|
video_format.add_option('-F', '--list-formats',
|
||||||
@@ -3931,7 +4354,7 @@ def parseOpts():
|
|||||||
action='store_true', dest='autonumber',
|
action='store_true', dest='autonumber',
|
||||||
help='number downloaded files starting from 00000', default=False)
|
help='number downloaded files starting from 00000', default=False)
|
||||||
filesystem.add_option('-o', '--output',
|
filesystem.add_option('-o', '--output',
|
||||||
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, and %% for a literal percent')
|
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.')
|
||||||
filesystem.add_option('-a', '--batch-file',
|
filesystem.add_option('-a', '--batch-file',
|
||||||
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
|
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
|
||||||
filesystem.add_option('-w', '--no-overwrites',
|
filesystem.add_option('-w', '--no-overwrites',
|
||||||
@@ -3959,7 +4382,7 @@ def parseOpts():
|
|||||||
postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
|
postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
|
||||||
help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
|
help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
|
||||||
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
|
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
|
||||||
help='"best", "aac", "vorbis" or "mp3"; best by default')
|
help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default')
|
||||||
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
|
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
|
||||||
help='ffmpeg audio bitrate specification, 128k by default')
|
help='ffmpeg audio bitrate specification, 128k by default')
|
||||||
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
|
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
|
||||||
@@ -3974,7 +4397,13 @@ def parseOpts():
|
|||||||
parser.add_option_group(authentication)
|
parser.add_option_group(authentication)
|
||||||
parser.add_option_group(postproc)
|
parser.add_option_group(postproc)
|
||||||
|
|
||||||
opts, args = parser.parse_args()
|
xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
|
||||||
|
if xdg_config_home:
|
||||||
|
userConf = os.path.join(xdg_config_home, 'youtube-dl.conf')
|
||||||
|
else:
|
||||||
|
userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
|
||||||
|
argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:]
|
||||||
|
opts, args = parser.parse_args(argv)
|
||||||
|
|
||||||
return parser, opts, args
|
return parser, opts, args
|
||||||
|
|
||||||
@@ -4008,6 +4437,9 @@ def gen_extractors():
|
|||||||
XVideosIE(),
|
XVideosIE(),
|
||||||
SoundcloudIE(),
|
SoundcloudIE(),
|
||||||
InfoQIE(),
|
InfoQIE(),
|
||||||
|
MixcloudIE(),
|
||||||
|
StanfordOpenClassroomIE(),
|
||||||
|
MTVIE(),
|
||||||
|
|
||||||
GenericIE()
|
GenericIE()
|
||||||
]
|
]
|
||||||
@@ -4097,7 +4529,7 @@ def _real_main():
|
|||||||
except (TypeError, ValueError), err:
|
except (TypeError, ValueError), err:
|
||||||
parser.error(u'invalid playlist end number specified')
|
parser.error(u'invalid playlist end number specified')
|
||||||
if opts.extractaudio:
|
if opts.extractaudio:
|
||||||
if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
|
if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']:
|
||||||
parser.error(u'invalid audio format specified')
|
parser.error(u'invalid audio format specified')
|
||||||
|
|
||||||
# File downloader
|
# File downloader
|
||||||
@@ -4143,6 +4575,8 @@ def _real_main():
|
|||||||
'writeinfojson': opts.writeinfojson,
|
'writeinfojson': opts.writeinfojson,
|
||||||
'matchtitle': opts.matchtitle,
|
'matchtitle': opts.matchtitle,
|
||||||
'rejecttitle': opts.rejecttitle,
|
'rejecttitle': opts.rejecttitle,
|
||||||
|
'max_downloads': opts.max_downloads,
|
||||||
|
'prefer_free_formats': opts.prefer_free_formats,
|
||||||
})
|
})
|
||||||
for extractor in extractors:
|
for extractor in extractors:
|
||||||
fd.add_info_extractor(extractor)
|
fd.add_info_extractor(extractor)
|
||||||
@@ -4161,7 +4595,12 @@ def _real_main():
|
|||||||
parser.error(u'you must provide at least one URL')
|
parser.error(u'you must provide at least one URL')
|
||||||
else:
|
else:
|
||||||
sys.exit()
|
sys.exit()
|
||||||
|
|
||||||
|
try:
|
||||||
retcode = fd.download(all_urls)
|
retcode = fd.download(all_urls)
|
||||||
|
except MaxDownloadsReached:
|
||||||
|
fd.to_screen(u'--max-download limit reached, aborting.')
|
||||||
|
retcode = 101
|
||||||
|
|
||||||
# Dump cookie jar if requested
|
# Dump cookie jar if requested
|
||||||
if opts.cookiefile is not None:
|
if opts.cookiefile is not None:
|
||||||
|
@@ -1,7 +1,7 @@
|
|||||||
#!/usr/bin/env python
|
#!/usr/bin/env python
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
__author__ = (
|
__authors__ = (
|
||||||
'Ricardo Garcia Gonzalez',
|
'Ricardo Garcia Gonzalez',
|
||||||
'Danny Colligan',
|
'Danny Colligan',
|
||||||
'Benjamin Johnson',
|
'Benjamin Johnson',
|
||||||
@@ -14,10 +14,11 @@ __author__ = (
|
|||||||
'Sören Schulze',
|
'Sören Schulze',
|
||||||
'Kevin Ngo',
|
'Kevin Ngo',
|
||||||
'Ori Avtalion',
|
'Ori Avtalion',
|
||||||
|
'shizeeg',
|
||||||
)
|
)
|
||||||
|
|
||||||
__license__ = 'Public Domain'
|
__license__ = 'Public Domain'
|
||||||
__version__ = '2011.11.23'
|
__version__ = '2012.01.08'
|
||||||
|
|
||||||
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
|
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
|
||||||
|
|
||||||
@@ -258,14 +259,14 @@ def sanitize_open(filename, open_mode):
|
|||||||
import msvcrt
|
import msvcrt
|
||||||
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
|
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
|
||||||
return (sys.stdout, filename)
|
return (sys.stdout, filename)
|
||||||
stream = open(filename, open_mode)
|
stream = open(_encodeFilename(filename), open_mode)
|
||||||
return (stream, filename)
|
return (stream, filename)
|
||||||
except (IOError, OSError), err:
|
except (IOError, OSError), err:
|
||||||
# In case of error, try to remove win32 forbidden chars
|
# In case of error, try to remove win32 forbidden chars
|
||||||
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
|
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
|
||||||
|
|
||||||
# An exception here should be caught in the caller
|
# An exception here should be caught in the caller
|
||||||
stream = open(filename, open_mode)
|
stream = open(_encodeFilename(filename), open_mode)
|
||||||
return (stream, filename)
|
return (stream, filename)
|
||||||
|
|
||||||
|
|
||||||
@@ -281,6 +282,31 @@ def _simplify_title(title):
|
|||||||
expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
|
expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
|
||||||
return expr.sub(u'_', title).strip(u'_')
|
return expr.sub(u'_', title).strip(u'_')
|
||||||
|
|
||||||
|
def _orderedSet(iterable):
|
||||||
|
""" Remove all duplicates from the input iterable """
|
||||||
|
res = []
|
||||||
|
for el in iterable:
|
||||||
|
if el not in res:
|
||||||
|
res.append(el)
|
||||||
|
return res
|
||||||
|
|
||||||
|
def _unescapeHTML(s):
|
||||||
|
"""
|
||||||
|
@param s a string (of type unicode)
|
||||||
|
"""
|
||||||
|
assert type(s) == type(u'')
|
||||||
|
|
||||||
|
htmlParser = HTMLParser.HTMLParser()
|
||||||
|
return htmlParser.unescape(s)
|
||||||
|
|
||||||
|
def _encodeFilename(s):
|
||||||
|
"""
|
||||||
|
@param s The name of the file (of type unicode)
|
||||||
|
"""
|
||||||
|
|
||||||
|
assert type(s) == type(u'')
|
||||||
|
return s.encode(sys.getfilesystemencoding(), 'ignore')
|
||||||
|
|
||||||
class DownloadError(Exception):
|
class DownloadError(Exception):
|
||||||
"""Download Error exception.
|
"""Download Error exception.
|
||||||
|
|
||||||
@@ -308,6 +334,10 @@ class PostProcessingError(Exception):
|
|||||||
"""
|
"""
|
||||||
pass
|
pass
|
||||||
|
|
||||||
|
class MaxDownloadsReached(Exception):
|
||||||
|
""" --max-downloads limit has been reached. """
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
class UnavailableVideoError(Exception):
|
class UnavailableVideoError(Exception):
|
||||||
"""Unavailable Format exception.
|
"""Unavailable Format exception.
|
||||||
@@ -541,16 +571,17 @@ class FileDownloader(object):
|
|||||||
self._pps.append(pp)
|
self._pps.append(pp)
|
||||||
pp.set_downloader(self)
|
pp.set_downloader(self)
|
||||||
|
|
||||||
def to_screen(self, message, skip_eol=False, ignore_encoding_errors=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."""
|
||||||
try:
|
assert type(message) == type(u'')
|
||||||
if not self.params.get('quiet', False):
|
if not self.params.get('quiet', False):
|
||||||
terminator = [u'\n', u''][skip_eol]
|
terminator = [u'\n', u''][skip_eol]
|
||||||
print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
|
output = message + terminator
|
||||||
|
|
||||||
|
if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
|
||||||
|
output = output.encode(preferredencoding(), 'ignore')
|
||||||
|
self._screen_file.write(output)
|
||||||
self._screen_file.flush()
|
self._screen_file.flush()
|
||||||
except (UnicodeEncodeError), err:
|
|
||||||
if not ignore_encoding_errors:
|
|
||||||
raise
|
|
||||||
|
|
||||||
def to_stderr(self, message):
|
def to_stderr(self, message):
|
||||||
"""Print message to stderr."""
|
"""Print message to stderr."""
|
||||||
@@ -600,7 +631,7 @@ class FileDownloader(object):
|
|||||||
def temp_name(self, filename):
|
def temp_name(self, filename):
|
||||||
"""Returns a temporary filename for the given filename."""
|
"""Returns a temporary filename for the given filename."""
|
||||||
if self.params.get('nopart', False) or filename == u'-' or \
|
if self.params.get('nopart', False) or filename == u'-' or \
|
||||||
(os.path.exists(filename) and not os.path.isfile(filename)):
|
(os.path.exists(_encodeFilename(filename)) and not os.path.isfile(_encodeFilename(filename))):
|
||||||
return filename
|
return filename
|
||||||
return filename + u'.part'
|
return filename + u'.part'
|
||||||
|
|
||||||
@@ -613,7 +644,7 @@ class FileDownloader(object):
|
|||||||
try:
|
try:
|
||||||
if old_filename == new_filename:
|
if old_filename == new_filename:
|
||||||
return
|
return
|
||||||
os.rename(old_filename, new_filename)
|
os.rename(_encodeFilename(old_filename), _encodeFilename(new_filename))
|
||||||
except (IOError, OSError), err:
|
except (IOError, OSError), err:
|
||||||
self.trouble(u'ERROR: unable to rename file')
|
self.trouble(u'ERROR: unable to rename file')
|
||||||
|
|
||||||
@@ -621,7 +652,7 @@ class FileDownloader(object):
|
|||||||
"""Try to set the last-modified time of the given file."""
|
"""Try to set the last-modified time of the given file."""
|
||||||
if last_modified_hdr is None:
|
if last_modified_hdr is None:
|
||||||
return
|
return
|
||||||
if not os.path.isfile(filename):
|
if not os.path.isfile(_encodeFilename(filename)):
|
||||||
return
|
return
|
||||||
timestr = last_modified_hdr
|
timestr = last_modified_hdr
|
||||||
if timestr is None:
|
if timestr is None:
|
||||||
@@ -637,15 +668,15 @@ class FileDownloader(object):
|
|||||||
|
|
||||||
def report_writedescription(self, descfn):
|
def report_writedescription(self, descfn):
|
||||||
""" Report that the description file is being written """
|
""" Report that the description file is being written """
|
||||||
self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
|
self.to_screen(u'[info] Writing video description to: ' + descfn)
|
||||||
|
|
||||||
def report_writeinfojson(self, infofn):
|
def report_writeinfojson(self, infofn):
|
||||||
""" Report that the metadata file has been written """
|
""" Report that the metadata file has been written """
|
||||||
self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
|
self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
|
||||||
|
|
||||||
def report_destination(self, filename):
|
def report_destination(self, filename):
|
||||||
"""Report destination filename."""
|
"""Report destination filename."""
|
||||||
self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
|
self.to_screen(u'[download] Destination: ' + filename)
|
||||||
|
|
||||||
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
|
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
|
||||||
"""Report download progress."""
|
"""Report download progress."""
|
||||||
@@ -698,8 +729,31 @@ class FileDownloader(object):
|
|||||||
self.trouble(u'ERROR: invalid system charset or erroneous output template')
|
self.trouble(u'ERROR: invalid system charset or erroneous output template')
|
||||||
return None
|
return None
|
||||||
|
|
||||||
|
def _match_entry(self, info_dict):
|
||||||
|
""" Returns None iff the file should be downloaded """
|
||||||
|
|
||||||
|
title = info_dict['title']
|
||||||
|
matchtitle = self.params.get('matchtitle', False)
|
||||||
|
if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
|
||||||
|
return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
|
||||||
|
rejecttitle = self.params.get('rejecttitle', False)
|
||||||
|
if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
|
||||||
|
return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
|
||||||
|
return None
|
||||||
|
|
||||||
def process_info(self, info_dict):
|
def process_info(self, info_dict):
|
||||||
"""Process a single dictionary returned by an InfoExtractor."""
|
"""Process a single dictionary returned by an InfoExtractor."""
|
||||||
|
|
||||||
|
reason = self._match_entry(info_dict)
|
||||||
|
if reason is not None:
|
||||||
|
self.to_screen(u'[download] ' + reason)
|
||||||
|
return
|
||||||
|
|
||||||
|
max_downloads = self.params.get('max_downloads')
|
||||||
|
if max_downloads is not None:
|
||||||
|
if self._num_downloads > int(max_downloads):
|
||||||
|
raise MaxDownloadsReached()
|
||||||
|
|
||||||
filename = self.prepare_filename(info_dict)
|
filename = self.prepare_filename(info_dict)
|
||||||
|
|
||||||
# Forced printings
|
# Forced printings
|
||||||
@@ -723,23 +777,9 @@ class FileDownloader(object):
|
|||||||
if filename is None:
|
if filename is None:
|
||||||
return
|
return
|
||||||
|
|
||||||
matchtitle=self.params.get('matchtitle',False)
|
|
||||||
rejecttitle=self.params.get('rejecttitle',False)
|
|
||||||
title=info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
|
|
||||||
if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
|
|
||||||
self.to_screen(u'[download] "%s" title did not match pattern "%s"' % (title, matchtitle))
|
|
||||||
return
|
|
||||||
if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
|
|
||||||
self.to_screen(u'[download] "%s" title matched reject pattern "%s"' % (title, rejecttitle))
|
|
||||||
return
|
|
||||||
|
|
||||||
if self.params.get('nooverwrites', False) and os.path.exists(filename):
|
|
||||||
self.to_stderr(u'WARNING: file exists and will be skipped')
|
|
||||||
return
|
|
||||||
|
|
||||||
try:
|
try:
|
||||||
dn = os.path.dirname(filename)
|
dn = os.path.dirname(_encodeFilename(filename))
|
||||||
if dn != '' and not os.path.exists(dn):
|
if dn != '' and not os.path.exists(dn): # dn is already encoded
|
||||||
os.makedirs(dn)
|
os.makedirs(dn)
|
||||||
except (OSError, IOError), err:
|
except (OSError, IOError), err:
|
||||||
self.trouble(u'ERROR: unable to create directory ' + unicode(err))
|
self.trouble(u'ERROR: unable to create directory ' + unicode(err))
|
||||||
@@ -747,9 +787,9 @@ class FileDownloader(object):
|
|||||||
|
|
||||||
if self.params.get('writedescription', False):
|
if self.params.get('writedescription', False):
|
||||||
try:
|
try:
|
||||||
descfn = filename + '.description'
|
descfn = filename + u'.description'
|
||||||
self.report_writedescription(descfn)
|
self.report_writedescription(descfn)
|
||||||
descfile = open(descfn, 'wb')
|
descfile = open(_encodeFilename(descfn), 'wb')
|
||||||
try:
|
try:
|
||||||
descfile.write(info_dict['description'].encode('utf-8'))
|
descfile.write(info_dict['description'].encode('utf-8'))
|
||||||
finally:
|
finally:
|
||||||
@@ -759,7 +799,7 @@ class FileDownloader(object):
|
|||||||
return
|
return
|
||||||
|
|
||||||
if self.params.get('writeinfojson', False):
|
if self.params.get('writeinfojson', False):
|
||||||
infofn = filename + '.info.json'
|
infofn = filename + u'.info.json'
|
||||||
self.report_writeinfojson(infofn)
|
self.report_writeinfojson(infofn)
|
||||||
try:
|
try:
|
||||||
json.dump
|
json.dump
|
||||||
@@ -767,7 +807,7 @@ class FileDownloader(object):
|
|||||||
self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
|
self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
|
||||||
return
|
return
|
||||||
try:
|
try:
|
||||||
infof = open(infofn, 'wb')
|
infof = open(_encodeFilename(infofn), 'wb')
|
||||||
try:
|
try:
|
||||||
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
|
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
|
||||||
json.dump(json_info_dict, infof)
|
json.dump(json_info_dict, infof)
|
||||||
@@ -778,6 +818,9 @@ class FileDownloader(object):
|
|||||||
return
|
return
|
||||||
|
|
||||||
if not self.params.get('skip_download', False):
|
if not self.params.get('skip_download', False):
|
||||||
|
if self.params.get('nooverwrites', False) and os.path.exists(_encodeFilename(filename)):
|
||||||
|
success = True
|
||||||
|
else:
|
||||||
try:
|
try:
|
||||||
success = self._do_download(filename, info_dict)
|
success = self._do_download(filename, info_dict)
|
||||||
except (OSError, IOError), err:
|
except (OSError, IOError), err:
|
||||||
@@ -848,11 +891,11 @@ class FileDownloader(object):
|
|||||||
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
|
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
|
||||||
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
|
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
|
||||||
while retval == 2 or retval == 1:
|
while retval == 2 or retval == 1:
|
||||||
prevsize = os.path.getsize(tmpfilename)
|
prevsize = os.path.getsize(_encodeFilename(tmpfilename))
|
||||||
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
|
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
|
||||||
time.sleep(5.0) # This seems to be needed
|
time.sleep(5.0) # This seems to be needed
|
||||||
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
|
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
|
||||||
cursize = os.path.getsize(tmpfilename)
|
cursize = os.path.getsize(_encodeFilename(tmpfilename))
|
||||||
if prevsize == cursize and retval == 1:
|
if prevsize == cursize and retval == 1:
|
||||||
break
|
break
|
||||||
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
|
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
|
||||||
@@ -861,7 +904,7 @@ class FileDownloader(object):
|
|||||||
retval = 0
|
retval = 0
|
||||||
break
|
break
|
||||||
if retval == 0:
|
if retval == 0:
|
||||||
self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
|
self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(_encodeFilename(tmpfilename)))
|
||||||
self.try_rename(tmpfilename, filename)
|
self.try_rename(tmpfilename, filename)
|
||||||
return True
|
return True
|
||||||
else:
|
else:
|
||||||
@@ -873,7 +916,7 @@ class FileDownloader(object):
|
|||||||
player_url = info_dict.get('player_url', None)
|
player_url = info_dict.get('player_url', None)
|
||||||
|
|
||||||
# Check file already present
|
# Check file already present
|
||||||
if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
|
if self.params.get('continuedl', False) and os.path.isfile(_encodeFilename(filename)) and not self.params.get('nopart', False):
|
||||||
self.report_file_already_downloaded(filename)
|
self.report_file_already_downloaded(filename)
|
||||||
return True
|
return True
|
||||||
|
|
||||||
@@ -890,8 +933,8 @@ class FileDownloader(object):
|
|||||||
request = urllib2.Request(url, None, headers)
|
request = urllib2.Request(url, None, headers)
|
||||||
|
|
||||||
# Establish possible resume length
|
# Establish possible resume length
|
||||||
if os.path.isfile(tmpfilename):
|
if os.path.isfile(_encodeFilename(tmpfilename)):
|
||||||
resume_len = os.path.getsize(tmpfilename)
|
resume_len = os.path.getsize(_encodeFilename(tmpfilename))
|
||||||
else:
|
else:
|
||||||
resume_len = 0
|
resume_len = 0
|
||||||
|
|
||||||
@@ -1095,6 +1138,7 @@ class YoutubeIE(InfoExtractor):
|
|||||||
_NETRC_MACHINE = 'youtube'
|
_NETRC_MACHINE = 'youtube'
|
||||||
# Listed in order of quality
|
# Listed in order of quality
|
||||||
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
|
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
|
||||||
|
_available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
|
||||||
_video_extensions = {
|
_video_extensions = {
|
||||||
'13': '3gp',
|
'13': '3gp',
|
||||||
'17': 'mp4',
|
'17': 'mp4',
|
||||||
@@ -1344,10 +1388,11 @@ class YoutubeIE(InfoExtractor):
|
|||||||
url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
|
url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
|
||||||
|
|
||||||
format_limit = self._downloader.params.get('format_limit', None)
|
format_limit = self._downloader.params.get('format_limit', None)
|
||||||
if format_limit is not None and format_limit in self._available_formats:
|
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
|
||||||
format_list = self._available_formats[self._available_formats.index(format_limit):]
|
if format_limit is not None and format_limit in available_formats:
|
||||||
|
format_list = available_formats[available_formats.index(format_limit):]
|
||||||
else:
|
else:
|
||||||
format_list = self._available_formats
|
format_list = available_formats
|
||||||
existing_formats = [x for x in format_list if x in url_map]
|
existing_formats = [x for x in format_list if x in url_map]
|
||||||
if len(existing_formats) == 0:
|
if len(existing_formats) == 0:
|
||||||
self._downloader.trouble(u'ERROR: no known formats available for video')
|
self._downloader.trouble(u'ERROR: no known formats available for video')
|
||||||
@@ -1573,7 +1618,6 @@ class DailymotionIE(InfoExtractor):
|
|||||||
self._downloader.increment_downloads()
|
self._downloader.increment_downloads()
|
||||||
video_id = mobj.group(1)
|
video_id = mobj.group(1)
|
||||||
|
|
||||||
simple_title = mobj.group(2).decode('utf-8')
|
|
||||||
video_extension = 'flv'
|
video_extension = 'flv'
|
||||||
|
|
||||||
# Retrieve video webpage to extract further information
|
# Retrieve video webpage to extract further information
|
||||||
@@ -1603,12 +1647,13 @@ class DailymotionIE(InfoExtractor):
|
|||||||
|
|
||||||
video_url = mediaURL
|
video_url = mediaURL
|
||||||
|
|
||||||
mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)
|
mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
self._downloader.trouble(u'ERROR: unable to extract title')
|
self._downloader.trouble(u'ERROR: unable to extract title')
|
||||||
return
|
return
|
||||||
video_title = mobj.group(1).decode('utf-8')
|
video_title = _unescapeHTML(mobj.group('title').decode('utf-8'))
|
||||||
video_title = sanitize_title(video_title)
|
video_title = sanitize_title(video_title)
|
||||||
|
simple_title = _simplify_title(video_title)
|
||||||
|
|
||||||
mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
|
mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
@@ -3122,7 +3167,7 @@ class ComedyCentralIE(InfoExtractor):
|
|||||||
return
|
return
|
||||||
epTitle = mobj.group('episode')
|
epTitle = mobj.group('episode')
|
||||||
|
|
||||||
mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"/>', html)
|
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html)
|
||||||
if len(mMovieParams) == 0:
|
if len(mMovieParams) == 0:
|
||||||
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
|
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
|
||||||
return
|
return
|
||||||
@@ -3608,6 +3653,339 @@ class InfoQIE(InfoExtractor):
|
|||||||
except UnavailableVideoError, err:
|
except UnavailableVideoError, err:
|
||||||
self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
|
self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
|
||||||
|
|
||||||
|
class MixcloudIE(InfoExtractor):
|
||||||
|
"""Information extractor for www.mixcloud.com"""
|
||||||
|
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
|
||||||
|
IE_NAME = u'mixcloud'
|
||||||
|
|
||||||
|
def __init__(self, downloader=None):
|
||||||
|
InfoExtractor.__init__(self, downloader)
|
||||||
|
|
||||||
|
def report_download_json(self, file_id):
|
||||||
|
"""Report JSON download."""
|
||||||
|
self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
|
||||||
|
|
||||||
|
def report_extraction(self, file_id):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
|
||||||
|
|
||||||
|
def get_urls(self, jsonData, fmt, bitrate='best'):
|
||||||
|
"""Get urls from 'audio_formats' section in json"""
|
||||||
|
file_url = None
|
||||||
|
try:
|
||||||
|
bitrate_list = jsonData[fmt]
|
||||||
|
if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
|
||||||
|
bitrate = max(bitrate_list) # select highest
|
||||||
|
|
||||||
|
url_list = jsonData[fmt][bitrate]
|
||||||
|
except TypeError: # we have no bitrate info.
|
||||||
|
url_list = jsonData[fmt]
|
||||||
|
|
||||||
|
return url_list
|
||||||
|
|
||||||
|
def check_urls(self, url_list):
|
||||||
|
"""Returns 1st active url from list"""
|
||||||
|
for url in url_list:
|
||||||
|
try:
|
||||||
|
urllib2.urlopen(url)
|
||||||
|
return url
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
url = None
|
||||||
|
|
||||||
|
return None
|
||||||
|
|
||||||
|
def _print_formats(self, formats):
|
||||||
|
print 'Available formats:'
|
||||||
|
for fmt in formats.keys():
|
||||||
|
for b in formats[fmt]:
|
||||||
|
try:
|
||||||
|
ext = formats[fmt][b][0]
|
||||||
|
print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])
|
||||||
|
except TypeError: # we have no bitrate info
|
||||||
|
ext = formats[fmt][0]
|
||||||
|
print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])
|
||||||
|
break
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||||
|
return
|
||||||
|
# extract uploader & filename from url
|
||||||
|
uploader = mobj.group(1).decode('utf-8')
|
||||||
|
file_id = uploader + "-" + mobj.group(2).decode('utf-8')
|
||||||
|
|
||||||
|
# construct API request
|
||||||
|
file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
|
||||||
|
# retrieve .json file with links to files
|
||||||
|
request = urllib2.Request(file_url)
|
||||||
|
try:
|
||||||
|
self.report_download_json(file_url)
|
||||||
|
jsonData = urllib2.urlopen(request).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
# parse JSON
|
||||||
|
json_data = json.loads(jsonData)
|
||||||
|
player_url = json_data['player_swf_url']
|
||||||
|
formats = dict(json_data['audio_formats'])
|
||||||
|
|
||||||
|
req_format = self._downloader.params.get('format', None)
|
||||||
|
bitrate = None
|
||||||
|
|
||||||
|
if self._downloader.params.get('listformats', None):
|
||||||
|
self._print_formats(formats)
|
||||||
|
return
|
||||||
|
|
||||||
|
if req_format is None or req_format == 'best':
|
||||||
|
for format_param in formats.keys():
|
||||||
|
url_list = self.get_urls(formats, format_param)
|
||||||
|
# check urls
|
||||||
|
file_url = self.check_urls(url_list)
|
||||||
|
if file_url is not None:
|
||||||
|
break # got it!
|
||||||
|
else:
|
||||||
|
if req_format not in formats.keys():
|
||||||
|
self._downloader.trouble(u'ERROR: format is not available')
|
||||||
|
return
|
||||||
|
|
||||||
|
url_list = self.get_urls(formats, req_format)
|
||||||
|
file_url = self.check_urls(url_list)
|
||||||
|
format_param = req_format
|
||||||
|
|
||||||
|
# We have audio
|
||||||
|
self._downloader.increment_downloads()
|
||||||
|
try:
|
||||||
|
# Process file information
|
||||||
|
self._downloader.process_info({
|
||||||
|
'id': file_id.decode('utf-8'),
|
||||||
|
'url': file_url.decode('utf-8'),
|
||||||
|
'uploader': uploader.decode('utf-8'),
|
||||||
|
'upload_date': u'NA',
|
||||||
|
'title': json_data['name'],
|
||||||
|
'stitle': _simplify_title(json_data['name']),
|
||||||
|
'ext': file_url.split('.')[-1].decode('utf-8'),
|
||||||
|
'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
|
||||||
|
'thumbnail': json_data['thumbnail_url'],
|
||||||
|
'description': json_data['description'],
|
||||||
|
'player_url': player_url.decode('utf-8'),
|
||||||
|
})
|
||||||
|
except UnavailableVideoError, err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download file')
|
||||||
|
|
||||||
|
class StanfordOpenClassroomIE(InfoExtractor):
|
||||||
|
"""Information extractor for Stanford's Open ClassRoom"""
|
||||||
|
|
||||||
|
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
|
||||||
|
IE_NAME = u'stanfordoc'
|
||||||
|
|
||||||
|
def report_download_webpage(self, objid):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid))
|
||||||
|
|
||||||
|
def report_extraction(self, video_id):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||||
|
return
|
||||||
|
|
||||||
|
if mobj.group('course') and mobj.group('video'): # A specific video
|
||||||
|
course = mobj.group('course')
|
||||||
|
video = mobj.group('video')
|
||||||
|
info = {
|
||||||
|
'id': _simplify_title(course + '_' + video),
|
||||||
|
}
|
||||||
|
|
||||||
|
self.report_extraction(info['id'])
|
||||||
|
baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
|
||||||
|
xmlUrl = baseUrl + video + '.xml'
|
||||||
|
try:
|
||||||
|
metaXml = urllib2.urlopen(xmlUrl).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err))
|
||||||
|
return
|
||||||
|
mdoc = xml.etree.ElementTree.fromstring(metaXml)
|
||||||
|
try:
|
||||||
|
info['title'] = mdoc.findall('./title')[0].text
|
||||||
|
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
|
||||||
|
except IndexError:
|
||||||
|
self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
|
||||||
|
return
|
||||||
|
info['stitle'] = _simplify_title(info['title'])
|
||||||
|
info['ext'] = info['url'].rpartition('.')[2]
|
||||||
|
info['format'] = info['ext']
|
||||||
|
self._downloader.increment_downloads()
|
||||||
|
try:
|
||||||
|
self._downloader.process_info(info)
|
||||||
|
except UnavailableVideoError, err:
|
||||||
|
self._downloader.trouble(u'\nERROR: unable to download video')
|
||||||
|
elif mobj.group('course'): # A course page
|
||||||
|
unescapeHTML = HTMLParser.HTMLParser().unescape
|
||||||
|
|
||||||
|
course = mobj.group('course')
|
||||||
|
info = {
|
||||||
|
'id': _simplify_title(course),
|
||||||
|
'type': 'playlist',
|
||||||
|
}
|
||||||
|
|
||||||
|
self.report_download_webpage(info['id'])
|
||||||
|
try:
|
||||||
|
coursepage = urllib2.urlopen(url).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
m = re.search('<h1>([^<]+)</h1>', coursepage)
|
||||||
|
if m:
|
||||||
|
info['title'] = unescapeHTML(m.group(1))
|
||||||
|
else:
|
||||||
|
info['title'] = info['id']
|
||||||
|
info['stitle'] = _simplify_title(info['title'])
|
||||||
|
|
||||||
|
m = re.search('<description>([^<]+)</description>', coursepage)
|
||||||
|
if m:
|
||||||
|
info['description'] = unescapeHTML(m.group(1))
|
||||||
|
|
||||||
|
links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
|
||||||
|
info['list'] = [
|
||||||
|
{
|
||||||
|
'type': 'reference',
|
||||||
|
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
|
||||||
|
}
|
||||||
|
for vpage in links]
|
||||||
|
|
||||||
|
for entry in info['list']:
|
||||||
|
assert entry['type'] == 'reference'
|
||||||
|
self.extract(entry['url'])
|
||||||
|
else: # Root page
|
||||||
|
unescapeHTML = HTMLParser.HTMLParser().unescape
|
||||||
|
|
||||||
|
info = {
|
||||||
|
'id': 'Stanford OpenClassroom',
|
||||||
|
'type': 'playlist',
|
||||||
|
}
|
||||||
|
|
||||||
|
self.report_download_webpage(info['id'])
|
||||||
|
rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
|
||||||
|
try:
|
||||||
|
rootpage = urllib2.urlopen(rootURL).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
info['title'] = info['id']
|
||||||
|
info['stitle'] = _simplify_title(info['title'])
|
||||||
|
|
||||||
|
links = _orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
|
||||||
|
info['list'] = [
|
||||||
|
{
|
||||||
|
'type': 'reference',
|
||||||
|
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
|
||||||
|
}
|
||||||
|
for cpage in links]
|
||||||
|
|
||||||
|
for entry in info['list']:
|
||||||
|
assert entry['type'] == 'reference'
|
||||||
|
self.extract(entry['url'])
|
||||||
|
|
||||||
|
class MTVIE(InfoExtractor):
|
||||||
|
"""Information extractor for MTV.com"""
|
||||||
|
|
||||||
|
_VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
|
||||||
|
IE_NAME = u'mtv'
|
||||||
|
|
||||||
|
def report_webpage(self, video_id):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
|
||||||
|
|
||||||
|
def report_extraction(self, video_id):
|
||||||
|
"""Report information extraction."""
|
||||||
|
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||||
|
return
|
||||||
|
if not mobj.group('proto'):
|
||||||
|
url = 'http://' + url
|
||||||
|
video_id = mobj.group('videoid')
|
||||||
|
self.report_webpage(video_id)
|
||||||
|
|
||||||
|
request = urllib2.Request(url)
|
||||||
|
try:
|
||||||
|
webpage = urllib2.urlopen(request).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to extract song name')
|
||||||
|
return
|
||||||
|
song_name = _unescapeHTML(mobj.group(1).decode('iso-8859-1'))
|
||||||
|
mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to extract performer')
|
||||||
|
return
|
||||||
|
performer = _unescapeHTML(mobj.group(1).decode('iso-8859-1'))
|
||||||
|
video_title = performer + ' - ' + song_name
|
||||||
|
|
||||||
|
mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to mtvn_uri')
|
||||||
|
return
|
||||||
|
mtvn_uri = mobj.group(1)
|
||||||
|
|
||||||
|
mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to extract content id')
|
||||||
|
return
|
||||||
|
content_id = mobj.group(1)
|
||||||
|
|
||||||
|
videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
|
||||||
|
self.report_extraction(video_id)
|
||||||
|
request = urllib2.Request(videogen_url)
|
||||||
|
try:
|
||||||
|
metadataXml = urllib2.urlopen(request).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
mdoc = xml.etree.ElementTree.fromstring(metadataXml)
|
||||||
|
renditions = mdoc.findall('.//rendition')
|
||||||
|
|
||||||
|
# For now, always pick the highest quality.
|
||||||
|
rendition = renditions[-1]
|
||||||
|
|
||||||
|
try:
|
||||||
|
_,_,ext = rendition.attrib['type'].partition('/')
|
||||||
|
format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
|
||||||
|
video_url = rendition.find('./src').text
|
||||||
|
except KeyError:
|
||||||
|
self._downloader.trouble('Invalid rendition field.')
|
||||||
|
return
|
||||||
|
|
||||||
|
self._downloader.increment_downloads()
|
||||||
|
info = {
|
||||||
|
'id': video_id,
|
||||||
|
'url': video_url,
|
||||||
|
'uploader': performer,
|
||||||
|
'title': video_title,
|
||||||
|
'stitle': _simplify_title(video_title),
|
||||||
|
'ext': ext,
|
||||||
|
'format': format,
|
||||||
|
}
|
||||||
|
|
||||||
|
try:
|
||||||
|
self._downloader.process_info(info)
|
||||||
|
except UnavailableVideoError, err:
|
||||||
|
self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
|
||||||
|
|
||||||
|
|
||||||
class PostProcessor(object):
|
class PostProcessor(object):
|
||||||
@@ -3656,6 +4034,9 @@ class PostProcessor(object):
|
|||||||
"""
|
"""
|
||||||
return information # by default, do nothing
|
return information # by default, do nothing
|
||||||
|
|
||||||
|
class AudioConversionError(BaseException):
|
||||||
|
def __init__(self, message):
|
||||||
|
self.message = message
|
||||||
|
|
||||||
class FFmpegExtractAudioPP(PostProcessor):
|
class FFmpegExtractAudioPP(PostProcessor):
|
||||||
|
|
||||||
@@ -3670,7 +4051,7 @@ class FFmpegExtractAudioPP(PostProcessor):
|
|||||||
@staticmethod
|
@staticmethod
|
||||||
def get_audio_codec(path):
|
def get_audio_codec(path):
|
||||||
try:
|
try:
|
||||||
cmd = ['ffprobe', '-show_streams', '--', path]
|
cmd = ['ffprobe', '-show_streams', '--', _encodeFilename(path)]
|
||||||
handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
|
handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
|
||||||
output = handle.communicate()[0]
|
output = handle.communicate()[0]
|
||||||
if handle.wait() != 0:
|
if handle.wait() != 0:
|
||||||
@@ -3687,12 +4068,23 @@ class FFmpegExtractAudioPP(PostProcessor):
|
|||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def run_ffmpeg(path, out_path, codec, more_opts):
|
def run_ffmpeg(path, out_path, codec, more_opts):
|
||||||
|
if codec is None:
|
||||||
|
acodec_opts = []
|
||||||
|
else:
|
||||||
|
acodec_opts = ['-acodec', codec]
|
||||||
|
cmd = ['ffmpeg', '-y', '-i', _encodeFilename(path), '-vn'] + acodec_opts + more_opts + ['--', _encodeFilename(out_path)]
|
||||||
try:
|
try:
|
||||||
cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
|
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||||
ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
|
stdout,stderr = p.communicate()
|
||||||
return (ret == 0)
|
|
||||||
except (IOError, OSError):
|
except (IOError, OSError):
|
||||||
return False
|
e = sys.exc_info()[1]
|
||||||
|
if isinstance(e, OSError) and e.errno == 2:
|
||||||
|
raise AudioConversionError('ffmpeg not found. Please install ffmpeg.')
|
||||||
|
else:
|
||||||
|
raise e
|
||||||
|
if p.returncode != 0:
|
||||||
|
msg = stderr.strip().split('\n')[-1]
|
||||||
|
raise AudioConversionError(msg)
|
||||||
|
|
||||||
def run(self, information):
|
def run(self, information):
|
||||||
path = information['filepath']
|
path = information['filepath']
|
||||||
@@ -3703,8 +4095,13 @@ class FFmpegExtractAudioPP(PostProcessor):
|
|||||||
return None
|
return None
|
||||||
|
|
||||||
more_opts = []
|
more_opts = []
|
||||||
if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
|
if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
|
||||||
if filecodec in ['aac', 'mp3', 'vorbis']:
|
if self._preferredcodec == 'm4a' and filecodec == 'aac':
|
||||||
|
# Lossless, but in another container
|
||||||
|
acodec = 'copy'
|
||||||
|
extension = self._preferredcodec
|
||||||
|
more_opts = ['-absf', 'aac_adtstoasc']
|
||||||
|
elif filecodec in ['aac', 'mp3', 'vorbis']:
|
||||||
# Lossless if possible
|
# Lossless if possible
|
||||||
acodec = 'copy'
|
acodec = 'copy'
|
||||||
extension = filecodec
|
extension = filecodec
|
||||||
@@ -3721,35 +4118,44 @@ class FFmpegExtractAudioPP(PostProcessor):
|
|||||||
more_opts += ['-ab', self._preferredquality]
|
more_opts += ['-ab', self._preferredquality]
|
||||||
else:
|
else:
|
||||||
# We convert the audio (lossy)
|
# We convert the audio (lossy)
|
||||||
acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
|
acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
|
||||||
extension = self._preferredcodec
|
extension = self._preferredcodec
|
||||||
more_opts = []
|
more_opts = []
|
||||||
if self._preferredquality is not None:
|
if self._preferredquality is not None:
|
||||||
more_opts += ['-ab', self._preferredquality]
|
more_opts += ['-ab', self._preferredquality]
|
||||||
if self._preferredcodec == 'aac':
|
if self._preferredcodec == 'aac':
|
||||||
more_opts += ['-f', 'adts']
|
more_opts += ['-f', 'adts']
|
||||||
|
if self._preferredcodec == 'm4a':
|
||||||
|
more_opts += ['-absf', 'aac_adtstoasc']
|
||||||
if self._preferredcodec == 'vorbis':
|
if self._preferredcodec == 'vorbis':
|
||||||
extension = 'ogg'
|
extension = 'ogg'
|
||||||
|
if self._preferredcodec == 'wav':
|
||||||
|
extension = 'wav'
|
||||||
|
more_opts += ['-f', 'wav']
|
||||||
|
|
||||||
(prefix, ext) = os.path.splitext(path)
|
prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
|
||||||
new_path = prefix + '.' + extension
|
new_path = prefix + sep + extension
|
||||||
self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path)
|
self._downloader.to_screen(u'[ffmpeg] Destination: ' + new_path)
|
||||||
status = self.run_ffmpeg(path, new_path, acodec, more_opts)
|
try:
|
||||||
|
self.run_ffmpeg(path, new_path, acodec, more_opts)
|
||||||
if not status:
|
except:
|
||||||
self._downloader.to_stderr(u'WARNING: error running ffmpeg')
|
etype,e,tb = sys.exc_info()
|
||||||
|
if isinstance(e, AudioConversionError):
|
||||||
|
self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message)
|
||||||
|
else:
|
||||||
|
self._downloader.to_stderr(u'ERROR: error running ffmpeg')
|
||||||
return None
|
return None
|
||||||
|
|
||||||
# Try to update the date time for extracted audio file.
|
# Try to update the date time for extracted audio file.
|
||||||
if information.get('filetime') is not None:
|
if information.get('filetime') is not None:
|
||||||
try:
|
try:
|
||||||
os.utime(new_path, (time.time(), information['filetime']))
|
os.utime(_encodeFilename(new_path), (time.time(), information['filetime']))
|
||||||
except:
|
except:
|
||||||
self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
|
self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
|
||||||
|
|
||||||
if not self._keepvideo:
|
if not self._keepvideo:
|
||||||
try:
|
try:
|
||||||
os.remove(path)
|
os.remove(_encodeFilename(path))
|
||||||
except (IOError, OSError):
|
except (IOError, OSError):
|
||||||
self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
|
self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
|
||||||
return None
|
return None
|
||||||
@@ -3795,6 +4201,20 @@ def parseOpts():
|
|||||||
# Deferred imports
|
# Deferred imports
|
||||||
import getpass
|
import getpass
|
||||||
import optparse
|
import optparse
|
||||||
|
import shlex
|
||||||
|
|
||||||
|
def _readOptions(filename_bytes):
|
||||||
|
try:
|
||||||
|
optionf = open(filename_bytes)
|
||||||
|
except IOError:
|
||||||
|
return [] # silently skip if file is not present
|
||||||
|
try:
|
||||||
|
res = []
|
||||||
|
for l in optionf:
|
||||||
|
res += shlex.split(l, comments=True)
|
||||||
|
finally:
|
||||||
|
optionf.close()
|
||||||
|
return res
|
||||||
|
|
||||||
def _format_option_string(option):
|
def _format_option_string(option):
|
||||||
''' ('-o', '--option') -> -o, --format METAVAR'''
|
''' ('-o', '--option') -> -o, --format METAVAR'''
|
||||||
@@ -3875,6 +4295,7 @@ def parseOpts():
|
|||||||
dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
|
dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
|
||||||
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
|
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
|
||||||
selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
|
selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
|
||||||
|
selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None)
|
||||||
|
|
||||||
authentication.add_option('-u', '--username',
|
authentication.add_option('-u', '--username',
|
||||||
dest='username', metavar='USERNAME', help='account username')
|
dest='username', metavar='USERNAME', help='account username')
|
||||||
@@ -3888,6 +4309,8 @@ def parseOpts():
|
|||||||
action='store', dest='format', metavar='FORMAT', help='video format code')
|
action='store', dest='format', metavar='FORMAT', help='video format code')
|
||||||
video_format.add_option('--all-formats',
|
video_format.add_option('--all-formats',
|
||||||
action='store_const', dest='format', help='download all available video formats', const='all')
|
action='store_const', dest='format', help='download all available video formats', const='all')
|
||||||
|
video_format.add_option('--prefer-free-formats',
|
||||||
|
action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested')
|
||||||
video_format.add_option('--max-quality',
|
video_format.add_option('--max-quality',
|
||||||
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
|
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
|
||||||
video_format.add_option('-F', '--list-formats',
|
video_format.add_option('-F', '--list-formats',
|
||||||
@@ -3931,7 +4354,7 @@ def parseOpts():
|
|||||||
action='store_true', dest='autonumber',
|
action='store_true', dest='autonumber',
|
||||||
help='number downloaded files starting from 00000', default=False)
|
help='number downloaded files starting from 00000', default=False)
|
||||||
filesystem.add_option('-o', '--output',
|
filesystem.add_option('-o', '--output',
|
||||||
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, and %% for a literal percent')
|
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.')
|
||||||
filesystem.add_option('-a', '--batch-file',
|
filesystem.add_option('-a', '--batch-file',
|
||||||
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
|
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
|
||||||
filesystem.add_option('-w', '--no-overwrites',
|
filesystem.add_option('-w', '--no-overwrites',
|
||||||
@@ -3959,7 +4382,7 @@ def parseOpts():
|
|||||||
postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
|
postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
|
||||||
help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
|
help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
|
||||||
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
|
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
|
||||||
help='"best", "aac", "vorbis" or "mp3"; best by default')
|
help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default')
|
||||||
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
|
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
|
||||||
help='ffmpeg audio bitrate specification, 128k by default')
|
help='ffmpeg audio bitrate specification, 128k by default')
|
||||||
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
|
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
|
||||||
@@ -3974,7 +4397,13 @@ def parseOpts():
|
|||||||
parser.add_option_group(authentication)
|
parser.add_option_group(authentication)
|
||||||
parser.add_option_group(postproc)
|
parser.add_option_group(postproc)
|
||||||
|
|
||||||
opts, args = parser.parse_args()
|
xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
|
||||||
|
if xdg_config_home:
|
||||||
|
userConf = os.path.join(xdg_config_home, 'youtube-dl.conf')
|
||||||
|
else:
|
||||||
|
userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
|
||||||
|
argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:]
|
||||||
|
opts, args = parser.parse_args(argv)
|
||||||
|
|
||||||
return parser, opts, args
|
return parser, opts, args
|
||||||
|
|
||||||
@@ -4008,6 +4437,9 @@ def gen_extractors():
|
|||||||
XVideosIE(),
|
XVideosIE(),
|
||||||
SoundcloudIE(),
|
SoundcloudIE(),
|
||||||
InfoQIE(),
|
InfoQIE(),
|
||||||
|
MixcloudIE(),
|
||||||
|
StanfordOpenClassroomIE(),
|
||||||
|
MTVIE(),
|
||||||
|
|
||||||
GenericIE()
|
GenericIE()
|
||||||
]
|
]
|
||||||
@@ -4097,7 +4529,7 @@ def _real_main():
|
|||||||
except (TypeError, ValueError), err:
|
except (TypeError, ValueError), err:
|
||||||
parser.error(u'invalid playlist end number specified')
|
parser.error(u'invalid playlist end number specified')
|
||||||
if opts.extractaudio:
|
if opts.extractaudio:
|
||||||
if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
|
if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']:
|
||||||
parser.error(u'invalid audio format specified')
|
parser.error(u'invalid audio format specified')
|
||||||
|
|
||||||
# File downloader
|
# File downloader
|
||||||
@@ -4143,6 +4575,8 @@ def _real_main():
|
|||||||
'writeinfojson': opts.writeinfojson,
|
'writeinfojson': opts.writeinfojson,
|
||||||
'matchtitle': opts.matchtitle,
|
'matchtitle': opts.matchtitle,
|
||||||
'rejecttitle': opts.rejecttitle,
|
'rejecttitle': opts.rejecttitle,
|
||||||
|
'max_downloads': opts.max_downloads,
|
||||||
|
'prefer_free_formats': opts.prefer_free_formats,
|
||||||
})
|
})
|
||||||
for extractor in extractors:
|
for extractor in extractors:
|
||||||
fd.add_info_extractor(extractor)
|
fd.add_info_extractor(extractor)
|
||||||
@@ -4161,7 +4595,12 @@ def _real_main():
|
|||||||
parser.error(u'you must provide at least one URL')
|
parser.error(u'you must provide at least one URL')
|
||||||
else:
|
else:
|
||||||
sys.exit()
|
sys.exit()
|
||||||
|
|
||||||
|
try:
|
||||||
retcode = fd.download(all_urls)
|
retcode = fd.download(all_urls)
|
||||||
|
except MaxDownloadsReached:
|
||||||
|
fd.to_screen(u'--max-download limit reached, aborting.')
|
||||||
|
retcode = 101
|
||||||
|
|
||||||
# Dump cookie jar if requested
|
# Dump cookie jar if requested
|
||||||
if opts.cookiefile is not None:
|
if opts.cookiefile is not None:
|
||||||
|
Reference in New Issue
Block a user