Compare commits

...

30 Commits

Author SHA1 Message Date
daa982bc01 release 2011.09.18c: Prefer mp4 over webm 2011-09-17 00:58:44 +02:00
767414a292 Prefer format 18 over 43 2011-09-17 00:58:14 +02:00
7b417b388a Add youtube format 44 2011-09-17 00:51:25 +02:00
44424ceee9 Prefer mp4 over webm - seems to work better for most users 2011-09-17 00:39:51 +02:00
08a5b7f800 Release 2011.09.18b 2011-09-16 22:33:08 +02:00
1cde6f1d52 Prevent youtube IE from taking youtube playlists 2011-09-16 22:31:31 +02:00
2d8acd8039 Fix escapist URL match 2011-09-15 20:25:22 +02:00
67035ede49 Fix progress message when Content-Length is not set 2011-09-15 20:24:21 +02:00
eb6c37da43 Clarified "restart" 2011-09-15 20:10:27 +02:00
2736595628 Do not update if already up-to-date (Closes #166) 2011-09-15 20:09:30 +02:00
7b1a2bbe17 release 2011.09.18 2011-09-15 19:29:16 +02:00
c25303c3d5 Set continue to false again; we need to send to actually send a HEAD request to determine whether we can continue or not 2011-09-15 19:27:21 +02:00
cc025e1226 release 2011.09.17 2011-09-15 19:23:52 +02:00
eca1b76f01 Update README 2011-09-15 19:23:17 +02:00
366cbfb04a Fix _do_download signature 2011-09-15 19:22:18 +02:00
18bb3d1e35 Make --continue the default and provide --no-continue (Closes #119) 2011-09-15 19:12:04 +02:00
10e7194db1 If --continue is not enabled, set resume_len to zero.
This corrects the reporting of download progress (which previously
started at a value greater than zero).
2011-09-15 19:07:53 +02:00
ef357c4bf2 Bump version number 2011-09-15 18:48:29 +02:00
5260e68f64 Add format fallback 2011-09-15 18:47:36 +02:00
6a1ca41e17 Update README 2011-09-15 12:45:56 +02:00
c99dcbd2d6 Merge remote-tracking branch 'rmanola/master' (Closes: #124)
Add option to specify mp3 quality and prevent the video from being deleted
2011-09-15 12:43:27 +02:00
da0db53a75 added option to get the available formats for a video (Closes #106) 2011-09-15 12:20:03 +02:00
c52b01f326 Added ability to download worst quality video file only. (Closes #113) 2011-09-15 12:14:16 +02:00
36597dc40f Updated to stamp extracted audio file with HTTP last modified date. 2011-09-15 12:04:54 +02:00
9b4556c469 New option --skip-download (Closes #162) 2011-09-15 11:36:49 +02:00
f3098c4d8a --list-extractors (Closes #161) 2011-09-15 11:03:29 +02:00
bdb3f7a769 Simplify suitable 2011-09-15 10:06:14 +02:00
afb5b55de6 Proper warning if xml.etree.ElementTree is not available 2011-09-15 09:59:03 +02:00
c23cec29a3 Update LATEST_VERSION (and wait for a script to do it so I do not forget ;) ) 2011-09-14 23:03:01 +02:00
18b7f87409 Added option to allow different audio encoding qualities and to allow specify whether erase or not the video when it's need to extract the audio. 2011-06-06 17:46:37 -07:00
3 changed files with 215 additions and 188 deletions

View File

@ -1 +1 @@
2011.09.14 2011.09.18c

View File

@ -18,6 +18,8 @@ which means you can modify it, redistribute it or use it however you like.
-r, --rate-limit LIMIT download rate limit (e.g. 50k or 44.6m) -r, --rate-limit LIMIT download rate limit (e.g. 50k or 44.6m)
-R, --retries RETRIES number of retries (default is 10) -R, --retries RETRIES number of retries (default is 10)
--dump-user-agent display the current browser identification --dump-user-agent display the current browser identification
--list-extractors List all supported extractors and the URLs they
would handle
### Video Selection: ### Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1) --playlist-start NUMBER playlist video to start at (default is 1)
@ -35,6 +37,8 @@ which means you can modify it, redistribute it or use it however you like.
-a, --batch-file FILE file containing URLs to download ('-' for stdin) -a, --batch-file FILE file containing URLs to download ('-' for stdin)
-w, --no-overwrites do not overwrite files -w, --no-overwrites do not overwrite files
-c, --continue resume partially downloaded files -c, --continue resume partially downloaded files
--no-continue do not resume partially downloaded files (restart
from beginning)
--cookies FILE file to dump cookie jar to --cookies FILE file to dump cookie jar to
--no-part do not use .part files --no-part do not use .part files
--no-mtime do not use the Last-modified header to set the file --no-mtime do not use the Last-modified header to set the file
@ -44,12 +48,15 @@ which means you can modify it, redistribute it or use it however you like.
### Verbosity / Simulation Options: ### Verbosity / Simulation Options:
-q, --quiet activates quiet mode -q, --quiet activates quiet mode
-s, --simulate do not download video -s, --simulate do not download the video and do not write anything
to disk
--skip-download do not download the video
-g, --get-url simulate, quiet but print URL -g, --get-url simulate, quiet but print URL
-e, --get-title simulate, quiet but print title -e, --get-title simulate, quiet but print title
--get-thumbnail simulate, quiet but print thumbnail URL --get-thumbnail simulate, quiet but print thumbnail URL
--get-description simulate, quiet but print video description --get-description simulate, quiet but print video description
--get-filename simulate, quiet but print output filename --get-filename simulate, quiet but print output filename
--get-format simulate, quiet but print output format
--no-progress do not print progress bar --no-progress do not print progress bar
--console-title display progress in console titlebar --console-title display progress in console titlebar
@ -67,6 +74,9 @@ which means you can modify it, redistribute it or use it however you like.
--extract-audio convert video files to audio-only files (requires --extract-audio convert video files to audio-only files (requires
ffmpeg and ffprobe) ffmpeg and ffprobe)
--audio-format FORMAT "best", "aac" or "mp3"; best by default --audio-format FORMAT "best", "aac" or "mp3"; best by default
--audio-quality QUALITY ffmpeg audio bitrate specification, 128k by default
-k, --keep-video keeps the video file on disk after the post-
processing; the video is erased by default
## FAQ ## FAQ

View File

@ -15,7 +15,7 @@ __author__ = (
) )
__license__ = 'Public Domain' __license__ = 'Public Domain'
__version__ = '2011.09.15' __version__ = '2011.09.18c'
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
@ -66,8 +66,8 @@ except ImportError:
try: try:
import xml.etree.ElementTree import xml.etree.ElementTree
except ImportError: # Python<2.5 except ImportError: # Python<2.5: Not officially supported, but let it slip
pass # Not officially supported, but let it slip warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.')
std_headers = { std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
@ -625,11 +625,12 @@ class FileDownloader(object):
return return
filetime = timeconvert(timestr) filetime = timeconvert(timestr)
if filetime is None: if filetime is None:
return return filetime
try: try:
os.utime(filename, (time.time(), filetime)) os.utime(filename, (time.time(), filetime))
except: except:
pass pass
return filetime
def report_writedescription(self, descfn): def report_writedescription(self, descfn):
""" Report that the description file is being written """ """ Report that the description file is being written """
@ -697,20 +698,23 @@ class FileDownloader(object):
def process_info(self, info_dict): def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor.""" """Process a single dictionary returned by an InfoExtractor."""
filename = self.prepare_filename(info_dict) filename = self.prepare_filename(info_dict)
# Forced printings
if self.params.get('forcetitle', False):
print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forceurl', False):
print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcedescription', False) and 'description' in info_dict:
print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcefilename', False) and filename is not None:
print filename.encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forceformat', False):
print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
# Do nothing else if in simulate mode # Do nothing else if in simulate mode
if self.params.get('simulate', False): if self.params.get('simulate', False):
# Forced printings
if self.params.get('forcetitle', False):
print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forceurl', False):
print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcedescription', False) and 'description' in info_dict:
print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcefilename', False) and filename is not None:
print filename.encode(preferredencoding(), 'xmlcharrefreplace')
return return
if filename is None: if filename is None:
@ -769,23 +773,24 @@ class FileDownloader(object):
self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
return return
try: if not self.params.get('skip_download', False):
success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
except (OSError, IOError), err:
raise UnavailableVideoError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble(u'ERROR: unable to download video data: %s' % str(err))
return
except (ContentTooShortError, ), err:
self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
try: try:
self.post_process(filename, info_dict) success = self._do_download(filename, info_dict)
except (PostProcessingError), err: except (OSError, IOError), err:
self.trouble(u'ERROR: postprocessing: %s' % str(err)) raise UnavailableVideoError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble(u'ERROR: unable to download video data: %s' % str(err))
return return
except (ContentTooShortError, ), err:
self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
self.trouble(u'ERROR: postprocessing: %s' % str(err))
return
def download(self, url_list): def download(self, url_list):
"""Download a given list of URLs.""" """Download a given list of URLs."""
@ -859,7 +864,10 @@ class FileDownloader(object):
self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
return False return False
def _do_download(self, filename, url, player_url): def _do_download(self, filename, info_dict):
url = info_dict['url']
player_url = info_dict.get('player_url', None)
# Check file already present # Check file already present
if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False): if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename) self.report_file_already_downloaded(filename)
@ -871,7 +879,6 @@ class FileDownloader(object):
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
stream = None stream = None
open_mode = 'wb'
# Do not include the Accept-Encoding header # Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'} headers = {'Youtubedl-no-compression': 'True'}
@ -884,11 +891,14 @@ class FileDownloader(object):
else: else:
resume_len = 0 resume_len = 0
# Request parameters in case of being able to resume open_mode = 'wb'
if self.params.get('continuedl', False) and resume_len != 0: if resume_len != 0:
self.report_resuming_byte(resume_len) if self.params.get('continuedl', False):
request.add_header('Range', 'bytes=%d-' % resume_len) self.report_resuming_byte(resume_len)
open_mode = 'ab' request.add_header('Range','bytes=%d-' % resume_len)
open_mode = 'ab'
else:
resume_len = 0
count = 0 count = 0
retries = self.params.get('retries', 0) retries = self.params.get('retries', 0)
@ -972,10 +982,13 @@ class FileDownloader(object):
block_size = self.best_block_size(after - before, len(data_block)) block_size = self.best_block_size(after - before, len(data_block))
# Progress message # Progress message
percent_str = self.calc_percent(byte_counter, data_len)
eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
self.report_progress(percent_str, data_len_str, speed_str, eta_str) if data_len is None:
self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
else:
percent_str = self.calc_percent(byte_counter, data_len)
eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Apply rate limit # Apply rate limit
self.slow_down(start, byte_counter - resume_len) self.slow_down(start, byte_counter - resume_len)
@ -991,7 +1004,7 @@ class FileDownloader(object):
# Update file modification time # Update file modification time
if self.params.get('updatetime', True): if self.params.get('updatetime', True):
self.try_utime(filename, data.info().get('last-modified', None)) info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
return True return True
@ -1026,9 +1039,8 @@ class InfoExtractor(object):
description: One-line video description. description: One-line video description.
Subclasses of this one should re-define the _real_initialize() and Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods, as well as the suitable() static method. _real_extract() methods and define a _VALID_URL regexp.
Probably, they should also be instantiated and added to the main Probably, they should also be added to the list of extractors.
downloader.
""" """
_ready = False _ready = False
@ -1039,10 +1051,9 @@ class InfoExtractor(object):
self._ready = False self._ready = False
self.set_downloader(downloader) self.set_downloader(downloader)
@staticmethod def suitable(self, url):
def suitable(url):
"""Receives a URL and returns True if suitable for this IE.""" """Receives a URL and returns True if suitable for this IE."""
return False return re.match(self._VALID_URL, url) is not None
def initialize(self): def initialize(self):
"""Initializes an instance (authentication, etc).""" """Initializes an instance (authentication, etc)."""
@ -1071,13 +1082,13 @@ class InfoExtractor(object):
class YoutubeIE(InfoExtractor): class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com.""" """Information extractor for youtube.com."""
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube' _NETRC_MACHINE = 'youtube'
# Listed in order of quality # Listed in order of quality
_available_formats = ['38', '37', '45', '22', '43', '35', '34', '18', '6', '5', '17', '13'] _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
_video_extensions = { _video_extensions = {
'13': '3gp', '13': '3gp',
'17': 'mp4', '17': 'mp4',
@ -1086,12 +1097,10 @@ class YoutubeIE(InfoExtractor):
'37': 'mp4', '37': 'mp4',
'38': 'video', # You actually don't know if this will be MOV, AVI or whatever '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
'43': 'webm', '43': 'webm',
'44': 'webm',
'45': 'webm', '45': 'webm',
} }
IE_NAME = u'youtube'
@staticmethod
def suitable(url):
return (re.match(YoutubeIE._VALID_URL, url) is not None)
def report_lang(self): def report_lang(self):
"""Report attempt to set language.""" """Report attempt to set language."""
@ -1318,16 +1327,24 @@ class YoutubeIE(InfoExtractor):
if len(existing_formats) == 0: if len(existing_formats) == 0:
self._downloader.trouble(u'ERROR: no known formats available for video') self._downloader.trouble(u'ERROR: no known formats available for video')
return return
if req_format is None: if req_format is None or req_format == 'best':
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif req_format == '-1': elif req_format == 'worst':
video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
elif req_format in ('-1', 'all'):
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else: else:
# Specific format # Specific formats. We pick the first in a slash-delimeted sequence.
if req_format not in url_map: # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
req_formats = req_format.split('/')
video_url_list = None
for rf in req_formats:
if rf in url_map:
video_url_list = [(rf, url_map[rf])]
break
if video_url_list is None:
self._downloader.trouble(u'ERROR: requested format not available') self._downloader.trouble(u'ERROR: requested format not available')
return return
video_url_list = [(req_format, url_map[req_format])] # Specific format
else: else:
self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
return return
@ -1365,15 +1382,12 @@ class MetacafeIE(InfoExtractor):
_DISCLAIMER = 'http://www.metacafe.com/family_filter/' _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
_youtube_ie = None _youtube_ie = None
IE_NAME = u'metacafe'
def __init__(self, youtube_ie, downloader=None): def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie self._youtube_ie = youtube_ie
@staticmethod
def suitable(url):
return (re.match(MetacafeIE._VALID_URL, url) is not None)
def report_disclaimer(self): def report_disclaimer(self):
"""Report disclaimer retrieval.""" """Report disclaimer retrieval."""
self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
@ -1507,14 +1521,11 @@ class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion""" """Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
IE_NAME = u'dailymotion'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(DailymotionIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
@ -1601,14 +1612,11 @@ class GoogleIE(InfoExtractor):
"""Information extractor for video.google.com.""" """Information extractor for video.google.com."""
_VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
IE_NAME = u'video.google'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(GoogleIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
@ -1711,14 +1719,11 @@ class PhotobucketIE(InfoExtractor):
"""Information extractor for photobucket.com.""" """Information extractor for photobucket.com."""
_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
IE_NAME = u'photobucket'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(PhotobucketIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
@ -1796,14 +1801,11 @@ class YahooIE(InfoExtractor):
# _VPAGE_URL matches only the extractable '/watch/' URLs # _VPAGE_URL matches only the extractable '/watch/' URLs
_VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
_VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
IE_NAME = u'video.yahoo'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(YahooIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
@ -1952,14 +1954,11 @@ class VimeoIE(InfoExtractor):
# _VALID_URL matches Vimeo URLs # _VALID_URL matches Vimeo URLs
_VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)' _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
IE_NAME = u'vimeo'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(VimeoIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
@ -2066,13 +2065,12 @@ class VimeoIE(InfoExtractor):
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
"""Generic last-resort information extractor.""" """Generic last-resort information extractor."""
_VALID_URL = r'.*'
IE_NAME = u'generic'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return True
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
@ -2166,21 +2164,18 @@ class GenericIE(InfoExtractor):
class YoutubeSearchIE(InfoExtractor): class YoutubeSearchIE(InfoExtractor):
"""Information Extractor for YouTube search queries.""" """Information Extractor for YouTube search queries."""
_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+' _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en' _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'href="/watch\?v=.+?"' _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None _youtube_ie = None
_max_youtube_results = 1000 _max_youtube_results = 1000
IE_NAME = u'youtube:search'
def __init__(self, youtube_ie, downloader=None): def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie self._youtube_ie = youtube_ie
@staticmethod
def suitable(url):
return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
def report_download_page(self, query, pagenum): def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number.""" """Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding()) query = query.decode(preferredencoding())
@ -2190,7 +2185,7 @@ class YoutubeSearchIE(InfoExtractor):
self._youtube_ie.initialize() self._youtube_ie.initialize()
def _real_extract(self, query): def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query) mobj = re.match(self._VALID_URL, query)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return return
@ -2258,21 +2253,18 @@ class YoutubeSearchIE(InfoExtractor):
class GoogleSearchIE(InfoExtractor): class GoogleSearchIE(InfoExtractor):
"""Information Extractor for Google Video search queries.""" """Information Extractor for Google Video search queries."""
_VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+' _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
_VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&' _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
_MORE_PAGES_INDICATOR = r'<span>Next</span>' _MORE_PAGES_INDICATOR = r'<span>Next</span>'
_google_ie = None _google_ie = None
_max_google_results = 1000 _max_google_results = 1000
IE_NAME = u'video.google:search'
def __init__(self, google_ie, downloader=None): def __init__(self, google_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._google_ie = google_ie self._google_ie = google_ie
@staticmethod
def suitable(url):
return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
def report_download_page(self, query, pagenum): def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number.""" """Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding()) query = query.decode(preferredencoding())
@ -2282,7 +2274,7 @@ class GoogleSearchIE(InfoExtractor):
self._google_ie.initialize() self._google_ie.initialize()
def _real_extract(self, query): def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query) mobj = re.match(self._VALID_URL, query)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return return
@ -2350,21 +2342,18 @@ class GoogleSearchIE(InfoExtractor):
class YahooSearchIE(InfoExtractor): class YahooSearchIE(InfoExtractor):
"""Information Extractor for Yahoo! Video search queries.""" """Information Extractor for Yahoo! Video search queries."""
_VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+' _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
_VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
_MORE_PAGES_INDICATOR = r'\s*Next' _MORE_PAGES_INDICATOR = r'\s*Next'
_yahoo_ie = None _yahoo_ie = None
_max_yahoo_results = 1000 _max_yahoo_results = 1000
IE_NAME = u'video.yahoo:search'
def __init__(self, yahoo_ie, downloader=None): def __init__(self, yahoo_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._yahoo_ie = yahoo_ie self._yahoo_ie = yahoo_ie
@staticmethod
def suitable(url):
return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
def report_download_page(self, query, pagenum): def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number.""" """Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding()) query = query.decode(preferredencoding())
@ -2374,7 +2363,7 @@ class YahooSearchIE(InfoExtractor):
self._yahoo_ie.initialize() self._yahoo_ie.initialize()
def _real_extract(self, query): def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query) mobj = re.match(self._VALID_URL, query)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return return
@ -2448,15 +2437,12 @@ class YoutubePlaylistIE(InfoExtractor):
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None _youtube_ie = None
IE_NAME = u'youtube:playlist'
def __init__(self, youtube_ie, downloader=None): def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie self._youtube_ie = youtube_ie
@staticmethod
def suitable(url):
return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
def report_download_page(self, playlist_id, pagenum): def report_download_page(self, playlist_id, pagenum):
"""Report attempt to download playlist page with given number.""" """Report attempt to download playlist page with given number."""
self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
@ -2526,15 +2512,12 @@ class YoutubeUserIE(InfoExtractor):
_GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_youtube_ie = None _youtube_ie = None
IE_NAME = u'youtube:user'
def __init__(self, youtube_ie, downloader=None): def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie self._youtube_ie = youtube_ie
@staticmethod
def suitable(url):
return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
def report_download_page(self, username, start_index): def report_download_page(self, username, start_index):
"""Report attempt to download user page.""" """Report attempt to download user page."""
self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
@ -2612,14 +2595,11 @@ class DepositFilesIE(InfoExtractor):
"""Information extractor for depositfiles.com""" """Information extractor for depositfiles.com"""
_VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)' _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
IE_NAME = u'DepositFiles'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(DepositFilesIE._VALID_URL, url) is not None)
def report_download_webpage(self, file_id): def report_download_webpage(self, file_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
@ -2699,14 +2679,11 @@ class FacebookIE(InfoExtractor):
'highqual': 'mp4', 'highqual': 'mp4',
'lowqual': 'mp4', 'lowqual': 'mp4',
} }
IE_NAME = u'facebook'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(FacebookIE._VALID_URL, url) is not None)
def _reporter(self, message): def _reporter(self, message):
"""Add header and report message.""" """Add header and report message."""
self._downloader.to_screen(u'[facebook] %s' % message) self._downloader.to_screen(u'[facebook] %s' % message)
@ -2872,6 +2849,8 @@ class FacebookIE(InfoExtractor):
return return
if req_format is None: if req_format is None:
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif req_format == 'worst':
video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
elif req_format == '-1': elif req_format == '-1':
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else: else:
@ -2912,10 +2891,7 @@ class BlipTVIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
_URL_EXT = r'^.*\.([a-z0-9]+)$' _URL_EXT = r'^.*\.([a-z0-9]+)$'
IE_NAME = u'blip.tv'
@staticmethod
def suitable(url):
return (re.match(BlipTVIE._VALID_URL, url) is not None)
def report_extraction(self, file_id): def report_extraction(self, file_id):
"""Report information extraction.""" """Report information extraction."""
@ -2987,14 +2963,11 @@ class MyVideoIE(InfoExtractor):
"""Information Extractor for myvideo.de.""" """Information Extractor for myvideo.de."""
_VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
IE_NAME = u'myvideo'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(MyVideoIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id) self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
@ -3062,11 +3035,8 @@ class MyVideoIE(InfoExtractor):
class ComedyCentralIE(InfoExtractor): class ComedyCentralIE(InfoExtractor):
"""Information extractor for The Daily Show and Colbert Report """ """Information extractor for The Daily Show and Colbert Report """
_VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$' _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
IE_NAME = u'comedycentral'
@staticmethod
def suitable(url):
return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
def report_extraction(self, episode_id): def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
@ -3206,11 +3176,8 @@ class ComedyCentralIE(InfoExtractor):
class EscapistIE(InfoExtractor): class EscapistIE(InfoExtractor):
"""Information extractor for The Escapist """ """Information extractor for The Escapist """
_VALID_URL = r'^(https?://)?(www\.)escapistmagazine.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?].*$' _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
IE_NAME = u'escapist'
@staticmethod
def suitable(url):
return (re.match(EscapistIE._VALID_URL, url) is not None)
def report_extraction(self, showName): def report_extraction(self, showName):
self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
@ -3339,11 +3306,13 @@ class PostProcessor(object):
class FFmpegExtractAudioPP(PostProcessor): class FFmpegExtractAudioPP(PostProcessor):
def __init__(self, downloader=None, preferredcodec=None): def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
PostProcessor.__init__(self, downloader) PostProcessor.__init__(self, downloader)
if preferredcodec is None: if preferredcodec is None:
preferredcodec = 'best' preferredcodec = 'best'
self._preferredcodec = preferredcodec self._preferredcodec = preferredcodec
self._preferredquality = preferredquality
self._keepvideo = keepvideo
@staticmethod @staticmethod
def get_audio_codec(path): def get_audio_codec(path):
@ -3392,12 +3361,16 @@ class FFmpegExtractAudioPP(PostProcessor):
# MP3 otherwise. # MP3 otherwise.
acodec = 'libmp3lame' acodec = 'libmp3lame'
extension = 'mp3' extension = 'mp3'
more_opts = ['-ab', '128k'] more_opts = []
if self._preferredquality is not None:
more_opts += ['-ab', self._preferredquality]
else: else:
# We convert the audio (lossy) # We convert the audio (lossy)
acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec] acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
extension = self._preferredcodec extension = self._preferredcodec
more_opts = ['-ab', '128k'] more_opts = []
if self._preferredquality is not None:
more_opts += ['-ab', self._preferredquality]
if self._preferredcodec == 'aac': if self._preferredcodec == 'aac':
more_opts += ['-f', 'adts'] more_opts += ['-f', 'adts']
@ -3410,11 +3383,19 @@ class FFmpegExtractAudioPP(PostProcessor):
self._downloader.to_stderr(u'WARNING: error running ffmpeg') self._downloader.to_stderr(u'WARNING: error running ffmpeg')
return None return None
try: # Try to update the date time for extracted audio file.
os.remove(path) if information.get('filetime') is not None:
except (IOError, OSError): try:
self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file') os.utime(new_path, (time.time(), information['filetime']))
return None except:
self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
if not self._keepvideo:
try:
os.remove(path)
except (IOError, OSError):
self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
return None
information['filepath'] = new_path information['filepath'] = new_path
return information return information
@ -3432,6 +3413,11 @@ def updateSelf(downloader, filename):
try: try:
urlh = urllib.urlopen(UPDATE_URL) urlh = urllib.urlopen(UPDATE_URL)
newcontent = urlh.read() newcontent = urlh.read()
vmatch = re.search("__version__ = '([^']+)'", newcontent)
if vmatch is not None and vmatch.group(1) == __version__:
downloader.to_screen('youtube-dl is up-to-date (' + __version__ + ')')
return
finally: finally:
urlh.close() urlh.close()
except (IOError, OSError), err: except (IOError, OSError), err:
@ -3446,7 +3432,7 @@ def updateSelf(downloader, filename):
except (IOError, OSError), err: except (IOError, OSError), err:
sys.exit('ERROR: unable to overwrite current version') sys.exit('ERROR: unable to overwrite current version')
downloader.to_screen('Updated youtube-dl. Restart to use the new version.') downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.')
def parseOpts(): def parseOpts():
# Deferred imports # Deferred imports
@ -3522,6 +3508,9 @@ def parseOpts():
general.add_option('--dump-user-agent', general.add_option('--dump-user-agent',
action='store_true', dest='dump_user_agent', action='store_true', dest='dump_user_agent',
help='display the current browser identification', default=False) help='display the current browser identification', default=False)
general.add_option('--list-extractors',
action='store_true', dest='list_extractors',
help='List all supported extractors and the URLs they would handle', default=False)
selection.add_option('--playlist-start', selection.add_option('--playlist-start',
dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
@ -3541,7 +3530,7 @@ def parseOpts():
video_format.add_option('-f', '--format', video_format.add_option('-f', '--format',
action='store', dest='format', metavar='FORMAT', help='video format code') action='store', dest='format', metavar='FORMAT', help='video format code')
video_format.add_option('--all-formats', video_format.add_option('--all-formats',
action='store_const', dest='format', help='download all available video formats', const='-1') action='store_const', dest='format', help='download all available video formats', const='all')
video_format.add_option('--max-quality', video_format.add_option('--max-quality',
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
@ -3549,7 +3538,9 @@ def parseOpts():
verbosity.add_option('-q', '--quiet', verbosity.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False) action='store_true', dest='quiet', help='activates quiet mode', default=False)
verbosity.add_option('-s', '--simulate', verbosity.add_option('-s', '--simulate',
action='store_true', dest='simulate', help='do not download video', default=False) action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
verbosity.add_option('--skip-download',
action='store_true', dest='skip_download', help='do not download the video', default=False)
verbosity.add_option('-g', '--get-url', verbosity.add_option('-g', '--get-url',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
verbosity.add_option('-e', '--get-title', verbosity.add_option('-e', '--get-title',
@ -3563,6 +3554,9 @@ def parseOpts():
verbosity.add_option('--get-filename', verbosity.add_option('--get-filename',
action='store_true', dest='getfilename', action='store_true', dest='getfilename',
help='simulate, quiet but print output filename', default=False) help='simulate, quiet but print output filename', default=False)
verbosity.add_option('--get-format',
action='store_true', dest='getformat',
help='simulate, quiet but print output format', default=False)
verbosity.add_option('--no-progress', verbosity.add_option('--no-progress',
action='store_true', dest='noprogress', help='do not print progress bar', default=False) action='store_true', dest='noprogress', help='do not print progress bar', default=False)
verbosity.add_option('--console-title', verbosity.add_option('--console-title',
@ -3585,6 +3579,9 @@ def parseOpts():
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue', filesystem.add_option('-c', '--continue',
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False) action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
filesystem.add_option('--no-continue',
action='store_false', dest='continue_dl',
help='do not resume partially downloaded files (restart from beginning)')
filesystem.add_option('--cookies', filesystem.add_option('--cookies',
dest='cookiefile', metavar='FILE', help='file to dump cookie jar to') dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
filesystem.add_option('--no-part', filesystem.add_option('--no-part',
@ -3604,6 +3601,10 @@ def parseOpts():
help='convert video files to audio-only files (requires ffmpeg and ffprobe)') help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
help='"best", "aac" or "mp3"; best by default') help='"best", "aac" or "mp3"; best by default')
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
help='ffmpeg audio bitrate specification, 128k by default')
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
help='keeps the video file on disk after the post-processing; the video is erased by default')
parser.add_option_group(general) parser.add_option_group(general)
@ -3618,6 +3619,36 @@ def parseOpts():
return parser, opts, args return parser, opts, args
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
"""
youtube_ie = YoutubeIE()
google_ie = GoogleIE()
yahoo_ie = YahooIE()
return [
YoutubePlaylistIE(youtube_ie),
YoutubeUserIE(youtube_ie),
YoutubeSearchIE(youtube_ie),
youtube_ie,
MetacafeIE(youtube_ie),
DailymotionIE(),
google_ie,
GoogleSearchIE(google_ie),
PhotobucketIE(),
yahoo_ie,
YahooSearchIE(yahoo_ie),
DepositFilesIE(),
FacebookIE(),
BlipTVIE(),
VimeoIE(),
MyVideoIE(),
ComedyCentralIE(),
EscapistIE(),
GenericIE()
]
def main(): def main():
parser, opts, args = parseOpts() parser, opts, args = parseOpts()
@ -3637,12 +3668,6 @@ def main():
print std_headers['User-Agent'] print std_headers['User-Agent']
sys.exit(0) sys.exit(0)
# General configuration
cookie_processor = urllib2.HTTPCookieProcessor(jar)
opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
urllib2.install_opener(opener)
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
# Batch file verification # Batch file verification
batchurls = [] batchurls = []
if opts.batchfile is not None: if opts.batchfile is not None:
@ -3658,6 +3683,23 @@ def main():
sys.exit(u'ERROR: batch file could not be read') sys.exit(u'ERROR: batch file could not be read')
all_urls = batchurls + args all_urls = batchurls + args
# General configuration
cookie_processor = urllib2.HTTPCookieProcessor(jar)
opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
urllib2.install_opener(opener)
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
extractors = gen_extractors()
if opts.list_extractors:
for ie in extractors:
print(ie.IE_NAME)
matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
all_urls = filter(lambda url: url not in matchedUrls, all_urls)
for mu in matchedUrls:
print(u' ' + mu)
sys.exit(0)
# Conflicting, missing and erroneous options # Conflicting, missing and erroneous options
if opts.usenetrc and (opts.username is not None or opts.password is not None): if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error(u'using .netrc conflicts with giving username/password') parser.error(u'using .netrc conflicts with giving username/password')
@ -3695,45 +3737,20 @@ def main():
if opts.audioformat not in ['best', 'aac', 'mp3']: if opts.audioformat not in ['best', 'aac', 'mp3']:
parser.error(u'invalid audio format specified') parser.error(u'invalid audio format specified')
# Information extractors
youtube_ie = YoutubeIE()
google_ie = GoogleIE()
yahoo_ie = YahooIE()
extractors = [ # Order does matter
youtube_ie,
MetacafeIE(youtube_ie),
DailymotionIE(),
YoutubePlaylistIE(youtube_ie),
YoutubeUserIE(youtube_ie),
YoutubeSearchIE(youtube_ie),
google_ie,
GoogleSearchIE(google_ie),
PhotobucketIE(),
yahoo_ie,
YahooSearchIE(yahoo_ie),
DepositFilesIE(),
FacebookIE(),
BlipTVIE(),
VimeoIE(),
MyVideoIE(),
ComedyCentralIE(),
EscapistIE(),
GenericIE()
]
# File downloader # File downloader
fd = FileDownloader({ fd = FileDownloader({
'usenetrc': opts.usenetrc, 'usenetrc': opts.usenetrc,
'username': opts.username, 'username': opts.username,
'password': opts.password, 'password': opts.password,
'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename), 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'forceurl': opts.geturl, 'forceurl': opts.geturl,
'forcetitle': opts.gettitle, 'forcetitle': opts.gettitle,
'forcethumbnail': opts.getthumbnail, 'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription, 'forcedescription': opts.getdescription,
'forcefilename': opts.getfilename, 'forcefilename': opts.getfilename,
'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename), 'forceformat': opts.getformat,
'simulate': opts.simulate,
'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'format': opts.format, 'format': opts.format,
'format_limit': opts.format_limit, 'format_limit': opts.format_limit,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
@ -3768,7 +3785,7 @@ def main():
# PostProcessors # PostProcessors
if opts.extractaudio: if opts.extractaudio:
fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat)) fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
# Update version # Update version
if opts.update_self: if opts.update_self: