Compare commits

...

46 Commits

Author SHA1 Message Date
Philipp Hagemeister
3b9f631c41 release 2014.11.20 2014-11-20 08:55:56 +01:00
Jaime Marquínez Ferrándiz
3ba098a6a5 Merge pull request #4247 from ivan/info-json
Fix #4246 and #4244 .info.json bugs
2014-11-20 08:16:42 +01:00
Ivan Kozik
1394646a0a Fix "ERROR: Cannot write metadata to JSON file" on Windows
Fixes #4246
2014-11-20 06:26:34 +00:00
Ivan Kozik
61ee5aeb73 Fix UnicodeEncodeError with --write-info-json on Python 2.7 + Windows
Fixes #4244
2014-11-20 06:26:34 +00:00
Philipp Hagemeister
07e378fa18 [compat] correct OptionGroup invocation for Python 3 (fixes #4243) 2014-11-20 07:21:12 +01:00
Philipp Hagemeister
e07e931375 Work around 2.7.0 deficencies (Fixes #4223) 2014-11-19 18:21:58 +01:00
Naglis Jonaitis
480b7c32a9 [rtlxl] Fix format order 2014-11-19 01:21:02 +02:00
Jaime Marquínez Ferrándiz
f56875f271 [test/test_compat] Restore the old value of the HOME environment variable
If the test was run before the YoutubeIE tests (for example by running
"nosetests -v test/test_compat.py test/test_download.py -m 'Youtube_1|compat_expand'"),
it wrote the signatures cache to the 'C:\Documents and Settings\тест\Application Data' folder.
It failed due to a problem in the cache code and the write_json_file function (fixed in f03e33b89a622af13fa5275c46b63aaa4814c499)
2014-11-19 00:02:24 +01:00
Jaime Marquínez Ferrándiz
92120217eb [cache] Fix writing to paths with unicode characters
* Use "compat_getenv"
* "write_json_file" now expects the filename to be a string
2014-11-19 00:02:24 +01:00
Naglis Jonaitis
37eddd3143 [rtlxl] Use m3u8 streams instead of f4m (#4115, #4118) 2014-11-19 00:26:44 +02:00
Philipp Hagemeister
0857baade3 [youtube] Add webm audio formats (Fixes #4229) 2014-11-18 11:08:37 +01:00
Philipp Hagemeister
23ad44b57b [youtube] Better error message for DASH manifest 2014-11-17 20:12:52 +01:00
Philipp Hagemeister
f48d3e9bbc [swfinterp] Improve undefined representation 2014-11-17 08:02:48 +01:00
Philipp Hagemeister
fbf94a7815 [swfinterp] Add more builtins and improve static variables 2014-11-17 07:54:06 +01:00
Philipp Hagemeister
1921b24551 [swfinterp] Add support for more complicated constants 2014-11-17 07:31:22 +01:00
Philipp Hagemeister
28e614de5c [utils] Remove stray u' 2014-11-17 07:16:12 +01:00
Philipp Hagemeister
cd9ad1d7e8 [swfinterp] Basic support for constants (only ints for now) 2014-11-17 07:14:02 +01:00
Philipp Hagemeister
162f54eca6 [swfinterp] Implement bitand and pushshort operators 2014-11-17 05:08:39 +01:00
Philipp Hagemeister
33a266f4ba [swfinterp] Implement charCodeAt 2014-11-17 05:03:46 +01:00
Philipp Hagemeister
6b592d93a2 [swfinterp] Formalize built-in classes 2014-11-17 04:54:54 +01:00
Philipp Hagemeister
4686ae4b64 [swfinterp] Implement various opcodes 2014-11-17 04:45:12 +01:00
Philipp Hagemeister
8d05f2c16a [swfinterp] Add support for void methods 2014-11-17 04:36:23 +01:00
Philipp Hagemeister
a4bb83956c [swfinterp] Implement pushtrue and pushfalse opcodes 2014-11-17 04:29:34 +01:00
Philipp Hagemeister
eb5376044c [swfinterp] Implement equals opcode 2014-11-17 04:27:51 +01:00
Philipp Hagemeister
3cbcff8a2d [swfinterp] Implement String basics 2014-11-17 04:25:10 +01:00
Philipp Hagemeister
e983cf5277 [swfinterp] Interpret yet more opcodes 2014-11-17 04:00:41 +01:00
Philipp Hagemeister
0ab1ca5501 [swfinterp] Better error message 2014-11-17 03:53:32 +01:00
Philipp Hagemeister
4baafa229d [swfinterp] Intepret more multinames 2014-11-17 03:46:23 +01:00
Philipp Hagemeister
7f3e33a147 [swfinterp] Implement member assignment 2014-11-17 01:27:34 +01:00
Philipp Hagemeister
b7558d9881 [swfinterp] Allow function patching 2014-11-17 01:27:15 +01:00
Philipp Hagemeister
a0f59cdcb4 [tests] Modernize 2014-11-16 15:17:48 +01:00
Philipp Hagemeister
a4bc433619 [__init__] Modernize 2014-11-16 15:08:34 +01:00
Philipp Hagemeister
b6b70730bf [downloader/common] Modernize 2014-11-16 15:06:59 +01:00
Philipp Hagemeister
6a68bb574a [eporner] Fix duration (Closes #4188) 2014-11-16 14:55:22 +01:00
Philipp Hagemeister
0cf166ad4f release 2014.11.16 2014-11-16 00:51:46 +01:00
Philipp Hagemeister
2707b50ffe [spiegel] Correct handling of redirects to spiegel.tv (Closes #4211) 2014-11-16 00:51:31 +01:00
Philipp Hagemeister
939fe70de0 [spiegeltv] Match hash-style URLs (Closes #4210) 2014-11-16 00:40:09 +01:00
Philipp Hagemeister
89c15fe0b3 [spiegeltv] Modernize 2014-11-16 00:33:51 +01:00
Jaime Marquínez Ferrándiz
ec5f601670 [utils] Fix "write_json_file" for unicode names in python 2.x (fixes #4125) 2014-11-15 22:00:32 +01:00
Naglis Jonaitis
8caa0c9779 [bliptv] Fix the resolve of lookup ID (Closes #4197) 2014-11-15 16:56:04 +02:00
Philipp Hagemeister
e2548b5b25 release 2014.11.15.1 2014-11-15 15:21:50 +01:00
Philipp Hagemeister
bbefcf04bf [goldenmoustache] Fix title (Closes #4203) 2014-11-15 15:21:34 +01:00
Philipp Hagemeister
c7b0add86f [compat] Work around kwargs bugs in old 2.6 Python releases (Fixes #3813) 2014-11-15 15:17:19 +01:00
Philipp Hagemeister
a0155d93d9 release 2014.11.15 2014-11-15 11:01:54 +01:00
Philipp Hagemeister
00d9ef0b70 [mailru] Adapt to new data format (Fixes #4201) 2014-11-15 11:01:17 +01:00
Philipp Hagemeister
0cc8888038 [crunchyroll] Remove NOP code (#2782) 2014-11-15 00:34:03 +01:00
35 changed files with 659 additions and 184 deletions

View File

@@ -0,0 +1,18 @@
// input: []
// output: 4
package {
public class ConstArrayAccess {
private static const x:int = 2;
private static const ar:Array = ["42", "3411"];
public static function main():int{
var c:ConstArrayAccess = new ConstArrayAccess();
return c.f();
}
public function f(): int {
return ar[1].length;
}
}
}

View File

@@ -0,0 +1,12 @@
// input: []
// output: 2
package {
public class ConstantInt {
private static const x:int = 2;
public static function main():int{
return x;
}
}
}

10
test/swftests/DictCall.as Normal file
View File

@@ -0,0 +1,10 @@
// input: [{"x": 1, "y": 2}]
// output: 3
package {
public class DictCall {
public static function main(d:Object):int{
return d.x + d.y;
}
}
}

View File

@@ -0,0 +1,10 @@
// input: []
// output: false
package {
public class EqualsOperator {
public static function main():Boolean{
return 1 == 2;
}
}
}

View File

@@ -0,0 +1,22 @@
// input: [1]
// output: 2
package {
public class MemberAssignment {
public var v:int;
public function g():int {
return this.v;
}
public function f(a:int):int{
this.v = a;
return this.v + this.g();
}
public static function main(a:int): int {
var v:MemberAssignment = new MemberAssignment();
return v.f(a);
}
}
}

View File

@@ -0,0 +1,24 @@
// input: []
// output: 123
package {
public class NeOperator {
public static function main(): int {
var res:int = 0;
if (1 != 2) {
res += 3;
} else {
res += 4;
}
if (2 != 2) {
res += 10;
} else {
res += 20;
}
if (9 == 9) {
res += 100;
}
return res;
}
}
}

View File

@@ -0,0 +1,22 @@
// input: []
// output: 9
package {
public class PrivateVoidCall {
public static function main():int{
var f:OtherClass = new OtherClass();
f.func();
return 9;
}
}
}
class OtherClass {
private function pf():void {
;
}
public function func():void {
this.pf();
}
}

View File

@@ -0,0 +1,11 @@
// input: []
// output: 3
package {
public class StringBasics {
public static function main():int{
var s:String = "abc";
return s.length;
}
}
}

View File

@@ -0,0 +1,11 @@
// input: []
// output: 9897
package {
public class StringCharCodeAt {
public static function main():int{
var s:String = "abc";
return s.charCodeAt(1) * 100 + s.charCodeAt();
}
}
}

View File

@@ -0,0 +1,11 @@
// input: []
// output: 2
package {
public class StringConversion {
public static function main():int{
var s:String = String(99);
return s.length;
}
}
}

View File

@@ -1,4 +1,5 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
@@ -19,7 +20,7 @@ def _download_restricted(url, filename, age):
'age_limit': age,
'skip_download': True,
'writeinfojson': True,
"outtmpl": "%(id)s.%(ext)s",
'outtmpl': '%(id)s.%(ext)s',
}
ydl = YoutubeDL(params)
ydl.add_default_info_extractors()

View File

@@ -26,11 +26,13 @@ class TestCompat(unittest.TestCase):
self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
def test_compat_expanduser(self):
old_home = os.environ.get('HOME')
test_str = 'C:\Documents and Settings\тест\Application Data'
os.environ['HOME'] = (
test_str if sys.version_info >= (3, 0)
else test_str.encode(get_filesystem_encoding()))
self.assertEqual(compat_expanduser('~'), test_str)
os.environ['HOME'] = old_home
def test_all_present(self):
import youtube_dl.compat

View File

@@ -1,5 +1,7 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
@@ -210,9 +212,9 @@ for n, test_case in enumerate(defs):
tname = 'test_' + str(test_case['name'])
i = 1
while hasattr(TestDownload, tname):
tname = 'test_' + str(test_case['name']) + '_' + str(i)
tname = 'test_%s_%d' % (test_case['name'], i)
i += 1
test_method.__name__ = tname
test_method.__name__ = str(tname)
setattr(TestDownload, test_method.__name__, test_method)
del test_method

View File

@@ -1,3 +1,6 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import unittest
import sys
@@ -6,17 +9,19 @@ import subprocess
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
try:
_DEV_NULL = subprocess.DEVNULL
except AttributeError:
_DEV_NULL = open(os.devnull, 'wb')
class TestExecution(unittest.TestCase):
def test_import(self):
subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir)
def test_module_exec(self):
if sys.version_info >= (2,7): # Python 2.6 doesn't support package execution
if sys.version_info >= (2, 7): # Python 2.6 doesn't support package execution
subprocess.check_call([sys.executable, '-m', 'youtube_dl', '--version'], cwd=rootDir, stdout=_DEV_NULL)
def test_main_exec(self):

View File

@@ -1,4 +1,5 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
@@ -74,7 +75,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
def test_youtube_list_subtitles(self):
self.DL.expect_warning(u'Video doesn\'t have automatic captions')
self.DL.expect_warning('Video doesn\'t have automatic captions')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
@@ -87,7 +88,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
self.assertTrue(subtitles['it'] is not None)
def test_youtube_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'n5BB19UTcdA'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
@@ -101,7 +102,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
class TestDailymotionSubtitles(BaseTestSubtitles):
@@ -130,20 +131,20 @@ class TestDailymotionSubtitles(BaseTestSubtitles):
self.assertEqual(len(subtitles.keys()), 5)
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
@@ -156,7 +157,7 @@ class TestDailymotionSubtitles(BaseTestSubtitles):
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
class TestTedSubtitles(BaseTestSubtitles):
@@ -185,13 +186,13 @@ class TestTedSubtitles(BaseTestSubtitles):
self.assertTrue(len(subtitles.keys()) >= 28)
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
@@ -203,7 +204,7 @@ class TestTedSubtitles(BaseTestSubtitles):
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
class TestBlipTVSubtitles(BaseTestSubtitles):
@@ -211,13 +212,13 @@ class TestBlipTVSubtitles(BaseTestSubtitles):
IE = BlipTVIE
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
@@ -251,20 +252,20 @@ class TestVimeoSubtitles(BaseTestSubtitles):
self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://vimeo.com/56015672'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
@@ -277,7 +278,7 @@ class TestVimeoSubtitles(BaseTestSubtitles):
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
class TestWallaSubtitles(BaseTestSubtitles):
@@ -285,13 +286,13 @@ class TestWallaSubtitles(BaseTestSubtitles):
IE = WallaIE
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
@@ -299,7 +300,7 @@ class TestWallaSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['heb']), 'e758c5d7cb982f6bef14f377ec7a3920')
def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True

View File

@@ -1,4 +1,5 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os

View File

@@ -218,6 +218,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_duration('0m0s'), 0)
self.assertEqual(parse_duration('0s'), 0)
self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
self.assertEqual(parse_duration('T30M38S'), 1838)
def test_fix_xml_ampersands(self):
self.assertEqual(

View File

@@ -1001,7 +1001,7 @@ class YoutubeDL(object):
else:
self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
try:
write_json_file(info_dict, encodeFilename(infofn))
write_json_file(info_dict, infofn)
except (OSError, IOError):
self.report_error('Cannot write metadata to JSON file ' + infofn)
return

View File

@@ -1,6 +1,8 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
__license__ = 'Public Domain'
import codecs
@@ -17,6 +19,7 @@ from .compat import (
compat_expanduser,
compat_getpass,
compat_print,
workaround_optparse_bug9161,
)
from .utils import (
DateRange,
@@ -55,7 +58,9 @@ def _real_main(argv=None):
# https://github.com/rg3/youtube-dl/issues/820
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
setproctitle(u'youtube-dl')
workaround_optparse_bug9161()
setproctitle('youtube-dl')
parser, opts, args = parseOpts(argv)
@@ -71,10 +76,10 @@ def _real_main(argv=None):
if opts.headers is not None:
for h in opts.headers:
if h.find(':', 1) < 0:
parser.error(u'wrong header formatting, it should be key:value, not "%s"'%h)
parser.error('wrong header formatting, it should be key:value, not "%s"'%h)
key, value = h.split(':', 2)
if opts.verbose:
write_string(u'[debug] Adding header from command line option %s:%s\n'%(key, value))
write_string('[debug] Adding header from command line option %s:%s\n'%(key, value))
std_headers[key] = value
# Dump user agent
@@ -92,9 +97,9 @@ def _real_main(argv=None):
batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
batch_urls = read_batch_urls(batchfd)
if opts.verbose:
write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
except IOError:
sys.exit(u'ERROR: batch file could not be read')
sys.exit('ERROR: batch file could not be read')
all_urls = batch_urls + args
all_urls = [url.strip() for url in all_urls]
_enc = preferredencoding()
@@ -107,7 +112,7 @@ def _real_main(argv=None):
compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
matchedUrls = [url for url in all_urls if ie.suitable(url)]
for mu in matchedUrls:
compat_print(u' ' + mu)
compat_print(' ' + mu)
sys.exit(0)
if opts.list_extractor_descriptions:
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
@@ -117,63 +122,63 @@ def _real_main(argv=None):
if desc is False:
continue
if hasattr(ie, 'SEARCH_KEY'):
_SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise', u'sleeping bunny')
_COUNTS = (u'', u'5', u'10', u'all')
desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
_SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny')
_COUNTS = ('', '5', '10', 'all')
desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
compat_print(desc)
sys.exit(0)
# Conflicting, missing and erroneous options
if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error(u'using .netrc conflicts with giving username/password')
parser.error('using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
parser.error(u'account username missing\n')
parser.error('account username missing\n')
if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
parser.error(u'using output template conflicts with using title, video ID or auto number')
parser.error('using output template conflicts with using title, video ID or auto number')
if opts.usetitle and opts.useid:
parser.error(u'using title conflicts with using video ID')
parser.error('using title conflicts with using video ID')
if opts.username is not None and opts.password is None:
opts.password = compat_getpass(u'Type account password and press [Return]: ')
opts.password = compat_getpass('Type account password and press [Return]: ')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
parser.error(u'invalid rate limit specified')
parser.error('invalid rate limit specified')
opts.ratelimit = numeric_limit
if opts.min_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
if numeric_limit is None:
parser.error(u'invalid min_filesize specified')
parser.error('invalid min_filesize specified')
opts.min_filesize = numeric_limit
if opts.max_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
if numeric_limit is None:
parser.error(u'invalid max_filesize specified')
parser.error('invalid max_filesize specified')
opts.max_filesize = numeric_limit
if opts.retries is not None:
try:
opts.retries = int(opts.retries)
except (TypeError, ValueError):
parser.error(u'invalid retry count specified')
parser.error('invalid retry count specified')
if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None:
parser.error(u'invalid buffer size specified')
parser.error('invalid buffer size specified')
opts.buffersize = numeric_buffersize
if opts.playliststart <= 0:
raise ValueError(u'Playlist start must be positive')
raise ValueError('Playlist start must be positive')
if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
raise ValueError(u'Playlist end must be greater than playlist start')
raise ValueError('Playlist end must be greater than playlist start')
if opts.extractaudio:
if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
parser.error(u'invalid audio format specified')
parser.error('invalid audio format specified')
if opts.audioquality:
opts.audioquality = opts.audioquality.strip('k').strip('K')
if not opts.audioquality.isdigit():
parser.error(u'invalid audio quality specified')
parser.error('invalid audio quality specified')
if opts.recodevideo is not None:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
parser.error(u'invalid video recode format specified')
parser.error('invalid video recode format specified')
if opts.date is not None:
date = DateRange.day(opts.date)
else:
@@ -193,17 +198,17 @@ def _real_main(argv=None):
if opts.outtmpl is not None:
opts.outtmpl = opts.outtmpl.decode(preferredencoding())
outtmpl =((opts.outtmpl is not None and opts.outtmpl)
or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
or (opts.useid and u'%(id)s.%(ext)s')
or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
or (opts.useid and '%(id)s.%(ext)s')
or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
or DEFAULT_OUTTMPL)
if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error(u'Cannot download a video and extract audio into the same'
u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
u' template'.format(outtmpl))
parser.error('Cannot download a video and extract audio into the same'
' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
' template'.format(outtmpl))
any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
@@ -330,7 +335,7 @@ def _real_main(argv=None):
# Maybe do nothing
if (len(all_urls) < 1) and (opts.load_info_filename is None):
if not (opts.update_self or opts.rm_cachedir):
parser.error(u'you must provide at least one URL')
parser.error('you must provide at least one URL')
else:
sys.exit()
@@ -340,7 +345,7 @@ def _real_main(argv=None):
else:
retcode = ydl.download(all_urls)
except MaxDownloadsReached:
ydl.to_screen(u'--max-download limit reached, aborting.')
ydl.to_screen('--max-download limit reached, aborting.')
retcode = 101
sys.exit(retcode)
@@ -352,6 +357,6 @@ def main(argv=None):
except DownloadError:
sys.exit(1)
except SameFileError:
sys.exit(u'ERROR: fixed output name but more than one file to download')
sys.exit('ERROR: fixed output name but more than one file to download')
except KeyboardInterrupt:
sys.exit(u'\nERROR: Interrupted by user')
sys.exit('\nERROR: Interrupted by user')

View File

@@ -8,7 +8,7 @@ import re
import shutil
import traceback
from .compat import compat_expanduser
from .compat import compat_expanduser, compat_getenv
from .utils import write_json_file
@@ -19,7 +19,7 @@ class Cache(object):
def _get_root_dir(self):
res = self._ydl.params.get('cachedir')
if res is None:
cache_root = os.environ.get('XDG_CACHE_HOME', '~/.cache')
cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
res = os.path.join(cache_root, 'youtube-dl')
return compat_expanduser(res)

View File

@@ -1,6 +1,7 @@
from __future__ import unicode_literals
import getpass
import optparse
import os
import subprocess
import sys
@@ -288,6 +289,36 @@ if sys.version_info < (3, 0) and sys.platform == 'win32':
else:
compat_getpass = getpass.getpass
# Old 2.6 and 2.7 releases require kwargs to be bytes
try:
(lambda x: x)(**{'x': 0})
except TypeError:
def compat_kwargs(kwargs):
return dict((bytes(k), v) for k, v in kwargs.items())
else:
compat_kwargs = lambda kwargs: kwargs
# Fix https://github.com/rg3/youtube-dl/issues/4223
# See http://bugs.python.org/issue9161 for what is broken
def workaround_optparse_bug9161():
op = optparse.OptionParser()
og = optparse.OptionGroup(op, 'foo')
try:
og.add_option('-t')
except TypeError as te:
real_add_option = optparse.OptionGroup.add_option
def _compat_add_option(self, *args, **kwargs):
enc = lambda v: (
v.encode('ascii', 'replace') if isinstance(v, compat_str)
else v)
bargs = [enc(a) for a in args]
bkwargs = dict(
(k, enc(v)) for k, v in kwargs.items())
return real_add_option(self, *bargs, **bkwargs)
optparse.OptionGroup.add_option = _compat_add_option
__all__ = [
'compat_HTTPError',
@@ -299,6 +330,7 @@ __all__ = [
'compat_html_entities',
'compat_html_parser',
'compat_http_client',
'compat_kwargs',
'compat_ord',
'compat_parse_qs',
'compat_print',
@@ -314,4 +346,5 @@ __all__ = [
'compat_xml_parse_error',
'shlex_quote',
'subprocess_check_output',
'workaround_optparse_bug9161',
]

View File

@@ -1,3 +1,5 @@
from __future__ import unicode_literals
import os
import re
import sys
@@ -159,14 +161,14 @@ class FileDownloader(object):
def temp_name(self, 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 == '-' or \
(os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
return filename
return filename + u'.part'
return filename + '.part'
def undo_temp_name(self, filename):
if filename.endswith(u'.part'):
return filename[:-len(u'.part')]
if filename.endswith('.part'):
return filename[:-len('.part')]
return filename
def try_rename(self, old_filename, new_filename):
@@ -175,7 +177,7 @@ class FileDownloader(object):
return
os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
except (IOError, OSError) as err:
self.report_error(u'unable to rename file: %s' % compat_str(err))
self.report_error('unable to rename file: %s' % compat_str(err))
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
@@ -200,10 +202,10 @@ class FileDownloader(object):
def report_destination(self, filename):
"""Report destination filename."""
self.to_screen(u'[download] Destination: ' + filename)
self.to_screen('[download] Destination: ' + filename)
def _report_progress_status(self, msg, is_last_line=False):
fullmsg = u'[download] ' + msg
fullmsg = '[download] ' + msg
if self.params.get('progress_with_newline', False):
self.to_screen(fullmsg)
else:
@@ -211,13 +213,13 @@ class FileDownloader(object):
prev_len = getattr(self, '_report_progress_prev_line_length',
0)
if prev_len > len(fullmsg):
fullmsg += u' ' * (prev_len - len(fullmsg))
fullmsg += ' ' * (prev_len - len(fullmsg))
self._report_progress_prev_line_length = len(fullmsg)
clear_line = u'\r'
clear_line = '\r'
else:
clear_line = (u'\r\x1b[K' if sys.stderr.isatty() else u'\r')
clear_line = ('\r\x1b[K' if sys.stderr.isatty() else '\r')
self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
self.to_console_title(u'youtube-dl ' + msg)
self.to_console_title('youtube-dl ' + msg)
def report_progress(self, percent, data_len_str, speed, eta):
"""Report download progress."""
@@ -233,7 +235,7 @@ class FileDownloader(object):
percent_str = 'Unknown %'
speed_str = self.format_speed(speed)
msg = (u'%s of %s at %s ETA %s' %
msg = ('%s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str))
self._report_progress_status(msg)
@@ -243,37 +245,37 @@ class FileDownloader(object):
downloaded_str = format_bytes(downloaded_data_len)
speed_str = self.format_speed(speed)
elapsed_str = FileDownloader.format_seconds(elapsed)
msg = u'%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
msg = '%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
self._report_progress_status(msg)
def report_finish(self, data_len_str, tot_time):
"""Report download finished."""
if self.params.get('noprogress', False):
self.to_screen(u'[download] Download completed')
self.to_screen('[download] Download completed')
else:
self._report_progress_status(
(u'100%% of %s in %s' %
('100%% of %s in %s' %
(data_len_str, self.format_seconds(tot_time))),
is_last_line=True)
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
self.to_screen('[download] Resuming download at byte %s' % resume_len)
def report_retry(self, count, retries):
"""Report retry in case of HTTP error 5xx"""
self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
self.to_screen(u'[download] %s has already been downloaded' % file_name)
self.to_screen('[download] %s has already been downloaded' % file_name)
except UnicodeEncodeError:
self.to_screen(u'[download] The file has already been downloaded')
self.to_screen('[download] The file has already been downloaded')
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
self.to_screen(u'[download] Unable to resume')
self.to_screen('[download] Unable to resume')
def download(self, filename, info_dict):
"""Download to a filename using the info from info_dict
@@ -293,7 +295,7 @@ class FileDownloader(object):
def real_download(self, filename, info_dict):
"""Real download process. Redefine in subclasses."""
raise NotImplementedError(u'This method must be implemented by subclasses')
raise NotImplementedError('This method must be implemented by subclasses')
def _hook_progress(self, status):
for ph in self._progress_hooks:

View File

@@ -71,11 +71,12 @@ class BlipTVIE(SubtitlesInfoExtractor):
mobj = re.match(self._VALID_URL, url)
lookup_id = mobj.group('lookup_id')
# See https://github.com/rg3/youtube-dl/issues/857
# See https://github.com/rg3/youtube-dl/issues/857 and
# https://github.com/rg3/youtube-dl/issues/4197
if lookup_id:
info_page = self._download_webpage(
'http://blip.tv/play/%s.x?p=1' % lookup_id, lookup_id, 'Resolving lookup id')
video_id = self._search_regex(r'data-episode-id="([0-9]+)', info_page, 'video_id')
video_id = self._search_regex(r'config\.id\s*=\s*"([0-9]+)', info_page, 'video_id')
else:
video_id = mobj.group('id')

View File

@@ -264,8 +264,6 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
if not lang_code:
continue
sub_root = xml.etree.ElementTree.fromstring(subtitle)
if not sub_root:
subtitles[lang_code] = ''
if sub_format == 'ass':
subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root)
else:

View File

@@ -20,7 +20,7 @@ class EpornerIE(InfoExtractor):
'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
'ext': 'mp4',
'title': 'Infamous Tiffany Teen Strip Tease Video',
'duration': 194,
'duration': 1838,
'view_count': int,
'age_limit': 18,
}
@@ -57,9 +57,7 @@ class EpornerIE(InfoExtractor):
formats.append(fmt)
self._sort_formats(formats)
duration = parse_duration(self._search_regex(
r'class="mbtim">([0-9:]+)</div>', webpage, 'duration',
fatal=False))
duration = parse_duration(self._html_search_meta('duration', webpage))
view_count = str_to_int(self._search_regex(
r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
webpage, 'view count', fatal=False))

View File

@@ -10,7 +10,7 @@ from ..utils import (
class GoldenMoustacheIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
'md5': '0f904432fa07da5054d6c8beb5efb51a',
'info_dict': {
@@ -21,7 +21,18 @@ class GoldenMoustacheIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$',
'view_count': int,
}
}
}, {
'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/',
'md5': '27f0c50fb4dd5f01dc9082fc67cd5700',
'info_dict': {
'id': '55249',
'ext': 'mp4',
'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)',
'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a',
'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
'view_count': int,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -30,7 +41,7 @@ class GoldenMoustacheIE(InfoExtractor):
video_url = self._html_search_regex(
r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
r'<title>(.*?) - Golden Moustache</title>', webpage, 'title')
r'<title>(.*?)(?: - Golden Moustache)?</title>', webpage, 'title')
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
view_count = int_or_none(self._html_search_regex(

View File

@@ -16,7 +16,7 @@ class MailRuIE(InfoExtractor):
'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
'md5': 'dea205f03120046894db4ebb6159879a',
'info_dict': {
'id': '46301138',
'id': '46301138_76',
'ext': 'mp4',
'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
'timestamp': 1393232740,
@@ -30,7 +30,7 @@ class MailRuIE(InfoExtractor):
'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html',
'md5': '00a91a58c3402204dcced523777b475f',
'info_dict': {
'id': '46843144',
'id': '46843144_1263',
'ext': 'mp4',
'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
'timestamp': 1397217632,
@@ -54,33 +54,36 @@ class MailRuIE(InfoExtractor):
author = video_data['author']
uploader = author['name']
uploader_id = author['id']
uploader_id = author.get('id') or author.get('email')
view_count = video_data.get('views_count')
movie = video_data['movie']
content_id = str(movie['contentId'])
title = movie['title']
meta_data = video_data['meta']
content_id = '%s_%s' % (
meta_data.get('accId', ''), meta_data['itemId'])
title = meta_data['title']
if title.endswith('.mp4'):
title = title[:-4]
thumbnail = movie['poster']
duration = movie['duration']
view_count = video_data['views_count']
thumbnail = meta_data['poster']
duration = meta_data['duration']
timestamp = meta_data['timestamp']
formats = [
{
'url': video['url'],
'format_id': video['name'],
'format_id': video['key'],
'height': int(video['key'].rstrip('p'))
} for video in video_data['videos']
]
self._sort_formats(formats)
return {
'id': content_id,
'title': title,
'thumbnail': thumbnail,
'timestamp': video_data['timestamp'],
'timestamp': timestamp,
'uploader': uploader,
'uploader_id': uploader_id,
'duration': duration,
'view_count': view_count,
'formats': formats,
}
}

View File

@@ -28,8 +28,9 @@ class RtlXlIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
uuid = mobj.group('uuid')
# Use m3u8 streams (see https://github.com/rg3/youtube-dl/issues/4118)
info = self._download_json(
'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/d=pc/fmt=adaptive/' % uuid,
uuid)
material = info['material'][0]
@@ -39,11 +40,11 @@ class RtlXlIE(InfoExtractor):
subtitle = material['title'] or info['episodes'][0]['name']
videopath = material['videopath']
f4m_url = 'http://manifest.us.rtl.nl' + videopath
m3u8_url = 'http://manifest.us.rtl.nl' + videopath
formats = self._extract_f4m_formats(f4m_url, uuid)
formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
video_urlpart = videopath.split('/flash/')[1][:-4]
video_urlpart = videopath.split('/adaptive/')[1][:-4]
PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
formats.extend([
@@ -54,9 +55,12 @@ class RtlXlIE(InfoExtractor):
{
'url': PG_URL_TEMPLATE % ('a3m', video_urlpart),
'format_id': 'pg-hd',
'quality': 0,
}
])
self._sort_formats(formats)
return {
'id': uuid,
'title': '%s - %s' % (progname, subtitle),

View File

@@ -5,6 +5,7 @@ import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from .spiegeltv import SpiegeltvIE
class SpiegelIE(InfoExtractor):
@@ -42,7 +43,11 @@ class SpiegelIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage, handle = self._download_webpage_handle(url, video_id)
# 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html
if SpiegeltvIE.suitable(handle.geturl()):
return self.url_result(handle.geturl(), 'Spiegeltv')
title = re.sub(r'\s+', ' ', self._html_search_regex(
r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)</(?:h1|div)>',

View File

@@ -1,13 +1,13 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import float_or_none
class SpiegeltvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?spiegel\.tv/(?:#/)?filme/(?P<id>[\-a-z0-9]+)'
_TESTS = [{
'url': 'http://www.spiegel.tv/filme/flug-mh370/',
'info_dict': {
'id': 'flug-mh370',
@@ -20,12 +20,15 @@ class SpiegeltvIE(InfoExtractor):
# rtmp download
'skip_download': True,
}
}
}, {
'url': 'http://www.spiegel.tv/#/filme/alleskino-die-wahrheit-ueber-maenner/',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if '/#/' in url:
url = url.replace('/#/', '/')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
@@ -61,12 +64,8 @@ class SpiegeltvIE(InfoExtractor):
})
description = media_json['subtitle']
duration = media_json['duration_in_ms'] / 1000.
if is_wide:
format = '16x9'
else:
format = '4x3'
duration = float_or_none(media_json.get('duration_in_ms'), scale=1000)
format = '16x9' if is_wide else '4x3'
url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'

View File

@@ -307,6 +307,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
'172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
# Dash webm audio with opus inside
'249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
'250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
'251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
# RTMP (unnamed)
'_rtmp': {'protocol': 'rtmp'},
}
@@ -991,7 +996,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
existing_format.update(f)
except (ExtractorError, KeyError) as e:
self.report_warning('Skipping DASH manifest: %s' % e, video_id)
self.report_warning('Skipping DASH manifest: %r' % e, video_id)
self._sort_formats(formats)

View File

@@ -8,6 +8,7 @@ import sys
from .compat import (
compat_expanduser,
compat_getenv,
compat_kwargs,
)
from .utils import (
get_term_width,
@@ -112,7 +113,7 @@ def parseOpts(overrideArguments=None):
'conflict_handler': 'resolve',
}
parser = optparse.OptionParser(**kw)
parser = optparse.OptionParser(**compat_kwargs(kw))
general = optparse.OptionGroup(parser, 'General Options')
general.add_option(

View File

@@ -62,15 +62,17 @@ class _ScopeDict(dict):
class _AVMClass(object):
def __init__(self, name_idx, name):
def __init__(self, name_idx, name, static_properties=None):
self.name_idx = name_idx
self.name = name
self.method_names = {}
self.method_idxs = {}
self.methods = {}
self.method_pyfunctions = {}
self.static_properties = static_properties if static_properties else {}
self.variables = _ScopeDict(self)
self.constants = {}
def make_object(self):
return _AVMClass_Object(self)
@@ -148,8 +150,38 @@ def _read_byte(reader):
return res
StringClass = _AVMClass('(no name idx)', 'String')
ByteArrayClass = _AVMClass('(no name idx)', 'ByteArray')
TimerClass = _AVMClass('(no name idx)', 'Timer')
TimerEventClass = _AVMClass('(no name idx)', 'TimerEvent', {'TIMER': 'timer'})
_builtin_classes = {
StringClass.name: StringClass,
ByteArrayClass.name: ByteArrayClass,
TimerClass.name: TimerClass,
TimerEventClass.name: TimerEventClass,
}
class _Undefined(object):
def __bool__(self):
return False
__nonzero__ = __bool__
def __hash__(self):
return 0
def __str__(self):
return 'undefined'
__repr__ = __str__
undefined = _Undefined()
class SWFInterpreter(object):
def __init__(self, file_contents):
self._patched_functions = {
(TimerClass, 'addEventListener'): lambda params: undefined,
}
code_tag = next(tag
for tag_code, tag in _extract_tags(file_contents)
if tag_code == 82)
@@ -170,11 +202,13 @@ class SWFInterpreter(object):
# Constant pool
int_count = u30()
self.constant_ints = [0]
for _c in range(1, int_count):
s32()
self.constant_ints.append(s32())
self.constant_uints = [0]
uint_count = u30()
for _c in range(1, uint_count):
u32()
self.constant_uints.append(u32())
double_count = u30()
read_bytes(max(0, (double_count - 1)) * 8)
string_count = u30()
@@ -212,6 +246,10 @@ class SWFInterpreter(object):
u30() # namespace_idx
name_idx = u30()
self.multinames.append(self.constant_strings[name_idx])
elif kind == 0x09:
name_idx = u30()
u30()
self.multinames.append(self.constant_strings[name_idx])
else:
self.multinames.append(_Multiname(kind))
for _c2 in range(MULTINAME_SIZES[kind]):
@@ -258,13 +296,28 @@ class SWFInterpreter(object):
kind = kind_full & 0x0f
attrs = kind_full >> 4
methods = {}
if kind in [0x00, 0x06]: # Slot or Const
constants = None
if kind == 0x00: # Slot
u30() # Slot id
u30() # type_name_idx
vindex = u30()
if vindex != 0:
read_byte() # vkind
elif kind in [0x01, 0x02, 0x03]: # Method / Getter / Setter
elif kind == 0x06: # Const
u30() # Slot id
u30() # type_name_idx
vindex = u30()
vkind = 'any'
if vindex != 0:
vkind = read_byte()
if vkind == 0x03: # Constant_Int
value = self.constant_ints[vindex]
elif vkind == 0x04: # Constant_UInt
value = self.constant_uints[vindex]
else:
return {}, None # Ignore silently for now
constants = {self.multinames[trait_name_idx]: value}
elif kind in (0x01, 0x02, 0x03): # Method / Getter / Setter
u30() # disp_id
method_idx = u30()
methods[self.multinames[trait_name_idx]] = method_idx
@@ -283,7 +336,7 @@ class SWFInterpreter(object):
for _c3 in range(metadata_count):
u30() # metadata index
return methods
return methods, constants
# Classes
class_count = u30()
@@ -305,18 +358,22 @@ class SWFInterpreter(object):
u30() # iinit
trait_count = u30()
for _c2 in range(trait_count):
trait_methods = parse_traits_info()
trait_methods, trait_constants = parse_traits_info()
avm_class.register_methods(trait_methods)
if trait_constants:
avm_class.constants.update(trait_constants)
assert len(classes) == class_count
self._classes_by_name = dict((c.name, c) for c in classes)
for avm_class in classes:
u30() # cinit
avm_class.cinit_idx = u30()
trait_count = u30()
for _c2 in range(trait_count):
trait_methods = parse_traits_info()
trait_methods, trait_constants = parse_traits_info()
avm_class.register_methods(trait_methods)
if trait_constants:
avm_class.constants.update(trait_constants)
# Scripts
script_count = u30()
@@ -329,6 +386,7 @@ class SWFInterpreter(object):
# Method bodies
method_body_count = u30()
Method = collections.namedtuple('Method', ['code', 'local_count'])
self._all_methods = []
for _c in range(method_body_count):
method_idx = u30()
u30() # max_stack
@@ -337,9 +395,10 @@ class SWFInterpreter(object):
u30() # max_scope_depth
code_length = u30()
code = read_bytes(code_length)
m = Method(code, local_count)
self._all_methods.append(m)
for avm_class in classes:
if method_idx in avm_class.method_idxs:
m = Method(code, local_count)
avm_class.methods[avm_class.method_idxs[method_idx]] = m
exception_count = u30()
for _c2 in range(exception_count):
@@ -354,13 +413,27 @@ class SWFInterpreter(object):
assert p + code_reader.tell() == len(code_tag)
def extract_class(self, class_name):
def patch_function(self, avm_class, func_name, f):
self._patched_functions[(avm_class, func_name)] = f
def extract_class(self, class_name, call_cinit=True):
try:
return self._classes_by_name[class_name]
res = self._classes_by_name[class_name]
except KeyError:
raise ExtractorError('Class %r not found' % class_name)
if call_cinit and hasattr(res, 'cinit_idx'):
res.register_methods({'$cinit': res.cinit_idx})
res.methods['$cinit'] = self._all_methods[res.cinit_idx]
cinit = self.extract_function(res, '$cinit')
cinit([])
return res
def extract_function(self, avm_class, func_name):
p = self._patched_functions.get((avm_class, func_name))
if p:
return p
if func_name in avm_class.method_pyfunctions:
return avm_class.method_pyfunctions[func_name]
if func_name in self._classes_by_name:
@@ -379,10 +452,15 @@ class SWFInterpreter(object):
registers = [avm_class.variables] + list(args) + [None] * m.local_count
stack = []
scopes = collections.deque([
self._classes_by_name, avm_class.variables])
self._classes_by_name, avm_class.constants, avm_class.variables])
while True:
opcode = _read_byte(coder)
if opcode == 17: # iftrue
if opcode == 9: # label
pass # Spec says: "Do nothing."
elif opcode == 16: # jump
offset = s24()
coder.seek(coder.tell() + offset)
elif opcode == 17: # iftrue
offset = s24()
value = stack.pop()
if value:
@@ -392,9 +470,40 @@ class SWFInterpreter(object):
value = stack.pop()
if not value:
coder.seek(coder.tell() + offset)
elif opcode == 19: # ifeq
offset = s24()
value2 = stack.pop()
value1 = stack.pop()
if value2 == value1:
coder.seek(coder.tell() + offset)
elif opcode == 20: # ifne
offset = s24()
value2 = stack.pop()
value1 = stack.pop()
if value2 != value1:
coder.seek(coder.tell() + offset)
elif opcode == 21: # iflt
offset = s24()
value2 = stack.pop()
value1 = stack.pop()
if value1 < value2:
coder.seek(coder.tell() + offset)
elif opcode == 32: # pushnull
stack.append(None)
elif opcode == 33: # pushundefined
stack.append(undefined)
elif opcode == 36: # pushbyte
v = _read_byte(coder)
stack.append(v)
elif opcode == 37: # pushshort
v = u30()
stack.append(v)
elif opcode == 38: # pushtrue
stack.append(True)
elif opcode == 39: # pushfalse
stack.append(False)
elif opcode == 40: # pushnan
stack.append(float('NaN'))
elif opcode == 42: # dup
value = stack[-1]
stack.append(value)
@@ -419,11 +528,31 @@ class SWFInterpreter(object):
[stack.pop() for _ in range(arg_count)]))
obj = stack.pop()
if isinstance(obj, _AVMClass_Object):
if obj == StringClass:
if mname == 'String':
assert len(args) == 1
assert isinstance(args[0], (
int, compat_str, _Undefined))
if args[0] == undefined:
res = 'undefined'
else:
res = compat_str(args[0])
stack.append(res)
continue
else:
raise NotImplementedError(
'Function String.%s is not yet implemented'
% mname)
elif isinstance(obj, _AVMClass_Object):
func = self.extract_function(obj.avm_class, mname)
res = func(args)
stack.append(res)
continue
elif isinstance(obj, _AVMClass):
func = self.extract_function(obj, mname)
res = func(args)
stack.append(res)
continue
elif isinstance(obj, _ScopeDict):
if mname in obj.avm_class.method_names:
func = self.extract_function(obj.avm_class, mname)
@@ -442,6 +571,13 @@ class SWFInterpreter(object):
res = obj.split(args[0])
stack.append(res)
continue
elif mname == 'charCodeAt':
assert len(args) <= 1
idx = 0 if len(args) == 0 else args[0]
assert isinstance(idx, int)
res = ord(obj[idx])
stack.append(res)
continue
elif isinstance(obj, list):
if mname == 'slice':
assert len(args) == 1
@@ -458,9 +594,18 @@ class SWFInterpreter(object):
raise NotImplementedError(
'Unsupported property %r on %r'
% (mname, obj))
elif opcode == 71: # returnvoid
res = undefined
return res
elif opcode == 72: # returnvalue
res = stack.pop()
return res
elif opcode == 73: # constructsuper
# Not yet implemented, just hope it works without it
arg_count = u30()
args = list(reversed(
[stack.pop() for _ in range(arg_count)]))
obj = stack.pop()
elif opcode == 74: # constructproperty
index = u30()
arg_count = u30()
@@ -481,6 +626,17 @@ class SWFInterpreter(object):
args = list(reversed(
[stack.pop() for _ in range(arg_count)]))
obj = stack.pop()
if isinstance(obj, _AVMClass_Object):
func = self.extract_function(obj.avm_class, mname)
res = func(args)
assert res is undefined
continue
if isinstance(obj, _ScopeDict):
assert mname in obj.avm_class.method_names
func = self.extract_function(obj.avm_class, mname)
res = func(args)
assert res is undefined
continue
if mname == 'reverse':
assert isinstance(obj, list)
obj.reverse()
@@ -504,7 +660,10 @@ class SWFInterpreter(object):
break
else:
res = scopes[0]
stack.append(res[mname])
if mname not in res and mname in _builtin_classes:
stack.append(_builtin_classes[mname])
else:
stack.append(res[mname])
elif opcode == 94: # findproperty
index = u30()
mname = self.multinames[index]
@@ -524,9 +683,15 @@ class SWFInterpreter(object):
break
else:
scope = avm_class.variables
# I cannot find where static variables are initialized
# so let's just return None
res = scope.get(mname)
if mname in scope:
res = scope[mname]
elif mname in _builtin_classes:
res = _builtin_classes[mname]
else:
# Assume unitialized
# TODO warn here
res = undefined
stack.append(res)
elif opcode == 97: # setproperty
index = u30()
@@ -548,22 +713,57 @@ class SWFInterpreter(object):
pname = self.multinames[index]
if pname == 'length':
obj = stack.pop()
assert isinstance(obj, list)
assert isinstance(obj, (compat_str, list))
stack.append(len(obj))
elif isinstance(pname, compat_str): # Member access
obj = stack.pop()
if isinstance(obj, _AVMClass):
res = obj.static_properties[pname]
stack.append(res)
continue
assert isinstance(obj, (dict, _ScopeDict)),\
'Accessing member %r on %r' % (pname, obj)
res = obj.get(pname, undefined)
stack.append(res)
else: # Assume attribute access
idx = stack.pop()
assert isinstance(idx, int)
obj = stack.pop()
assert isinstance(obj, list)
stack.append(obj[idx])
elif opcode == 104: # initproperty
index = u30()
value = stack.pop()
idx = self.multinames[index]
if isinstance(idx, _Multiname):
idx = stack.pop()
obj = stack.pop()
obj[idx] = value
elif opcode == 115: # convert_
value = stack.pop()
intvalue = int(value)
stack.append(intvalue)
elif opcode == 128: # coerce
u30()
elif opcode == 130: # coerce_a
value = stack.pop()
# um, yes, it's any value
stack.append(value)
elif opcode == 133: # coerce_s
assert isinstance(stack[-1], (type(None), compat_str))
elif opcode == 147: # decrement
value = stack.pop()
assert isinstance(value, int)
stack.append(value - 1)
elif opcode == 149: # typeof
value = stack.pop()
return {
_Undefined: 'undefined',
compat_str: 'String',
int: 'Number',
float: 'Number',
}[type(value)]
elif opcode == 160: # add
value2 = stack.pop()
value1 = stack.pop()
@@ -574,16 +774,37 @@ class SWFInterpreter(object):
value1 = stack.pop()
res = value1 - value2
stack.append(res)
elif opcode == 162: # multiply
value2 = stack.pop()
value1 = stack.pop()
res = value1 * value2
stack.append(res)
elif opcode == 164: # modulo
value2 = stack.pop()
value1 = stack.pop()
res = value1 % value2
stack.append(res)
elif opcode == 168: # bitand
value2 = stack.pop()
value1 = stack.pop()
assert isinstance(value1, int)
assert isinstance(value2, int)
res = value1 & value2
stack.append(res)
elif opcode == 171: # equals
value2 = stack.pop()
value1 = stack.pop()
result = value1 == value2
stack.append(result)
elif opcode == 175: # greaterequals
value2 = stack.pop()
value1 = stack.pop()
result = value1 >= value2
stack.append(result)
elif opcode == 192: # increment_i
value = stack.pop()
assert isinstance(value, int)
stack.append(value + 1)
elif opcode == 208: # getlocal_0
stack.append(registers[0])
elif opcode == 209: # getlocal_1

View File

@@ -63,7 +63,7 @@ def preferredencoding():
"""
try:
pref = locale.getpreferredencoding()
u'TEST'.encode(pref)
'TEST'.encode(pref)
except:
pref = 'UTF-8'
@@ -71,12 +71,25 @@ def preferredencoding():
def write_json_file(obj, fn):
""" Encode obj as JSON and write it to fn, atomically """
""" Encode obj as JSON and write it to fn, atomically if possible """
fn = encodeFilename(fn)
if sys.version_info < (3, 0) and sys.platform != 'win32':
encoding = get_filesystem_encoding()
# os.path.basename returns a bytes object, but NamedTemporaryFile
# will fail if the filename contains non ascii characters unless we
# use a unicode object
path_basename = lambda f: os.path.basename(fn).decode(encoding)
# the same for os.path.dirname
path_dirname = lambda f: os.path.dirname(fn).decode(encoding)
else:
path_basename = os.path.basename
path_dirname = os.path.dirname
args = {
'suffix': '.tmp',
'prefix': os.path.basename(fn) + '.',
'dir': os.path.dirname(fn),
'prefix': path_basename(fn) + '.',
'dir': path_dirname(fn),
'delete': False,
}
@@ -95,6 +108,13 @@ def write_json_file(obj, fn):
try:
with tf:
json.dump(obj, tf)
if sys.platform == 'win32':
# Need to remove existing file on Windows, else os.rename raises
# WindowsError or FileExistsError.
try:
os.unlink(fn)
except OSError:
pass
os.rename(tf.name, fn)
except:
try:
@@ -203,7 +223,7 @@ def sanitize_open(filename, open_mode):
It returns the tuple (stream, definitive_file_name).
"""
try:
if filename == u'-':
if filename == '-':
if sys.platform == 'win32':
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
@@ -216,7 +236,7 @@ def sanitize_open(filename, open_mode):
# In case of error, try to remove win32 forbidden chars
alt_filename = os.path.join(
re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', path_part)
re.sub('[/<>:"\\|\\\\?\\*]', '#', path_part)
for path_part in os.path.split(filename)
)
if alt_filename == filename:
@@ -255,7 +275,7 @@ def sanitize_filename(s, restricted=False, is_id=False):
return '_'
return char
result = u''.join(map(replace_insane, s))
result = ''.join(map(replace_insane, s))
if not is_id:
while '__' in result:
result = result.replace('__', '_')
@@ -285,15 +305,15 @@ def _htmlentity_transform(entity):
mobj = re.match(r'#(x?[0-9]+)', entity)
if mobj is not None:
numstr = mobj.group(1)
if numstr.startswith(u'x'):
if numstr.startswith('x'):
base = 16
numstr = u'0%s' % numstr
numstr = '0%s' % numstr
else:
base = 10
return compat_chr(int(numstr, base))
# Unknown entity in name, return its literal representation
return (u'&%s;' % entity)
return ('&%s;' % entity)
def unescapeHTML(s):
@@ -317,7 +337,7 @@ def encodeFilename(s, for_subprocess=False):
return s
if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
# Pass u'' directly to use Unicode APIs on Windows 2000 and up
# Pass '' directly to use Unicode APIs on Windows 2000 and up
# (Detecting Windows NT 4 is tricky because 'major >= 4' would
# match Windows 9x series as well. Besides, NT 4 is obsolete.)
if not for_subprocess:
@@ -412,9 +432,9 @@ class ExtractorError(Exception):
if video_id is not None:
msg = video_id + ': ' + msg
if cause:
msg += u' (caused by %r)' % cause
msg += ' (caused by %r)' % cause
if not expected:
msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output. Make sure you are using the latest version; type youtube-dl -U to update.'
msg = msg + '; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output. Make sure you are using the latest version; type youtube-dl -U to update.'
super(ExtractorError, self).__init__(msg)
self.traceback = tb
@@ -425,7 +445,7 @@ class ExtractorError(Exception):
def format_traceback(self):
if self.traceback is None:
return None
return u''.join(traceback.format_tb(self.traceback))
return ''.join(traceback.format_tb(self.traceback))
class RegexNotFoundError(ExtractorError):
@@ -653,17 +673,17 @@ def unified_strdate(date_str):
upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
return upload_date
def determine_ext(url, default_ext=u'unknown_video'):
def determine_ext(url, default_ext='unknown_video'):
if url is None:
return default_ext
guess = url.partition(u'?')[0].rpartition(u'.')[2]
guess = url.partition('?')[0].rpartition('.')[2]
if re.match(r'^[A-Za-z0-9]+$', guess):
return guess
else:
return default_ext
def subtitles_filename(filename, sub_lang, sub_format):
return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format
def date_from_str(date_str):
"""
@@ -955,7 +975,7 @@ def shell_quote(args):
# We may get a filename encoded with 'encodeFilename'
a = a.decode(encoding)
quoted_args.append(pipes.quote(a))
return u' '.join(quoted_args)
return ' '.join(quoted_args)
def takewhile_inclusive(pred, seq):
@@ -971,31 +991,31 @@ def smuggle_url(url, data):
""" Pass additional data in a URL for internal use. """
sdata = compat_urllib_parse.urlencode(
{u'__youtubedl_smuggle': json.dumps(data)})
return url + u'#' + sdata
{'__youtubedl_smuggle': json.dumps(data)})
return url + '#' + sdata
def unsmuggle_url(smug_url, default=None):
if not '#__youtubedl_smuggle' in smug_url:
return smug_url, default
url, _, sdata = smug_url.rpartition(u'#')
jsond = compat_parse_qs(sdata)[u'__youtubedl_smuggle'][0]
url, _, sdata = smug_url.rpartition('#')
jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0]
data = json.loads(jsond)
return url, data
def format_bytes(bytes):
if bytes is None:
return u'N/A'
return 'N/A'
if type(bytes) is str:
bytes = float(bytes)
if bytes == 0.0:
exponent = 0
else:
exponent = int(math.log(bytes, 1024.0))
suffix = [u'B', u'KiB', u'MiB', u'GiB', u'TiB', u'PiB', u'EiB', u'ZiB', u'YiB'][exponent]
suffix = ['B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB', 'EiB', 'ZiB', 'YiB'][exponent]
converted = float(bytes) / float(1024 ** exponent)
return u'%.2f%s' % (converted, suffix)
return '%.2f%s' % (converted, suffix)
def get_term_width():
@@ -1018,8 +1038,8 @@ def month_by_name(name):
""" Return the number of a month by (locale-independently) English name """
ENGLISH_NAMES = [
u'January', u'February', u'March', u'April', u'May', u'June',
u'July', u'August', u'September', u'October', u'November', u'December']
'January', 'February', 'March', 'April', 'May', 'June',
'July', 'August', 'September', 'October', 'November', 'December']
try:
return ENGLISH_NAMES.index(name) + 1
except ValueError:
@@ -1030,7 +1050,7 @@ def fix_xml_ampersands(xml_str):
"""Replace all the '&' by '&amp;' in XML"""
return re.sub(
r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)',
u'&amp;',
'&amp;',
xml_str)
@@ -1063,7 +1083,7 @@ def remove_end(s, end):
def url_basename(url):
path = compat_urlparse.urlparse(url).path
return path.strip(u'/').split(u'/')[-1]
return path.strip('/').split('/')[-1]
class HEADRequest(compat_urllib_request.Request):
@@ -1088,7 +1108,7 @@ def str_to_int(int_str):
""" A more relaxed version of int_or_none """
if int_str is None:
return None
int_str = re.sub(r'[,\.\+]', u'', int_str)
int_str = re.sub(r'[,\.\+]', '', int_str)
return int(int_str)
@@ -1103,7 +1123,12 @@ def parse_duration(s):
s = s.strip()
m = re.match(
r'(?i)(?:(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s)
r'''(?ix)T?
(?:
(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?
(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*
)?
(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$''', s)
if not m:
return None
res = int(m.group('secs'))
@@ -1118,7 +1143,7 @@ def parse_duration(s):
def prepend_extension(filename, ext):
name, real_ext = os.path.splitext(filename)
return u'{0}.{1}{2}'.format(name, ext, real_ext)
return '{0}.{1}{2}'.format(name, ext, real_ext)
def check_executable(exe, args=[]):
@@ -1133,7 +1158,7 @@ def check_executable(exe, args=[]):
def get_exe_version(exe, args=['--version'],
version_re=r'version\s+([0-9._-a-zA-Z]+)',
unrecognized=u'present'):
unrecognized='present'):
""" Returns the version of the specified executable,
or False if the executable is not present """
try:
@@ -1254,7 +1279,7 @@ def escape_url(url):
).geturl()
try:
struct.pack(u'!I', 0)
struct.pack('!I', 0)
except TypeError:
# In Python 2.6 (and some 2.7 versions), struct requires a bytes argument
def struct_pack(spec, *args):
@@ -1275,7 +1300,7 @@ def read_batch_urls(batch_fd):
def fixup(url):
if not isinstance(url, compat_str):
url = url.decode('utf-8', 'replace')
BOM_UTF8 = u'\xef\xbb\xbf'
BOM_UTF8 = '\xef\xbb\xbf'
if url.startswith(BOM_UTF8):
url = url[len(BOM_UTF8):]
url = url.strip()

View File

@@ -1,2 +1,2 @@
__version__ = '2014.11.14'
__version__ = '2014.11.20'