'Witold Baryluk',
'Paweł Paprota',
'Gergely Imreh',
+ 'Rogério Brito',
+ 'Philipp Hagemeister',
+ 'Sören Schulze',
)
__license__ = 'Public Domain'
-__version__ = '2011.08.24-phihag'
+__version__ = '2011.09.18c'
+
+UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
import cookielib
import datetime
import gzip
import htmlentitydefs
+import HTMLParser
import httplib
import locale
import math
except ImportError:
pass # Handled below
+try:
+ import xml.etree.ElementTree
+except ImportError: # Python<2.5: 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 = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
yield pref
return yield_preferredencoding().next()
+
def htmlentity_transform(matchobj):
"""Transforms an HTML entity to a Unicode character.
# Unknown entity in name, return its literal representation
return (u'&%s;' % entity)
+
def sanitize_title(utitle):
"""Sanitizes a video title so it could be used as part of a filename."""
utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
return utitle.replace(unicode(os.sep), u'%')
+
def sanitize_open(filename, open_mode):
"""Try to open the given filename, and slightly tweak it if this fails.
stream = open(filename, open_mode)
return (stream, filename)
+
def timeconvert(timestr):
- """Convert RFC 2822 defined time string into system timestamp"""
- timestamp = None
- timetuple = email.utils.parsedate_tz(timestr)
- if timetuple is not None:
- timestamp = email.utils.mktime_tz(timetuple)
- return timestamp
+ """Convert RFC 2822 defined time string into system timestamp"""
+ timestamp = None
+ timetuple = email.utils.parsedate_tz(timestr)
+ if timetuple is not None:
+ timestamp = email.utils.mktime_tz(timetuple)
+ return timestamp
+
class DownloadError(Exception):
"""Download Error exception.
"""
pass
+
class SameFileError(Exception):
"""Same File exception.
"""
pass
+
class PostProcessingError(Exception):
"""Post Processing exception.
"""
pass
+
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
"""
pass
+
class ContentTooShortError(Exception):
"""Content Too Short exception.
self.downloaded = downloaded
self.expected = expected
+
class YoutubeDLHandler(urllib2.HTTPHandler):
"""Handler for HTTP requests and responses.
a particular request, the original request in the program code only has
to include the HTTP header "Youtubedl-No-Compression", which will be
removed before making the real request.
-
+
Part of this code was copied from:
- http://techknack.net/python-urllib2-handlers/
-
+ http://techknack.net/python-urllib2-handlers/
+
Andrew Rowls, the author of that code, agreed to release it to the
public domain.
"""
return zlib.decompress(data, -zlib.MAX_WBITS)
except zlib.error:
return zlib.decompress(data)
-
+
@staticmethod
def addinfourl_wrapper(stream, headers, url, code):
if hasattr(urllib2.addinfourl, 'getcode'):
ret = urllib2.addinfourl(stream, headers, url)
ret.code = code
return ret
-
+
def http_request(self, req):
for h in std_headers:
if h in req.headers:
resp.msg = old_resp.msg
return resp
+
class FileDownloader(object):
"""File Downloader class.
noprogress: Do not print the progress bar.
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
+ matchtitle: Download only matching titles.
+ rejecttitle: Reject downloads for matching titles.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self.params = params
- @staticmethod
- def pmkdir(filename):
- """Create directory components in filename. Similar to Unix "mkdir -p"."""
- components = filename.split(os.sep)
- aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
- aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
- for dir in aggregate:
- if not os.path.exists(dir):
- os.mkdir(dir)
-
@staticmethod
def format_bytes(bytes):
if bytes is None:
else:
exponent = long(math.log(bytes, 1024.0))
suffix = 'bkMGTPEZY'[exponent]
- converted = float(bytes) / float(1024**exponent)
+ converted = float(bytes) / float(1024 ** exponent)
return '%.2f%s' % (converted, suffix)
@staticmethod
os.rename(old_filename, new_filename)
except (IOError, OSError), err:
self.trouble(u'ERROR: unable to rename file')
-
+
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
if last_modified_hdr is None:
return
filetime = timeconvert(timestr)
if filetime is None:
- return
+ return filetime
try:
- os.utime(filename,(time.time(), filetime))
+ os.utime(filename, (time.time(), filetime))
except:
pass
+ return filetime
def report_writedescription(self, descfn):
""" Report that the description file is being written """
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
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
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
if filename is None:
return
+
+ matchtitle=self.params.get('matchtitle',False)
+ rejecttitle=self.params.get('rejecttitle',False)
+ title=info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
+ self.to_screen(u'[download] "%s" title did not match pattern "%s"' % (title, matchtitle))
+ return
+ if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
+ self.to_screen(u'[download] "%s" title matched reject pattern "%s"' % (title, rejecttitle))
+ return
+
if self.params.get('nooverwrites', False) and os.path.exists(filename):
self.to_stderr(u'WARNING: file exists and will be skipped')
return
try:
- self.pmkdir(filename)
+ dn = os.path.dirname(filename)
+ if dn != '' and not os.path.exists(dn):
+ os.makedirs(dn)
except (OSError, IOError), err:
- self.trouble(u'ERROR: unable to create directories: %s' % str(err))
+ self.trouble(u'ERROR: unable to create directory ' + unicode(err))
return
if self.params.get('writedescription', False):
finally:
descfile.close()
except (OSError, IOError):
- self.trouble(u'ERROR: Cannot write description file: %s' % str(descfn))
+ self.trouble(u'ERROR: Cannot write description file ' + descfn)
return
if self.params.get('writeinfojson', False):
finally:
infof.close()
except (OSError, IOError):
- self.trouble(u'ERROR: Cannot write metadata to JSON file: %s' % str(infofn))
+ self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
return
- try:
- 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:
+ if not self.params.get('skip_download', False):
try:
- self.post_process(filename, info_dict)
- except (PostProcessingError), err:
- self.trouble(u'ERROR: postprocessing: %s' % str(err))
+ success = self._do_download(filename, info_dict)
+ 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:
+ self.post_process(filename, info_dict)
+ except (PostProcessingError), err:
+ self.trouble(u'ERROR: postprocessing: %s' % str(err))
+ return
def download(self, url_list):
"""Download a given list of URLs."""
cursize = os.path.getsize(tmpfilename)
if prevsize == cursize and retval == 1:
break
+ # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
+ if prevsize == cursize and retval == 2 and cursize > 1024:
+ self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+ retval = 0
+ break
if retval == 0:
self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
self.try_rename(tmpfilename, filename)
self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
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
if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename)
tmpfilename = self.temp_name(filename)
stream = None
- open_mode = 'wb'
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
else:
resume_len = 0
- # Request parameters in case of being able to resume
- if self.params.get('continuedl', False) and resume_len != 0:
- self.report_resuming_byte(resume_len)
- request.add_header('Range','bytes=%d-' % resume_len)
- open_mode = 'ab'
+ open_mode = 'wb'
+ if resume_len != 0:
+ if self.params.get('continuedl', False):
+ self.report_resuming_byte(resume_len)
+ request.add_header('Range','bytes=%d-' % resume_len)
+ open_mode = 'ab'
+ else:
+ resume_len = 0
count = 0
retries = self.params.get('retries', 0)
else:
# Examine the reported length
if (content_length is not None and
- (resume_len - 100 < long(content_length) < resume_len + 100)):
+ (resume_len - 100 < long(content_length) < resume_len + 100)):
# The file had already been fully downloaded.
# Explanation to the above condition: in issue #175 it was revealed that
# YouTube sometimes adds or removes a few bytes from the end of the file,
if stream is None:
try:
(stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
+ assert stream is not None
filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename)
except (OSError, IOError), err:
block_size = self.best_block_size(after - before, len(data_block))
# 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)
- 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
self.slow_down(start, byte_counter - resume_len)
+ if stream is None:
+ self.trouble(u'\nERROR: Did not get any data blocks')
+ return False
stream.close()
self.report_finish()
if data_len is not None and byte_counter != data_len:
# Update file modification time
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
+
class InfoExtractor(object):
"""Information Extractor class.
description: One-line video description.
Subclasses of this one should re-define the _real_initialize() and
- _real_extract() methods, as well as the suitable() static method.
- Probably, they should also be instantiated and added to the main
- downloader.
+ _real_extract() methods and define a _VALID_URL regexp.
+ Probably, they should also be added to the list of extractors.
"""
_ready = False
self._ready = False
self.set_downloader(downloader)
- @staticmethod
- def suitable(url):
+ def suitable(self, url):
"""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):
"""Initializes an instance (authentication, etc)."""
"""Real extraction process. Redefine in subclasses."""
pass
+
class YoutubeIE(InfoExtractor):
"""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'
_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'
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
- _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
+ _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'37': 'mp4',
'38': 'video', # You actually don't know if this will be MOV, AVI or whatever
'43': 'webm',
+ '44': 'webm',
'45': 'webm',
}
-
- @staticmethod
- def suitable(url):
- return (re.match(YoutubeIE._VALID_URL, url) is not None)
+ IE_NAME = u'youtube'
def report_lang(self):
"""Report attempt to set language."""
self.report_video_info_webpage_download(video_id)
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
+ % (video_id, el_type))
request = urllib2.Request(video_info_url)
try:
video_info_webpage = urllib2.urlopen(request).read()
if len(existing_formats) == 0:
self._downloader.trouble(u'ERROR: no known formats available for video')
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
- 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
else:
- # Specific format
- if req_format not in url_map:
+ # Specific formats. We pick the first in a slash-delimeted sequence.
+ # 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')
return
- video_url_list = [(req_format, url_map[req_format])] # Specific format
else:
self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
return
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
_youtube_ie = None
+ IE_NAME = u'metacafe'
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
- @staticmethod
- def suitable(url):
- return (re.match(MetacafeIE._VALID_URL, url) is not None)
-
def report_disclaimer(self):
"""Report disclaimer retrieval."""
self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+ IE_NAME = u'dailymotion'
def __init__(self, downloader=None):
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):
"""Report webpage download."""
self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
+ request.add_header('Cookie', 'family_filter=off')
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+ mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- mediaURL = urllib.unquote(mobj.group(1))
+ sequence = urllib.unquote(mobj.group(1))
+ mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
# if needed add http://www.dailymotion.com/ if relative URL
video_url = mediaURL
- # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
- mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+ mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
+ mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
except UnavailableVideoError:
self._downloader.trouble(u'\nERROR: unable to download video')
+
class GoogleIE(InfoExtractor):
"""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=([^\&]+).*'
+ IE_NAME = u'video.google'
def __init__(self, downloader=None):
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):
"""Report webpage download."""
self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
else: # we need something to pass to process_info
video_thumbnail = ''
-
try:
# Process video information
self._downloader.process_info({
"""Information extractor for photobucket.com."""
_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+ IE_NAME = u'photobucket'
def __init__(self, downloader=None):
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):
"""Report webpage download."""
self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
# _VPAGE_URL matches only the extractable '/watch/' URLs
_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]+)(?:[#\?].*)?'
+ IE_NAME = u'video.yahoo'
def __init__(self, downloader=None):
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):
"""Report webpage download."""
self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
self._downloader.trouble(u'ERROR: unable to extract video description')
return
video_description = mobj.group(1).decode('utf-8')
- if not video_description: video_description = 'No description available.'
+ if not video_description:
+ video_description = 'No description available.'
# Extract video height and width
mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
yv_bitrate = '700' # according to Wikipedia this is hard-coded
request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
+ '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
+ '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'thumbnail': video_thumbnail,
- 'description': video_description,
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'\nERROR: unable to download video')
+class VimeoIE(InfoExtractor):
+ """Information extractor for vimeo.com."""
+
+ # _VALID_URL matches Vimeo URLs
+ _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+ IE_NAME = u'vimeo'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url, new_video=True):
+ # Extract ID from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+ video_id = mobj.group(1)
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Now we begin extracting as much information as we can from what we
+ # retrieved. First we extract the information common to all extractors,
+ # and latter we extract those that are Vimeo specific.
+ self.report_extraction(video_id)
+
+ # Extract title
+ mobj = re.search(r'<caption>(.*?)</caption>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # Extract uploader
+ mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video uploader')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ # Extract video thumbnail
+ mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
+
+ # # Extract video description
+ # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage)
+ # if mobj is None:
+ # self._downloader.trouble(u'ERROR: unable to extract video description')
+ # return
+ # video_description = mobj.group(1).decode('utf-8')
+ # if not video_description: video_description = 'No description available.'
+ video_description = 'Foo.'
+
+ # Vimeo specific: extract request signature
+ mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract request signature')
+ return
+ sig = mobj.group(1).decode('utf-8')
+
+ # Vimeo specific: Extract request signature expiration
+ mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
+ return
+ sig_exp = mobj.group(1).decode('utf-8')
+
+ video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': u'mp4',
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
class GenericIE(InfoExtractor):
"""Generic last-resort information extractor."""
+ _VALID_URL = r'.*'
+ IE_NAME = u'generic'
+
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- @staticmethod
- def suitable(url):
- return True
-
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
return
video_url = urllib.unquote(mobj.group(1))
- video_id = os.path.basename(video_url)
+ video_id = os.path.basename(video_url)
# here's a fun little line of code for you:
video_extension = os.path.splitext(video_id)[1][1:]
- video_id = os.path.splitext(video_id)[0]
+ video_id = os.path.splitext(video_id)[0]
# it's tempting to parse this further, but you would
# have to take into account all the variations like
class YoutubeSearchIE(InfoExtractor):
"""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'
_VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
_max_youtube_results = 1000
+ IE_NAME = u'youtube:search'
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
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):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._youtube_ie.initialize()
def _real_extract(self, query):
- mobj = re.match(self._VALID_QUERY, query)
+ mobj = re.match(self._VALID_URL, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
prefix, query = query.split(':')
prefix = prefix[8:]
- query = query.encode('utf-8')
+ query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
n = self._max_youtube_results
self._download_n_results(query, n)
return
pagenum = pagenum + 1
+
class GoogleSearchIE(InfoExtractor):
"""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'
_VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
_MORE_PAGES_INDICATOR = r'<span>Next</span>'
_google_ie = None
_max_google_results = 1000
+ IE_NAME = u'video.google:search'
def __init__(self, google_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
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):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._google_ie.initialize()
def _real_extract(self, query):
- mobj = re.match(self._VALID_QUERY, query)
+ mobj = re.match(self._VALID_URL, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
prefix, query = query.split(':')
prefix = prefix[8:]
- query = query.encode('utf-8')
+ query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
n = self._max_google_results
self._download_n_results(query, n)
return
pagenum = pagenum + 1
+
class YahooSearchIE(InfoExtractor):
"""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'
_VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
_MORE_PAGES_INDICATOR = r'\s*Next'
_yahoo_ie = None
_max_yahoo_results = 1000
+ IE_NAME = u'video.yahoo:search'
def __init__(self, yahoo_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
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):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._yahoo_ie.initialize()
def _real_extract(self, query):
- mobj = re.match(self._VALID_QUERY, query)
+ mobj = re.match(self._VALID_URL, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
prefix, query = query.split(':')
prefix = prefix[8:]
- query = query.encode('utf-8')
+ query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_yahoo_results:
- self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
n = self._max_yahoo_results
self._download_n_results(query, n)
return
pagenum = pagenum + 1
+
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+ _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
_TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
+ IE_NAME = u'youtube:playlist'
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
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):
"""Report attempt to download playlist page with given number."""
self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
+
class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users."""
- _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+ _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_GDATA_PAGE_SIZE = 50
_GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_youtube_ie = None
+ IE_NAME = u'youtube:user'
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
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):
"""Report attempt to download user page."""
self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
- (username, start_index, start_index + self._GDATA_PAGE_SIZE))
+ (username, start_index, start_index + self._GDATA_PAGE_SIZE))
def _real_initialize(self):
self._youtube_ie.initialize()
video_ids = video_ids[playliststart:playlistend]
self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
- (username, all_ids_count, len(video_ids)))
+ (username, all_ids_count, len(video_ids)))
for video_id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
class DepositFilesIE(InfoExtractor):
"""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):
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):
"""Report webpage download."""
self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download file')
+
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
_LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
_NETRC_MACHINE = 'facebook'
_available_formats = ['highqual', 'lowqual']
'highqual': 'mp4',
'lowqual': 'mp4',
}
+ IE_NAME = u'facebook'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- @staticmethod
- def suitable(url):
- return (re.match(FacebookIE._VALID_URL, url) is not None)
-
def _reporter(self, message):
"""Add header and report message."""
self._downloader.to_screen(u'[facebook] %s' % message)
return
if req_format is None:
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':
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else:
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
_URL_EXT = r'^.*\.([a-z0-9]+)$'
-
- @staticmethod
- def suitable(url):
- return (re.match(BlipTVIE._VALID_URL, url) is not None)
+ IE_NAME = u'blip.tv'
def report_extraction(self, file_id):
"""Report information extraction."""
self._downloader.trouble(u'\nERROR: unable to download video')
+class MyVideoIE(InfoExtractor):
+ """Information Extractor for myvideo.de."""
+
+ _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+ IE_NAME = u'myvideo'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._download.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(1)
+ simple_title = mobj.group(2).decode('utf-8')
+ # should actually not be necessary
+ simple_title = sanitize_title(simple_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
+
+ # Get video webpage
+ request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ self.report_extraction(video_id)
+ mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
+ webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ video_url = mobj.group(1) + ('/%s.flv' % video_id)
+
+ mobj = re.search('<title>([^<]+)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+
+ video_title = mobj.group(1)
+ video_title = sanitize_title(video_title)
+
+ try:
+ print(video_url)
+ self._downloader.process_info({
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': u'NA',
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': u'flv',
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: Unable to download video')
+
+class ComedyCentralIE(InfoExtractor):
+ """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>.*)$'
+ IE_NAME = u'comedycentral'
+
+ def report_extraction(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
+
+ def report_config_download(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
+
+ def report_index_download(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
+
+ def report_player_url(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
+
+ def _simplify_title(self, title):
+ res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+ res = res.strip(ur'_')
+ return res
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ if mobj.group('shortname'):
+ if mobj.group('shortname') in ('tds', 'thedailyshow'):
+ url = 'http://www.thedailyshow.com/full-episodes/'
+ else:
+ url = 'http://www.colbertnation.com/full-episodes/'
+ mobj = re.match(self._VALID_URL, url)
+ assert mobj is not None
+
+ dlNewest = not mobj.group('episode')
+ if dlNewest:
+ epTitle = mobj.group('showname')
+ else:
+ epTitle = mobj.group('episode')
+
+ req = urllib2.Request(url)
+ self.report_extraction(epTitle)
+ try:
+ htmlHandle = urllib2.urlopen(req)
+ html = htmlHandle.read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+ return
+ if dlNewest:
+ url = htmlHandle.geturl()
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
+ return
+ if mobj.group('episode') == '':
+ self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
+ return
+ epTitle = mobj.group('episode')
+
+ mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"/>', html)
+ if len(mMovieParams) == 0:
+ self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+ return
+
+ playerUrl_raw = mMovieParams[0][0]
+ self.report_player_url(epTitle)
+ try:
+ urlHandle = urllib2.urlopen(playerUrl_raw)
+ playerUrl = urlHandle.geturl()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err))
+ return
+
+ uri = mMovieParams[0][1]
+ indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri})
+ self.report_index_download(epTitle)
+ try:
+ indexXml = urllib2.urlopen(indexUrl).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err))
+ return
+
+ idoc = xml.etree.ElementTree.fromstring(indexXml)
+ itemEls = idoc.findall('.//item')
+ for itemEl in itemEls:
+ mediaId = itemEl.findall('./guid')[0].text
+ shortMediaId = mediaId.split(':')[-1]
+ showId = mediaId.split(':')[-2].replace('.com', '')
+ officialTitle = itemEl.findall('./title')[0].text
+ officialDate = itemEl.findall('./pubDate')[0].text
+
+ configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
+ urllib.urlencode({'uri': mediaId}))
+ configReq = urllib2.Request(configUrl)
+ self.report_config_download(epTitle)
+ try:
+ configXml = urllib2.urlopen(configReq).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+ return
+
+ cdoc = xml.etree.ElementTree.fromstring(configXml)
+ turls = []
+ for rendition in cdoc.findall('.//rendition'):
+ finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
+ turls.append(finfo)
+
+ if len(turls) == 0:
+ self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
+ continue
+
+ # For now, just pick the highest bitrate
+ format,video_url = turls[-1]
+
+ self._downloader.increment_downloads()
+
+ effTitle = showId + '-' + epTitle
+ info = {
+ 'id': shortMediaId,
+ 'url': video_url,
+ 'uploader': showId,
+ 'upload_date': officialDate,
+ 'title': effTitle,
+ 'stitle': self._simplify_title(effTitle),
+ 'ext': 'mp4',
+ 'format': format,
+ 'thumbnail': None,
+ 'description': officialTitle,
+ 'player_url': playerUrl
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + mediaId)
+ continue
+
+
+class EscapistIE(InfoExtractor):
+ """Information extractor for The Escapist """
+
+ _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+ IE_NAME = u'escapist'
+
+ def report_extraction(self, showName):
+ self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
+
+ def report_config_download(self, showName):
+ self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
+
+ def _simplify_title(self, title):
+ res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+ res = res.strip(ur'_')
+ return res
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ showName = mobj.group('showname')
+ videoId = mobj.group('episode')
+
+ self.report_extraction(showName)
+ try:
+ webPage = urllib2.urlopen(url).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
+ return
+
+ descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
+ description = htmlParser.unescape(descMatch.group(1))
+ imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
+ imgUrl = htmlParser.unescape(imgMatch.group(1))
+ playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
+ playerUrl = htmlParser.unescape(playerUrlMatch.group(1))
+ configUrlMatch = re.search('config=(.*)$', playerUrl)
+ configUrl = urllib2.unquote(configUrlMatch.group(1))
+
+ self.report_config_download(showName)
+ try:
+ configJSON = urllib2.urlopen(configUrl).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err))
+ return
+
+ # Technically, it's JavaScript, not JSON
+ configJSON = configJSON.replace("'", '"')
+
+ try:
+ config = json.loads(configJSON)
+ except (ValueError,), err:
+ self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err))
+ return
+
+ playlist = config['playlist']
+ videoUrl = playlist[1]['url']
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': videoId,
+ 'url': videoUrl,
+ 'uploader': showName,
+ 'upload_date': None,
+ 'title': showName,
+ 'stitle': self._simplify_title(showName),
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'thumbnail': imgUrl,
+ 'description': description,
+ 'player_url': playerUrl,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
+
+
+
class PostProcessor(object):
"""Post Processor class.
"""
return information # by default, do nothing
+
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)
if preferredcodec is None:
preferredcodec = 'best'
self._preferredcodec = preferredcodec
+ self._preferredquality = preferredquality
+ self._keepvideo = keepvideo
@staticmethod
def get_audio_codec(path):
more_opts = []
if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
- if filecodec == 'aac' or filecodec == 'mp3':
+ if filecodec in ['aac', 'mp3', 'vorbis']:
# Lossless if possible
acodec = 'copy'
extension = filecodec
if filecodec == 'aac':
more_opts = ['-f', 'adts']
+ if filecodec == 'vorbis':
+ extension = 'ogg'
else:
# MP3 otherwise.
acodec = 'libmp3lame'
extension = 'mp3'
- more_opts = ['-ab', '128k']
+ more_opts = []
+ if self._preferredquality is not None:
+ more_opts += ['-ab', self._preferredquality]
else:
# We convert the audio (lossy)
- acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
+ acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[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':
more_opts += ['-f', 'adts']
+ if self._preferredcodec == 'vorbis':
+ extension = 'ogg'
(prefix, ext) = os.path.splitext(path)
new_path = prefix + '.' + extension
self._downloader.to_stderr(u'WARNING: error running ffmpeg')
return None
- try:
- os.remove(path)
- except (IOError, OSError):
- self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
- return None
+ # Try to update the date time for extracted audio file.
+ if information.get('filetime') is not None:
+ try:
+ os.utime(new_path, (time.time(), information['filetime']))
+ 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
return information
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
- downloader.to_screen('Updating to latest stable version...')
+ downloader.to_screen('Updating to latest version...')
try:
- latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
- latest_version = urllib.urlopen(latest_url).read().strip()
- prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
- newcontent = urllib.urlopen(prog_url).read()
+ try:
+ urlh = urllib.urlopen(UPDATE_URL)
+ 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:
+ urlh.close()
except (IOError, OSError), err:
sys.exit('ERROR: unable to download latest version')
try:
- stream = open(filename, 'w')
- stream.write(newcontent)
- stream.close()
+ outf = open(filename, 'wb')
+ try:
+ outf.write(newcontent)
+ finally:
+ outf.close()
except (IOError, OSError), err:
sys.exit('ERROR: unable to overwrite current version')
- downloader.to_screen('Updated to version %s' % latest_version)
+ downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.')
def parseOpts():
# Deferred imports
try:
sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out,err = sp.communicate()
- return out.split()[1]
+ return int(out.split()[1])
except:
pass
return None
kw = {
'version' : __version__,
'formatter' : fmt,
- 'usage' : '%prog [options] url...',
+ 'usage' : '%prog [options] url [url...]',
'conflict_handler' : 'resolve',
}
# option groups
general = optparse.OptionGroup(parser, 'General Options')
+ selection = optparse.OptionGroup(parser, 'Video Selection')
authentication = optparse.OptionGroup(parser, 'Authentication Options')
video_format = optparse.OptionGroup(parser, 'Video Format Options')
postproc = optparse.OptionGroup(parser, 'Post-processing Options')
general.add_option('-v', '--version',
action='version', help='print program version and exit')
general.add_option('-U', '--update',
- action='store_true', dest='update_self', help='update this program to latest stable version')
+ action='store_true', dest='update_self', help='update this program to latest version')
general.add_option('-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
general.add_option('-r', '--rate-limit',
dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
general.add_option('-R', '--retries',
dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
- general.add_option('--playlist-start',
- dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
- general.add_option('--playlist-end',
- dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
general.add_option('--dump-user-agent',
action='store_true', dest='dump_user_agent',
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',
+ dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
+ selection.add_option('--playlist-end',
+ dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+ selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
+ selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
authentication.add_option('-u', '--username',
dest='username', metavar='USERNAME', help='account username')
video_format.add_option('-f', '--format',
action='store', dest='format', metavar='FORMAT', help='video format code')
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',
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
verbosity.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
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',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
verbosity.add_option('-e', '--get-title',
verbosity.add_option('--get-filename',
action='store_true', dest='getfilename',
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',
action='store_true', dest='noprogress', help='do not print progress bar', default=False)
verbosity.add_option('--console-title',
action='store_true', dest='autonumber',
help='number downloaded files starting from 00000', default=False)
filesystem.add_option('-o', '--output',
- dest='outtmpl', metavar='TEMPLATE', help='output filename template')
+ dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, and %% for a literal percent')
filesystem.add_option('-a', '--batch-file',
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
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=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',
- dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
+ dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
filesystem.add_option('--no-part',
action='store_true', dest='nopart', help='do not use .part files', default=False)
filesystem.add_option('--no-mtime',
postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
- help='"best", "aac" or "mp3"; best by default')
+ help='"best", "aac", "vorbis" 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(selection)
parser.add_option_group(filesystem)
parser.add_option_group(verbosity)
parser.add_option_group(video_format)
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():
parser, opts, args = parseOpts()
print std_headers['User-Agent']
sys.exit(0)
- # General configuration
- cookie_processor = urllib2.HTTPCookieProcessor(jar)
- urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()))
- socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
-
# Batch file verification
batchurls = []
if opts.batchfile is not None:
sys.exit(u'ERROR: batch file could not be read')
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
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')
except (TypeError, ValueError), err:
parser.error(u'invalid playlist end number specified')
if opts.extractaudio:
- if opts.audioformat not in ['best', 'aac', 'mp3']:
+ if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
parser.error(u'invalid audio format specified')
- # Information extractors
- youtube_ie = YoutubeIE()
- metacafe_ie = MetacafeIE(youtube_ie)
- dailymotion_ie = DailymotionIE()
- youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
- youtube_user_ie = YoutubeUserIE(youtube_ie)
- youtube_search_ie = YoutubeSearchIE(youtube_ie)
- google_ie = GoogleIE()
- google_search_ie = GoogleSearchIE(google_ie)
- photobucket_ie = PhotobucketIE()
- yahoo_ie = YahooIE()
- yahoo_search_ie = YahooSearchIE(yahoo_ie)
- deposit_files_ie = DepositFilesIE()
- facebook_ie = FacebookIE()
- bliptv_ie = BlipTVIE()
- generic_ie = GenericIE()
-
# File downloader
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
'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,
'forcetitle': opts.gettitle,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
'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_limit': opts.format_limit,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
'writeinfojson': opts.writeinfojson,
+ 'matchtitle': opts.matchtitle,
+ 'rejecttitle': opts.rejecttitle,
})
- fd.add_info_extractor(youtube_search_ie)
- fd.add_info_extractor(youtube_pl_ie)
- fd.add_info_extractor(youtube_user_ie)
- fd.add_info_extractor(metacafe_ie)
- fd.add_info_extractor(dailymotion_ie)
- fd.add_info_extractor(youtube_ie)
- fd.add_info_extractor(google_ie)
- fd.add_info_extractor(google_search_ie)
- fd.add_info_extractor(photobucket_ie)
- fd.add_info_extractor(yahoo_ie)
- fd.add_info_extractor(yahoo_search_ie)
- fd.add_info_extractor(deposit_files_ie)
- fd.add_info_extractor(facebook_ie)
- fd.add_info_extractor(bliptv_ie)
-
- # This must come last since it's the
- # fallback if none of the others work
- fd.add_info_extractor(generic_ie)
+ for extractor in extractors:
+ fd.add_info_extractor(extractor)
# PostProcessors
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
if opts.update_self: