aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/FileDownloader.py75
-rw-r--r--youtube_dl/PostProcessor.py2
-rw-r--r--youtube_dl/YoutubeDL.py158
-rw-r--r--youtube_dl/__init__.py113
-rw-r--r--youtube_dl/extractor/__init__.py18
-rw-r--r--youtube_dl/extractor/arte.py52
-rw-r--r--youtube_dl/extractor/bambuser.py81
-rw-r--r--youtube_dl/extractor/brightcove.py61
-rw-r--r--youtube_dl/extractor/canalc2.py6
-rw-r--r--youtube_dl/extractor/cinemassacre.py4
-rw-r--r--youtube_dl/extractor/cnn.py2
-rw-r--r--youtube_dl/extractor/common.py27
-rw-r--r--youtube_dl/extractor/dailymotion.py31
-rw-r--r--youtube_dl/extractor/depositfiles.py2
-rw-r--r--youtube_dl/extractor/eitb.py37
-rw-r--r--youtube_dl/extractor/exfm.py2
-rw-r--r--youtube_dl/extractor/extremetube.py50
-rw-r--r--youtube_dl/extractor/gamekings.py38
-rw-r--r--youtube_dl/extractor/generic.py28
-rw-r--r--youtube_dl/extractor/hypem.py4
-rw-r--r--youtube_dl/extractor/kankan.py7
-rw-r--r--youtube_dl/extractor/keezmovies.py8
-rw-r--r--youtube_dl/extractor/livestream.py54
-rw-r--r--youtube_dl/extractor/metacafe.py51
-rw-r--r--youtube_dl/extractor/mofosex.py49
-rw-r--r--youtube_dl/extractor/mtv.py5
-rw-r--r--youtube_dl/extractor/myspace.py48
-rw-r--r--youtube_dl/extractor/pornhub.py6
-rw-r--r--youtube_dl/extractor/redtube.py4
-rw-r--r--youtube_dl/extractor/rtlnow.py12
-rw-r--r--youtube_dl/extractor/slashdot.py1
-rw-r--r--youtube_dl/extractor/soundcloud.py132
-rw-r--r--youtube_dl/extractor/southparkstudios.py25
-rw-r--r--youtube_dl/extractor/space.py35
-rw-r--r--youtube_dl/extractor/spankwire.py6
-rw-r--r--youtube_dl/extractor/spiegel.py50
-rw-r--r--youtube_dl/extractor/subtitles.py12
-rw-r--r--youtube_dl/extractor/teamcoco.py41
-rw-r--r--youtube_dl/extractor/ted.py72
-rw-r--r--youtube_dl/extractor/tube8.py6
-rw-r--r--youtube_dl/extractor/tvp.py42
-rw-r--r--youtube_dl/extractor/vevo.py95
-rw-r--r--youtube_dl/extractor/viddler.py2
-rw-r--r--youtube_dl/extractor/vimeo.py17
-rw-r--r--youtube_dl/extractor/vine.py2
-rw-r--r--youtube_dl/extractor/vk.py45
-rw-r--r--youtube_dl/extractor/weibo.py1
-rw-r--r--youtube_dl/extractor/xnxx.py2
-rw-r--r--youtube_dl/extractor/xtube.py55
-rw-r--r--youtube_dl/extractor/yahoo.py2
-rw-r--r--youtube_dl/extractor/youku.py6
-rw-r--r--youtube_dl/extractor/youporn.py8
-rw-r--r--youtube_dl/extractor/youtube.py78
-rw-r--r--youtube_dl/update.py6
-rw-r--r--youtube_dl/version.py2
55 files changed, 1334 insertions, 444 deletions
diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py
index 664b78662..84a539b82 100644
--- a/youtube_dl/FileDownloader.py
+++ b/youtube_dl/FileDownloader.py
@@ -4,12 +4,16 @@ import re
import subprocess
import sys
import time
-import traceback
-if os.name == 'nt':
- import ctypes
-
-from .utils import *
+from .utils import (
+ compat_urllib_error,
+ compat_urllib_request,
+ ContentTooShortError,
+ determine_ext,
+ encodeFilename,
+ sanitize_open,
+ timeconvert,
+)
class FileDownloader(object):
@@ -144,16 +148,8 @@ class FileDownloader(object):
def to_stderr(self, message):
self.ydl.to_screen(message)
- def to_cons_title(self, message):
- """Set console/terminal window title to message."""
- if not self.params.get('consoletitle', False):
- return
- if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
- # c_wchar_p() might not be necessary if `message` is
- # already of type unicode()
- ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
- elif 'TERM' in os.environ:
- self.to_screen('\033]0;%s\007' % message, skip_eol=True)
+ def to_console_title(self, message):
+ self.ydl.to_console_title(message)
def trouble(self, *args, **kargs):
self.ydl.trouble(*args, **kargs)
@@ -194,7 +190,7 @@ class FileDownloader(object):
if old_filename == new_filename:
return
os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
- except (IOError, OSError) as err:
+ except (IOError, OSError):
self.report_error(u'unable to rename file')
def try_utime(self, filename, last_modified_hdr):
@@ -227,8 +223,14 @@ class FileDownloader(object):
if self.params.get('noprogress', False):
return
clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
- eta_str = self.format_eta(eta)
- percent_str = self.format_percent(percent)
+ if eta is not None:
+ eta_str = self.format_eta(eta)
+ else:
+ eta_str = 'Unknown ETA'
+ if percent is not None:
+ percent_str = self.format_percent(percent)
+ else:
+ percent_str = 'Unknown %'
speed_str = self.format_speed(speed)
if self.params.get('progress_with_newline', False):
self.to_screen(u'[download] %s of %s at %s ETA %s' %
@@ -236,7 +238,7 @@ class FileDownloader(object):
else:
self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' %
(clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
- self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
+ self.to_console_title(u'youtube-dl - %s of %s at %s ETA %s' %
(percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
def report_resuming_byte(self, resume_len):
@@ -251,7 +253,7 @@ class FileDownloader(object):
"""Report file has already been fully downloaded."""
try:
self.to_screen(u'[download] %s has already been downloaded' % file_name)
- except (UnicodeEncodeError) as err:
+ except UnicodeEncodeError:
self.to_screen(u'[download] The file has already been downloaded')
def report_unable_to_resume(self):
@@ -267,7 +269,7 @@ class FileDownloader(object):
self.to_screen(u'\r%s[download] 100%% of %s in %s' %
(clear_line, data_len_str, self.format_seconds(tot_time)))
- def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
+ def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url, live):
def run_rtmpdump(args):
start = time.time()
resume_percent = None
@@ -348,6 +350,8 @@ class FileDownloader(object):
basic_args += ['--tcUrl', url]
if test:
basic_args += ['--stop', '1']
+ if live:
+ basic_args += ['--live']
args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)]
if self.params.get('verbose', False):
try:
@@ -422,15 +426,20 @@ class FileDownloader(object):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
- args = ['ffmpeg', '-y', '-i', url, '-f', 'mp4', tmpfilename]
- # Check for ffmpeg first
- try:
- subprocess.call(['ffmpeg', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
- except (OSError, IOError):
- self.report_error(u'm3u8 download detected but "%s" could not be run' % args[0] )
- return False
+ args = ['-y', '-i', url, '-f', 'mp4', '-c', 'copy',
+ '-bsf:a', 'aac_adtstoasc', tmpfilename]
- retval = subprocess.call(args)
+ for program in ['avconv', 'ffmpeg']:
+ try:
+ subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+ break
+ except (OSError, IOError):
+ pass
+ else:
+ self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found')
+ cmd = [program] + args
+
+ retval = subprocess.call(cmd)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
@@ -467,7 +476,8 @@ class FileDownloader(object):
info_dict.get('player_url', None),
info_dict.get('page_url', None),
info_dict.get('play_path', None),
- info_dict.get('tc_url', None))
+ info_dict.get('tc_url', None),
+ info_dict.get('rtmp_live', False))
# Attempt to download using mplayer
if url.startswith('mms') or url.startswith('rtsp'):
@@ -606,12 +616,11 @@ class FileDownloader(object):
# Progress message
speed = self.calc_speed(start, time.time(), byte_counter - resume_len)
if data_len is None:
- self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
- eta = None
+ eta = percent = None
else:
percent = self.calc_percent(byte_counter, data_len)
eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
- self.report_progress(percent, data_len_str, speed, eta)
+ self.report_progress(percent, data_len_str, speed, eta)
self._hook_progress({
'downloaded_bytes': byte_counter,
diff --git a/youtube_dl/PostProcessor.py b/youtube_dl/PostProcessor.py
index 13b56ede5..69aedf87a 100644
--- a/youtube_dl/PostProcessor.py
+++ b/youtube_dl/PostProcessor.py
@@ -501,7 +501,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
options = ['-c', 'copy']
for (name, value) in metadata.items():
- options.extend(['-metadata', '%s="%s"' % (name, value)])
+ options.extend(['-metadata', '%s=%s' % (name, value)])
options.extend(['-f', ext])
self._downloader.to_screen(u'[ffmpeg] Adding metadata to \'%s\'' % filename)
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index 313295839..20eed96ca 100644
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -13,7 +13,34 @@ import sys
import time
import traceback
-from .utils import *
+if os.name == 'nt':
+ import ctypes
+
+from .utils import (
+ compat_http_client,
+ compat_print,
+ compat_str,
+ compat_urllib_error,
+ compat_urllib_request,
+ ContentTooShortError,
+ date_from_str,
+ DateRange,
+ determine_ext,
+ DownloadError,
+ encodeFilename,
+ ExtractorError,
+ locked_file,
+ MaxDownloadsReached,
+ PostProcessingError,
+ preferredencoding,
+ SameFileError,
+ sanitize_filename,
+ subtitles_filename,
+ takewhile_inclusive,
+ UnavailableVideoError,
+ write_json_file,
+ write_string,
+)
from .extractor import get_info_extractor, gen_extractors
from .FileDownloader import FileDownloader
@@ -176,6 +203,35 @@ class YoutubeDL(object):
output = output.encode(preferredencoding())
sys.stderr.write(output)
+ def to_console_title(self, message):
+ if not self.params.get('consoletitle', False):
+ return
+ if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
+ # c_wchar_p() might not be necessary if `message` is
+ # already of type unicode()
+ ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
+ elif 'TERM' in os.environ:
+ write_string(u'\033]0;%s\007' % message, self._screen_file)
+
+ def save_console_title(self):
+ if not self.params.get('consoletitle', False):
+ return
+ if 'TERM' in os.environ:
+ write_string(u'\033[22t', self._screen_file)
+
+ def restore_console_title(self):
+ if not self.params.get('consoletitle', False):
+ return
+ if 'TERM' in os.environ:
+ write_string(u'\033[23t', self._screen_file)
+
+ def __enter__(self):
+ self.save_console_title()
+ return self
+
+ def __exit__(self, *args):
+ self.restore_console_title()
+
def fixed_template(self):
"""Checks if the output template is fixed."""
return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None)
@@ -254,7 +310,7 @@ class YoutubeDL(object):
"""Report file has already been fully downloaded."""
try:
self.to_screen(u'[download] %s has already been downloaded' % file_name)
- except (UnicodeEncodeError) as err:
+ except UnicodeEncodeError:
self.to_screen(u'[download] The file has already been downloaded')
def increment_downloads(self):
@@ -272,7 +328,7 @@ class YoutubeDL(object):
autonumber_size = 5
autonumber_templ = u'%0' + str(autonumber_size) + u'd'
template_dict['autonumber'] = autonumber_templ % self._num_downloads
- if template_dict['playlist_index'] is not None:
+ if template_dict.get('playlist_index') is not None:
template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index']
sanitize = lambda k, v: sanitize_filename(
@@ -318,6 +374,12 @@ class YoutubeDL(object):
% info_dict)
return None
+ @staticmethod
+ def add_extra_info(info_dict, extra_info):
+ '''Set the keys from extra_info in info dict if they are missing'''
+ for key, value in extra_info.items():
+ info_dict.setdefault(key, value)
+
def extract_info(self, url, download=True, ie_key=None, extra_info={}):
'''
Returns a list with a dictionary for each video we find.
@@ -344,17 +406,17 @@ class YoutubeDL(object):
break
if isinstance(ie_result, list):
# Backwards compatibility: old IE result format
- for result in ie_result:
- result.update(extra_info)
ie_result = {
'_type': 'compat_list',
'entries': ie_result,
}
- else:
- ie_result.update(extra_info)
- if 'extractor' not in ie_result:
- ie_result['extractor'] = ie.IE_NAME
- return self.process_ie_result(ie_result, download=download)
+ self.add_extra_info(ie_result,
+ {
+ 'extractor': ie.IE_NAME,
+ 'webpage_url': url,
+ 'extractor_key': ie.ie_key(),
+ })
+ return self.process_ie_result(ie_result, download, extra_info)
except ExtractorError as de: # An error we somewhat expected
self.report_error(compat_str(de), de.format_traceback())
break
@@ -378,8 +440,8 @@ class YoutubeDL(object):
result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
if result_type == 'video':
- ie_result.update(extra_info)
- return self.process_video_result(ie_result)
+ self.add_extra_info(ie_result, extra_info)
+ return self.process_video_result(ie_result, download=download)
elif result_type == 'url':
# We have to add extra_info to the results because it may be
# contained in a playlist
@@ -388,6 +450,7 @@ class YoutubeDL(object):
ie_key=ie_result.get('ie_key'),
extra_info=extra_info)
elif result_type == 'playlist':
+ self.add_extra_info(ie_result, extra_info)
# We process each entry in the playlist
playlist = ie_result.get('title', None) or ie_result.get('id', None)
self.to_screen(u'[download] Downloading playlist: %s' % playlist)
@@ -413,12 +476,10 @@ class YoutubeDL(object):
extra = {
'playlist': playlist,
'playlist_index': i + playliststart,
+ 'extractor': ie_result['extractor'],
+ 'webpage_url': ie_result['webpage_url'],
+ 'extractor_key': ie_result['extractor_key'],
}
- if not 'extractor' in entry:
- # We set the extractor, if it's an url it will be set then to
- # the new extractor, but if it's already a video we must make
- # sure it's present: see issue #877
- entry['extractor'] = ie_result['extractor']
entry_result = self.process_ie_result(entry,
download=download,
extra_info=extra)
@@ -427,10 +488,15 @@ class YoutubeDL(object):
return ie_result
elif result_type == 'compat_list':
def _fixup(r):
- r.setdefault('extractor', ie_result['extractor'])
+ self.add_extra_info(r,
+ {
+ 'extractor': ie_result['extractor'],
+ 'webpage_url': ie_result['webpage_url'],
+ 'extractor_key': ie_result['extractor_key'],
+ })
return r
ie_result['entries'] = [
- self.process_ie_result(_fixup(r), download=download)
+ self.process_ie_result(_fixup(r), download, extra_info)
for r in ie_result['entries']
]
return ie_result
@@ -482,7 +548,7 @@ class YoutubeDL(object):
format['format'] = u'{id} - {res}{note}'.format(
id=format['format_id'],
res=self.format_resolution(format),
- note=u' ({})'.format(format['format_note']) if format.get('format_note') is not None else '',
+ note=u' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '',
)
# Automatically determine file extension if missing
if 'ext' not in format:
@@ -630,7 +696,7 @@ class YoutubeDL(object):
# subtitles download errors are already managed as troubles in relevant IE
# that way it will silently go on when used with unsupporting IE
subtitles = info_dict['subtitles']
- sub_format = self.params.get('subtitlesformat')
+ sub_format = self.params.get('subtitlesformat', 'srt')
for sub_lang in subtitles.keys():
sub = subtitles[sub_lang]
if sub is None:
@@ -759,6 +825,8 @@ class YoutubeDL(object):
@staticmethod
def format_resolution(format, default='unknown'):
+ if format.get('_resolution') is not None:
+ return format['_resolution']
if format.get('height') is not None:
if format.get('width') is not None:
res = u'%sx%s' % (format['width'], format['height'])
@@ -769,19 +837,45 @@ class YoutubeDL(object):
return res
def list_formats(self, info_dict):
- formats_s = []
- for format in info_dict.get('formats', [info_dict]):
- formats_s.append(u'%-15s%-7s %-15s%s' % (
+ def format_note(fdict):
+ if fdict.get('format_note') is not None:
+ return fdict['format_note']
+ res = u''
+ if fdict.get('vcodec') is not None:
+ res += u'%-5s' % fdict['vcodec']
+ elif fdict.get('vbr') is not None:
+ res += u'video'
+ if fdict.get('vbr') is not None:
+ res += u'@%4dk' % fdict['vbr']
+ if fdict.get('acodec') is not None:
+ if res:
+ res += u', '
+ res += u'%-5s' % fdict['acodec']
+ elif fdict.get('abr') is not None:
+ if res:
+ res += u', '
+ res += 'audio'
+ if fdict.get('abr') is not None:
+ res += u'@%3dk' % fdict['abr']
+ return res
+
+ def line(format):
+ return (u'%-20s%-10s%-12s%s' % (
format['format_id'],
format['ext'],
- format.get('format_note', ''),
self.format_resolution(format),
+ format_note(format),
)
)
- if len(formats_s) != 1:
- formats_s[0] += ' (worst)'
- formats_s[-1] += ' (best)'
- formats_s = "\n".join(formats_s)
- self.to_screen(u'[info] Available formats for %s:\n'
- u'format code extension note resolution\n%s' % (
- info_dict['id'], formats_s))
+
+ formats = info_dict.get('formats', [info_dict])
+ formats_s = list(map(line, formats))
+ if len(formats) > 1:
+ formats_s[0] += (' ' if format_note(formats[0]) else '') + '(worst)'
+ formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)'
+
+ header_line = line({
+ 'format_id': u'format code', 'ext': u'extension',
+ '_resolution': u'resolution', 'format_note': u'note'})
+ self.to_screen(u'[info] Available formats for %s:\n%s\n%s' %
+ (info_dict['id'], header_line, u"\n".join(formats_s)))
diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index 48ffcbf8e..af4c9c5c4 100644
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -32,6 +32,8 @@ __authors__ = (
'Ismael Mejía',
'Steffan \'Ruirize\' James',
'Andras Elso',
+ 'Jelle van der Waa',
+ 'Marcin Cieślak',
)
__license__ = 'Public Domain'
@@ -349,7 +351,7 @@ def parseOpts(overrideArguments=None):
'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
filesystem.add_option('--autonumber-size',
dest='autonumber_size', metavar='NUMBER',
- help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --autonumber option is given')
+ help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
filesystem.add_option('--restrict-filenames',
action='store_true', dest='restrictfilenames',
help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
@@ -358,7 +360,7 @@ def parseOpts(overrideArguments=None):
filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue',
- action='store_true', dest='continue_dl', help='resume partially downloaded files', default=True)
+ action='store_true', dest='continue_dl', help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.', default=True)
filesystem.add_option('--no-continue',
action='store_false', dest='continue_dl',
help='do not resume partially downloaded files (restart from beginning)')
@@ -601,8 +603,7 @@ def _real_main(argv=None):
u' file! Use "%%(ext)s" instead of %r' %
determine_ext(outtmpl, u''))
- # YoutubeDL
- ydl = YoutubeDL({
+ ydl_opts = {
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
@@ -665,61 +666,63 @@ def _real_main(argv=None):
'youtube_print_sig_code': opts.youtube_print_sig_code,
'age_limit': opts.age_limit,
'download_archive': opts.download_archive,
- })
+ }
- if opts.verbose:
- write_string(u'[debug] youtube-dl version ' + __version__ + u'\n')
- try:
- sp = subprocess.Popen(
- ['git', 'rev-parse', '--short', 'HEAD'],
- stdout=subprocess.PIPE, stderr=subprocess.PIPE,
- cwd=os.path.dirname(os.path.abspath(__file__)))
- out, err = sp.communicate()
- out = out.decode().strip()
- if re.match('[0-9a-f]+', out):
- write_string(u'[debug] Git HEAD: ' + out + u'\n')
- except:
+ with YoutubeDL(ydl_opts) as ydl:
+ if opts.verbose:
+ write_string(u'[debug] youtube-dl version ' + __version__ + u'\n')
try:
- sys.exc_clear()
+ sp = subprocess.Popen(
+ ['git', 'rev-parse', '--short', 'HEAD'],
+ stdout=subprocess.PIPE, stderr=subprocess.PIPE,
+ cwd=os.path.dirname(os.path.abspath(__file__)))
+ out, err = sp.communicate()
+ out = out.decode().strip()
+ if re.match('[0-9a-f]+', out):
+ write_string(u'[debug] Git HEAD: ' + out + u'\n')
except:
- pass
- write_string(u'[debug] Python version %s - %s' %(platform.python_version(), platform_name()) + u'\n')
-
- proxy_map = {}
- for handler in opener.handlers:
- if hasattr(handler, 'proxies'):
- proxy_map.update(handler.proxies)
- write_string(u'[debug] Proxy map: ' + compat_str(proxy_map) + u'\n')
-
- ydl.add_default_info_extractors()
-
- # PostProcessors
- # Add the metadata pp first, the other pps will copy it
- if opts.addmetadata:
- ydl.add_post_processor(FFmpegMetadataPP())
- if opts.extractaudio:
- ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
- if opts.recodevideo:
- ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
- if opts.embedsubtitles:
- ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
-
- # Update version
- if opts.update_self:
- update_self(ydl.to_screen, opts.verbose)
-
- # Maybe do nothing
- if len(all_urls) < 1:
- if not opts.update_self:
- parser.error(u'you must provide at least one URL')
- else:
- sys.exit()
+ try:
+ sys.exc_clear()
+ except:
+ pass
+ write_string(u'[debug] Python version %s - %s' %
+ (platform.python_version(), platform_name()) + u'\n')
+
+ proxy_map = {}
+ for handler in opener.handlers:
+ if hasattr(handler, 'proxies'):
+ proxy_map.update(handler.proxies)
+ write_string(u'[debug] Proxy map: ' + compat_str(proxy_map) + u'\n')
+
+ ydl.add_default_info_extractors()
+
+ # PostProcessors
+ # Add the metadata pp first, the other pps will copy it
+ if opts.addmetadata:
+ ydl.add_post_processor(FFmpegMetadataPP())
+ if opts.extractaudio:
+ ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
+ if opts.recodevideo:
+ ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
+ if opts.embedsubtitles:
+ ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
+
+ # Update version
+ if opts.update_self:
+ update_self(ydl.to_screen, opts.verbose)
+
+ # Maybe do nothing
+ if len(all_urls) < 1:
+ if not opts.update_self:
+ parser.error(u'you must provide at least one URL')
+ else:
+ sys.exit()
- try:
- retcode = ydl.download(all_urls)
- except MaxDownloadsReached:
- ydl.to_screen(u'--max-download limit reached, aborting.')
- retcode = 101
+ try:
+ retcode = ydl.download(all_urls)
+ except MaxDownloadsReached:
+ ydl.to_screen(u'--max-download limit reached, aborting.')
+ retcode = 101
# Dump cookie jar if requested
if opts.cookiefile is not None:
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 0d933986f..2d1e3cdfd 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -9,6 +9,7 @@ from .arte import (
ArteTVFutureIE,
)
from .auengine import AUEngineIE
+from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE
from .bliptv import BlipTVIE, BlipTVUserIE
from .bloomberg import BloombergIE
@@ -37,8 +38,10 @@ from .defense import DefenseGouvFrIE
from .ebaumsworld import EbaumsWorldIE
from .ehow import EHowIE
from .eighttracks import EightTracksIE
+from .eitb import EitbIE
from .escapist import EscapistIE
from .exfm import ExfmIE
+from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE
from .faz import FazIE
from .fktv import (
@@ -54,6 +57,7 @@ from .francetv import (
)
from .freesound import FreesoundIE
from .funnyordie import FunnyOrDieIE
+from .gamekings import GamekingsIE
from .gamespot import GameSpotIE
from .gametrailers import GametrailersIE
from .generic import GenericIE
@@ -76,13 +80,15 @@ from .keezmovies import KeezMoviesIE
from .kickstarter import KickStarterIE
from .keek import KeekIE
from .liveleak import LiveLeakIE
-from .livestream import LivestreamIE
+from .livestream import LivestreamIE, LivestreamOriginalIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mit import TechTVMITIE, MITIE
from .mixcloud import MixcloudIE
+from .mofosex import MofosexIE
from .mtv import MTVIE
from .muzu import MuzuTVIE
+from .myspace import MySpaceIE
from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .naver import NaverIE
@@ -110,7 +116,11 @@ from .slashdot import SlashdotIE
from .slideshare import SlideshareIE
from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
-from .southparkstudios import SouthParkStudiosIE
+from .southparkstudios import (
+ SouthParkStudiosIE,
+ SouthparkDeIE,
+)
+from .space import SpaceIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE
@@ -128,6 +138,7 @@ from .tube8 import Tube8IE
from .tudou import TudouIE
from .tumblr import TumblrIE
from .tutv import TutvIE
+from .tvp import TvpIE
from .unistra import UnistraIE
from .ustream import UstreamIE, UstreamChannelIE
from .vbox7 import Vbox7IE
@@ -141,6 +152,7 @@ from .videofyme import VideofyMeIE
from .videopremium import VideoPremiumIE
from .vimeo import VimeoIE, VimeoChannelIE
from .vine import VineIE
+from .vk import VKIE
from .wat import WatIE
from .websurg import WeBSurgIE
from .weibo import WeiboIE
@@ -149,6 +161,7 @@ from .worldstarhiphop import WorldStarHipHopIE
from .xhamster import XHamsterIE
from .xnxx import XNXXIE
from .xvideos import XVideosIE
+from .xtube import XTubeIE
from .yahoo import YahooIE, YahooSearchIE
from .youjizz import YouJizzIE
from .youku import YoukuIE
@@ -157,6 +170,7 @@ from .youtube import (
YoutubeIE,
YoutubePlaylistIE,
YoutubeSearchIE,
+ YoutubeSearchDateIE,
YoutubeUserIE,
YoutubeChannelIE,
YoutubeShowIE,
diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py
index d39b48951..44d0b5d70 100644
--- a/youtube_dl/extractor/arte.py
+++ b/youtube_dl/extractor/arte.py
@@ -10,6 +10,7 @@ from ..utils import (
unified_strdate,
determine_ext,
get_element_by_id,
+ compat_str,
)
# There are different sources of video in arte.tv, the extraction process
@@ -68,7 +69,7 @@ class ArteTvIE(InfoExtractor):
lang = mobj.group('lang')
return self._extract_liveweb(url, name, lang)
- if re.search(self._LIVE_URL, video_id) is not None:
+ if re.search(self._LIVE_URL, url) is not None:
raise ExtractorError(u'Arte live streams are not yet supported, sorry')
# self.extractLiveStream(url)
# return
@@ -114,7 +115,7 @@ class ArteTvIE(InfoExtractor):
event_doc = config_doc.find('event')
url_node = event_doc.find('video').find('urlHd')
if url_node is None:
- url_node = video_doc.find('urlSd')
+ url_node = event_doc.find('urlSd')
return {'id': video_id,
'title': event_doc.find('name%s' % lang.capitalize()).text,
@@ -158,7 +159,9 @@ class ArteTVPlus7IE(InfoExtractor):
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
}
- formats = player_info['VSR'].values()
+ all_formats = player_info['VSR'].values()
+ # Some formats use the m3u8 protocol
+ all_formats = list(filter(lambda f: f.get('videoFormat') != 'M3U8', all_formats))
def _match_lang(f):
if f.get('versionCode') is None:
return True
@@ -170,24 +173,39 @@ class ArteTVPlus7IE(InfoExtractor):
regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
return any(re.match(r, f['versionCode']) for r in regexes)
# Some formats may not be in the same language as the url
- formats = filter(_match_lang, formats)
- # Some formats use the m3u8 protocol
- formats = filter(lambda f: f.get('videoFormat') != 'M3U8', formats)
- # We order the formats by quality
+ formats = filter(_match_lang, all_formats)
formats = list(formats) # in python3 filter returns an iterator
+ if not formats:
+ # Some videos are only available in the 'Originalversion'
+ # they aren't tagged as being in French or German
+ if all(f['versionCode'] == 'VO' for f in all_formats):
+ formats = all_formats
+ else:
+ raise ExtractorError(u'The formats list is empty')
+
if re.match(r'[A-Z]Q', formats[0]['quality']) is not None:
- sort_key = lambda f: ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
+ def sort_key(f):
+ return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
else:
- sort_key = lambda f: int(f.get('height',-1))
+ def sort_key(f):
+ return (
+ # Sort first by quality
+ int(f.get('height',-1)),
+ int(f.get('bitrate',-1)),
+ # The original version with subtitles has lower relevance
+ re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
+ # The version with sourds/mal subtitles has also lower relevance
+ re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None,
+ )
formats = sorted(formats, key=sort_key)
- # Prefer videos without subtitles in the same language
- formats = sorted(formats, key=lambda f: re.match(r'VO(F|A)-STM\1', f.get('versionCode', '')) is None)
- # Pick the best quality
def _format(format_info):
- quality = format_info['quality']
- m_quality = re.match(r'\w*? - (\d*)p', quality)
- if m_quality is not None:
- quality = m_quality.group(1)
+ quality = ''
+ height = format_info.get('height')
+ if height is not None:
+ quality = compat_str(height)
+ bitrate = format_info.get('bitrate')
+ if bitrate is not None:
+ quality += '-%d' % bitrate
if format_info.get('versionCode') is not None:
format_id = u'%s-%s' % (quality, format_info['versionCode'])
else:
@@ -196,7 +214,7 @@ class ArteTVPlus7IE(InfoExtractor):
'format_id': format_id,
'format_note': format_info.get('versionLibelle'),
'width': format_info.get('width'),
- 'height': format_info.get('height'),
+ 'height': height,
}
if format_info['mediaType'] == u'rtmp':
info['url'] = format_info['streamer']
diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py
new file mode 100644
index 000000000..967568c4a
--- /dev/null
+++ b/youtube_dl/extractor/bambuser.py
@@ -0,0 +1,81 @@
+import re
+import json
+import itertools
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_request,
+)
+
+
+class BambuserIE(InfoExtractor):
+ IE_NAME = u'bambuser'
+ _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
+ _API_KEY = '005f64509e19a868399060af746a00aa'
+
+ _TEST = {
+ u'url': u'http://bambuser.com/v/4050584',
+ # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
+ #u'md5': u'fba8f7693e48fd4e8641b3fd5539a641',
+ u'info_dict': {
+ u'id': u'4050584',
+ u'ext': u'flv',
+ u'title': u'Education engineering days - lightning talks',
+ u'duration': 3741,
+ u'uploader': u'pixelversity',
+ u'uploader_id': u'344706',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ info_url = ('http://player-c.api.bambuser.com/getVideo.json?'
+ '&api_key=%s&vid=%s' % (self._API_KEY, video_id))
+ info_json = self._download_webpage(info_url, video_id)
+ info = json.loads(info_json)['result']
+
+ return {
+ 'id': video_id,
+ 'title': info['title'],
+ 'url': info['url'],
+ 'thumbnail': info.get('preview'),
+ 'duration': int(info['length']),
+ 'view_count': int(info['views_total']),
+ 'uploader': info['username'],
+ 'uploader_id': info['uid'],
+ }
+
+
+class BambuserChannelIE(InfoExtractor):
+ IE_NAME = u'bambuser:channel'
+ _VALID_URL = r'http://bambuser.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
+ # The maximum number we can get with each request
+ _STEP = 50
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user = mobj.group('user')
+ urls = []
+ last_id = ''
+ for i in itertools.count(1):
+ req_url = ('http://bambuser.com/xhr-api/index.php?username={user}'
+ '&sort=created&access_mode=0%2C1%2C2&limit={count}'
+ '&method=broadcast&format=json&vid_older_than={last}'
+ ).format(user=user, count=self._STEP, last=last_id)
+ req = compat_urllib_request.Request(req_url)
+ # Without setting this header, we wouldn't get any result
+ req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
+ info_json = self._download_webpage(req, user,
+ u'Downloading page %d' % i)
+ results = json.loads(info_json)['result']
+ if len(results) == 0:
+ break
+ last_id = results[-1]['vid']
+ urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)
+
+ return {
+ '_type': 'playlist',
+ 'title': user,
+ 'entries': urls,
+ }
diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
index 1392f382a..d8c35465a 100644
--- a/youtube_dl/extractor/brightcove.py
+++ b/youtube_dl/extractor/brightcove.py
@@ -9,10 +9,13 @@ from ..utils import (
compat_urllib_parse,
find_xpath_attr,
compat_urlparse,
+ compat_str,
+ compat_urllib_request,
ExtractorError,
)
+
class BrightcoveIE(InfoExtractor):
_VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
_FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
@@ -23,7 +26,7 @@ class BrightcoveIE(InfoExtractor):
# From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
u'file': u'2371591881001.mp4',
- u'md5': u'9e80619e0a94663f0bdc849b4566af19',
+ u'md5': u'8eccab865181d29ec2958f32a6a754f5',
u'note': u'Test Brightcove downloads and detection in GenericIE',
u'info_dict': {
u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
@@ -41,6 +44,17 @@ class BrightcoveIE(InfoExtractor):
u'uploader': u'Oracle',
},
},
+ {
+ # From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/
+ u'url': u'http://c.brightcove.com/services/viewer/federated_f9?&playerID=1265504713001&publisherID=AQ%7E%7E%2CAAABBzUwv1E%7E%2CxP-xFHVUstiMFlNYfvF4G9yFnNaqCw_9&videoID=2750934548001',
+ u'info_dict': {
+ u'id': u'2750934548001',
+ u'ext': u'mp4',
+ u'title': u'This Bracelet Acts as a Personal Thermostat',
+ u'description': u'md5:547b78c64f4112766ccf4e151c20b6a0',
+ u'uploader': u'Mashable',
+ },
+ },
]
@classmethod
@@ -68,24 +82,48 @@ class BrightcoveIE(InfoExtractor):
videoPlayer = find_xpath_attr(object_doc, './param', 'name', '@videoPlayer')
if videoPlayer is not None:
params['@videoPlayer'] = videoPlayer.attrib['value']
+ linkBase = find_xpath_attr(object_doc, './param', 'name', 'linkBaseURL')
+ if linkBase is not None:
+ params['linkBaseURL'] = linkBase.attrib['value']
data = compat_urllib_parse.urlencode(params)
return cls._FEDERATED_URL_TEMPLATE % data
+ @classmethod
+ def _extract_brightcove_url(cls, webpage):
+ """Try to extract the brightcove url from the wepbage, returns None
+ if it can't be found
+ """
+ m_brightcove = re.search(
+ r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>',
+ webpage, re.DOTALL)
+ if m_brightcove is not None:
+ return cls._build_brighcove_url(m_brightcove.group())
+ else:
+ return None
+
def _real_extract(self, url):
+ # Change the 'videoId' and others field to '@videoPlayer'
+ url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url)
+ # Change bckey (used by bcove.me urls) to playerKey
+ url = re.sub(r'(?<=[?&])bckey', 'playerKey', url)
mobj = re.match(self._VALID_URL, url)
query_str = mobj.group('query')
query = compat_urlparse.parse_qs(query_str)
videoPlayer = query.get('@videoPlayer')
if videoPlayer:
- return self._get_video_info(videoPlayer[0], query_str)
+ return self._get_video_info(videoPlayer[0], query_str, query)
else:
player_key = query['playerKey']
return self._get_playlist_info(player_key[0])
- def _get_video_info(self, video_id, query):
- request_url = self._FEDERATED_URL_TEMPLATE % query
- webpage = self._download_webpage(request_url, video_id)
+ def _get_video_info(self, video_id, query_str, query):
+ request_url = self._FEDERATED_URL_TEMPLATE % query_str
+ req = compat_urllib_request.Request(request_url)
+ linkBase = query.get('linkBaseURL')
+ if linkBase is not None:
+ req.add_header('Referer', linkBase[0])
+ webpage = self._download_webpage(req, video_id)
self.report_extraction(video_id)
info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
@@ -109,7 +147,7 @@ class BrightcoveIE(InfoExtractor):
def _extract_video_info(self, video_info):
info = {
- 'id': video_info['id'],
+ 'id': compat_str(video_info['id']),
'title': video_info['displayName'],
'description': video_info.get('shortDescription'),
'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
@@ -119,15 +157,14 @@ class BrightcoveIE(InfoExtractor):
renditions = video_info.get('renditions')
if renditions:
renditions = sorted(renditions, key=lambda r: r['size'])
- best_format = renditions[-1]
- info.update({
- 'url': best_format['defaultURL'],
- 'ext': 'mp4',
- })
+ info['formats'] = [{
+ 'url': rend['defaultURL'],
+ 'height': rend.get('frameHeight'),
+ 'width': rend.get('frameWidth'),
+ } for rend in renditions]
elif video_info.get('FLVFullLengthURL') is not None:
info.update({
'url': video_info['FLVFullLengthURL'],
- 'ext': 'flv',
})
else:
raise ExtractorError(u'Unable to extract video url for %s' % info['id'])
diff --git a/youtube_dl/extractor/canalc2.py b/youtube_dl/extractor/canalc2.py
index e7f4fa9fd..3d8d7f9d2 100644
--- a/youtube_dl/extractor/canalc2.py
+++ b/youtube_dl/extractor/canalc2.py
@@ -6,7 +6,7 @@ from .common import InfoExtractor
class Canalc2IE(InfoExtractor):
IE_NAME = 'canalc2.tv'
- _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
+ _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
_TEST = {
u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
@@ -18,7 +18,9 @@ class Canalc2IE(InfoExtractor):
}
def _real_extract(self, url):
- video_id = re.match(self._VALID_URL, url).group(1)
+ video_id = re.match(self._VALID_URL, url).group('id')
+ # We need to set the voir field for getting the file name
+ url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
webpage = self._download_webpage(url, video_id)
file_name = self._search_regex(
r"so\.addVariable\('file','(.*?)'\);",
diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py
index 2fe1033f0..f0d08cebf 100644
--- a/youtube_dl/extractor/cinemassacre.py
+++ b/youtube_dl/extractor/cinemassacre.py
@@ -41,7 +41,7 @@ class CinemassacreIE(InfoExtractor):
webpage_url = u'http://' + mobj.group('url')
webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
- mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/(?:embed|player)\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
+ mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
if not mobj:
raise ExtractorError(u'Can\'t extract embed url and video id')
playerdata_url = mobj.group(u'embed_url')
@@ -65,6 +65,7 @@ class CinemassacreIE(InfoExtractor):
{
'url': url,
'play_path': 'mp4:' + sd_file,
+ 'rtmp_live': True, # workaround
'ext': 'flv',
'format': 'sd',
'format_id': 'sd',
@@ -72,6 +73,7 @@ class CinemassacreIE(InfoExtractor):
{
'url': url,
'play_path': 'mp4:' + hd_file,
+ 'rtmp_live': True, # workaround
'ext': 'flv',
'format': 'hd',
'format_id': 'hd',
diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py
index a79f881cd..34adf6dda 100644
--- a/youtube_dl/extractor/cnn.py
+++ b/youtube_dl/extractor/cnn.py
@@ -6,7 +6,7 @@ from ..utils import determine_ext
class CNNIE(InfoExtractor):
- _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/
+ _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
(?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
_TESTS = [{
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index ce349fe20..f787d0a3c 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -63,7 +63,7 @@ class InfoExtractor(object):
* ext Will be calculated from url if missing
* format A human-readable description of the format
("mp4 container with h264/opus").
- Calculated from the format_id, width, height
+ Calculated from the format_id, width, height.
and format_note fields if missing.
* format_id A short description of the format
("mp4_h264_opus" or "19")
@@ -71,6 +71,13 @@ class InfoExtractor(object):
("3D" or "DASH video")
* width Width of the video, if known
* height Height of the video, if known
+ * abr Average audio bitrate in KBit/s
+ * acodec Name of the audio codec in use
+ * vbr Average video bitrate in KBit/s
+ * vcodec Name of the video codec in use
+ webpage_url: The url to the video webpage, if given to youtube-dl it
+ should allow to get the same result again. (It will be set
+ by YoutubeDL if it's missing)
Unless mentioned otherwise, the fields should be Unicode strings.
@@ -312,13 +319,21 @@ class InfoExtractor(object):
# Helper functions for extracting OpenGraph info
@staticmethod
- def _og_regex(prop):
- return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop)
+ def _og_regexes(prop):
+ content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
+ property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop)
+ template = r'<meta[^>]+?%s[^>]+?%s'
+ return [
+ template % (property_re, content_re),
+ template % (content_re, property_re),
+ ]
def _og_search_property(self, prop, html, name=None, **kargs):
if name is None:
name = 'OpenGraph %s' % prop
- escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+ escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs)
+ if escaped is None:
+ return None
return unescapeHTML(escaped)
def _og_search_thumbnail(self, html, **kargs):
@@ -331,8 +346,8 @@ class InfoExtractor(object):
return self._og_search_property('title', html, **kargs)
def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
- regexes = [self._og_regex('video')]
- if secure: regexes.insert(0, self._og_regex('video:secure_url'))
+ regexes = self._og_regexes('video')
+ if secure: regexes = self._og_regexes('video:secure_url') + regexes
return self._html_search_regex(regexes, html, name, **kargs)
def _rta_search(self, html):
diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 4c0488245..71f5e03ee 100644
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -21,6 +21,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
"""Build a request with the family filter disabled"""
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
+ request.add_header('Cookie', 'ff=off')
return request
class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
@@ -61,6 +62,18 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
},
u'skip': u'VEVO is only available in some countries',
},
+ # age-restricted video
+ {
+ u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
+ u'file': u'xyh2zz.mp4',
+ u'md5': u'0d667a7b9cebecc3c89ee93099c4159d',
+ u'info_dict': {
+ u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
+ u'uploader': 'HotWaves1012',
+ u'age_limit': 18,
+ }
+
+ }
]
def _real_extract(self, url):
@@ -90,7 +103,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
# Looking for official user
r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
- webpage, 'video uploader')
+ webpage, 'video uploader', fatal=False)
+ age_limit = self._rta_search(webpage)
video_upload_date = None
mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
@@ -127,22 +141,23 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
raise ExtractorError(u'Unable to extract video URL')
# subtitles
- video_subtitles = self.extract_subtitles(video_id)
+ video_subtitles = self.extract_subtitles(video_id, webpage)
if self._downloader.params.get('listsubtitles', False):
- self._list_available_subtitles(video_id)
+ self._list_available_subtitles(video_id, webpage)
return
- return [{
+ return {
'id': video_id,
'formats': formats,
'uploader': video_uploader,
'upload_date': video_upload_date,
'title': self._og_search_title(webpage),
'subtitles': video_subtitles,
- 'thumbnail': info['thumbnail_url']
- }]
+ 'thumbnail': info['thumbnail_url'],
+ 'age_limit': age_limit,
+ }
- def _get_available_subtitles(self, video_id):
+ def _get_available_subtitles(self, video_id, webpage):
try:
sub_list = self._download_webpage(
'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
@@ -171,7 +186,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
webpage = self._download_webpage(request,
id, u'Downloading page %s' % pagenum)
- playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
+ playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage)
video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
diff --git a/youtube_dl/extractor/depositfiles.py b/youtube_dl/extractor/depositfiles.py
index d43348955..2c9fb5f2e 100644
--- a/youtube_dl/extractor/depositfiles.py
+++ b/youtube_dl/extractor/depositfiles.py
@@ -25,7 +25,7 @@ class DepositFilesIE(InfoExtractor):
url = 'http://depositfiles.com/en/files/' + file_id
# Retrieve file webpage with 'Free download' button pressed
- free_download_indication = { 'gateway_result' : '1' }
+ free_download_indication = {'gateway_result' : '1'}
request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
try:
self.report_download_webpage(file_id)
diff --git a/youtube_dl/extractor/eitb.py b/youtube_dl/extractor/eitb.py
new file mode 100644
index 000000000..4ba323148
--- /dev/null
+++ b/youtube_dl/extractor/eitb.py
@@ -0,0 +1,37 @@
+# encoding: utf-8
+import re
+
+from .common import InfoExtractor
+from .brightcove import BrightcoveIE
+from ..utils import ExtractorError
+
+
+class EitbIE(InfoExtractor):
+ IE_NAME = u'eitb.tv'
+ _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
+
+ _TEST = {
+ u'add_ie': ['Brightcove'],
+ u'url': u'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
+ u'md5': u'edf4436247185adee3ea18ce64c47998',
+ u'info_dict': {
+ u'id': u'2743577154001',
+ u'ext': u'mp4',
+ u'title': u'60 minutos (Lasa y Zabala, 30 años)',
+ # All videos from eitb has this description in the brightcove info
+ u'description': u'.',
+ u'uploader': u'Euskal Telebista',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ chapter_id = mobj.group('chapter_id')
+ webpage = self._download_webpage(url, chapter_id)
+ bc_url = BrightcoveIE._extract_brightcove_url(webpage)
+ if bc_url is None:
+ raise ExtractorError(u'Could not extract the Brightcove url')
+ # The BrightcoveExperience object doesn't contain the video id, we set
+ # it manually
+ bc_url += '&%40videoPlayer={0}'.format(chapter_id)
+ return self.url_result(bc_url, BrightcoveIE.ie_key())
diff --git a/youtube_dl/extractor/exfm.py b/youtube_dl/extractor/exfm.py
index c74556579..a51d79b08 100644
--- a/youtube_dl/extractor/exfm.py
+++ b/youtube_dl/extractor/exfm.py
@@ -21,6 +21,7 @@ class ExfmIE(InfoExtractor):
u'description': u'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
},
u'note': u'Soundcloud song',
+ u'skip': u'The site is down too often',
},
{
u'url': u'http://ex.fm/song/wddt8',
@@ -30,6 +31,7 @@ class ExfmIE(InfoExtractor):
u'title': u'Safe and Sound',
u'uploader': u'Capital Cities',
},
+ u'skip': u'The site is down too often',
},
]
diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
new file mode 100644
index 000000000..1c20e4364
--- /dev/null
+++ b/youtube_dl/extractor/extremetube.py
@@ -0,0 +1,50 @@
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse_urlparse,
+ compat_urllib_request,
+ compat_urllib_parse,
+)
+
+class ExtremeTubeIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+ _TEST = {
+ u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+ u'file': u'652431.mp4',
+ u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
+ u'info_dict': {
+ u"title": u"Music Video 14 british euro brit european cumshots swallow",
+ u"uploader": u"unknown",
+ u"age_limit": 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+ url = 'http://www.' + mobj.group('url')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ video_title = self._html_search_regex(r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title')
+ uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False)
+ video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
+ format = path.split('/')[5].split('_')[:2]
+ format = "-".join(format)
+
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'uploader': uploader,
+ 'url': video_url,
+ 'ext': extension,
+ 'format': format,
+ 'format_id': format,
+ 'age_limit': 18,
+ }
diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py
new file mode 100644
index 000000000..c91669b0e
--- /dev/null
+++ b/youtube_dl/extractor/gamekings.py
@@ -0,0 +1,38 @@
+import re
+
+from .common import InfoExtractor
+
+
+class GamekingsIE(InfoExtractor):
+ _VALID_URL = r'http?://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
+ _TEST = {
+ u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/",
+ u'file': u'20130811.mp4',
+ # MD5 is flaky, seems to change regularly
+ #u'md5': u'2f32b1f7b80fdc5cb616efb4f387f8a3',
+ u'info_dict': {
+ u"title": u"Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review",
+ u"description": u"Melle en Steven hebben voor de review een week in de rechtbank doorbracht met Phoenix Wright: Ace Attorney - Dual Destinies.",
+ }
+ }
+
+ def _real_extract(self, url):
+
+ mobj = re.match(self._VALID_URL, url)
+ name = mobj.group('name')
+ webpage = self._download_webpage(url, name)
+ video_url = self._og_search_video_url(webpage)
+
+ video = re.search(r'[0-9]+', video_url)
+ video_id = video.group(0)
+
+ # Todo: add medium format
+ video_url = video_url.replace(video_id, 'large/' + video_id)
+
+ return {
+ 'id': video_id,
+ 'ext': 'mp4',
+ 'url': video_url,
+ 'title': self._og_search_title(webpage),
+ 'description': self._og_search_description(webpage),
+ }
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 2c8fcf5ae..c7552fddb 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -33,6 +33,7 @@ class GenericIE(InfoExtractor):
},
# embedded vimeo video
{
+ u'add_ie': ['Vimeo'],
u'url': u'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references',
u'file': u'22444065.mp4',
u'md5': u'2903896e23df39722c33f015af0666e2',
@@ -44,6 +45,7 @@ class GenericIE(InfoExtractor):
},
# bandcamp page with custom domain
{
+ u'add_ie': ['Bandcamp'],
u'url': u'http://bronyrock.com/track/the-pony-mash',
u'file': u'3235767654.mp3',
u'info_dict': {
@@ -52,6 +54,23 @@ class GenericIE(InfoExtractor):
},
u'skip': u'There is a limit of 200 free downloads / month for the test song',
},
+ # embedded brightcove video
+ # it also tests brightcove videos that need to set the 'Referer' in the
+ # http requests
+ {
+ u'add_ie': ['Brightcove'],
+ u'url': u'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
+ u'info_dict': {
+ u'id': u'2765128793001',
+ u'ext': u'mp4',
+ u'title': u'Le cours de bourse : l’analyse technique',
+ u'description': u'md5:7e9ad046e968cb2d1114004aba466fd9',
+ u'uploader': u'BFM BUSINESS',
+ },
+ u'params': {
+ u'skip_download': True,
+ },
+ },
]
def report_download_webpage(self, video_id):
@@ -144,10 +163,9 @@ class GenericIE(InfoExtractor):
self.report_extraction(video_id)
# Look for BrightCove:
- m_brightcove = re.search(r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL)
- if m_brightcove is not None:
+ bc_url = BrightcoveIE._extract_brightcove_url(webpage)
+ if bc_url is not None:
self.to_screen(u'Brightcove video detected.')
- bc_url = BrightcoveIE._build_brighcove_url(m_brightcove.group())
return self.url_result(bc_url, 'Brightcove')
# Look for embedded Vimeo player
@@ -160,9 +178,9 @@ class GenericIE(InfoExtractor):
# Look for embedded YouTube player
mobj = re.search(
- r'<iframe[^>]+?src="(https?://(?:www\.)?youtube.com/embed/.+?)"', webpage)
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?youtube.com/embed/.+?)\1', webpage)
if mobj:
- surl = unescapeHTML(mobj.group(1))
+ surl = unescapeHTML(mobj.group(u'url'))
return self.url_result(surl, 'Youtube')
# Look for Bandcamp pages with custom domain
diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py
index ab2b59103..9bd06e7c7 100644
--- a/youtube_dl/extractor/hypem.py
+++ b/youtube_dl/extractor/hypem.py
@@ -30,7 +30,7 @@ class HypemIE(InfoExtractor):
raise ExtractorError(u'Invalid URL: %s' % url)
track_id = mobj.group(1)
- data = { 'ax': 1, 'ts': time.time() }
+ data = {'ax': 1, 'ts': time.time()}
data_encoded = compat_urllib_parse.urlencode(data)
complete_url = url + "?" + data_encoded
request = compat_urllib_request.Request(complete_url)
@@ -68,4 +68,4 @@ class HypemIE(InfoExtractor):
'ext': "mp3",
'title': title,
'artist': artist,
- }] \ No newline at end of file
+ }]
diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py
index 445d46501..50916f4a6 100644
--- a/youtube_dl/extractor/kankan.py
+++ b/youtube_dl/extractor/kankan.py
@@ -1,8 +1,10 @@
import re
+import hashlib
from .common import InfoExtractor
from ..utils import determine_ext
+_md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
class KankanIE(InfoExtractor):
_VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
@@ -30,7 +32,10 @@ class KankanIE(InfoExtractor):
video_id, u'Downloading video url info')
ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip')
path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path')
- video_url = 'http://%s%s' % (ip, path)
+ param1 = self._search_regex(r'param1:(\d+)', video_info_page, u'param1')
+ param2 = self._search_regex(r'param2:(\d+)', video_info_page, u'param2')
+ key = _md5('xl_mp43651' + param1 + param2)
+ video_url = 'http://%s%s?key=%s&key1=%s' % (ip, path, key, param2)
return {'id': video_id,
'title': title,
diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py
index 5e05900da..29658a7d6 100644
--- a/youtube_dl/extractor/keezmovies.py
+++ b/youtube_dl/extractor/keezmovies.py
@@ -12,7 +12,7 @@ from ..aes import (
)
class KeezMoviesIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))'
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
_TEST = {
u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
u'file': u'1214711.mp4',
@@ -43,10 +43,10 @@ class KeezMoviesIE(InfoExtractor):
if webpage.find('encrypted=true')!=-1:
password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, u'password')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
- format = "-".join( format )
+ format = "-".join(format)
age_limit = self._rta_search(webpage)
diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py
index d04da98c8..1a3e0ae6b 100644
--- a/youtube_dl/extractor/livestream.py
+++ b/youtube_dl/extractor/livestream.py
@@ -1,16 +1,19 @@
import re
import json
+import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urlparse,
get_meta_content,
+ xpath_with_ns,
ExtractorError,
)
class LivestreamIE(InfoExtractor):
+ IE_NAME = u'livestream'
_VALID_URL = r'http://new.livestream.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
_TEST = {
u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
@@ -40,13 +43,9 @@ class LivestreamIE(InfoExtractor):
if video_id is None:
# This is an event page:
- player = get_meta_content('twitter:player', webpage)
- if player is None:
- raise ExtractorError('Couldn\'t extract event api url')
- api_url = player.replace('/player', '')
- api_url = re.sub(r'^(https?://)(new\.)', r'\1api.\2', api_url)
- info = json.loads(self._download_webpage(api_url, event_name,
- u'Downloading event info'))
+ config_json = self._search_regex(r'window.config = ({.*?});',
+ webpage, u'window config')
+ info = json.loads(config_json)['event']
videos = [self._extract_video_info(video_data['data'])
for video_data in info['feed']['data'] if video_data['type'] == u'video']
return self.playlist_result(videos, info['id'], info['full_name'])
@@ -58,3 +57,44 @@ class LivestreamIE(InfoExtractor):
info = json.loads(self._download_webpage(api_url, video_id,
u'Downloading video info'))
return self._extract_video_info(info)
+
+
+# The original version of Livestream uses a different system
+class LivestreamOriginalIE(InfoExtractor):
+ IE_NAME = u'livestream:original'
+ _VALID_URL = r'https?://www\.livestream\.com/(?P<user>[^/]+)/video\?.*?clipId=(?P<id>.*?)(&|$)'
+ _TEST = {
+ u'url': u'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+ u'info_dict': {
+ u'id': u'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+ u'ext': u'flv',
+ u'title': u'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
+ },
+ u'params': {
+ # rtmp
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ user = mobj.group('user')
+ api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
+
+ api_response = self._download_webpage(api_url, video_id)
+ info = xml.etree.ElementTree.fromstring(api_response.encode('utf-8'))
+ item = info.find('channel').find('item')
+ ns = {'media': 'http://search.yahoo.com/mrss'}
+ thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
+ # Remove the extension and number from the path (like 1.jpg)
+ path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, u'path')
+
+ return {
+ 'id': video_id,
+ 'title': item.find('title').text,
+ 'url': 'rtmp://extondemand.livestream.com/ondemand',
+ 'play_path': 'mp4:trans/dv15/mogulus-{0}.mp4'.format(path),
+ 'ext': 'flv',
+ 'thumbnail': thumbnail_url,
+ }
diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 234b9e80f..91480ba87 100644
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -20,7 +20,9 @@ class MetacafeIE(InfoExtractor):
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
IE_NAME = u'metacafe'
- _TESTS = [{
+ _TESTS = [
+ # Youtube video
+ {
u"add_ie": ["Youtube"],
u"url": u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
u"file": u"_aUehQsCQtM.mp4",
@@ -32,15 +34,42 @@ class MetacafeIE(InfoExtractor):
u"uploader_id": u"PBS"
}
},
+ # Normal metacafe video
+ {
+ u'url': u'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
+ u'md5': u'6e0bca200eaad2552e6915ed6fd4d9ad',
+ u'info_dict': {
+ u'id': u'11121940',
+ u'ext': u'mp4',
+ u'title': u'News: Stuff You Won\'t Do with Your PlayStation 4',
+ u'uploader': u'ign',
+ u'description': u'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
+ },
+ },
+ # AnyClip video
{
u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
u"file": u"an-dVVXnuY7Jh77J.mp4",
u"info_dict": {
u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
u"uploader": u"anyclip",
- u"description": u"md5:38c711dd98f5bb87acf973d573442e67"
- }
- }]
+ u"description": u"md5:38c711dd98f5bb87acf973d573442e67",
+ },
+ },
+ # age-restricted video
+ {
+ u'url': u'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
+ u'md5': u'98dde7c1a35d02178e8ab7560fe8bd09',
+ u'info_dict': {
+ u'id': u'5186653',
+ u'ext': u'mp4',
+ u'title': u'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
+ u'uploader': u'Dwayne Pipe',
+ u'description': u'md5:950bf4c581e2c059911fa3ffbe377e4b',
+ u'age_limit': 18,
+ },
+ },
+ ]
def report_disclaimer(self):
@@ -62,6 +91,7 @@ class MetacafeIE(InfoExtractor):
'submit': "Continue - I'm over 18",
}
request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
+ request.add_header('Content-Type', 'application/x-www-form-urlencoded')
try:
self.report_age_confirmation()
compat_urllib_request.urlopen(request).read()
@@ -83,7 +113,12 @@ class MetacafeIE(InfoExtractor):
# Retrieve video webpage to extract further information
req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
- req.headers['Cookie'] = 'flashVersion=0;'
+
+ # AnyClip videos require the flashversion cookie so that we get the link
+ # to the mp4 file
+ mobj_an = re.match(r'^an-(.*?)$', video_id)
+ if mobj_an:
+ req.headers['Cookie'] = 'flashVersion=0;'
webpage = self._download_webpage(req, video_id)
# Extract URL, uploader and title from webpage
@@ -125,6 +160,11 @@ class MetacafeIE(InfoExtractor):
r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
webpage, u'uploader nickname', fatal=False)
+ if re.search(r'"contentRating":"restricted"', webpage) is not None:
+ age_limit = 18
+ else:
+ age_limit = 0
+
return {
'_type': 'video',
'id': video_id,
@@ -134,4 +174,5 @@ class MetacafeIE(InfoExtractor):
'upload_date': None,
'title': video_title,
'ext': video_ext,
+ 'age_limit': age_limit,
}
diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py
new file mode 100644
index 000000000..b9430b09b
--- /dev/null
+++ b/youtube_dl/extractor/mofosex.py
@@ -0,0 +1,49 @@
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse_urlparse,
+ compat_urllib_request,
+ compat_urllib_parse,
+)
+
+class MofosexIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
+ _TEST = {
+ u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
+ u'file': u'5018.mp4',
+ u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a',
+ u'info_dict': {
+ u"title": u"Japanese Teen Music Video",
+ u"age_limit": 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+ url = 'http://www.' + mobj.group('url')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title')
+ video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url'))
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
+ format = path.split('/')[5].split('_')[:2]
+ format = "-".join(format)
+
+ age_limit = self._rta_search(webpage)
+
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'url': video_url,
+ 'ext': extension,
+ 'format': format,
+ 'format_id': format,
+ 'age_limit': age_limit,
+ }
diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py
index e520e2bb4..3df7f9b85 100644
--- a/youtube_dl/extractor/mtv.py
+++ b/youtube_dl/extractor/mtv.py
@@ -26,6 +26,7 @@ class MTVIE(InfoExtractor):
},
},
{
+ u'add_ie': ['Vevo'],
u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
u'file': u'USCJY1331283.mp4',
u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
@@ -47,7 +48,7 @@ class MTVIE(InfoExtractor):
def _transform_rtmp_url(rtmp_video_url):
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
if not m:
- raise ExtractorError(u'Cannot transform RTMP url')
+ return rtmp_video_url
base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
return base + m.group('finalid')
@@ -80,6 +81,8 @@ class MTVIE(InfoExtractor):
video_id = self._id_from_uri(uri)
self.report_extraction(video_id)
mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url']
+ # Remove the templates, like &device={device}
+ mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', u'', mediagen_url)
if 'acceptMethods' not in mediagen_url:
mediagen_url += '&acceptMethods=fms'
mediagen_page = self._download_webpage(mediagen_url, video_id,
diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py
new file mode 100644
index 000000000..050f54a5a
--- /dev/null
+++ b/youtube_dl/extractor/myspace.py
@@ -0,0 +1,48 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_str,
+)
+
+
+class MySpaceIE(InfoExtractor):
+ _VALID_URL = r'https?://myspace\.com/([^/]+)/video/[^/]+/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'https://myspace.com/coldplay/video/viva-la-vida/100008689',
+ u'info_dict': {
+ u'id': u'100008689',
+ u'ext': u'flv',
+ u'title': u'Viva La Vida',
+ u'description': u'The official Viva La Vida video, directed by Hype Williams',
+ u'uploader': u'Coldplay',
+ u'uploader_id': u'coldplay',
+ },
+ u'params': {
+ # rtmp download
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ context = json.loads(self._search_regex(r'context = ({.*?});', webpage,
+ u'context'))
+ video = context['video']
+ rtmp_url, play_path = video['streamUrl'].split(';', 1)
+
+ return {
+ 'id': compat_str(video['mediaId']),
+ 'title': video['title'],
+ 'url': rtmp_url,
+ 'play_path': play_path,
+ 'ext': 'flv',
+ 'description': video['description'],
+ 'thumbnail': video['imageUrl'],
+ 'uploader': video['artistName'],
+ 'uploader_id': video['artistUsername'],
+ }
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 5e2454f1b..75cf4bb9f 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -47,10 +47,10 @@ class PornHubIE(InfoExtractor):
formats = []
for video_url in video_urls:
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[5].split('_')[:2]
- format = "-".join( format )
+ format = "-".join(format)
formats.append({
'url': video_url,
'ext': extension,
diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py
index 994778e16..3bbda128e 100644
--- a/youtube_dl/extractor/redtube.py
+++ b/youtube_dl/extractor/redtube.py
@@ -8,7 +8,9 @@ class RedTubeIE(InfoExtractor):
_TEST = {
u'url': u'http://www.redtube.com/66418',
u'file': u'66418.mp4',
- u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
+ # md5 varies from time to time, as in
+ # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295
+ #u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
u'info_dict': {
u"title": u"Sucked on a toilet",
u"age_limit": 18,
diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py
index 9ac7c3be8..2f238de35 100644
--- a/youtube_dl/extractor/rtlnow.py
+++ b/youtube_dl/extractor/rtlnow.py
@@ -63,18 +63,6 @@ class RTLnowIE(InfoExtractor):
},
},
{
- u'url': u'http://www.rtlnitronow.de/recht-ordnung/stadtpolizei-frankfurt-gerichtsvollzieher-leipzig.php?film_id=129679&player=1&season=1',
- u'file': u'129679.flv',
- u'info_dict': {
- u'upload_date': u'20131016',
- u'title': u'Recht & Ordnung - Stadtpolizei Frankfurt/ Gerichtsvollzieher...',
- u'description': u'Stadtpolizei Frankfurt/ Gerichtsvollzieher Leipzig',
- },
- u'params': {
- u'skip_download': True,
- },
- },
- {
u'url': u'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10',
u'file': u'124903.flv',
u'info_dict': {
diff --git a/youtube_dl/extractor/slashdot.py b/youtube_dl/extractor/slashdot.py
index 2cba53076..f5003c7f9 100644
--- a/youtube_dl/extractor/slashdot.py
+++ b/youtube_dl/extractor/slashdot.py
@@ -7,6 +7,7 @@ class SlashdotIE(InfoExtractor):
_VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
_TEST = {
+ u'add_ie': ['Ooyala'],
u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz',
u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4',
u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735',
diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index 29cd5617c..83e1f055f 100644
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -29,17 +29,34 @@ class SoundcloudIE(InfoExtractor):
)
'''
IE_NAME = u'soundcloud'
- _TEST = {
- u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
- u'file': u'62986583.mp3',
- u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
- u'info_dict': {
- u"upload_date": u"20121011",
- u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
- u"uploader": u"E.T. ExTerrestrial Music",
- u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
- }
- }
+ _TESTS = [
+ {
+ u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
+ u'file': u'62986583.mp3',
+ u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
+ u'info_dict': {
+ u"upload_date": u"20121011",
+ u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
+ u"uploader": u"E.T. ExTerrestrial Music",
+ u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+ }
+ },
+ # not streamable song
+ {
+ u'url': u'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
+ u'info_dict': {
+ u'id': u'47127627',
+ u'ext': u'mp3',
+ u'title': u'Goldrushed',
+ u'uploader': u'The Royal Concept',
+ u'upload_date': u'20120521',
+ },
+ u'params': {
+ # rtmp
+ u'skip_download': True,
+ },
+ },
+ ]
_CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
@@ -56,24 +73,39 @@ class SoundcloudIE(InfoExtractor):
return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
def _extract_info_dict(self, info, full_title=None, quiet=False):
- video_id = info['id']
- name = full_title or video_id
+ track_id = compat_str(info['id'])
+ name = full_title or track_id
if quiet == False:
self.report_extraction(name)
thumbnail = info['artwork_url']
if thumbnail is not None:
thumbnail = thumbnail.replace('-large', '-t500x500')
- return {
- 'id': info['id'],
+ result = {
+ 'id': track_id,
'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
'uploader': info['user']['username'],
'upload_date': unified_strdate(info['created_at']),
'title': info['title'],
- 'ext': u'mp3',
+ 'ext': info.get('original_format', u'mp3'),
'description': info['description'],
'thumbnail': thumbnail,
}
+ if info.get('downloadable', False):
+ result['url'] = 'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(track_id, self._CLIENT_ID)
+ if not info.get('streamable', False):
+ # We have to get the rtmp url
+ stream_json = self._download_webpage(
+ 'http://api.soundcloud.com/i1/tracks/{0}/streams?client_id={1}'.format(track_id, self._CLIENT_ID),
+ track_id, u'Downloading track url')
+ rtmp_url = json.loads(stream_json)['rtmp_mp3_128_url']
+ # The url doesn't have an rtmp app, we have to extract the playpath
+ url, path = rtmp_url.split('mp3:', 1)
+ result.update({
+ 'url': url,
+ 'play_path': 'mp3:' + path,
+ })
+ return result
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
@@ -106,70 +138,8 @@ class SoundcloudIE(InfoExtractor):
class SoundcloudSetIE(SoundcloudIE):
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
IE_NAME = u'soundcloud:set'
- _TEST = {
- u"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
- u"playlist": [
- {
- u"file":"30510138.mp3",
- u"md5":"f9136bf103901728f29e419d2c70f55d",
- u"info_dict": {
- u"upload_date": u"20111213",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"D-D-Dance"
- }
- },
- {
- u"file":"47127625.mp3",
- u"md5":"09b6758a018470570f8fd423c9453dd8",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"The Royal Concept - Gimme Twice"
- }
- },
- {
- u"file":"47127627.mp3",
- u"md5":"154abd4e418cea19c3b901f1e1306d9c",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"uploader": u"The Royal Concept",
- u"title": u"Goldrushed"
- }
- },
- {
- u"file":"47127629.mp3",
- u"md5":"2f5471edc79ad3f33a683153e96a79c1",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"In the End"
- }
- },
- {
- u"file":"47127631.mp3",
- u"md5":"f9ba87aa940af7213f98949254f1c6e2",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"Knocked Up"
- }
- },
- {
- u"file":"75206121.mp3",
- u"md5":"f9d1fe9406717e302980c30de4af9353",
- u"info_dict": {
- u"upload_date": u"20130116",
- u"description": u"The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central). \r\nAs a gift to our fans we would like to offer you a free download of the track! ",
- u"uploader": u"The Royal Concept",
- u"title": u"World On Fire"
- }
- }
- ]
- }
+ # it's in tests/test_playlists.py
+ _TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -208,7 +178,7 @@ class SoundcloudUserIE(SoundcloudIE):
IE_NAME = u'soundcloud:user'
# it's in tests/test_playlists.py
- _TEST = None
+ _TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
diff --git a/youtube_dl/extractor/southparkstudios.py b/youtube_dl/extractor/southparkstudios.py
index b1e96b679..a711531e6 100644
--- a/youtube_dl/extractor/southparkstudios.py
+++ b/youtube_dl/extractor/southparkstudios.py
@@ -5,21 +5,19 @@ from .mtv import MTVIE, _media_xml_tag
class SouthParkStudiosIE(MTVIE):
IE_NAME = u'southparkstudios.com'
- _VALID_URL = r'https?://www\.southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$)'
+ _VALID_URL = r'(https?://)?(www\.)?(?P<url>southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
- _TEST = {
+ # Overwrite MTVIE properties we don't want
+ _TESTS = [{
u'url': u'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured',
u'file': u'a7bff6c2-ed00-11e0-aca6-0026b9414f30.mp4',
u'info_dict': {
u'title': u'Bat Daded',
u'description': u'Randy disqualifies South Park by getting into a fight with Bat Dad.',
},
- }
-
- # Overwrite MTVIE properties we don't want
- _TESTS = []
+ }]
def _get_thumbnail_url(self, uri, itemdoc):
search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
@@ -31,8 +29,23 @@ class SouthParkStudiosIE(MTVIE):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
+ url = u'http://www.' + mobj.group(u'url')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
mgid = self._search_regex(r'swfobject.embedSWF\(".*?(mgid:.*?)"',
webpage, u'mgid')
return self._get_videos_info(mgid)
+
+class SouthparkDeIE(SouthParkStudiosIE):
+ IE_NAME = u'southpark.de'
+ _VALID_URL = r'(https?://)?(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
+ _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
+
+ _TESTS = [{
+ u'url': u'http://www.southpark.de/clips/uygssh/the-government-wont-respect-my-privacy#tab=featured',
+ u'file': u'85487c96-b3b9-4e39-9127-ad88583d9bf2.mp4',
+ u'info_dict': {
+ u'title': u'The Government Won\'t Respect My Privacy',
+ u'description': u'Cartman explains the benefits of "Shitter" to Stan, Kyle and Craig.',
+ },
+ }]
diff --git a/youtube_dl/extractor/space.py b/youtube_dl/extractor/space.py
new file mode 100644
index 000000000..0d32a0688
--- /dev/null
+++ b/youtube_dl/extractor/space.py
@@ -0,0 +1,35 @@
+import re
+
+from .common import InfoExtractor
+from .brightcove import BrightcoveIE
+from ..utils import RegexNotFoundError, ExtractorError
+
+
+class SpaceIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video.html'
+ _TEST = {
+ u'add_ie': ['Brightcove'],
+ u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',
+ u'info_dict': {
+ u'id': u'2780937028001',
+ u'ext': u'mp4',
+ u'title': u'Huge Martian Landforms\' Detail Revealed By European Probe | Video',
+ u'description': u'md5:db81cf7f3122f95ed234b631a6ea1e61',
+ u'uploader': u'TechMedia Networks',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ title = mobj.group('title')
+ webpage = self._download_webpage(url, title)
+ try:
+ # Some videos require the playerKey field, which isn't define in
+ # the BrightcoveExperience object
+ brightcove_url = self._og_search_video_url(webpage)
+ except RegexNotFoundError:
+ # Other videos works fine with the info from the object
+ brightcove_url = BrightcoveIE._extract_brightcove_url(webpage)
+ if brightcove_url is None:
+ raise ExtractorError(u'The webpage does not contain a video', expected=True)
+ return self.url_result(brightcove_url, BrightcoveIE.ie_key())
diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py
index 32df0a7fb..97f9c268a 100644
--- a/youtube_dl/extractor/spankwire.py
+++ b/youtube_dl/extractor/spankwire.py
@@ -49,10 +49,10 @@ class SpankwireIE(InfoExtractor):
formats = []
for video_url in video_urls:
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
- format = "-".join( format )
+ format = "-".join(format)
formats.append({
'url': video_url,
'ext': extension,
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
index 13c86401c..6dc2eda6d 100644
--- a/youtube_dl/extractor/spiegel.py
+++ b/youtube_dl/extractor/spiegel.py
@@ -2,18 +2,27 @@ import re
import xml.etree.ElementTree
from .common import InfoExtractor
+from ..utils import determine_ext
class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
- _TEST = {
+ _TESTS = [{
u'url': u'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
u'file': u'1259285.mp4',
u'md5': u'2c2754212136f35fb4b19767d242f66e',
u'info_dict': {
u"title": u"Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
}
- }
+ },
+ {
+ u'url': u'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
+ u'file': u'1309159.mp4',
+ u'md5': u'f2cdf638d7aa47654e251e1aee360af1',
+ u'info_dict': {
+ u'title': u'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers'
+ }
+ }]
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
@@ -21,25 +30,38 @@ class SpiegelIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
- video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
- webpage, u'title')
+ video_title = self._html_search_regex(
+ r'<div class="module-title">(.*?)</div>', webpage, u'title')
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
- xml_code = self._download_webpage(xml_url, video_id,
- note=u'Downloading XML', errnote=u'Failed to download XML')
+ xml_code = self._download_webpage(
+ xml_url, video_id,
+ note=u'Downloading XML', errnote=u'Failed to download XML')
idoc = xml.etree.ElementTree.fromstring(xml_code)
- last_type = idoc[-1]
- filename = last_type.findall('./filename')[0].text
- duration = float(last_type.findall('./duration')[0].text)
- video_url = 'http://video2.spiegel.de/flash/' + filename
- video_ext = filename.rpartition('.')[2]
+ formats = [
+ {
+ 'format_id': n.tag.rpartition('type')[2],
+ 'url': u'http://video2.spiegel.de/flash/' + n.find('./filename').text,
+ 'width': int(n.find('./width').text),
+ 'height': int(n.find('./height').text),
+ 'abr': int(n.find('./audiobitrate').text),
+ 'vbr': int(n.find('./videobitrate').text),
+ 'vcodec': n.find('./codec').text,
+ 'acodec': 'MP4A',
+ }
+ for n in list(idoc)
+ # Blacklist type 6, it's extremely LQ and not available on the same server
+ if n.tag.startswith('type') and n.tag != 'type6'
+ ]
+ formats.sort(key=lambda f: f['vbr'])
+ duration = float(idoc[0].findall('./duration')[0].text)
+
info = {
'id': video_id,
- 'url': video_url,
- 'ext': video_ext,
'title': video_title,
'duration': duration,
+ 'formats': formats,
}
- return [info]
+ return info
diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py
index 90de7de3a..4b4c5235d 100644
--- a/youtube_dl/extractor/subtitles.py
+++ b/youtube_dl/extractor/subtitles.py
@@ -12,9 +12,9 @@ class SubtitlesInfoExtractor(InfoExtractor):
return any([self._downloader.params.get('writesubtitles', False),
self._downloader.params.get('writeautomaticsub')])
- def _list_available_subtitles(self, video_id, webpage=None):
+ def _list_available_subtitles(self, video_id, webpage):
""" outputs the available subtitles for the video """
- sub_lang_list = self._get_available_subtitles(video_id)
+ sub_lang_list = self._get_available_subtitles(video_id, webpage)
auto_captions_list = self._get_available_automatic_caption(video_id, webpage)
sub_lang = ",".join(list(sub_lang_list.keys()))
self.to_screen(u'%s: Available subtitles for video: %s' %
@@ -23,7 +23,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
self.to_screen(u'%s: Available automatic captions for video: %s' %
(video_id, auto_lang))
- def extract_subtitles(self, video_id, video_webpage=None):
+ def extract_subtitles(self, video_id, webpage):
"""
returns {sub_lang: sub} ,{} if subtitles not found or None if the
subtitles aren't requested.
@@ -32,9 +32,9 @@ class SubtitlesInfoExtractor(InfoExtractor):
return None
available_subs_list = {}
if self._downloader.params.get('writeautomaticsub', False):
- available_subs_list.update(self._get_available_automatic_caption(video_id, video_webpage))
+ available_subs_list.update(self._get_available_automatic_caption(video_id, webpage))
if self._downloader.params.get('writesubtitles', False):
- available_subs_list.update(self._get_available_subtitles(video_id))
+ available_subs_list.update(self._get_available_subtitles(video_id, webpage))
if not available_subs_list: # error, it didn't get the available subtitles
return {}
@@ -74,7 +74,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
return
return sub
- def _get_available_subtitles(self, video_id):
+ def _get_available_subtitles(self, video_id, webpage):
"""
returns {sub_lang: url} or {} if not available
Must be redefined by the subclasses
diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index c910110ca..bc48620f0 100644
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -1,4 +1,5 @@
import re
+import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
@@ -11,7 +12,7 @@ class TeamcocoIE(InfoExtractor):
_TEST = {
u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
u'file': u'19705.mp4',
- u'md5': u'27b6f7527da5acf534b15f21b032656e',
+ u'md5': u'cde9ba0fa3506f5f017ce11ead928f9a',
u'info_dict': {
u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.",
u"title": u"Louis C.K. Interview Pt. 1 11/3/11"
@@ -31,16 +32,40 @@ class TeamcocoIE(InfoExtractor):
self.report_extraction(video_id)
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
- data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
+ data_xml = self._download_webpage(data_url, video_id, 'Downloading data webpage')
+ data = xml.etree.ElementTree.fromstring(data_xml.encode('utf-8'))
- video_url = self._html_search_regex(r'<file [^>]*type="high".*?>(.*?)</file>',
- data, u'video URL')
- return [{
+ qualities = ['500k', '480p', '1000k', '720p', '1080p']
+ formats = []
+ for file in data.findall('files/file'):
+ if file.attrib.get('playmode') == 'all':
+ # it just duplicates one of the entries
+ break
+ file_url = file.text
+ m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
+ if m_format is not None:
+ format_id = m_format.group(1)
+ else:
+ format_id = file.attrib['bitrate']
+ formats.append({
+ 'url': file_url,
+ 'ext': 'mp4',
+ 'format_id': format_id,
+ })
+ def sort_key(f):
+ try:
+ return qualities.index(f['format_id'])
+ except ValueError:
+ return -1
+ formats.sort(key=sort_key)
+ if not formats:
+ raise RegexNotFoundError(u'Unable to extract video URL')
+
+ return {
'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
+ 'formats': formats,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
- }]
+ }
diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py
index dfa1176a3..2e497c86e 100644
--- a/youtube_dl/extractor/ted.py
+++ b/youtube_dl/extractor/ted.py
@@ -1,10 +1,14 @@
import json
import re
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
+from ..utils import (
+ compat_str,
+ RegexNotFoundError,
+)
-class TEDIE(InfoExtractor):
+class TEDIE(SubtitlesInfoExtractor):
_VALID_URL=r'''http://www\.ted\.com/
(
((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
@@ -32,33 +36,32 @@ class TEDIE(InfoExtractor):
def _real_extract(self, url):
m=re.match(self._VALID_URL, url, re.VERBOSE)
if m.group('type_talk'):
- return [self._talk_info(url)]
+ return self._talk_info(url)
else :
playlist_id=m.group('playlist_id')
name=m.group('name')
self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
return [self._playlist_videos_info(url,name,playlist_id)]
- def _playlist_videos_info(self,url,name,playlist_id=0):
+
+ def _playlist_videos_info(self, url, name, playlist_id):
'''Returns the videos of the playlist'''
- video_RE=r'''
- <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
- ([.\s]*?)data-playlist_item_id="(\d+)"
- ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
- '''
- video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
- webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
- m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
- m_names=re.finditer(video_name_RE,webpage)
+
+ webpage = self._download_webpage(
+ url, playlist_id, u'Downloading playlist webpage')
+ matches = re.finditer(
+ r'<p\s+class="talk-title[^"]*"><a\s+href="(?P<talk_url>/talks/[^"]+\.html)">[^<]*</a></p>',
+ webpage)
playlist_title = self._html_search_regex(r'div class="headline">\s*?<h1>\s*?<span>(.*?)</span>',
webpage, 'playlist title')
- playlist_entries = []
- for m_video, m_name in zip(m_videos,m_names):
- talk_url='http://www.ted.com%s' % m_name.group('talk_url')
- playlist_entries.append(self.url_result(talk_url, 'TED'))
- return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
+ playlist_entries = [
+ self.url_result(u'http://www.ted.com' + m.group('talk_url'), 'TED')
+ for m in matches
+ ]
+ return self.playlist_result(
+ playlist_entries, playlist_id=playlist_id, playlist_title=playlist_title)
def _talk_info(self, url, video_id=0):
"""Return the video for the talk in the url"""
@@ -81,16 +84,35 @@ class TEDIE(InfoExtractor):
'ext': 'mp4',
'url': stream['file'],
'format': stream['id']
- } for stream in info['htmlStreams']]
- info = {
- 'id': info['id'],
+ } for stream in info['htmlStreams']]
+
+ video_id = info['id']
+
+ # subtitles
+ video_subtitles = self.extract_subtitles(video_id, webpage)
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, webpage)
+ return
+
+ return {
+ 'id': video_id,
'title': title,
'thumbnail': thumbnail,
'description': desc,
+ 'subtitles': video_subtitles,
'formats': formats,
}
- # TODO: Remove when #980 has been merged
- info.update(info['formats'][-1])
-
- return info
+ def _get_available_subtitles(self, video_id, webpage):
+ try:
+ options = self._search_regex(r'(?:<select name="subtitles_language_select" id="subtitles_language_select">)(.*?)(?:</select>)', webpage, 'subtitles_language_select', flags=re.DOTALL)
+ languages = re.findall(r'(?:<option value=")(\S+)"', options)
+ if languages:
+ sub_lang_list = {}
+ for l in languages:
+ url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l)
+ sub_lang_list[l] = url
+ return sub_lang_list
+ except RegexNotFoundError as err:
+ self._downloader.report_warning(u'video doesn\'t have subtitles')
+ return {}
diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index aea9d9a24..d4b7603c7 100644
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -46,10 +46,10 @@ class Tube8IE(InfoExtractor):
if webpage.find('"encrypted":true')!=-1:
password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
- format = "-".join( format )
+ format = "-".join(format)
return {
'id': video_id,
diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py
new file mode 100644
index 000000000..bfed9dd04
--- /dev/null
+++ b/youtube_dl/extractor/tvp.py
@@ -0,0 +1,42 @@
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class TvpIE(InfoExtractor):
+ IE_NAME = u'tvp.pl'
+ _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
+ u'md5': u'148408967a6a468953c0a75cbdaf0d7a',
+ u'file': u'12878238.wmv',
+ u'info_dict': {
+ u'title': u'31.10.2013 - Odcinek 2',
+ u'description': u'31.10.2013 - Odcinek 2',
+ },
+ u'skip': u'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.'
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id
+ json_params = self._download_webpage(
+ json_url, video_id, u"Downloading video metadata")
+
+ params = json.loads(json_params)
+ self.report_extraction(video_id)
+ video_url = params['video_url']
+
+ title = self._og_search_title(webpage, fatal=True)
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'ext': 'wmv',
+ 'url': video_url,
+ 'description': self._og_search_description(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ }
diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py
index 1c1cc418d..4378b1780 100644
--- a/youtube_dl/extractor/vevo.py
+++ b/youtube_dl/extractor/vevo.py
@@ -5,7 +5,7 @@ import datetime
from .common import InfoExtractor
from ..utils import (
- determine_ext,
+ compat_HTTPError,
ExtractorError,
)
@@ -16,26 +16,22 @@ class VevoIE(InfoExtractor):
(currently used by MTVIE)
"""
_VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*?)(\?|$)'
- _TEST = {
+ _TESTS = [{
u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
u'file': u'GB1101300280.mp4',
+ u"md5": u"06bea460acb744eab74a9d7dcb4bfd61",
u'info_dict': {
u"upload_date": u"20130624",
u"uploader": u"Hurts",
u"title": u"Somebody to Die For",
- u'duration': 230,
+ u"duration": 230,
+ u"width": 1920,
+ u"height": 1080,
}
- }
+ }]
+ _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/'
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
- info_json = self._download_webpage(json_url, video_id, u'Downloading json info')
-
- self.report_extraction(video_id)
- video_info = json.loads(info_json)['video']
+ def _formats_from_json(self, video_info):
last_version = {'version': -1}
for version in video_info['videoVersions']:
# These are the HTTP downloads, other types are for different manifests
@@ -50,17 +46,75 @@ class VevoIE(InfoExtractor):
# Already sorted from worst to best quality
for rend in renditions.findall('rendition'):
attr = rend.attrib
- f_url = attr['url']
+ format_note = '%(videoCodec)s@%(videoBitrate)4sk, %(audioCodec)s@%(audioBitrate)3sk' % attr
formats.append({
- 'url': f_url,
- 'ext': determine_ext(f_url),
+ 'url': attr['url'],
+ 'format_id': attr['name'],
+ 'format_note': format_note,
'height': int(attr['frameheight']),
'width': int(attr['frameWidth']),
})
+ return formats
+
+ def _formats_from_smil(self, smil_xml):
+ formats = []
+ smil_doc = xml.etree.ElementTree.fromstring(smil_xml.encode('utf-8'))
+ els = smil_doc.findall('.//{http://www.w3.org/2001/SMIL20/Language}video')
+ for el in els:
+ src = el.attrib['src']
+ m = re.match(r'''(?xi)
+ (?P<ext>[a-z0-9]+):
+ (?P<path>
+ [/a-z0-9]+ # The directory and main part of the URL
+ _(?P<cbr>[0-9]+)k
+ _(?P<width>[0-9]+)x(?P<height>[0-9]+)
+ _(?P<vcodec>[a-z0-9]+)
+ _(?P<vbr>[0-9]+)
+ _(?P<acodec>[a-z0-9]+)
+ _(?P<abr>[0-9]+)
+ \.[a-z0-9]+ # File extension
+ )''', src)
+ if not m:
+ continue
- date_epoch = int(self._search_regex(
- r'/Date\((\d+)\)/', video_info['launchDate'], u'launch date'))/1000
- upload_date = datetime.datetime.fromtimestamp(date_epoch)
+ format_url = self._SMIL_BASE_URL + m.group('path')
+ formats.append({
+ 'url': format_url,
+ 'format_id': u'SMIL_' + m.group('cbr'),
+ 'vcodec': m.group('vcodec'),
+ 'acodec': m.group('acodec'),
+ 'vbr': int(m.group('vbr')),
+ 'abr': int(m.group('abr')),
+ 'ext': m.group('ext'),
+ 'width': int(m.group('width')),
+ 'height': int(m.group('height')),
+ })
+ return formats
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
+ info_json = self._download_webpage(json_url, video_id, u'Downloading json info')
+ video_info = json.loads(info_json)['video']
+
+ formats = self._formats_from_json(video_info)
+ try:
+ smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
+ self._SMIL_BASE_URL, video_id, video_id.lower())
+ smil_xml = self._download_webpage(smil_url, video_id,
+ u'Downloading SMIL info')
+ formats.extend(self._formats_from_smil(smil_xml))
+ except ExtractorError as ee:
+ if not isinstance(ee.cause, compat_HTTPError):
+ raise
+ self._downloader.report_warning(
+ u'Cannot download SMIL information, falling back to JSON ..')
+
+ timestamp_ms = int(self._search_regex(
+ r'/Date\((\d+)\)/', video_info['launchDate'], u'launch date'))
+ upload_date = datetime.datetime.fromtimestamp(timestamp_ms // 1000)
info = {
'id': video_id,
'title': video_info['title'],
@@ -71,7 +125,4 @@ class VevoIE(InfoExtractor):
'duration': video_info['duration'],
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
-
return info
diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py
index 12c84a985..826804af3 100644
--- a/youtube_dl/extractor/viddler.py
+++ b/youtube_dl/extractor/viddler.py
@@ -8,7 +8,7 @@ from ..utils import (
class ViddlerIE(InfoExtractor):
- _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[0-9]+)'
+ _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
_TEST = {
u"url": u"http://www.viddler.com/v/43903784",
u'file': u'43903784.mp4',
diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index b4dbcd2ee..d465bf20b 100644
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -20,14 +20,14 @@ class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'
+ _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'
_NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TESTS = [
{
u'url': u'http://vimeo.com/56015672#at=0',
u'file': u'56015672.mp4',
- u'md5': u'ae7a1d8b183758a0506b0622f37dfa14',
+ u'md5': u'8879b6cc097e987f02484baf890129e5',
u'info_dict': {
u"upload_date": u"20121220",
u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
@@ -128,11 +128,9 @@ class VimeoIE(InfoExtractor):
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id')
- if not mobj.group('proto'):
- url = 'https://' + url
- elif mobj.group('pro'):
+ if mobj.group('pro') or mobj.group('player'):
url = 'http://player.vimeo.com/video/' + video_id
- elif mobj.group('direct_link'):
+ else:
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
@@ -205,7 +203,7 @@ class VimeoIE(InfoExtractor):
# Vimeo specific: extract video codec and quality information
# First consider quality, then codecs, then take everything
codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
- files = { 'hd': [], 'sd': [], 'other': []}
+ files = {'hd': [], 'sd': [], 'other': []}
config_files = config["video"].get("files") or config["request"].get("files")
for codec_name, codec_extension in codecs:
for quality in config_files.get(codec_name, []):
@@ -234,7 +232,7 @@ class VimeoIE(InfoExtractor):
if len(formats) == 0:
raise ExtractorError(u'No known codec found')
- return [{
+ return {
'id': video_id,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
@@ -243,7 +241,8 @@ class VimeoIE(InfoExtractor):
'thumbnail': video_thumbnail,
'description': video_description,
'formats': formats,
- }]
+ 'webpage_url': url,
+ }
class VimeoChannelIE(InfoExtractor):
diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py
index c4ec1f06f..651ba317d 100644
--- a/youtube_dl/extractor/vine.py
+++ b/youtube_dl/extractor/vine.py
@@ -27,7 +27,7 @@ class VineIE(InfoExtractor):
video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
webpage, u'video URL')
- uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
+ uploader = self._html_search_regex(r'<p class="username">(.*?)</p>',
webpage, u'uploader', fatal=False, flags=re.DOTALL)
return [{
diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py
new file mode 100644
index 000000000..90d8a6d07
--- /dev/null
+++ b/youtube_dl/extractor/vk.py
@@ -0,0 +1,45 @@
+# encoding: utf-8
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_str,
+ unescapeHTML,
+)
+
+
+class VKIE(InfoExtractor):
+ IE_NAME = u'vk.com'
+ _VALID_URL = r'https?://vk\.com/(?:videos.*?\?.*?z=)?video(?P<id>.*?)(?:\?|%2F|$)'
+
+ _TEST = {
+ u'url': u'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
+ u'md5': u'0deae91935c54e00003c2a00646315f0',
+ u'info_dict': {
+ u'id': u'162222515',
+ u'ext': u'flv',
+ u'title': u'ProtivoGunz - Хуёвая песня',
+ u'uploader': u'Noize MC',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
+ info_page = self._download_webpage(info_url, video_id)
+ m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
+ if m_yt is not None:
+ self.to_screen(u'Youtube video detected')
+ return self.url_result(m_yt.group(1), 'Youtube')
+ vars_json = self._search_regex(r'var vars = ({.*?});', info_page, u'vars')
+ vars = json.loads(vars_json)
+
+ return {
+ 'id': compat_str(vars['vid']),
+ 'url': vars['url240'],
+ 'title': unescapeHTML(vars['md_title']),
+ 'thumbnail': vars['jpg'],
+ 'uploader': vars['md_author'],
+ }
diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py
index 0757495bd..fa784ab99 100644
--- a/youtube_dl/extractor/weibo.py
+++ b/youtube_dl/extractor/weibo.py
@@ -13,6 +13,7 @@ class WeiboIE(InfoExtractor):
_VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm'
_TEST = {
+ u'add_ie': ['Sina'],
u'url': u'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm',
u'file': u'98322879.flv',
u'info_dict': {
diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py
index 8a0eb1afd..1177a4b14 100644
--- a/youtube_dl/extractor/xnxx.py
+++ b/youtube_dl/extractor/xnxx.py
@@ -9,7 +9,7 @@ from ..utils import (
class XNXXIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
+ _VALID_URL = r'^(?:https?://)?(?:video|www)\.xnxx\.com/video([0-9]+)/(.*)'
VIDEO_URL_RE = r'flv_url=(.*?)&amp;'
VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py
new file mode 100644
index 000000000..03ad88bed
--- /dev/null
+++ b/youtube_dl/extractor/xtube.py
@@ -0,0 +1,55 @@
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse_urlparse,
+ compat_urllib_request,
+ compat_urllib_parse,
+)
+
+class XTubeIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
+ _TEST = {
+ u'url': u'http://www.xtube.com/watch.php?v=kVTUy_G222_',
+ u'file': u'kVTUy_G222_.mp4',
+ u'md5': u'092fbdd3cbe292c920ef6fc6a8a9cdab',
+ u'info_dict': {
+ u"title": u"strange erotica",
+ u"description": u"surreal gay themed erotica...almost an ET kind of thing",
+ u"uploader": u"greenshowers",
+ u"age_limit": 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+ url = 'http://www.' + mobj.group('url')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, u'title')
+ video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False)
+ video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', default=None)
+ video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/')
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
+ format = path.split('/')[5].split('_')[:2]
+ format[0] += 'p'
+ format[1] += 'k'
+ format = "-".join(format)
+
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'uploader': video_uploader,
+ 'description': video_description,
+ 'url': video_url,
+ 'ext': extension,
+ 'format': format,
+ 'format_id': format,
+ 'age_limit': 18,
+ }
diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 464b498f5..34e6afb20 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -132,7 +132,7 @@ class YahooSearchIE(SearchInfoExtractor):
mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
res['entries'].append(e)
- if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
+ if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1)):
break
return res
diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py
index 9d88c17f5..a8fd40c83 100644
--- a/youtube_dl/extractor/youku.py
+++ b/youtube_dl/extractor/youku.py
@@ -18,7 +18,7 @@ class YoukuIE(InfoExtractor):
u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
u"file": u"XNDgyMDQ2NTQw_part00.flv",
u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b",
- u"params": { u"test": False },
+ u"params": {u"test": False},
u"info_dict": {
u"title": u"youtube-dl test video \"'/\\ä↭𝕐"
}
@@ -37,8 +37,8 @@ class YoukuIE(InfoExtractor):
source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
seed = float(seed)
for i in range(len(source)):
- seed = (seed * 211 + 30031 ) % 65536
- index = math.floor(seed / 65536 * len(source) )
+ seed = (seed * 211 + 30031) % 65536
+ index = math.floor(seed / 65536 * len(source))
mixed.append(source[int(index)])
source.remove(source[int(index)])
#return ''.join(mixed)
diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index e46a9b4d6..bd0f2cae0 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -81,14 +81,14 @@ class YouPornIE(InfoExtractor):
# http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
# A path looks like this:
# /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
- video_url = unescapeHTML( link )
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ video_url = unescapeHTML(link)
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
# size = format[0]
# bitrate = format[1]
- format = "-".join( format )
+ format = "-".join(format)
# title = u'%s-%s-%s' % (video_title, size, bitrate)
formats.append({
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index d05d0a8c1..1aa549740 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -74,14 +74,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
return False
- galx = None
- dsh = None
- match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page)
- if match:
- galx = match.group(1)
- match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page)
- if match:
- dsh = match.group(1)
+ galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"',
+ login_page, u'Login GALX parameter')
# Log in
login_form_strs = {
@@ -95,7 +89,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
u'checkConnection': u'',
u'checkedDomains': u'youtube',
u'dnConn': u'',
- u'dsh': dsh,
u'pstMsg': u'0',
u'rmShown': u'1',
u'secTok': u'',
@@ -347,18 +340,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
}
},
{
- u"url": u"http://www.youtube.com/watch?v=1ltcDfZMA3U",
- u"file": u"1ltcDfZMA3U.mp4",
- u"note": u"Test VEVO video (#897)",
- u"info_dict": {
- u"upload_date": u"20070518",
- u"title": u"Maps - It Will Find You",
- u"description": u"Music video by Maps performing It Will Find You.",
- u"uploader": u"MuteUSA",
- u"uploader_id": u"MuteUSA"
- }
- },
- {
u"url": u"http://www.youtube.com/watch?v=UxxajLWwzqY",
u"file": u"UxxajLWwzqY.mp4",
u"note": u"Test generic use_cipher_signature video (#897)",
@@ -1038,6 +1019,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
"""Turn the encrypted s field into a working signature"""
if player_url is not None:
+ if player_url.startswith(u'//'):
+ player_url = u'https:' + player_url
try:
player_id = (player_url, len(s))
if player_id not in self._player_cache:
@@ -1101,7 +1084,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
else:
raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s)))
- def _get_available_subtitles(self, video_id):
+ def _get_available_subtitles(self, video_id, webpage):
try:
sub_list = self._download_webpage(
'http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
@@ -1117,8 +1100,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
params = compat_urllib_parse.urlencode({
'lang': lang,
'v': video_id,
- 'fmt': self._downloader.params.get('subtitlesformat'),
- 'name': l[0],
+ 'fmt': self._downloader.params.get('subtitlesformat', 'srt'),
+ 'name': l[0].encode('utf-8'),
})
url = u'http://www.youtube.com/api/timedtext?' + params
sub_lang_list[lang] = url
@@ -1130,7 +1113,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
def _get_available_automatic_caption(self, video_id, webpage):
"""We need the webpage for getting the captions url, pass it as an
argument to speed up the process."""
- sub_format = self._downloader.params.get('subtitlesformat')
+ sub_format = self._downloader.params.get('subtitlesformat', 'srt')
self.to_screen(u'%s: Looking for automatic captions' % video_id)
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
err_msg = u'Couldn\'t find automatic captions for %s' % video_id
@@ -1318,6 +1301,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
else:
raise ExtractorError(u'"token" parameter not in video info for unknown reason')
+ if 'view_count' in video_info:
+ view_count = int(video_info['view_count'][0])
+ else:
+ view_count = None
+
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
raise ExtractorError(u'"rental" videos not supported')
@@ -1504,7 +1492,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'subtitles': video_subtitles,
'duration': video_duration,
'age_limit': 18 if age_gate else 0,
- 'annotations': video_annotations
+ 'annotations': video_annotations,
+ 'webpage_url': 'https://www.youtube.com/watch?v=%s' % video_id,
+ 'view_count': view_count,
})
return results
@@ -1590,7 +1580,6 @@ class YoutubePlaylistIE(InfoExtractor):
class YoutubeChannelIE(InfoExtractor):
IE_DESC = u'YouTube.com channels'
_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
- _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
_MORE_PAGES_INDICATOR = 'yt-uix-load-more'
_MORE_PAGES_URL = 'http://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
IE_NAME = u'youtube:channel'
@@ -1611,29 +1600,30 @@ class YoutubeChannelIE(InfoExtractor):
# Download channel page
channel_id = mobj.group(1)
video_ids = []
- pagenum = 1
-
- url = self._TEMPLATE_URL % (channel_id, pagenum)
- page = self._download_webpage(url, channel_id,
- u'Downloading page #%s' % pagenum)
-
- # Extract video identifiers
- ids_in_page = self.extract_videos_from_page(page)
- video_ids.extend(ids_in_page)
+ url = 'https://www.youtube.com/channel/%s/videos' % channel_id
+ channel_page = self._download_webpage(url, channel_id)
+ if re.search(r'channel-header-autogenerated-label', channel_page) is not None:
+ autogenerated = True
+ else:
+ autogenerated = False
- # Download any subsequent channel pages using the json-based channel_ajax query
- if self._MORE_PAGES_INDICATOR in page:
+ if autogenerated:
+ # The videos are contained in a single page
+ # the ajax pages can't be used, they are empty
+ video_ids = self.extract_videos_from_page(channel_page)
+ else:
+ # Download all channel pages using the json-based channel_ajax query
for pagenum in itertools.count(1):
url = self._MORE_PAGES_URL % (pagenum, channel_id)
page = self._download_webpage(url, channel_id,
u'Downloading page #%s' % pagenum)
-
+
page = json.loads(page)
-
+
ids_in_page = self.extract_videos_from_page(page['content_html'])
video_ids.extend(ids_in_page)
-
- if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
+
+ if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
break
self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
@@ -1750,6 +1740,10 @@ class YoutubeSearchIE(SearchInfoExtractor):
videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
return self.playlist_result(videos, query)
+class YoutubeSearchDateIE(YoutubeSearchIE):
+ _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc&orderby=published'
+ _SEARCH_KEY = 'ytsearchdate'
+ IE_DESC = u'YouTube.com searches, newest videos first'
class YoutubeShowIE(InfoExtractor):
IE_DESC = u'YouTube.com (multi-season) shows'
diff --git a/youtube_dl/update.py b/youtube_dl/update.py
index 0689a4891..f41b4785a 100644
--- a/youtube_dl/update.py
+++ b/youtube_dl/update.py
@@ -2,11 +2,15 @@ import io
import json
import traceback
import hashlib
+import os
import subprocess
import sys
from zipimport import zipimporter
-from .utils import *
+from .utils import (
+ compat_str,
+ compat_urllib_request,
+)
from .version import __version__
def rsa_verify(message, signature, key):
diff --git a/youtube_dl/version.py b/youtube_dl/version.py
index 048afc8e7..110058c79 100644
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@@ -1,2 +1,2 @@
-__version__ = '2013.10.28'
+__version__ = '2013.11.17'