Merge remote-tracking branch 'jtwaleson/master'

pull/8/head
Philipp Hagemeister 10 years ago
commit 784b6d3a9b

@ -9,16 +9,17 @@ import youtube_dl
BASH_COMPLETION_FILE = "youtube-dl.bash-completion" BASH_COMPLETION_FILE = "youtube-dl.bash-completion"
BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in" BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
def build_completion(opt_parser): def build_completion(opt_parser):
opts_flag = [] opts_flag = []
for group in opt_parser.option_groups: for group in opt_parser.option_groups:
for option in group.option_list: for option in group.option_list:
#for every long flag # for every long flag
opts_flag.append(option.get_opt_string()) opts_flag.append(option.get_opt_string())
with open(BASH_COMPLETION_TEMPLATE) as f: with open(BASH_COMPLETION_TEMPLATE) as f:
template = f.read() template = f.read()
with open(BASH_COMPLETION_FILE, "w") as f: with open(BASH_COMPLETION_FILE, "w") as f:
#just using the special char # just using the special char
filled_template = template.replace("{{flags}}", " ".join(opts_flag)) filled_template = template.replace("{{flags}}", " ".join(opts_flag))
f.write(filled_template) f.write(filled_template)

@ -233,6 +233,7 @@ def rmtree(path):
#============================================================================== #==============================================================================
class BuildError(Exception): class BuildError(Exception):
def __init__(self, output, code=500): def __init__(self, output, code=500):
self.output = output self.output = output
@ -369,7 +370,7 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea
class BuildHTTPRequestHandler(BaseHTTPRequestHandler): class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
actionDict = { 'build': Builder, 'download': Builder } # They're the same, no more caching. actionDict = {'build': Builder, 'download': Builder} # They're the same, no more caching.
def do_GET(self): def do_GET(self):
path = urlparse.urlparse(self.path) path = urlparse.urlparse(self.path)

@ -23,6 +23,7 @@ EXTRA_ARGS = {
'batch-file': ['--require-parameter'], 'batch-file': ['--require-parameter'],
} }
def build_completion(opt_parser): def build_completion(opt_parser):
commands = [] commands = []

@ -1,8 +1,5 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
import hashlib import hashlib
import shutil
import subprocess
import tempfile
import urllib.request import urllib.request
import json import json

@ -11,18 +11,18 @@ except NameError:
versions_info = json.load(open('update/versions.json')) versions_info = json.load(open('update/versions.json'))
if 'signature' in versions_info: if 'signature' in versions_info:
del versions_info['signature'] del versions_info['signature']
print('Enter the PKCS1 private key, followed by a blank line:') print('Enter the PKCS1 private key, followed by a blank line:')
privkey = b'' privkey = b''
while True: while True:
try: try:
line = input() line = input()
except EOFError: except EOFError:
break break
if line == '': if line == '':
break break
privkey += line.encode('ascii') + b'\n' privkey += line.encode('ascii') + b'\n'
privkey = rsa.PrivateKey.load_pkcs1(privkey) privkey = rsa.PrivateKey.load_pkcs1(privkey)
signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).encode('utf-8'), privkey, 'SHA-256')).decode() signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).encode('utf-8'), privkey, 'SHA-256')).decode()

@ -5,7 +5,7 @@ from __future__ import with_statement
import datetime import datetime
import glob import glob
import io # For Python 2 compatibilty import io # For Python 2 compatibilty
import os import os
import re import re

@ -73,4 +73,3 @@ atom_template = atom_template.replace('@ENTRIES@', entries_str)
with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file: with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file:
atom_file.write(atom_template) atom_file.write(atom_template)

@ -9,6 +9,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(
import youtube_dl import youtube_dl
def main(): def main():
with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf: with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf:
template = tmplf.read() template = tmplf.read()

@ -4,7 +4,7 @@ import sys, os
try: try:
import urllib.request as compat_urllib_request import urllib.request as compat_urllib_request
except ImportError: # Python 2 except ImportError: # Python 2
import urllib2 as compat_urllib_request import urllib2 as compat_urllib_request
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n') sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
@ -12,9 +12,9 @@ sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorr
sys.stderr.write(u'The new location of the binaries is https://github.com/rg3/youtube-dl/downloads, not the git repository.\n\n') sys.stderr.write(u'The new location of the binaries is https://github.com/rg3/youtube-dl/downloads, not the git repository.\n\n')
try: try:
raw_input() raw_input()
except NameError: # Python 3 except NameError: # Python 3
input() input()
filename = sys.argv[0] filename = sys.argv[0]

@ -9,4 +9,4 @@ py2exe_options = {
"dll_excludes": ['w9xpopen.exe'] "dll_excludes": ['w9xpopen.exe']
} }
setup(console=['youtube-dl.py'], options={ "py2exe": py2exe_options }, zipfile=None) setup(console=['youtube-dl.py'], options={"py2exe": py2exe_options}, zipfile=None)

@ -4,13 +4,17 @@ import sys, os
import urllib2 import urllib2
import json, hashlib import json, hashlib
def rsa_verify(message, signature, key): def rsa_verify(message, signature, key):
from struct import pack from struct import pack
from hashlib import sha256 from hashlib import sha256
from sys import version_info from sys import version_info
def b(x): def b(x):
if version_info[0] == 2: return x if version_info[0] == 2:
else: return x.encode('latin1') return x
else:
return x.encode('latin1')
assert(type(message) == type(b(''))) assert(type(message) == type(b('')))
block_size = 0 block_size = 0
n = key[0] n = key[0]
@ -23,13 +27,17 @@ def rsa_verify(message, signature, key):
raw_bytes.insert(0, pack("B", signature & 0xFF)) raw_bytes.insert(0, pack("B", signature & 0xFF))
signature >>= 8 signature >>= 8
signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes) signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
if signature[0:2] != b('\x00\x01'): return False if signature[0:2] != b('\x00\x01'):
return False
signature = signature[2:] signature = signature[2:]
if not b('\x00') in signature: return False if not b('\x00') in signature:
signature = signature[signature.index(b('\x00'))+1:] return False
if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False signature = signature[signature.index(b('\x00')) + 1:]
if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')):
return False
signature = signature[19:] signature = signature[19:]
if signature != sha256(message).digest(): return False if signature != sha256(message).digest():
return False
return True return True
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n') sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
@ -92,7 +100,7 @@ echo Updating youtube-dl...
ping 127.0.0.1 -n 5 -w 1000 > NUL ping 127.0.0.1 -n 5 -w 1000 > NUL
move /Y "%s.new" "%s" move /Y "%s.new" "%s"
del "%s" del "%s"
\n""" %(exe, exe, bat)) \n""" % (exe, exe, bat))
b.close() b.close()
os.startfile(bat) os.startfile(bat)

@ -72,8 +72,10 @@ class FakeYDL(YoutubeDL):
def expect_warning(self, regex): def expect_warning(self, regex):
# Silence an expected warning matching a regex # Silence an expected warning matching a regex
old_report_warning = self.report_warning old_report_warning = self.report_warning
def report_warning(self, message): def report_warning(self, message):
if re.match(regex, message): return if re.match(regex, message):
return
old_report_warning(message) old_report_warning(message)
self.report_warning = types.MethodType(report_warning, self) self.report_warning = types.MethodType(report_warning, self)

@ -266,6 +266,7 @@ class TestFormatSelection(unittest.TestCase):
'ext': 'mp4', 'ext': 'mp4',
'width': None, 'width': None,
} }
def fname(templ): def fname(templ):
ydl = YoutubeDL({'outtmpl': templ}) ydl = YoutubeDL({'outtmpl': templ})
return ydl.prepare_filename(info) return ydl.prepare_filename(info)

@ -32,19 +32,19 @@ class TestAllURLsMatching(unittest.TestCase):
def test_youtube_playlist_matching(self): def test_youtube_playlist_matching(self):
assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist']) assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') #585 assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585
assertPlaylist('PL63F0C78739B09958') assertPlaylist('PL63F0C78739B09958')
assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q') assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668 assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668
self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M')) self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
# Top tracks # Top tracks
assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101') assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
def test_youtube_matching(self): def test_youtube_matching(self):
self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M')) self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668 self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) # 668
self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube']) self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube']) self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube']) self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])

@ -40,18 +40,22 @@ from youtube_dl.extractor import get_info_extractor
RETRIES = 3 RETRIES = 3
class YoutubeDL(youtube_dl.YoutubeDL): class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
self.to_stderr = self.to_screen self.to_stderr = self.to_screen
self.processed_info_dicts = [] self.processed_info_dicts = []
super(YoutubeDL, self).__init__(*args, **kwargs) super(YoutubeDL, self).__init__(*args, **kwargs)
def report_warning(self, message): def report_warning(self, message):
# Don't accept warnings during tests # Don't accept warnings during tests
raise ExtractorError(message) raise ExtractorError(message)
def process_info(self, info_dict): def process_info(self, info_dict):
self.processed_info_dicts.append(info_dict) self.processed_info_dicts.append(info_dict)
return super(YoutubeDL, self).process_info(info_dict) return super(YoutubeDL, self).process_info(info_dict)
def _file_md5(fn): def _file_md5(fn):
with open(fn, 'rb') as f: with open(fn, 'rb') as f:
return hashlib.md5(f.read()).hexdigest() return hashlib.md5(f.read()).hexdigest()
@ -61,10 +65,13 @@ defs = gettestcases()
class TestDownload(unittest.TestCase): class TestDownload(unittest.TestCase):
maxDiff = None maxDiff = None
def setUp(self): def setUp(self):
self.defs = defs self.defs = defs
### Dynamically generate tests # Dynamically generate tests
def generator(test_case): def generator(test_case):
def test_template(self): def test_template(self):
@ -101,6 +108,7 @@ def generator(test_case):
ydl = YoutubeDL(params, auto_init=False) ydl = YoutubeDL(params, auto_init=False)
ydl.add_default_info_extractors() ydl.add_default_info_extractors()
finished_hook_called = set() finished_hook_called = set()
def _hook(status): def _hook(status):
if status['status'] == 'finished': if status['status'] == 'finished':
finished_hook_called.add(status['filename']) finished_hook_called.add(status['filename'])
@ -111,6 +119,7 @@ def generator(test_case):
return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {})) return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
res_dict = None res_dict = None
def try_rm_tcs_files(tcs=None): def try_rm_tcs_files(tcs=None):
if tcs is None: if tcs is None:
tcs = test_cases tcs = test_cases
@ -206,7 +215,7 @@ def generator(test_case):
return test_template return test_template
### And add them to TestDownload # And add them to TestDownload
for n, test_case in enumerate(defs): for n, test_case in enumerate(defs):
test_method = generator(test_case) test_method = generator(test_case)
tname = 'test_' + str(test_case['name']) tname = 'test_' + str(test_case['name'])

@ -23,6 +23,7 @@ from youtube_dl.extractor import (
class BaseTestSubtitles(unittest.TestCase): class BaseTestSubtitles(unittest.TestCase):
url = None url = None
IE = None IE = None
def setUp(self): def setUp(self):
self.DL = FakeYDL() self.DL = FakeYDL()
self.ie = self.IE(self.DL) self.ie = self.IE(self.DL)

@ -45,7 +45,6 @@ from youtube_dl.utils import (
escape_rfc3986, escape_rfc3986,
escape_url, escape_url,
js_to_json, js_to_json,
get_filesystem_encoding,
intlist_to_bytes, intlist_to_bytes,
args_to_str, args_to_str,
) )
@ -120,7 +119,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7]) self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
self.assertEqual(orderedSet([]), []) self.assertEqual(orderedSet([]), [])
self.assertEqual(orderedSet([1]), [1]) self.assertEqual(orderedSet([1]), [1])
#keep the list ordered # keep the list ordered
self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1]) self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
def test_unescape_html(self): def test_unescape_html(self):
@ -129,7 +128,7 @@ class TestUtil(unittest.TestCase):
unescapeHTML('é'), 'é') unescapeHTML('é'), 'é')
def test_daterange(self): def test_daterange(self):
_20century = DateRange("19000101","20000101") _20century = DateRange("19000101", "20000101")
self.assertFalse("17890714" in _20century) self.assertFalse("17890714" in _20century)
_ac = DateRange("00010101") _ac = DateRange("00010101")
self.assertTrue("19690721" in _ac) self.assertTrue("19690721" in _ac)

@ -31,19 +31,18 @@ params = get_params({
}) })
TEST_ID = 'gr51aVj-mLg' TEST_ID = 'gr51aVj-mLg'
ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml' ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label'] EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
class TestAnnotations(unittest.TestCase): class TestAnnotations(unittest.TestCase):
def setUp(self): def setUp(self):
# Clear old files # Clear old files
self.tearDown() self.tearDown()
def test_info_json(self): def test_info_json(self):
expected = list(EXPECTED_ANNOTATIONS) #Two annotations could have the same text. expected = list(EXPECTED_ANNOTATIONS) # Two annotations could have the same text.
ie = youtube_dl.extractor.YoutubeIE() ie = youtube_dl.extractor.YoutubeIE()
ydl = YoutubeDL(params) ydl = YoutubeDL(params)
ydl.add_info_extractor(ie) ydl.add_info_extractor(ie)
@ -51,7 +50,7 @@ class TestAnnotations(unittest.TestCase):
self.assertTrue(os.path.exists(ANNOTATIONS_FILE)) self.assertTrue(os.path.exists(ANNOTATIONS_FILE))
annoxml = None annoxml = None
with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof: with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
annoxml = xml.etree.ElementTree.parse(annof) annoxml = xml.etree.ElementTree.parse(annof)
self.assertTrue(annoxml is not None, 'Failed to parse annotations XML') self.assertTrue(annoxml is not None, 'Failed to parse annotations XML')
root = annoxml.getroot() root = annoxml.getroot()
self.assertEqual(root.tag, 'document') self.assertEqual(root.tag, 'document')
@ -59,19 +58,18 @@ class TestAnnotations(unittest.TestCase):
self.assertEqual(annotationsTag.tag, 'annotations') self.assertEqual(annotationsTag.tag, 'annotations')
annotations = annotationsTag.findall('annotation') annotations = annotationsTag.findall('annotation')
#Not all the annotations have TEXT children and the annotations are returned unsorted. # Not all the annotations have TEXT children and the annotations are returned unsorted.
for a in annotations: for a in annotations:
self.assertEqual(a.tag, 'annotation') self.assertEqual(a.tag, 'annotation')
if a.get('type') == 'text': if a.get('type') == 'text':
textTag = a.find('TEXT') textTag = a.find('TEXT')
text = textTag.text text = textTag.text
self.assertTrue(text in expected) #assertIn only added in python 2.7 self.assertTrue(text in expected) # assertIn only added in python 2.7
#remove the first occurance, there could be more than one annotation with the same text # remove the first occurance, there could be more than one annotation with the same text
expected.remove(text) expected.remove(text)
#We should have seen (and removed) all the expected annotation texts. # We should have seen (and removed) all the expected annotation texts.
self.assertEqual(len(expected), 0, 'Not all expected annotations were found.') self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')
def tearDown(self): def tearDown(self):
try_rm(ANNOTATIONS_FILE) try_rm(ANNOTATIONS_FILE)

@ -12,10 +12,6 @@ from test.helper import FakeYDL
from youtube_dl.extractor import ( from youtube_dl.extractor import (
YoutubePlaylistIE, YoutubePlaylistIE,
YoutubeIE, YoutubeIE,
YoutubeChannelIE,
YoutubeShowIE,
YoutubeTopListIE,
YoutubeSearchURLIE,
) )

@ -29,7 +29,6 @@ from .compat import (
compat_str, compat_str,
compat_urllib_error, compat_urllib_error,
compat_urllib_request, compat_urllib_request,
shlex_quote,
) )
from .utils import ( from .utils import (
escape_url, escape_url,
@ -552,7 +551,7 @@ class YoutubeDL(object):
try: try:
ie_result = ie.extract(url) ie_result = ie.extract(url)
if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
break break
if isinstance(ie_result, list): if isinstance(ie_result, list):
# Backwards compatibility: old IE result format # Backwards compatibility: old IE result format
@ -565,7 +564,7 @@ class YoutubeDL(object):
return self.process_ie_result(ie_result, download, extra_info) return self.process_ie_result(ie_result, download, extra_info)
else: else:
return ie_result return ie_result
except ExtractorError as de: # An error we somewhat expected except ExtractorError as de: # An error we somewhat expected
self.report_error(compat_str(de), de.format_traceback()) self.report_error(compat_str(de), de.format_traceback())
break break
except MaxDownloadsReached: except MaxDownloadsReached:
@ -700,6 +699,7 @@ class YoutubeDL(object):
self.report_warning( self.report_warning(
'Extractor %s returned a compat_list result. ' 'Extractor %s returned a compat_list result. '
'It needs to be updated.' % ie_result.get('extractor')) 'It needs to be updated.' % ie_result.get('extractor'))
def _fixup(r): def _fixup(r):
self.add_extra_info(r, self.add_extra_info(r,
{ {
@ -1010,7 +1010,7 @@ class YoutubeDL(object):
else: else:
self.to_screen('[info] Writing video subtitles to: ' + sub_filename) self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
subfile.write(sub) subfile.write(sub)
except (OSError, IOError): except (OSError, IOError):
self.report_error('Cannot write subtitles file ' + sub_filename) self.report_error('Cannot write subtitles file ' + sub_filename)
return return
@ -1111,7 +1111,7 @@ class YoutubeDL(object):
for url in url_list: for url in url_list:
try: try:
#It also downloads the videos # It also downloads the videos
res = self.extract_info(url) res = self.extract_info(url)
except UnavailableVideoError: except UnavailableVideoError:
self.report_error('unable to download video') self.report_error('unable to download video')
@ -1428,4 +1428,3 @@ class YoutubeDL(object):
if encoding is None: if encoding is None:
encoding = preferredencoding() encoding = preferredencoding()
return encoding return encoding

@ -76,10 +76,10 @@ def _real_main(argv=None):
if opts.headers is not None: if opts.headers is not None:
for h in opts.headers: for h in opts.headers:
if h.find(':', 1) < 0: if h.find(':', 1) < 0:
parser.error('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) key, value = h.split(':', 2)
if opts.verbose: if opts.verbose:
write_string('[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 std_headers[key] = value
# Dump user agent # Dump user agent
@ -128,7 +128,6 @@ def _real_main(argv=None):
compat_print(desc) compat_print(desc)
sys.exit(0) sys.exit(0)
# Conflicting, missing and erroneous options # Conflicting, missing and erroneous options
if opts.usenetrc and (opts.username is not None or opts.password is not None): if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error('using .netrc conflicts with giving username/password') parser.error('using .netrc conflicts with giving username/password')
@ -197,14 +196,14 @@ def _real_main(argv=None):
# In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems) # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
if opts.outtmpl is not None: if opts.outtmpl is not None:
opts.outtmpl = opts.outtmpl.decode(preferredencoding()) opts.outtmpl = opts.outtmpl.decode(preferredencoding())
outtmpl =((opts.outtmpl is not None and opts.outtmpl) outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)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.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 opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
or (opts.usetitle and '%(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.useid and '%(id)s.%(ext)s')
or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
or DEFAULT_OUTTMPL) or DEFAULT_OUTTMPL)
if not os.path.splitext(outtmpl)[1] and opts.extractaudio: if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error('Cannot download a video and extract audio into the same' parser.error('Cannot download a video and extract audio into the same'
' file! Use "{0}.%(ext)s" instead of "{0}" as the output' ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
@ -317,7 +316,6 @@ def _real_main(argv=None):
ydl.add_post_processor(FFmpegAudioFixPP()) ydl.add_post_processor(FFmpegAudioFixPP())
ydl.add_post_processor(AtomicParsleyPP()) ydl.add_post_processor(AtomicParsleyPP())
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way. # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems. # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd: if opts.exec_cmd:

@ -7,6 +7,7 @@ from .utils import bytes_to_intlist, intlist_to_bytes
BLOCK_SIZE_BYTES = 16 BLOCK_SIZE_BYTES = 16
def aes_ctr_decrypt(data, key, counter): def aes_ctr_decrypt(data, key, counter):
""" """
Decrypt with aes in counter mode Decrypt with aes in counter mode
@ -20,11 +21,11 @@ def aes_ctr_decrypt(data, key, counter):
expanded_key = key_expansion(key) expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES)) block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
decrypted_data=[] decrypted_data = []
for i in range(block_count): for i in range(block_count):
counter_block = counter.next_value() counter_block = counter.next_value()
block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES] block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
block += [0]*(BLOCK_SIZE_BYTES - len(block)) block += [0] * (BLOCK_SIZE_BYTES - len(block))
cipher_counter_block = aes_encrypt(counter_block, expanded_key) cipher_counter_block = aes_encrypt(counter_block, expanded_key)
decrypted_data += xor(block, cipher_counter_block) decrypted_data += xor(block, cipher_counter_block)
@ -32,6 +33,7 @@ def aes_ctr_decrypt(data, key, counter):
return decrypted_data return decrypted_data
def aes_cbc_decrypt(data, key, iv): def aes_cbc_decrypt(data, key, iv):
""" """
Decrypt with aes in CBC mode Decrypt with aes in CBC mode
@ -44,11 +46,11 @@ def aes_cbc_decrypt(data, key, iv):
expanded_key = key_expansion(key) expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES)) block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
decrypted_data=[] decrypted_data = []
previous_cipher_block = iv previous_cipher_block = iv
for i in range(block_count): for i in range(block_count):
block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES] block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
block += [0]*(BLOCK_SIZE_BYTES - len(block)) block += [0] * (BLOCK_SIZE_BYTES - len(block))
decrypted_block = aes_decrypt(block, expanded_key) decrypted_block = aes_decrypt(block, expanded_key)
decrypted_data += xor(decrypted_block, previous_cipher_block) decrypted_data += xor(decrypted_block, previous_cipher_block)
@ -57,6 +59,7 @@ def aes_cbc_decrypt(data, key, iv):
return decrypted_data return decrypted_data
def key_expansion(data): def key_expansion(data):
""" """
Generate key schedule Generate key schedule
@ -64,7 +67,7 @@ def key_expansion(data):
@param {int[]} data 16/24/32-Byte cipher key @param {int[]} data 16/24/32-Byte cipher key
@returns {int[]} 176/208/240-Byte expanded key @returns {int[]} 176/208/240-Byte expanded key
""" """
data = data[:] # copy data = data[:] # copy
rcon_iteration = 1 rcon_iteration = 1
key_size_bytes = len(data) key_size_bytes = len(data)
expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES
@ -73,24 +76,25 @@ def key_expansion(data):
temp = data[-4:] temp = data[-4:]
temp = key_schedule_core(temp, rcon_iteration) temp = key_schedule_core(temp, rcon_iteration)
rcon_iteration += 1 rcon_iteration += 1
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
for _ in range(3): for _ in range(3):
temp = data[-4:] temp = data[-4:]
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
if key_size_bytes == 32: if key_size_bytes == 32:
temp = data[-4:] temp = data[-4:]
temp = sub_bytes(temp) temp = sub_bytes(temp)
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0): for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0):
temp = data[-4:] temp = data[-4:]
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
data = data[:expanded_key_size_bytes] data = data[:expanded_key_size_bytes]
return data return data
def aes_encrypt(data, expanded_key): def aes_encrypt(data, expanded_key):
""" """
Encrypt one block with aes Encrypt one block with aes
@ -102,15 +106,16 @@ def aes_encrypt(data, expanded_key):
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1 rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES]) data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
for i in range(1, rounds+1): for i in range(1, rounds + 1):
data = sub_bytes(data) data = sub_bytes(data)
data = shift_rows(data) data = shift_rows(data)
if i != rounds: if i != rounds:
data = mix_columns(data) data = mix_columns(data)
data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]) data = xor(data, expanded_key[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES])
return data return data
def aes_decrypt(data, expanded_key): def aes_decrypt(data, expanded_key):
""" """
Decrypt one block with aes Decrypt one block with aes
@ -122,7 +127,7 @@ def aes_decrypt(data, expanded_key):
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1 rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
for i in range(rounds, 0, -1): for i in range(rounds, 0, -1):
data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]) data = xor(data, expanded_key[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES])
if i != rounds: if i != rounds:
data = mix_columns_inv(data) data = mix_columns_inv(data)
data = shift_rows_inv(data) data = shift_rows_inv(data)
@ -131,6 +136,7 @@ def aes_decrypt(data, expanded_key):
return data return data
def aes_decrypt_text(data, password, key_size_bytes): def aes_decrypt_text(data, password, key_size_bytes):
""" """
Decrypt text Decrypt text
@ -149,14 +155,15 @@ def aes_decrypt_text(data, password, key_size_bytes):
data = bytes_to_intlist(base64.b64decode(data)) data = bytes_to_intlist(base64.b64decode(data))
password = bytes_to_intlist(password.encode('utf-8')) password = bytes_to_intlist(password.encode('utf-8'))
key = password[:key_size_bytes] + [0]*(key_size_bytes - len(password)) key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password))
key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES) key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES)
nonce = data[:NONCE_LENGTH_BYTES] nonce = data[:NONCE_LENGTH_BYTES]
cipher = data[NONCE_LENGTH_BYTES:] cipher = data[NONCE_LENGTH_BYTES:]
class Counter: class Counter:
__value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES) __value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
def next_value(self): def next_value(self):
temp = self.__value temp = self.__value
self.__value = inc(self.__value) self.__value = inc(self.__value)
@ -200,14 +207,14 @@ SBOX_INV = (0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x
0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef, 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61, 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d) 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d)
MIX_COLUMN_MATRIX = ((0x2,0x3,0x1,0x1), MIX_COLUMN_MATRIX = ((0x2, 0x3, 0x1, 0x1),
(0x1,0x2,0x3,0x1), (0x1, 0x2, 0x3, 0x1),
(0x1,0x1,0x2,0x3), (0x1, 0x1, 0x2, 0x3),
(0x3,0x1,0x1,0x2)) (0x3, 0x1, 0x1, 0x2))
MIX_COLUMN_MATRIX_INV = ((0xE,0xB,0xD,0x9), MIX_COLUMN_MATRIX_INV = ((0xE, 0xB, 0xD, 0x9),
(0x9,0xE,0xB,0xD), (0x9, 0xE, 0xB, 0xD),
(0xD,0x9,0xE,0xB), (0xD, 0x9, 0xE, 0xB),
(0xB,0xD,0x9,0xE)) (0xB, 0xD, 0x9, 0xE))
RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35, RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35,
0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA, 0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA,
0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31, 0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31,
@ -241,15 +248,19 @@ RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7
0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5, 0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07) 0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07)
def sub_bytes(data): def sub_bytes(data):
return [SBOX[x] for x in data] return [SBOX[x] for x in data]
def sub_bytes_inv(data): def sub_bytes_inv(data):
return [SBOX_INV[x] for x in data] return [SBOX_INV[x] for x in data]
def rotate(data): def rotate(data):
return data[1:] + [data[0]] return data[1:] + [data[0]]
def key_schedule_core(data, rcon_iteration): def key_schedule_core(data, rcon_iteration):
data = rotate(data) data = rotate(data)
data = sub_bytes(data) data = sub_bytes(data)
@ -257,14 +268,17 @@ def key_schedule_core(data, rcon_iteration):
return data return data
def xor(data1, data2): def xor(data1, data2):
return [x^y for x, y in zip(data1, data2)] return [x ^ y for x, y in zip(data1, data2)]
def rijndael_mul(a, b): def rijndael_mul(a, b):
if(a==0 or b==0): if(a == 0 or b == 0):
return 0 return 0
return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF] return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]
def mix_column(data, matrix): def mix_column(data, matrix):
data_mixed = [] data_mixed = []
for row in range(4): for row in range(4):
@ -275,33 +289,38 @@ def mix_column(data, matrix):
data_mixed.append(mixed) data_mixed.append(mixed)
return data_mixed return data_mixed
def mix_columns(data, matrix=MIX_COLUMN_MATRIX): def mix_columns(data, matrix=MIX_COLUMN_MATRIX):
data_mixed = [] data_mixed = []
for i in range(4): for i in range(4):
column = data[i*4 : (i+1)*4] column = data[i * 4: (i + 1) * 4]
data_mixed += mix_column(column, matrix) data_mixed += mix_column(column, matrix)
return data_mixed return data_mixed
def mix_columns_inv(data): def mix_columns_inv(data):
return mix_columns(data, MIX_COLUMN_MATRIX_INV) return mix_columns(data, MIX_COLUMN_MATRIX_INV)
def shift_rows(data): def shift_rows(data):
data_shifted = [] data_shifted = []
for column in range(4): for column in range(4):
for row in range(4): for row in range(4):
data_shifted.append( data[((column + row) & 0b11) * 4 + row] ) data_shifted.append(data[((column + row) & 0b11) * 4 + row])
return data_shifted return data_shifted
def shift_rows_inv(data): def shift_rows_inv(data):
data_shifted = [] data_shifted = []
for column in range(4): for column in range(4):
for row in range(4): for row in range(4):
data_shifted.append( data[((column - row) & 0b11) * 4 + row] ) data_shifted.append(data[((column - row) & 0b11) * 4 + row])
return data_shifted return data_shifted
def inc(data): def inc(data):
data = data[:] # copy data = data[:] # copy
for i in range(len(data)-1,-1,-1): for i in range(len(data) - 1, -1, -1):
if data[i] == 255: if data[i] == 255:
data[i] = 0 data[i] = 0
else: else:

@ -10,47 +10,47 @@ import sys
try: try:
import urllib.request as compat_urllib_request import urllib.request as compat_urllib_request
except ImportError: # Python 2 except ImportError: # Python 2
import urllib2 as compat_urllib_request import urllib2 as compat_urllib_request
try: try:
import urllib.error as compat_urllib_error import urllib.error as compat_urllib_error
except ImportError: # Python 2 except ImportError: # Python 2
import urllib2 as compat_urllib_error import urllib2 as compat_urllib_error
try: try:
import urllib.parse as compat_urllib_parse import urllib.parse as compat_urllib_parse
except ImportError: # Python 2 except ImportError: # Python 2
import urllib as compat_urllib_parse import urllib as compat_urllib_parse
try: try:
from urllib.parse import urlparse as compat_urllib_parse_urlparse from urllib.parse import urlparse as compat_urllib_parse_urlparse
except ImportError: # Python 2 except ImportError: # Python 2
from urlparse import urlparse as compat_urllib_parse_urlparse from urlparse import urlparse as compat_urllib_parse_urlparse
try: try:
import urllib.parse as compat_urlparse import urllib.parse as compat_urlparse
except ImportError: # Python 2 except ImportError: # Python 2
import urlparse as compat_urlparse import urlparse as compat_urlparse
try: try:
import http.cookiejar as compat_cookiejar import http.cookiejar as compat_cookiejar
except ImportError: # Python 2 except ImportError: # Python 2
import cookielib as compat_cookiejar import cookielib as compat_cookiejar
try: try:
import html.entities as compat_html_entities import html.entities as compat_html_entities
except ImportError: # Python 2 except ImportError: # Python 2
import htmlentitydefs as compat_html_entities import htmlentitydefs as compat_html_entities
try: try:
import html.parser as compat_html_parser import html.parser as compat_html_parser
except ImportError: # Python 2 except ImportError: # Python 2
import HTMLParser as compat_html_parser import HTMLParser as compat_html_parser
try: try:
import http.client as compat_http_client import http.client as compat_http_client
except ImportError: # Python 2 except ImportError: # Python 2
import httplib as compat_http_client import httplib as compat_http_client
try: try:
@ -111,7 +111,7 @@ except ImportError:
try: try:
from urllib.parse import parse_qs as compat_parse_qs from urllib.parse import parse_qs as compat_parse_qs
except ImportError: # Python 2 except ImportError: # Python 2
# HACK: The following is the correct parse_qs implementation from cpython 3's stdlib. # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
# Python 2's version is apparently totally broken # Python 2's version is apparently totally broken
@ -157,12 +157,12 @@ except ImportError: # Python 2
return parsed_result return parsed_result
try: try:
compat_str = unicode # Python 2 compat_str = unicode # Python 2
except NameError: except NameError:
compat_str = str compat_str = str
try: try:
compat_chr = unichr # Python 2 compat_chr = unichr # Python 2
except NameError: except NameError:
compat_chr = chr compat_chr = chr
@ -182,8 +182,10 @@ except ImportError: # Python < 3.3
def compat_ord(c): def compat_ord(c):
if type(c) is int: return c if type(c) is int:
else: return ord(c) return c
else:
return ord(c)
if sys.version_info >= (3, 0): if sys.version_info >= (3, 0):
@ -254,7 +256,7 @@ else:
drive = '' drive = ''
userhome = os.path.join(drive, compat_getenv('HOMEPATH')) userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
if i != 1: #~user if i != 1: # ~user
userhome = os.path.join(os.path.dirname(userhome), path[1:i]) userhome = os.path.join(os.path.dirname(userhome), path[1:i])
return userhome + path[i:] return userhome + path[i:]

@ -81,7 +81,7 @@ class FileDownloader(object):
if total is None: if total is None:
return None return None
dif = now - start dif = now - start
if current == 0 or dif < 0.001: # One millisecond if current == 0 or dif < 0.001: # One millisecond
return None return None
rate = float(current) / dif rate = float(current) / dif
return int((float(total) - float(current)) / rate) return int((float(total) - float(current)) / rate)
@ -95,7 +95,7 @@ class FileDownloader(object):
@staticmethod @staticmethod
def calc_speed(start, now, bytes): def calc_speed(start, now, bytes):
dif = now - start dif = now - start
if bytes == 0 or dif < 0.001: # One millisecond if bytes == 0 or dif < 0.001: # One millisecond
return None return None
return float(bytes) / dif return float(bytes) / dif
@ -108,7 +108,7 @@ class FileDownloader(object):
@staticmethod @staticmethod
def best_block_size(elapsed_time, bytes): def best_block_size(elapsed_time, bytes):
new_min = max(bytes / 2.0, 1.0) new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001: if elapsed_time < 0.001:
return int(new_max) return int(new_max)
rate = bytes / elapsed_time rate = bytes / elapsed_time

@ -55,7 +55,7 @@ class FlvReader(io.BytesIO):
if size == 1: if size == 1:
real_size = self.read_unsigned_long_long() real_size = self.read_unsigned_long_long()
header_end = 16 header_end = 16
return real_size, box_type, self.read(real_size-header_end) return real_size, box_type, self.read(real_size - header_end)
def read_asrt(self): def read_asrt(self):
# version # version
@ -180,7 +180,7 @@ def build_fragments_list(boot_info):
n_frags = segment_run_entry[1] n_frags = segment_run_entry[1]
fragment_run_entry_table = boot_info['fragments'][0]['fragments'] fragment_run_entry_table = boot_info['fragments'][0]['fragments']
first_frag_number = fragment_run_entry_table[0]['first'] first_frag_number = fragment_run_entry_table[0]['first']
for (i, frag_number) in zip(range(1, n_frags+1), itertools.count(first_frag_number)): for (i, frag_number) in zip(range(1, n_frags + 1), itertools.count(first_frag_number)):
res.append((1, frag_number)) res.append((1, frag_number))
return res return res

@ -101,4 +101,3 @@ class NativeHlsFD(FileDownloader):
}) })
self.try_rename(tmpfilename, filename) self.try_rename(tmpfilename, filename)
return True return True

@ -46,13 +46,13 @@ class RtmpFD(FileDownloader):
continue continue
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line) mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
if mobj: if mobj:
downloaded_data_len = int(float(mobj.group(1))*1024) downloaded_data_len = int(float(mobj.group(1)) * 1024)
percent = float(mobj.group(2)) percent = float(mobj.group(2))
if not resume_percent: if not resume_percent:
resume_percent = percent resume_percent = percent
resume_downloaded_data_len = downloaded_data_len resume_downloaded_data_len = downloaded_data_len
eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent) eta = self.calc_eta(start, time.time(), 100 - resume_percent, percent - resume_percent)
speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_downloaded_data_len) speed = self.calc_speed(start, time.time(), downloaded_data_len - resume_downloaded_data_len)
data_len = None data_len = None
if percent > 0: if percent > 0:
data_len = int(downloaded_data_len * 100 / percent) data_len = int(downloaded_data_len * 100 / percent)
@ -72,7 +72,7 @@ class RtmpFD(FileDownloader):
# no percent for live streams # no percent for live streams
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line) mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
if mobj: if mobj:
downloaded_data_len = int(float(mobj.group(1))*1024) downloaded_data_len = int(float(mobj.group(1)) * 1024)
time_now = time.time() time_now = time.time()
speed = self.calc_speed(start, time_now, downloaded_data_len) speed = self.calc_speed(start, time_now, downloaded_data_len)
self.report_progress_live_stream(downloaded_data_len, speed, time_now - start) self.report_progress_live_stream(downloaded_data_len, speed, time_now - start)
@ -88,7 +88,7 @@ class RtmpFD(FileDownloader):
if not cursor_in_new_line: if not cursor_in_new_line:
self.to_screen('') self.to_screen('')
cursor_in_new_line = True cursor_in_new_line = True
self.to_screen('[rtmpdump] '+line) self.to_screen('[rtmpdump] ' + line)
proc.wait() proc.wait()
if not cursor_in_new_line: if not cursor_in_new_line:
self.to_screen('') self.to_screen('')
@ -180,7 +180,7 @@ class RtmpFD(FileDownloader):
while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live: while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live:
prevsize = os.path.getsize(encodeFilename(tmpfilename)) prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % prevsize) self.to_screen('[rtmpdump] %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed time.sleep(5.0) # This seems to be needed
retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED]) retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
cursize = os.path.getsize(encodeFilename(tmpfilename)) cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == RD_FAILED: if prevsize == cursize and retval == RD_FAILED:

@ -529,4 +529,4 @@ def gen_extractors():
def get_info_extractor(ie_name): def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name""" """Returns the info extractor class with the given ie_name"""
return globals()[ie_name+'IE'] return globals()[ie_name + 'IE']

@ -5,6 +5,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
class AdultSwimIE(InfoExtractor): class AdultSwimIE(InfoExtractor):
_VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$'
_TEST = { _TEST = {

@ -1,4 +1,4 @@
#coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals

@ -70,11 +70,13 @@ class AppleTrailersIE(InfoExtractor):
uploader_id = mobj.group('company') uploader_id = mobj.group('company')
playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc') playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
def fix_html(s): def fix_html(s):
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s) s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s) s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
# The ' in the onClick attributes are not escaped, it couldn't be parsed # The ' in the onClick attributes are not escaped, it couldn't be parsed
# like: http://trailers.apple.com/trailers/wb/gravity/ # like: http://trailers.apple.com/trailers/wb/gravity/
def _clean_json(m): def _clean_json(m):
return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;') return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
s = re.sub(self._JSON_RE, _clean_json, s) s = re.sub(self._JSON_RE, _clean_json, s)

@ -192,4 +192,3 @@ class ARDIE(InfoExtractor):
'upload_date': upload_date, 'upload_date': upload_date,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }

@ -12,17 +12,17 @@ class AudiomackIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)' _VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)'
IE_NAME = 'audiomack' IE_NAME = 'audiomack'
_TESTS = [ _TESTS = [
#hosted on audiomack # hosted on audiomack
{ {
'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary', 'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
'info_dict': 'info_dict':
{ {
'id' : 'roosh-williams/extraordinary', 'id': 'roosh-williams/extraordinary',
'ext': 'mp3', 'ext': 'mp3',
'title': 'Roosh Williams - Extraordinary' 'title': 'Roosh Williams - Extraordinary'
} }
}, },
#hosted on soundcloud via audiomack # hosted on soundcloud via audiomack
{ {
'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare', 'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
'file': '172419696.mp3', 'file': '172419696.mp3',
@ -49,7 +49,7 @@ class AudiomackIE(InfoExtractor):
raise ExtractorError("Unable to deduce api url of song") raise ExtractorError("Unable to deduce api url of song")
realurl = api_response["url"] realurl = api_response["url"]
#Audiomack wraps a lot of soundcloud tracks in their branded wrapper # Audiomack wraps a lot of soundcloud tracks in their branded wrapper
# - if so, pass the work off to the soundcloud extractor # - if so, pass the work off to the soundcloud extractor
if SoundcloudIE.suitable(realurl): if SoundcloudIE.suitable(realurl):
return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'} return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'}

@ -18,7 +18,7 @@ class BambuserIE(InfoExtractor):
_TEST = { _TEST = {
'url': 'http://bambuser.com/v/4050584', 'url': 'http://bambuser.com/v/4050584',
# MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388 # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
#u'md5': 'fba8f7693e48fd4e8641b3fd5539a641', # u'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
'info_dict': { 'info_dict': {
'id': '4050584', 'id': '4050584',
'ext': 'flv', 'ext': 'flv',

@ -83,12 +83,12 @@ class BandcampIE(InfoExtractor):
initial_url = mp3_info['url'] initial_url = mp3_info['url']
re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$' re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
m_url = re.match(re_url, initial_url) m_url = re.match(re_url, initial_url)
#We build the url we will use to get the final track url # We build the url we will use to get the final track url
# This url is build in Bandcamp in the script download_bunde_*.js # This url is build in Bandcamp in the script download_bunde_*.js
request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts')) request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url') final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
# If we could correctly generate the .rand field the url would be # If we could correctly generate the .rand field the url would be
#in the "download_url" key # in the "download_url" key
final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1) final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
return { return {

@ -195,7 +195,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
duration = int(item.get('duration')) duration = int(item.get('duration'))
media_selection = self._download_xml( media_selection = self._download_xml(
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id,
programme_id, 'Downloading media selection XML') programme_id, 'Downloading media selection XML')
for media in self._extract_medias(media_selection): for media in self._extract_medias(media_selection):

@ -1,4 +1,4 @@
#coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor

@ -5,6 +5,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ExtractorError from ..utils import ExtractorError
class Channel9IE(InfoExtractor): class Channel9IE(InfoExtractor):
''' '''
Common extractor for channel9.msdn.com. Common extractor for channel9.msdn.com.
@ -31,7 +32,7 @@ class Channel9IE(InfoExtractor):
'session_code': 'KOS002', 'session_code': 'KOS002',
'session_day': 'Day 1', 'session_day': 'Day 1',
'session_room': 'Arena 1A', 'session_room': 'Arena 1A',
'session_speakers': [ 'Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen' ], 'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen'],
}, },
}, },
{ {
@ -44,7 +45,7 @@ class Channel9IE(InfoExtractor):
'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
'duration': 1540, 'duration': 1540,
'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg', 'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
'authors': [ 'Mike Wilmot' ], 'authors': ['Mike Wilmot'],
}, },
} }
] ]
@ -83,7 +84,7 @@ class Channel9IE(InfoExtractor):
'format_id': x.group('quality'), 'format_id': x.group('quality'),
'format_note': x.group('note'), 'format_note': x.group('note'),
'format': '%s (%s)' % (x.group('quality'), x.group('note')), 'format': '%s (%s)' % (x.group('quality'), x.group('note')),
'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate 'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate
'preference': self._known_formats.index(x.group('quality')), 'preference': self._known_formats.index(x.group('quality')),
'vcodec': 'none' if x.group('note') == 'Audio only' else None, 'vcodec': 'none' if x.group('note') == 'Audio only' else None,
} for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats] } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
@ -202,17 +203,17 @@ class Channel9IE(InfoExtractor):
if slides is not None: if slides is not None:
d = common.copy() d = common.copy()
d.update({ 'title': title + '-Slides', 'url': slides }) d.update({'title': title + '-Slides', 'url': slides})
result.append(d) result.append(d)
if zip_ is not None: if zip_ is not None:
d = common.copy() d = common.copy()
d.update({ 'title': title + '-Zip', 'url': zip_ }) d.update({'title': title + '-Zip', 'url': zip_})
result.append(d) result.append(d)
if len(formats) > 0: if len(formats) > 0:
d = common.copy() d = common.copy()
d.update({ 'title': title, 'formats': formats }) d.update({'title': title, 'formats': formats})
result.append(d) result.append(d)
return result return result
@ -270,5 +271,5 @@ class Channel9IE(InfoExtractor):
else: else:
raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True) raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True)
else: # Assuming list else: # Assuming list
return self._extract_list(content_path) return self._extract_list(content_path)

@ -77,7 +77,7 @@ class CinemassacreIE(InfoExtractor):
if videolist_url: if videolist_url:
videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML') videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
formats = [] formats = []
baseurl = vidurl[:vidurl.rfind('/')+1] baseurl = vidurl[:vidurl.rfind('/') + 1]
for video in videolist.findall('.//video'): for video in videolist.findall('.//video'):
src = video.get('src') src = video.get('src')
if not src: if not src:

@ -39,6 +39,7 @@ class ClipsyndicateIE(InfoExtractor):
transform_source=fix_xml_ampersands) transform_source=fix_xml_ampersands)
track_doc = pdoc.find('trackList/track') track_doc = pdoc.find('trackList/track')
def find_param(name): def find_param(name):
node = find_xpath_attr(track_doc, './/param', 'name', name) node = find_xpath_attr(track_doc, './/param', 'name', name)
if node is not None: if node is not None:

@ -423,17 +423,18 @@ class InfoExtractor(object):
"""Report attempt to log in.""" """Report attempt to log in."""
self.to_screen('Logging in') self.to_screen('Logging in')
#Methods for following #608 # Methods for following #608
@staticmethod @staticmethod
def url_result(url, ie=None, video_id=None): def url_result(url, ie=None, video_id=None):
"""Returns a url that points to a page that should be processed""" """Returns a url that points to a page that should be processed"""
#TODO: ie should be the class used for getting the info # TODO: ie should be the class used for getting the info
video_info = {'_type': 'url', video_info = {'_type': 'url',
'url': url, 'url': url,
'ie_key': ie} 'ie_key': ie}
if video_id is not None: if video_id is not None:
video_info['id'] = video_id video_info['id'] = video_id
return video_info return video_info
@staticmethod @staticmethod
def playlist_result(entries, playlist_id=None, playlist_title=None): def playlist_result(entries, playlist_id=None, playlist_title=None):
"""Returns a playlist""" """Returns a playlist"""

@ -54,7 +54,7 @@ class CrackedIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'url':video_url, 'url': video_url,
'title': title, 'title': title,
'description': description, 'description': description,
'timestamp': timestamp, 'timestamp': timestamp,

@ -69,11 +69,9 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info') self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self): def _real_initialize(self):
self._login() self._login()
def _decrypt_subtitles(self, data, iv, id): def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(data) data = bytes_to_intlist(data)
iv = bytes_to_intlist(iv) iv = bytes_to_intlist(iv)
@ -99,8 +97,10 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
return shaHash + [0] * 12 return shaHash + [0] * 12
key = obfuscate_key(id) key = obfuscate_key(id)
class Counter: class Counter:
__value = iv __value = iv
def next_value(self): def next_value(self):
temp = self.__value temp = self.__value
self.__value = inc(self.__value) self.__value = inc(self.__value)
@ -183,7 +183,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
return output return output
def _real_extract(self,url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id') video_id = mobj.group('video_id')
@ -226,10 +226,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
formats = [] formats = []
for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage): for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
stream_quality, stream_format = self._FORMAT_IDS[fmt] stream_quality, stream_format = self._FORMAT_IDS[fmt]
video_format = fmt+'p' video_format = fmt + 'p'
streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/') streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
# urlencode doesn't work! # urlencode doesn't work!
streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format
streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
streamdata_req.add_header('Content-Length', str(len(streamdata_req.data))) streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
streamdata = self._download_xml( streamdata = self._download_xml(
@ -248,8 +248,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
subtitles = {} subtitles = {}
sub_format = self._downloader.params.get('subtitlesformat', 'srt') sub_format = self._downloader.params.get('subtitlesformat', 'srt')
for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\ sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,\
video_id, note='Downloading subtitles for '+sub_name) video_id, note='Downloading subtitles for ' + sub_name)
id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False) id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False) iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)
data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False) data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False)
@ -274,14 +274,14 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
return return
return { return {
'id': video_id, 'id': video_id,
'title': video_title, 'title': video_title,
'description': video_description, 'description': video_description,
'thumbnail': video_thumbnail, 'thumbnail': video_thumbnail,
'uploader': video_uploader, 'uploader': video_uploader,
'upload_date': video_upload_date, 'upload_date': video_upload_date,
'subtitles': subtitles, 'subtitles': subtitles,
'formats': formats, 'formats': formats,
} }

@ -1,4 +1,4 @@
#coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
@ -18,6 +18,7 @@ from ..utils import (
unescapeHTML, unescapeHTML,
) )
class DailymotionBaseInfoExtractor(InfoExtractor): class DailymotionBaseInfoExtractor(InfoExtractor):
@staticmethod @staticmethod
def _build_request(url): def _build_request(url):
@ -27,6 +28,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
request.add_header('Cookie', 'ff=off') request.add_header('Cookie', 'ff=off')
return request return request
class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
"""Information Extractor for Dailymotion""" """Information Extractor for Dailymotion"""

@ -27,7 +27,7 @@ class DotsubIE(InfoExtractor):
video_id = mobj.group('id') video_id = mobj.group('id')
info_url = "https://dotsub.com/api/media/%s/metadata" % video_id info_url = "https://dotsub.com/api/media/%s/metadata" % video_id
info = self._download_json(info_url, video_id) info = self._download_json(info_url, video_id)
date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds date = time.gmtime(info['dateCreated'] / 1000) # The timestamp is in miliseconds
return { return {
'id': video_id, 'id': video_id,

@ -40,7 +40,7 @@ class FC2IE(InfoExtractor):
info_url = ( info_url = (
"http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&". "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&".
format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.','%2E'))) format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.', '%2E')))
info_webpage = self._download_webpage( info_webpage = self._download_webpage(
info_url, video_id, note='Downloading info page') info_url, video_id, note='Downloading info page')

@ -748,7 +748,7 @@ class GenericIE(InfoExtractor):
# Look for embedded blip.tv player # Look for embedded blip.tv player
mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
if mobj: if mobj:
return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
if mobj: if mobj:
return self.url_result(mobj.group(1), 'BlipTV') return self.url_result(mobj.group(1), 'BlipTV')
@ -1025,4 +1025,3 @@ class GenericIE(InfoExtractor):
'_type': 'playlist', '_type': 'playlist',
'entries': entries, 'entries': entries,
} }

@ -32,7 +32,7 @@ class InternetVideoArchiveIE(InfoExtractor):
def _clean_query(query): def _clean_query(query):
NEEDED_ARGS = ['publishedid', 'customerid'] NEEDED_ARGS = ['publishedid', 'customerid']
query_dic = compat_urlparse.parse_qs(query) query_dic = compat_urlparse.parse_qs(query)
cleaned_dic = dict((k,v[0]) for (k,v) in query_dic.items() if k in NEEDED_ARGS) cleaned_dic = dict((k, v[0]) for (k, v) in query_dic.items() if k in NEEDED_ARGS)
# Other player ids return m3u8 urls # Other player ids return m3u8 urls
cleaned_dic['playerid'] = '247' cleaned_dic['playerid'] = '247'
cleaned_dic['videokbrate'] = '100000' cleaned_dic['videokbrate'] = '100000'

@ -54,7 +54,7 @@ class IPrimaIE(InfoExtractor):
player_url = ( player_url = (
'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
(floor(random()*1073741824), floor(random()*1073741824)) (floor(random() * 1073741824), floor(random() * 1073741824))
) )
req = compat_urllib_request.Request(player_url) req = compat_urllib_request.Request(player_url)

@ -152,17 +152,17 @@ class IviCompilationIE(InfoExtractor):
compilation_id = mobj.group('compilationid') compilation_id = mobj.group('compilationid')
season_id = mobj.group('seasonid') season_id = mobj.group('seasonid')
if season_id is not None: # Season link if season_id is not None: # Season link
season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id) season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id)
playlist_id = '%s/season%s' % (compilation_id, season_id) playlist_id = '%s/season%s' % (compilation_id, season_id)
playlist_title = self._html_search_meta('title', season_page, 'title') playlist_title = self._html_search_meta('title', season_page, 'title')
entries = self._extract_entries(season_page, compilation_id) entries = self._extract_entries(season_page, compilation_id)
else: # Compilation link else: # Compilation link
compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page') compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
playlist_id = compilation_id playlist_id = compilation_id
playlist_title = self._html_search_meta('title', compilation_page, 'title') playlist_title = self._html_search_meta('title', compilation_page, 'title')
seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page) seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page)
if len(seasons) == 0: # No seasons in this compilation if len(seasons) == 0: # No seasons in this compilation
entries = self._extract_entries(compilation_page, compilation_id) entries = self._extract_entries(compilation_page, compilation_id)
else: else:
entries = [] entries = []

@ -45,4 +45,3 @@ class JadoreCettePubIE(InfoExtractor):
'title': title, 'title': title,
'description': description, 'description': description,
} }

@ -30,4 +30,3 @@ class Ku6IE(InfoExtractor):
'title': title, 'title': title,
'url': downloadUrl 'url': downloadUrl
} }

@ -75,4 +75,3 @@ class Laola1TvIE(InfoExtractor):
'categories': categories, 'categories': categories,
'ext': 'mp4', 'ext': 'mp4',
} }

@ -52,7 +52,7 @@ class LifeNewsIE(InfoExtractor):
r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False) r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False)
upload_date = self._html_search_regex( upload_date = self._html_search_regex(
r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False) r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
if upload_date is not None: if upload_date is not None:
upload_date = unified_strdate(upload_date) upload_date = unified_strdate(upload_date)
@ -71,4 +71,4 @@ class LifeNewsIE(InfoExtractor):
if len(videos) == 1: if len(videos) == 1:
return make_entry(video_id, videos[0]) return make_entry(video_id, videos[0])
else: else:
return [make_entry(video_id, media, video_number+1) for video_number, media in enumerate(videos)] return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)]

@ -19,8 +19,7 @@ class LiveLeakIE(InfoExtractor):
'uploader': 'ljfriel2', 'uploader': 'ljfriel2',
'title': 'Most unlucky car accident' 'title': 'Most unlucky car accident'
} }
}, }, {
{
'url': 'http://www.liveleak.com/view?i=f93_1390833151', 'url': 'http://www.liveleak.com/view?i=f93_1390833151',
'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf', 'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
'info_dict': { 'info_dict': {
@ -30,8 +29,7 @@ class LiveLeakIE(InfoExtractor):
'uploader': 'ARD_Stinkt', 'uploader': 'ARD_Stinkt',
'title': 'German Television does first Edward Snowden Interview (ENGLISH)', 'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
} }
}, }, {
{
'url': 'http://www.liveleak.com/view?i=4f7_1392687779', 'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
'md5': '42c6d97d54f1db107958760788c5f48f', 'md5': '42c6d97d54f1db107958760788c5f48f',
'info_dict': { 'info_dict': {

@ -7,6 +7,7 @@ from ..utils import (
compat_urllib_parse, compat_urllib_parse,
) )
class MalemotionIE(InfoExtractor): class MalemotionIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)' _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
_TEST = { _TEST = {

@ -22,7 +22,7 @@ class MetacafeIE(InfoExtractor):
# Youtube video # Youtube video
{ {
'add_ie': ['Youtube'], 'add_ie': ['Youtube'],
'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/', 'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
'info_dict': { 'info_dict': {
'id': '_aUehQsCQtM', 'id': '_aUehQsCQtM',
'ext': 'mp4', 'ext': 'mp4',

@ -54,7 +54,7 @@ class MonikerIE(InfoExtractor):
title = os.path.splitext(data['fname'])[0] title = os.path.splitext(data['fname'])[0]
#Could be several links with different quality # Could be several links with different quality
links = re.findall(r'"file" : "?(.+?)",', webpage) links = re.findall(r'"file" : "?(.+?)",', webpage)
# Assume the links are ordered in quality # Assume the links are ordered in quality
formats = [{ formats = [{

@ -27,7 +27,7 @@ class MoviezineIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
jsplayer = self._download_webpage('http://www.moviezine.se/api/player.js?video=%s' % video_id, video_id, 'Downloading js api player') jsplayer = self._download_webpage('http://www.moviezine.se/api/player.js?video=%s' % video_id, video_id, 'Downloading js api player')
formats =[{ formats = [{
'format_id': 'sd', 'format_id': 'sd',
'url': self._html_search_regex(r'file: "(.+?)",', jsplayer, 'file'), 'url': self._html_search_regex(r'file: "(.+?)",', jsplayer, 'file'),
'quality': 0, 'quality': 0,

@ -60,7 +60,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
url = response.geturl() url = response.geturl()
# Transform the url to get the best quality: # Transform the url to get the best quality:
url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1) url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
return [{'url': url,'ext': 'mp4'}] return [{'url': url, 'ext': 'mp4'}]
def _extract_video_formats(self, mdoc, mtvn_id): def _extract_video_formats(self, mdoc, mtvn_id):
if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None: if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None:
@ -245,7 +245,7 @@ class MTVIE(MTVServicesInfoExtractor):
m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";', m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
webpage, re.DOTALL) webpage, re.DOTALL)
if m_vevo: if m_vevo:
vevo_id = m_vevo.group(1); vevo_id = m_vevo.group(1)
self.to_screen('Vevo video detected: %s' % vevo_id) self.to_screen('Vevo video detected: %s' % vevo_id)
return self.url_result('vevo:%s' % vevo_id, ie='Vevo') return self.url_result('vevo:%s' % vevo_id, ie='Vevo')

@ -73,4 +73,3 @@ class MuenchenTVIE(InfoExtractor):
'is_live': True, 'is_live': True,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }

@ -37,7 +37,7 @@ class MuzuTVIE(InfoExtractor):
player_info_page = self._download_webpage('http://player.muzu.tv/player/playerInit?ai=%s' % video_id, player_info_page = self._download_webpage('http://player.muzu.tv/player/playerInit?ai=%s' % video_id,
video_id, u'Downloading player info') video_id, u'Downloading player info')
video_info = json.loads(player_info_page)['videos'][0] video_info = json.loads(player_info_page)['videos'][0]
for quality in ['1080' , '720', '480', '360']: for quality in ['1080', '720', '480', '360']:
if video_info.get('v%s' % quality): if video_info.get('v%s' % quality):
break break

@ -33,7 +33,7 @@ class MyVideoIE(InfoExtractor):
# Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
# Released into the Public Domain by Tristan Fischer on 2013-05-19 # Released into the Public Domain by Tristan Fischer on 2013-05-19
# https://github.com/rg3/youtube-dl/pull/842 # https://github.com/rg3/youtube-dl/pull/842
def __rc4crypt(self,data, key): def __rc4crypt(self, data, key):
x = 0 x = 0
box = list(range(256)) box = list(range(256))
for i in list(range(256)): for i in list(range(256)):
@ -49,10 +49,10 @@ class MyVideoIE(InfoExtractor):
out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256]) out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256])
return out return out
def __md5(self,s): def __md5(self, s):
return hashlib.md5(s).hexdigest().encode() return hashlib.md5(s).hexdigest().encode()
def _real_extract(self,url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
@ -173,4 +173,3 @@ class MyVideoIE(InfoExtractor):
'play_path': video_playpath, 'play_path': video_playpath,
'player_url': video_swfobj, 'player_url': video_swfobj,
} }

@ -40,7 +40,7 @@ class NaverIE(InfoExtractor):
raise ExtractorError('couldn\'t extract vid and key') raise ExtractorError('couldn\'t extract vid and key')
vid = m_id.group(1) vid = m_id.group(1)
key = m_id.group(2) key = m_id.group(2)
query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,}) query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key, })
query_urls = compat_urllib_parse.urlencode({ query_urls = compat_urllib_parse.urlencode({
'masterVid': vid, 'masterVid': vid,
'protocol': 'p2p', 'protocol': 'p2p',
@ -65,7 +65,7 @@ class NaverIE(InfoExtractor):
if domain.startswith('rtmp'): if domain.startswith('rtmp'):
f.update({ f.update({
'ext': 'flv', 'ext': 'flv',
'rtmp_protocol': '1', # rtmpt 'rtmp_protocol': '1', # rtmpt
}) })
formats.append(f) formats.append(f)
self._sort_formats(formats) self._sort_formats(formats)

@ -39,7 +39,6 @@ class NBAIE(InfoExtractor):
duration = parse_duration( duration = parse_duration(
self._html_search_meta('duration', webpage, 'duration', fatal=False)) self._html_search_meta('duration', webpage, 'duration', fatal=False))
return { return {
'id': shortened_video_id, 'id': shortened_video_id,
'url': video_url, 'url': video_url,

@ -31,7 +31,7 @@ class NHLBaseInfoExtractor(InfoExtractor):
path_url, video_id, 'Downloading final video url') path_url, video_id, 'Downloading final video url')
video_url = path_doc.find('path').text video_url = path_doc.find('path').text
else: else:
video_url = initial_video_url video_url = initial_video_url
join = compat_urlparse.urljoin join = compat_urlparse.urljoin
return { return {

@ -97,4 +97,3 @@ class OoyalaIE(InfoExtractor):
} }
else: else:
return self._extract_result(videos_info[0], videos_more_info) return self._extract_result(videos_info[0], videos_more_info)

@ -6,6 +6,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import int_or_none
class PodomaticIE(InfoExtractor): class PodomaticIE(InfoExtractor):
IE_NAME = 'podomatic' IE_NAME = 'podomatic'
_VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)' _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'

@ -56,7 +56,7 @@ class PornHubIE(InfoExtractor):
comment_count = self._extract_count( comment_count = self._extract_count(
r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment') r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment')
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
if webpage.find('"encrypted":true') != -1: if webpage.find('"encrypted":true') != -1:
password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password')) password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))

@ -38,7 +38,7 @@ class PornotubeIE(InfoExtractor):
video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url') video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url')
video_url = compat_urllib_parse.unquote(video_url) video_url = compat_urllib_parse.unquote(video_url)
#Get the uploaded date # Get the uploaded date
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False) upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False)
if upload_date: if upload_date:

@ -41,4 +41,3 @@ class RingTVIE(InfoExtractor):
'thumbnail': thumbnail_url, 'thumbnail': thumbnail_url,
'description': description, 'description': description,
} }

@ -44,7 +44,7 @@ class RtlXlIE(InfoExtractor):
formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4') formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
video_urlpart = videopath.split('/flash/')[1][:-4] video_urlpart = videopath.split('/flash/')[1][:-5]
PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4' PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
formats.extend([ formats.extend([

@ -54,7 +54,6 @@ def _decrypt_url(png):
return url return url
class RTVEALaCartaIE(InfoExtractor): class RTVEALaCartaIE(InfoExtractor):
IE_NAME = 'rtve.es:alacarta' IE_NAME = 'rtve.es:alacarta'
IE_DESC = 'RTVE a la carta' IE_DESC = 'RTVE a la carta'

@ -67,5 +67,3 @@ class ServingSysIE(InfoExtractor):
'title': title, 'title': title,
'entries': entries, 'entries': entries,
} }

@ -1,7 +1,6 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import os.path
import re import re
import json import json
import hashlib import hashlib
@ -12,15 +11,15 @@ from ..utils import (
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request, compat_urllib_request,
ExtractorError, ExtractorError,
url_basename,
int_or_none, int_or_none,
unified_strdate,
) )
class SmotriIE(InfoExtractor): class SmotriIE(InfoExtractor):
IE_DESC = 'Smotri.com' IE_DESC = 'Smotri.com'
IE_NAME = 'smotri' IE_NAME = 'smotri'
_VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})' _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
_NETRC_MACHINE = 'smotri' _NETRC_MACHINE = 'smotri'
_TESTS = [ _TESTS = [
@ -35,7 +34,6 @@ class SmotriIE(InfoExtractor):
'uploader': 'rbc2008', 'uploader': 'rbc2008',
'uploader_id': 'rbc08', 'uploader_id': 'rbc08',
'upload_date': '20131118', 'upload_date': '20131118',
'description': 'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg', 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
}, },
}, },
@ -50,7 +48,6 @@ class SmotriIE(InfoExtractor):
'uploader': 'Support Photofile@photofile', 'uploader': 'Support Photofile@photofile',
'uploader_id': 'support-photofile', 'uploader_id': 'support-photofile',
'upload_date': '20070704', 'upload_date': '20070704',
'description': 'test, видео test',
'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg', 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
}, },
}, },
@ -66,7 +63,6 @@ class SmotriIE(InfoExtractor):
'uploader_id': 'timoxa40', 'uploader_id': 'timoxa40',
'upload_date': '20100404', 'upload_date': '20100404',
'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg', 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
'description': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
}, },
'params': { 'params': {
'videopassword': 'qwerty', 'videopassword': 'qwerty',
@ -85,7 +81,6 @@ class SmotriIE(InfoExtractor):
'upload_date': '20101001', 'upload_date': '20101001',
'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg', 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
'age_limit': 18, 'age_limit': 18,
'description': 'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
}, },
'params': { 'params': {
'videopassword': '333' 'videopassword': '333'
@ -102,17 +97,11 @@ class SmotriIE(InfoExtractor):
'uploader': 'HannahL', 'uploader': 'HannahL',
'uploader_id': 'lisaha95', 'uploader_id': 'lisaha95',
'upload_date': '20090331', 'upload_date': '20090331',
'description': 'Shakira - Don\'t Bother, видео Shakira - Don\'t Bother',
'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg', 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
}, },
}, },
] ]
_SUCCESS = 0
_PASSWORD_NOT_VERIFIED = 1
_PASSWORD_DETECTED = 2
_VIDEO_NOT_FOUND = 3
@classmethod @classmethod
def _extract_url(cls, webpage): def _extract_url(cls, webpage):
mobj = re.search( mobj = re.search(
@ -137,44 +126,44 @@ class SmotriIE(InfoExtractor):
return self._html_search_meta(name, html, display_name) return self._html_search_meta(name, html, display_name)
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('videoid')
real_video_id = mobj.group('realvideoid') video_form = {
'ticket': video_id,
'video_url': '1',
'frame_url': '1',
'devid': 'LoadupFlashPlayer',
'getvideoinfo': '1',
}
# Download video JSON data request = compat_urllib_request.Request(
video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id 'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON') request.add_header('Content-Type', 'application/x-www-form-urlencoded')
video_json = json.loads(video_json_page)
status = video_json['status'] video = self._download_json(request, video_id, 'Downloading video JSON')
if status == self._VIDEO_NOT_FOUND:
if video.get('_moderate_no') or not video.get('moderated'):
raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True)
if video.get('error'):
raise ExtractorError('Video %s does not exist' % video_id, expected=True) raise ExtractorError('Video %s does not exist' % video_id, expected=True)
elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with
# video-password set video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
video_password = self._downloader.params.get('videopassword', None) title = video['title']
if not video_password: thumbnail = video['_imgURL']
raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) upload_date = unified_strdate(video['added'])
video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest() uploader = video['userNick']
video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON (video-password set)') uploader_id = video['userLogin']
video_json = json.loads(video_json_page) duration = int_or_none(video['duration'])
status = video_json['status']
if status == self._PASSWORD_NOT_VERIFIED:
raise ExtractorError('Video password is invalid', expected=True)
if status != self._SUCCESS:
raise ExtractorError('Unexpected status value %s' % status)
# Extract the URL of the video
video_url = video_json['file_data']
# Video JSON does not provide enough meta data # Video JSON does not provide enough meta data
# We will extract some from the video web page instead # We will extract some from the video web page instead
video_page_url = 'http://smotri.com/video/view/?id=%s' % video_id webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page') webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
# Warning if video is unavailable # Warning if video is unavailable
warning = self._html_search_regex( warning = self._html_search_regex(
r'<div class="videoUnModer">(.*?)</div>', video_page, r'<div class="videoUnModer">(.*?)</div>', webpage,
'warning message', default=None) 'warning message', default=None)
if warning is not None: if warning is not None:
self._downloader.report_warning( self._downloader.report_warning(
@ -182,84 +171,32 @@ class SmotriIE(InfoExtractor):
(video_id, warning)) (video_id, warning))
# Adult content # Adult content
if re.search('EroConfirmText">', video_page) is not None: if re.search('EroConfirmText">', webpage) is not None:
self.report_age_confirmation() self.report_age_confirmation()
confirm_string = self._html_search_regex( confirm_string = self._html_search_regex(
r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id, r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
video_page, 'confirm string') webpage, 'confirm string')
confirm_url = video_page_url + '&confirm=%s' % confirm_string confirm_url = webpage_url + '&confirm=%s' % confirm_string
video_page = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)') webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
adult_content = True adult_content = True
else: else:
adult_content = False adult_content = False
# Extract the rest of meta data view_count = self._html_search_regex(
video_title = self._search_meta('name', video_page, 'title')
if not video_title:
video_title = os.path.splitext(url_basename(video_url))[0]
video_description = self._search_meta('description', video_page)
END_TEXT = ' на сайте Smotri.com'
if video_description and video_description.endswith(END_TEXT):
video_description = video_description[:-len(END_TEXT)]
START_TEXT = 'Смотреть онлайн ролик '
if video_description and video_description.startswith(START_TEXT):
video_description = video_description[len(START_TEXT):]
video_thumbnail = self._search_meta('thumbnail', video_page)
upload_date_str = self._search_meta('uploadDate', video_page, 'upload date')
if upload_date_str:
upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str)
video_upload_date = (
(
upload_date_m.group('year') +
upload_date_m.group('month') +
upload_date_m.group('day')
)
if upload_date_m else None
)
else:
video_upload_date = None
duration_str = self._search_meta('duration', video_page)
if duration_str:
duration_m = re.search(r'T(?P<hours>[0-9]{2})H(?P<minutes>[0-9]{2})M(?P<seconds>[0-9]{2})S', duration_str)
video_duration = (
(
(int(duration_m.group('hours')) * 60 * 60) +
(int(duration_m.group('minutes')) * 60) +
int(duration_m.group('seconds'))
)
if duration_m else None
)
else:
video_duration = None
video_uploader = self._html_search_regex(
'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
video_page, 'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
video_uploader_id = self._html_search_regex(
'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
video_page, 'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
video_view_count = self._html_search_regex(
'Общее количество просмотров.*?<span class="Number">(\\d+)</span>', 'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
video_page, 'view count', fatal=False, flags=re.MULTILINE|re.DOTALL) webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'title': video_title, 'title': title,
'thumbnail': video_thumbnail, 'thumbnail': thumbnail,
'description': video_description, 'uploader': uploader,
'uploader': video_uploader, 'upload_date': upload_date,
'upload_date': video_upload_date, 'uploader_id': uploader_id,
'uploader_id': video_uploader_id, 'duration': duration,
'duration': video_duration, 'view_count': int_or_none(view_count),
'view_count': int_or_none(video_view_count),
'age_limit': 18 if adult_content else 0, 'age_limit': 18 if adult_content else 0,
'video_page_url': video_page_url
} }

@ -69,7 +69,7 @@ class SohuIE(InfoExtractor):
(allot, prot, clipsURL[i], su[i])) (allot, prot, clipsURL[i], su[i]))
part_str = self._download_webpage( part_str = self._download_webpage(
part_url, video_id, part_url, video_id,
note=u'Downloading part %d of %d' % (i+1, part_count)) note=u'Downloading part %d of %d' % (i + 1, part_count))
part_info = part_str.split('|') part_info = part_str.split('|')
video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])

@ -224,7 +224,7 @@ class SoundcloudIE(InfoExtractor):
# extract uploader (which is in the url) # extract uploader (which is in the url)
uploader = mobj.group('uploader') uploader = mobj.group('uploader')
# extract simple title (uploader + slug of song title) # extract simple title (uploader + slug of song title)
slug_title = mobj.group('title') slug_title = mobj.group('title')
token = mobj.group('token') token = mobj.group('token')
full_title = resolve_title = '%s/%s' % (uploader, slug_title) full_title = resolve_title = '%s/%s' % (uploader, slug_title)
if token: if token:

@ -93,4 +93,3 @@ class SportDeutschlandIE(InfoExtractor):
'rtmp_live': asset.get('live'), 'rtmp_live': asset.get('live'),
'timestamp': parse_iso8601(asset.get('date')), 'timestamp': parse_iso8601(asset.get('date')),
} }

@ -50,7 +50,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
sub_lang_list = {} sub_lang_list = {}
for sub_lang in requested_langs: for sub_lang in requested_langs:
if not sub_lang in available_subs_list: if sub_lang not in available_subs_list:
self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang) self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
continue continue
sub_lang_list[sub_lang] = available_subs_list[sub_lang] sub_lang_list[sub_lang] = available_subs_list[sub_lang]

@ -80,7 +80,7 @@ class SWRMediathekIE(InfoExtractor):
if media_type == 'Video': if media_type == 'Video':
fmt.update({ fmt.update({
'format_note': ['144p', '288p', '544p', '720p'][quality-1], 'format_note': ['144p', '288p', '544p', '720p'][quality - 1],
'vcodec': codec, 'vcodec': codec,
}) })
elif media_type == 'Audio': elif media_type == 'Audio':

@ -1,4 +1,4 @@
#coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .mitele import MiTeleIE from .mitele import MiTeleIE

@ -35,11 +35,12 @@ class ThePlatformIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
if mobj.group('config'): if mobj.group('config'):
config_url = url+ '&form=json' config_url = url + '&form=json'
config_url = config_url.replace('swf/', 'config/') config_url = config_url.replace('swf/', 'config/')
config_url = config_url.replace('onsite/', 'onsite/config/') config_url = config_url.replace('onsite/', 'onsite/config/')
config = self._download_json(config_url, video_id, 'Downloading config') config = self._download_json(config_url, video_id, 'Downloading config')
@ -48,7 +49,6 @@ class ThePlatformIE(InfoExtractor):
smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?' smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
'format=smil&mbr=true'.format(video_id)) 'format=smil&mbr=true'.format(video_id))
meta = self._download_xml(smil_url, video_id) meta = self._download_xml(smil_url, video_id)
try: try:
error_msg = next( error_msg = next(
@ -118,5 +118,5 @@ class ThePlatformIE(InfoExtractor):
'formats': formats, 'formats': formats,
'description': info['description'], 'description': info['description'],
'thumbnail': info['defaultThumbnailUrl'], 'thumbnail': info['defaultThumbnailUrl'],
'duration': info['duration']//1000, 'duration': info['duration'] // 1000,
} }

@ -1,4 +1,4 @@
#coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
@ -38,10 +38,10 @@ class ThisAVIE(InfoExtractor):
ext = determine_ext(video_url) ext = determine_ext(video_url)
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'uploader': uploader, 'uploader': uploader,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'title': title, 'title': title,
'ext': ext, 'ext': ext,
} }

@ -25,7 +25,7 @@ class TrailerAddictIE(InfoExtractor):
webpage = self._download_webpage(url, name) webpage = self._download_webpage(url, name)
title = self._search_regex(r'<title>(.+?)</title>', title = self._search_regex(r'<title>(.+?)</title>',
webpage, 'video title').replace(' - Trailer Addict','') webpage, 'video title').replace(' - Trailer Addict', '')
view_count_str = self._search_regex( view_count_str = self._search_regex(
r'<span class="views_n">([0-9,.]+)</span>', r'<span class="views_n">([0-9,.]+)</span>',
webpage, 'view count', fatal=False) webpage, 'view count', fatal=False)
@ -43,10 +43,10 @@ class TrailerAddictIE(InfoExtractor):
fvar = "fvar" fvar = "fvar"
info_url = "http://www.traileraddict.com/%s.php?tid=%s" % (fvar, str(video_id)) info_url = "http://www.traileraddict.com/%s.php?tid=%s" % (fvar, str(video_id))
info_webpage = self._download_webpage(info_url, video_id , "Downloading the info webpage") info_webpage = self._download_webpage(info_url, video_id, "Downloading the info webpage")
final_url = self._search_regex(r'&fileurl=(.+)', final_url = self._search_regex(r'&fileurl=(.+)',
info_webpage, 'Download url').replace('%3F','?') info_webpage, 'Download url').replace('%3F', '?')
thumbnail_url = self._search_regex(r'&image=(.+?)&', thumbnail_url = self._search_regex(r'&image=(.+?)&',
info_webpage, 'thumbnail url') info_webpage, 'thumbnail url')

@ -63,4 +63,3 @@ class TriluliluIE(InfoExtractor):
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }

@ -37,11 +37,11 @@ class TudouIE(InfoExtractor):
}] }]
def _url_for_id(self, id, quality = None): def _url_for_id(self, id, quality = None):
info_url = "http://v2.tudou.com/f?id="+str(id) info_url = "http://v2.tudou.com/f?id=" + str(id)
if quality: if quality:
info_url += '&hd' + quality info_url += '&hd' + quality
webpage = self._download_webpage(info_url, id, "Opening the info webpage") webpage = self._download_webpage(info_url, id, "Opening the info webpage")
final_url = self._html_search_regex('>(.+?)</f>',webpage, 'video url') final_url = self._html_search_regex('>(.+?)</f>', webpage, 'video url')
return final_url return final_url
def _real_extract(self, url): def _real_extract(self, url):

@ -35,4 +35,3 @@ class ViceIE(InfoExtractor):
except ExtractorError: except ExtractorError:
raise ExtractorError('The page doesn\'t contain a video', expected=True) raise ExtractorError('The page doesn\'t contain a video', expected=True)
return self.url_result(ooyala_url, ie='Ooyala') return self.url_result(ooyala_url, ie='Ooyala')

@ -6,13 +6,14 @@ from ..utils import (
determine_ext, determine_ext,
) )
class VideofyMeIE(InfoExtractor): class VideofyMeIE(InfoExtractor):
_VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)' _VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)'
IE_NAME = u'videofy.me' IE_NAME = u'videofy.me'
_TEST = { _TEST = {
u'url': u'http://www.videofy.me/thisisvideofyme/1100701', u'url': u'http://www.videofy.me/thisisvideofyme/1100701',
u'file': u'1100701.mp4', u'file': u'1100701.mp4',
u'md5': u'c77d700bdc16ae2e9f3c26019bd96143', u'md5': u'c77d700bdc16ae2e9f3c26019bd96143',
u'info_dict': { u'info_dict': {
u'title': u'This is VideofyMe', u'title': u'This is VideofyMe',

@ -35,11 +35,11 @@ class VideoPremiumIE(InfoExtractor):
r'<h2(?:.*?)>\s*(.+?)\s*<', webpage, u'video title') r'<h2(?:.*?)>\s*(.+?)\s*<', webpage, u'video title')
return { return {
'id': video_id, 'id': video_id,
'url': "rtmp://e%d.md.iplay.md/play" % random.randint(1, 16), 'url': "rtmp://e%d.md.iplay.md/play" % random.randint(1, 16),
'play_path': "mp4:%s.f4v" % video_id, 'play_path': "mp4:%s.f4v" % video_id,
'page_url': "http://videopremium.tv/" + video_id, 'page_url': "http://videopremium.tv/" + video_id,
'player_url': "http://videopremium.tv/uplayer/uppod.swf", 'player_url': "http://videopremium.tv/uplayer/uppod.swf",
'ext': 'f4v', 'ext': 'f4v',
'title': video_title, 'title': video_title,
} }

@ -1,4 +1,4 @@
#coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
@ -30,4 +30,3 @@ class VidziIE(InfoExtractor):
'title': title, 'title': title,
'url': video_url, 'url': video_url,
} }

@ -51,4 +51,3 @@ class WorldStarHipHopIE(InfoExtractor):
'title': video_title, 'title': video_title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }

@ -47,4 +47,3 @@ class XBefIE(InfoExtractor):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'age_limit': 18, 'age_limit': 18,
} }

@ -42,7 +42,7 @@ class XHamsterIE(InfoExtractor):
} }
] ]
def _real_extract(self,url): def _real_extract(self, url):
def extract_video_url(webpage): def extract_video_url(webpage):
mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage) mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
if mp4 is None: if mp4 is None:

@ -97,7 +97,7 @@ class XTubeUserIE(InfoExtractor):
url, username, note='Retrieving profile page') url, username, note='Retrieving profile page')
video_count = int(self._search_regex( video_count = int(self._search_regex(
r'<strong>%s\'s Videos \(([0-9]+)\)</strong>'%username, profile_page, r'<strong>%s\'s Videos \(([0-9]+)\)</strong>' % username, profile_page,
'video count')) 'video count'))
PAGE_SIZE = 25 PAGE_SIZE = 25

@ -229,7 +229,7 @@ class YahooSearchIE(SearchInfoExtractor):
for pagenum in itertools.count(0): for pagenum in itertools.count(0):
result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
info = self._download_json(result_url, query, info = self._download_json(result_url, query,
note='Downloading results page '+str(pagenum+1)) note='Downloading results page ' + str(pagenum + 1))
m = info['m'] m = info['m']
results = info['results'] results = info['results']

@ -35,21 +35,21 @@ class YoukuIE(InfoExtractor):
def _gen_sid(self): def _gen_sid(self):
nowTime = int(time.time() * 1000) nowTime = int(time.time() * 1000)
random1 = random.randint(1000,1998) random1 = random.randint(1000, 1998)
random2 = random.randint(1000,9999) random2 = random.randint(1000, 9999)
return "%d%d%d" %(nowTime,random1,random2) return "%d%d%d" % (nowTime, random1, random2)
def _get_file_ID_mix_string(self, seed): def _get_file_ID_mix_string(self, seed):
mixed = [] mixed = []
source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
seed = float(seed) seed = float(seed)
for i in range(len(source)): for i in range(len(source)):
seed = (seed * 211 + 30031) % 65536 seed = (seed * 211 + 30031) % 65536
index = math.floor(seed / 65536 * len(source)) index = math.floor(seed / 65536 * len(source))
mixed.append(source[int(index)]) mixed.append(source[int(index)])
source.remove(source[int(index)]) source.remove(source[int(index)])
#return ''.join(mixed) # return ''.join(mixed)
return mixed return mixed
def _get_file_id(self, fileId, seed): def _get_file_id(self, fileId, seed):
@ -100,12 +100,12 @@ class YoukuIE(InfoExtractor):
keys = [s['k'] for s in config['data'][0]['segs'][format]] keys = [s['k'] for s in config['data'][0]['segs'][format]]
# segs is usually a dictionary, but an empty *list* if an error occured. # segs is usually a dictionary, but an empty *list* if an error occured.
files_info=[] files_info = []
sid = self._gen_sid() sid = self._gen_sid()
fileid = self._get_file_id(fileid, seed) fileid = self._get_file_id(fileid, seed)
#column 8,9 of fileid represent the segment number # column 8,9 of fileid represent the segment number
#fileid[7:9] should be changed # fileid[7:9] should be changed
for index, key in enumerate(keys): for index, key in enumerate(keys):
temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)

@ -33,6 +33,7 @@ from ..utils import (
uppercase_escape, uppercase_escape,
) )
class YoutubeBaseInfoExtractor(InfoExtractor): class YoutubeBaseInfoExtractor(InfoExtractor):
"""Provide base functions for Youtube extractors""" """Provide base functions for Youtube extractors"""
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin' _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
@ -76,30 +77,30 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
# Log in # Log in
login_form_strs = { login_form_strs = {
'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
'Email': username, 'Email': username,
'GALX': galx, 'GALX': galx,
'Passwd': password, 'Passwd': password,
'PersistentCookie': 'yes', 'PersistentCookie': 'yes',
'_utf8': '', '_utf8': '',
'bgresponse': 'js_disabled', 'bgresponse': 'js_disabled',
'checkConnection': '', 'checkConnection': '',
'checkedDomains': 'youtube', 'checkedDomains': 'youtube',
'dnConn': '', 'dnConn': '',
'pstMsg': '0', 'pstMsg': '0',
'rmShown': '1', 'rmShown': '1',
'secTok': '', 'secTok': '',
'signIn': 'Sign in', 'signIn': 'Sign in',
'timeStmp': '', 'timeStmp': '',
'service': 'youtube', 'service': 'youtube',
'uilel': '3', 'uilel': '3',
'hl': 'en_US', 'hl': 'en_US',
} }
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode # chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
req = compat_urllib_request.Request(self._LOGIN_URL, login_data) req = compat_urllib_request.Request(self._LOGIN_URL, login_data)
@ -149,7 +150,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
'service': 'youtube', 'service': 'youtube',
'hl': 'en_US', 'hl': 'en_US',
} }
tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in tfa_form_strs.items()) tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items())
tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii')
tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data)
@ -180,8 +181,10 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
'next_url': '/', 'next_url': '/',
'action_confirm': 'Confirm', 'action_confirm': 'Confirm',
} }
req = compat_urllib_request.Request(self._AGE_URL, req = compat_urllib_request.Request(
compat_urllib_parse.urlencode(age_form).encode('ascii')) self._AGE_URL,
compat_urllib_parse.urlencode(age_form).encode('ascii')
)
self._download_webpage( self._download_webpage(
req, None, req, None,
@ -491,7 +494,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
def gen_sig_code(idxs): def gen_sig_code(idxs):
def _genslice(start, end, step): def _genslice(start, end, step):
starts = '' if start == 0 else str(start) starts = '' if start == 0 else str(start)
ends = (':%d' % (end+step)) if end + step >= 0 else ':' ends = (':%d' % (end + step)) if end + step >= 0 else ':'
steps = '' if step == 1 else (':%d' % step) steps = '' if step == 1 else (':%d' % step)
return 's[%s%s%s]' % (starts, ends, steps) return 's[%s%s%s]' % (starts, ends, steps)
@ -529,7 +532,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
def _parse_sig_js(self, jscode): def _parse_sig_js(self, jscode):
funcname = self._search_regex( funcname = self._search_regex(
r'\.sig\|\|([a-zA-Z0-9]+)\(', jscode, r'\.sig\|\|([a-zA-Z0-9]+)\(', jscode,
'Initial JS player signature function name') 'Initial JS player signature function name')
jsi = JSInterpreter(jscode) jsi = JSInterpreter(jscode)
initial_function = jsi.extract_function(funcname) initial_function = jsi.extract_function(funcname)
@ -618,7 +621,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
list_url = caption_url + '&' + list_params list_url = caption_url + '&' + list_params
caption_list = self._download_xml(list_url, video_id) caption_list = self._download_xml(list_url, video_id)
original_lang_node = caption_list.find('track') original_lang_node = caption_list.find('track')
if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr' : if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr':
self._downloader.report_warning('Video doesn\'t have automatic captions') self._downloader.report_warning('Video doesn\'t have automatic captions')
return {} return {}
original_lang = original_lang_node.attrib['lang_code'] original_lang = original_lang_node.attrib['lang_code']
@ -651,10 +654,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
def _extract_from_m3u8(self, manifest_url, video_id): def _extract_from_m3u8(self, manifest_url, video_id):
url_map = {} url_map = {}
def _get_urls(_manifest): def _get_urls(_manifest):
lines = _manifest.split('\n') lines = _manifest.split('\n')
urls = filter(lambda l: l and not l.startswith('#'), urls = filter(lambda l: l and not l.startswith('#'),
lines) lines)
return urls return urls
manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest') manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
formats_urls = _get_urls(manifest) formats_urls = _get_urls(manifest)
@ -721,10 +725,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
age_gate = False age_gate = False
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
video_info_url = (proto + '://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' video_info_url = (proto + '://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
% (video_id, el_type)) % (video_id, el_type))
video_info_webpage = self._download_webpage(video_info_url, video_id, video_info_webpage = self._download_webpage(video_info_url, video_id,
note=False, note=False,
errnote='unable to download video info webpage') errnote='unable to download video info webpage')
video_info = compat_parse_qs(video_info_webpage) video_info = compat_parse_qs(video_info_webpage)
if 'token' in video_info: if 'token' in video_info:
break break
@ -850,7 +854,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
# annotations # annotations
video_annotations = None video_annotations = None
if self._downloader.params.get('writeannotations', False): if self._downloader.params.get('writeannotations', False):
video_annotations = self._extract_annotations(video_id) video_annotations = self._extract_annotations(video_id)
# Decide which formats to download # Decide which formats to download
try: try:
@ -900,7 +904,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'player_url': player_url, 'player_url': player_url,
}] }]
elif len(video_info.get('url_encoded_fmt_stream_map', [])) >= 1 or len(video_info.get('adaptive_fmts', [])) >= 1: elif len(video_info.get('url_encoded_fmt_stream_map', [])) >= 1 or len(video_info.get('adaptive_fmts', [])) >= 1:
encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts',[''])[0] encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
if 'rtmpe%3Dyes' in encoded_url_map: if 'rtmpe%3Dyes' in encoded_url_map:
raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
url_map = {} url_map = {}
@ -974,6 +978,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
dash_manifest_url = video_info.get('dashmpd')[0] dash_manifest_url = video_info.get('dashmpd')[0]
else: else:
dash_manifest_url = ytplayer_config['args']['dashmpd'] dash_manifest_url = ytplayer_config['args']['dashmpd']
def decrypt_sig(mobj): def decrypt_sig(mobj):
s = mobj.group(1) s = mobj.group(1)
dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
@ -1014,25 +1019,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'uploader': video_uploader, 'uploader': video_uploader,
'uploader_id': video_uploader_id, 'uploader_id': video_uploader_id,
'upload_date': upload_date, 'upload_date': upload_date,
'title': video_title, 'title': video_title,
'thumbnail': video_thumbnail, 'thumbnail': video_thumbnail,
'description': video_description, 'description': video_description,
'categories': video_categories, 'categories': video_categories,
'subtitles': video_subtitles, 'subtitles': video_subtitles,
'duration': video_duration, 'duration': video_duration,
'age_limit': 18 if age_gate else 0, 'age_limit': 18 if age_gate else 0,
'annotations': video_annotations, 'annotations': video_annotations,
'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
'view_count': view_count, 'view_count': view_count,
'like_count': like_count, 'like_count': like_count,
'dislike_count': dislike_count, 'dislike_count': dislike_count,
'formats': formats, 'formats': formats,
} }
class YoutubePlaylistIE(YoutubeBaseInfoExtractor): class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com playlists' IE_DESC = 'YouTube.com playlists'
_VALID_URL = r"""(?x)(?: _VALID_URL = r"""(?x)(?:
@ -1163,7 +1169,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
return self._extract_mix(playlist_id) return self._extract_mix(playlist_id)
if playlist_id.startswith('TL'): if playlist_id.startswith('TL'):
raise ExtractorError('For downloading YouTube.com top lists, use ' raise ExtractorError('For downloading YouTube.com top lists, use '
'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True) 'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True)
url = self._TEMPLATE_URL % playlist_id url = self._TEMPLATE_URL % playlist_id
page = self._download_webpage(url, playlist_id) page = self._download_webpage(url, playlist_id)
@ -1333,8 +1339,10 @@ class YoutubeUserIE(InfoExtractor):
# Don't return True if the url can be extracted with other youtube # Don't return True if the url can be extracted with other youtube
# extractor, the regex would is too permissive and it would match. # extractor, the regex would is too permissive and it would match.
other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls)
if any(ie.suitable(url) for ie in other_ies): return False if any(ie.suitable(url) for ie in other_ies):
else: return super(YoutubeUserIE, cls).suitable(url) return False
else:
return super(YoutubeUserIE, cls).suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
# Extract username # Extract username
@ -1540,8 +1548,8 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
paging = 0 paging = 0
for i in itertools.count(1): for i in itertools.count(1):
info = self._download_json(self._FEED_TEMPLATE % paging, info = self._download_json(self._FEED_TEMPLATE % paging,
'%s feed' % self._FEED_NAME, '%s feed' % self._FEED_NAME,
'Downloading page %s' % i) 'Downloading page %s' % i)
feed_html = info.get('feed_html') or info.get('content_html') feed_html = info.get('feed_html') or info.get('content_html')
load_more_widget_html = info.get('load_more_widget_html') or feed_html load_more_widget_html = info.get('load_more_widget_html') or feed_html
m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
@ -1557,12 +1565,14 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
paging = mobj.group('paging') paging = mobj.group('paging')
return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
_VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
_FEED_NAME = 'recommended' _FEED_NAME = 'recommended'
_PLAYLIST_TITLE = 'Youtube Recommended videos' _PLAYLIST_TITLE = 'Youtube Recommended videos'
class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor): class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor):
IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
_VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater' _VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater'
@ -1570,6 +1580,7 @@ class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor):
_PLAYLIST_TITLE = 'Youtube Watch Later' _PLAYLIST_TITLE = 'Youtube Watch Later'
_PERSONAL_FEED = True _PERSONAL_FEED = True
class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
_VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory'
@ -1577,6 +1588,7 @@ class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
_PERSONAL_FEED = True _PERSONAL_FEED = True
_PLAYLIST_TITLE = 'Youtube Watch History' _PLAYLIST_TITLE = 'Youtube Watch History'
class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
IE_NAME = 'youtube:favorites' IE_NAME = 'youtube:favorites'
IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'

@ -621,7 +621,7 @@ def parseOpts(overrideArguments=None):
postproc.add_option( postproc.add_option(
'--exec', '--exec',
metavar='CMD', dest='exec_cmd', metavar='CMD', dest='exec_cmd',
help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'' ) help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'')
parser.add_option_group(general) parser.add_option_group(general)
parser.add_option_group(selection) parser.add_option_group(selection)

@ -26,4 +26,3 @@ class ExecAfterDownloadPP(PostProcessor):
'Command returned error code %d' % retCode) 'Command returned error code %d' % retCode)
return None, information # by default, keep file and do nothing return None, information # by default, keep file and do nothing

@ -202,7 +202,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
extension = 'wav' extension = 'wav'
more_opts += ['-f', 'wav'] more_opts += ['-f', 'wav']
prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
new_path = prefix + sep + extension new_path = prefix + sep + extension
# If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly. # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
@ -216,7 +216,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
self._downloader.to_screen(u'[' + self._executable + '] Destination: ' + new_path) self._downloader.to_screen(u'[' + self._executable + '] Destination: ' + new_path)
self.run_ffmpeg(path, new_path, acodec, more_opts) self.run_ffmpeg(path, new_path, acodec, more_opts)
except: except:
etype,e,tb = sys.exc_info() etype, e, tb = sys.exc_info()
if isinstance(e, AudioConversionError): if isinstance(e, AudioConversionError):
msg = u'audio conversion failed: ' + e.msg msg = u'audio conversion failed: ' + e.msg
else: else:
@ -231,13 +231,13 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
self._downloader.report_warning(u'Cannot update utime of audio file') self._downloader.report_warning(u'Cannot update utime of audio file')
information['filepath'] = new_path information['filepath'] = new_path
return self._nopostoverwrites,information return self._nopostoverwrites, information
class FFmpegVideoConvertor(FFmpegPostProcessor): class FFmpegVideoConvertor(FFmpegPostProcessor):
def __init__(self, downloader=None,preferedformat=None): def __init__(self, downloader=None, preferedformat=None):
super(FFmpegVideoConvertor, self).__init__(downloader) super(FFmpegVideoConvertor, self).__init__(downloader)
self._preferedformat=preferedformat self._preferedformat = preferedformat
def run(self, information): def run(self, information):
path = information['filepath'] path = information['filepath']
@ -245,13 +245,13 @@ class FFmpegVideoConvertor(FFmpegPostProcessor):
outpath = prefix + sep + self._preferedformat outpath = prefix + sep + self._preferedformat
if information['ext'] == self._preferedformat: if information['ext'] == self._preferedformat:
self._downloader.to_screen(u'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat)) self._downloader.to_screen(u'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
return True,information return True, information
self._downloader.to_screen(u'['+'ffmpeg'+'] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) +outpath) self._downloader.to_screen(u'[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
self.run_ffmpeg(path, outpath, []) self.run_ffmpeg(path, outpath, [])
information['filepath'] = outpath information['filepath'] = outpath
information['format'] = self._preferedformat information['format'] = self._preferedformat
information['ext'] = self._preferedformat information['ext'] = self._preferedformat
return False,information return False, information
class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
@ -466,7 +466,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy'] opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy']
for (i, lang) in enumerate(sub_langs): for (i, lang) in enumerate(sub_langs):
opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text']) opts.extend(['-map', '%d:0' % (i + 1), '-c:s:%d' % i, 'mov_text'])
lang_code = self._conver_lang_code(lang) lang_code = self._conver_lang_code(lang)
if lang_code is not None: if lang_code is not None:
opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])

Some files were not shown because too many files have changed in this diff Show More

Loading…
Cancel
Save