'Rogério Brito',
'Philipp Hagemeister',
'Sören Schulze',
+ 'Kevin Ngo',
+ 'Ori Avtalion',
)
__license__ = 'Public Domain'
-__version__ = '2011.09.15'
+__version__ = '2011.11.21'
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
try:
import xml.etree.ElementTree
-except ImportError: # Python<2.5
- pass # Not officially supported, but let it slip
+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-Language': 'en-us,en;q=0.5',
}
-simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
-
try:
import json
except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
+def _simplify_title(title):
+ expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
+ return expr.sub(u'_', title).strip(u'_')
class DownloadError(Exception):
"""Download Error exception.
return
filetime = timeconvert(timestr)
if filetime is None:
- return
+ return filetime
try:
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:
try:
infof = open(infofn, 'wb')
try:
- json.dump(info_dict, infof)
+ json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
+ json.dump(json_info_dict, infof)
finally:
infof.close()
except (OSError, IOError):
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."""
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)
while count <= retries:
# Establish connection
try:
+ if count == 0 and 'urlhandle' in info_dict:
+ data = info_dict['urlhandle']
data = urllib2.urlopen(request)
break
except (urllib2.HTTPError, ), 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)
# 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
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)."""
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', '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 = {
'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)
+ _video_dimensions = {
+ '5': '240x400',
+ '6': '???',
+ '13': '???',
+ '17': '144x176',
+ '18': '360x640',
+ '22': '720x1280',
+ '34': '360x640',
+ '35': '480x854',
+ '37': '1080x1920',
+ '38': '3072x4096',
+ '43': '360x640',
+ '44': '480x854',
+ '45': '720x1280',
+ }
+ IE_NAME = u'youtube'
def report_lang(self):
"""Report attempt to set language."""
"""Indicate the download will use the RTMP protocol."""
self._downloader.to_screen(u'[youtube] RTMP download detected')
+ def _print_formats(self, formats):
+ print 'Available formats:'
+ for x in formats:
+ print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))
+
def _real_initialize(self):
if self._downloader is None:
return
# Get video webpage
self.report_video_webpage_download(video_id)
- request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
+ request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
try:
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
video_title = sanitize_title(video_title)
# simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail_url' not in video_info:
if len(existing_formats) == 0:
self._downloader.trouble(u'ERROR: no known formats available for video')
return
- if req_format is None:
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(existing_formats)
+ return
+ 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)
"""Report information extraction."""
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
"""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)
"""Report information extraction."""
self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
# Extract video description
mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
"""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)
"""Report information extraction."""
self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(vide_title)
video_uploader = mobj.group(2).decode('utf-8')
# _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)
"""Report information extraction."""
self._downloader.to_screen(u'[video.yahoo] %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)
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)
+ simple_title = _simplify_title(video_title)
mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
if mobj is None:
# _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)
- @staticmethod
- def suitable(url):
- return (re.match(VimeoIE._VALID_URL, url) is not None)
-
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % 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)
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)
+ simple_title = _simple_title(video_title)
# Extract uploader
mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
return
sig = mobj.group(1).decode('utf-8')
+ # Vimeo specific: extract video quality information
+ mobj = re.search(r'<isHD>(\d+)</isHD>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video quality information')
+ return
+ quality = mobj.group(1).decode('utf-8')
+
+ if int(quality) == 1:
+ quality = 'hd'
+ else:
+ quality = 'sd'
+
# Vimeo specific: Extract request signature expiration
mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
if mobj is None:
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)
+ video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality)
try:
# Process video information
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.')
"""Report information extraction."""
self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
# At this point we have a new video
self._downloader.increment_downloads()
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
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
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
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
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:http://)?(?:\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_-]+))?.*'
+ _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([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))
while True:
self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
+ url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
+ request = urllib2.Request(url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
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=(.+?)&'
+ _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' %
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)
"""Report information extraction."""
self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
# At this point we have a new file
self._downloader.increment_downloads()
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|photo)\.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']
+ _available_formats = ['video', 'highqual', 'lowqual']
_video_extensions = {
+ 'video': 'mp4',
'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)
def _parse_page(self, video_webpage):
"""Extract video information from page"""
# General data
- data = {'title': r'class="video_title datawrap">(.*?)</',
+ data = {'title': r'\("video_title", "(.*?)"\)',
'description': r'<div class="datawrap">(.*?)</div>',
'owner': r'\("video_owner_name", "(.*?)"\)',
- 'upload_date': r'data-date="(.*?)"',
'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
}
video_info = {}
video_title = video_title.decode('utf-8')
video_title = sanitize_title(video_title)
- # simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail' not in video_info:
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.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
+ def report_direct_download(self, title):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
request = urllib2.Request(json_url)
self.report_extraction(mobj.group(1))
+ info = None
try:
- json_code = urllib2.urlopen(request).read()
+ urlh = urllib2.urlopen(request)
+ if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
+ basename = url.split('/')[-1]
+ title,ext = os.path.splitext(basename)
+ title = title.decode('UTF-8')
+ ext = ext.replace('.', '')
+ self.report_direct_download(title)
+ info = {
+ 'id': title,
+ 'url': url,
+ 'title': title,
+ 'stitle': _simplify_title(title),
+ 'ext': ext,
+ 'urlhandle': urlh
+ }
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
return
- try:
- json_data = json.loads(json_code)
- if 'Post' in json_data:
- data = json_data['Post']
- else:
- data = json_data
-
- upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
- video_url = data['media']['url']
- umobj = re.match(self._URL_EXT, video_url)
- if umobj is None:
- raise ValueError('Can not determine filename extension')
- ext = umobj.group(1)
+ if info is None: # Regular URL
+ try:
+ json_code = urlh.read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
+ return
- self._downloader.increment_downloads()
+ try:
+ json_data = json.loads(json_code)
+ if 'Post' in json_data:
+ data = json_data['Post']
+ else:
+ data = json_data
+
+ upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+ video_url = data['media']['url']
+ umobj = re.match(self._URL_EXT, video_url)
+ if umobj is None:
+ raise ValueError('Can not determine filename extension')
+ ext = umobj.group(1)
+
+ info = {
+ 'id': data['item_id'],
+ 'url': video_url,
+ 'uploader': data['display_name'],
+ 'upload_date': upload_date,
+ 'title': data['title'],
+ 'stitle': _simplify_title(data['title']),
+ 'ext': ext,
+ 'format': data['media']['mimeType'],
+ 'thumbnail': data['thumbnailUrl'],
+ 'description': data['description'],
+ 'player_url': data['embedUrl']
+ }
+ except (ValueError,KeyError), err:
+ self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
+ return
- info = {
- 'id': data['item_id'],
- 'url': video_url,
- 'uploader': data['display_name'],
- 'upload_date': upload_date,
- 'title': data['title'],
- 'stitle': self._simplify_title(data['title']),
- 'ext': ext,
- 'format': data['media']['mimeType'],
- 'thumbnail': data['thumbnailUrl'],
- 'description': data['description'],
- 'player_url': data['embedUrl']
- }
- except (ValueError,KeyError), err:
- self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
- return
+ self._downloader.increment_downloads()
try:
self._downloader.process_info(info)
"""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)
- @staticmethod
- def suitable(url):
- return (re.match(MyVideoIE._VALID_URL, url) is not None)
-
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % 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:
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)
video_title = mobj.group(1)
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
+
try:
- print(video_url)
self._downloader.process_info({
'id': video_id,
'url': video_url,
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>.*)$'
-
- @staticmethod
- def suitable(url):
- return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
+ _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
+ IE_NAME = u'comedycentral'
def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
def report_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:
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = 'http://www.thedailyshow.com/full-episodes/'
+ url = u'http://www.thedailyshow.com/full-episodes/'
else:
- url = 'http://www.colbertnation.com/full-episodes/'
+ url = u'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url)
assert mobj is not None
self._downloader.increment_downloads()
- effTitle = showId + '-' + epTitle
+ effTitle = showId + u'-' + epTitle
info = {
'id': shortMediaId,
'url': video_url,
class EscapistIE(InfoExtractor):
"""Information extractor for The Escapist """
- _VALID_URL = r'^(https?://)?(www\.)escapistmagazine.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?].*$'
-
- @staticmethod
- def suitable(url):
- return (re.match(EscapistIE._VALID_URL, url) is not None)
+ _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+ 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()
'uploader': showName,
'upload_date': None,
'title': showName,
- 'stitle': self._simplify_title(showName),
+ 'stitle': _simplify_title(showName),
'ext': 'flv',
'format': 'flv',
'thumbnail': imgUrl,
self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
+class CollegeHumorIE(InfoExtractor):
+ """Information extractor for collegehumor.com"""
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
+ IE_NAME = u'collegehumor'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ 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
+ video_id = mobj.group('videoid')
+
+ self.report_webpage(video_id)
+ request = urllib2.Request(url)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
+ if m is None:
+ self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
+ return
+ internal_video_id = m.group('internalvideoid')
+
+ info = {
+ 'id': video_id,
+ 'internal_id': internal_video_id,
+ }
+
+ self.report_extraction(video_id)
+ xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
+ try:
+ metaXml = urllib2.urlopen(xmlUrl).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
+ return
+
+ mdoc = xml.etree.ElementTree.fromstring(metaXml)
+ try:
+ videoNode = mdoc.findall('./video')[0]
+ info['description'] = videoNode.findall('./description')[0].text
+ info['title'] = videoNode.findall('./caption')[0].text
+ info['stitle'] = _simplify_title(info['title'])
+ info['url'] = videoNode.findall('./file')[0].text
+ info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
+ info['ext'] = info['url'].rpartition('.')[2]
+ info['format'] = info['ext']
+ except IndexError:
+ self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+ return
+
+ self._downloader.increment_downloads()
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class XVideosIE(InfoExtractor):
+ """Information extractor for xvideos.com"""
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+ IE_NAME = u'xvideos'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ 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
+ video_id = mobj.group(1).decode('utf-8')
+
+ self.report_webpage(video_id)
+
+ request = urllib2.Request(r'http://www.xvideos.com/video' + video_id)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ self.report_extraction(video_id)
+
+
+ # Extract video URL
+ mobj = re.search(r'flv_url=(.+?)&', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
+
+
+ # Extract title
+ mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+
+
+ # Extract video thumbnail
+ mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
+
+
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'stitle': _simplify_title(video_title),
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'thumbnail': video_thumbnail,
+ 'description': None,
+ 'player_url': None,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
+
+
+class SoundcloudIE(InfoExtractor):
+ """Information extractor for soundcloud.com
+ To access the media, the uid of the song and a stream token
+ must be extracted from the page source and the script must make
+ a request to media.soundcloud.com/crossdomain.xml. Then
+ the media can be grabbed by requesting from an url composed
+ of the stream token and uid
+ """
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
+ IE_NAME = u'soundcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ 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
+
+ # extract uploader (which is in the url)
+ uploader = mobj.group(1).decode('utf-8')
+ # extract simple title (uploader + slug of song title)
+ slug_title = mobj.group(2).decode('utf-8')
+ simple_title = uploader + '-' + slug_title
+
+ self.report_webpage('%s/%s' % (uploader, slug_title))
+
+ request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ self.report_extraction('%s/%s' % (uploader, slug_title))
+
+ # extract uid and stream token that soundcloud hands out for access
+ mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
+ if mobj:
+ video_id = mobj.group(1)
+ stream_token = mobj.group(2)
+
+ # extract unsimplified title
+ mobj = re.search('"title":"(.*?)",', webpage)
+ if mobj:
+ title = mobj.group(1)
+
+ # construct media url (with uid/token)
+ mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
+ mediaURL = mediaURL % (video_id, stream_token)
+
+ # description
+ description = u'No description available'
+ mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
+ if mobj:
+ description = mobj.group(1)
+
+ # upload date
+ upload_date = None
+ mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
+ if mobj:
+ try:
+ upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
+ except Exception as e:
+ print str(e)
+
+ # for soundcloud, a request to a cross domain is required for cookies
+ request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
+
+ try:
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': mediaURL,
+ 'uploader': uploader.decode('utf-8'),
+ 'upload_date': upload_date,
+ 'title': simple_title.decode('utf-8'),
+ 'stitle': simple_title.decode('utf-8'),
+ 'ext': u'mp3',
+ 'format': u'NA',
+ 'player_url': None,
+ 'description': description.decode('utf-8')
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class InfoQIE(InfoExtractor):
+ """Information extractor for infoq.com"""
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+ IE_NAME = u'infoq'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ 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
+
+ self.report_webpage(url)
+
+ request = urllib2.Request(url)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ self.report_extraction(url)
+
+
+ # Extract video URL
+ mobj = re.search(r"jsclassref='([^']*)'", webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64'))
+
+
+ # Extract title
+ mobj = re.search(r'contentTitle = "(.*?)";', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+
+ # Extract description
+ video_description = u'No description available.'
+ mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
+ if mobj is not None:
+ video_description = mobj.group(1).decode('utf-8')
+
+ video_filename = video_url.split('/')[-1]
+ video_id, extension = video_filename.split('.')
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'stitle': _simplify_title(video_title),
+ 'ext': extension,
+ 'format': extension, # Extension is always(?) mp4, but seems to be flv
+ 'thumbnail': None,
+ 'description': video_description,
+ 'player_url': None,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
+
+
class PostProcessor(object):
"""Post Processor class.
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
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:
except (IOError, OSError), err:
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():
# Deferred imports
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)
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')
+ video_format.add_option('-F', '--list-formats',
+ action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
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, %(ext)s for the filename extension, 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)
return parser, opts, args
-def main():
+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(),
+ CollegeHumorIE(),
+ XVideosIE(),
+ SoundcloudIE(),
+ InfoQIE(),
+
+ GenericIE()
+ ]
+
+def _real_main():
parser, opts, args = parseOpts()
# Open appropriate CookieJar
print std_headers['User-Agent']
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
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()
- 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
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,
+ 'listformats': opts.listformats,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
# 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:
sys.exit(retcode)
-
-if __name__ == '__main__':
+def main():
try:
- main()
+ _real_main()
except DownloadError:
sys.exit(1)
except SameFileError:
except KeyboardInterrupt:
sys.exit(u'\nERROR: Interrupted by user')
+if __name__ == '__main__':
+ main()
+
# vim: set ts=4 sw=4 sts=4 noet ai si filetype=python:
git://git.jankratochvil.net / youtube-dl.git / blobdiff