X-Git-Url: http://git.jankratochvil.net/?a=blobdiff_plain;f=youtube-dl;h=c2511e8644ed5c7ab65c69697deec68c9387c61d;hb=ba5059dd66310055116e77e0f1c57685830f1b84;hp=1b2ccae2fbe82a713602c7d5b698565695752629;hpb=d793aebaed09f9ec19e5b7d07e8e3063545e9a72;p=youtube-dl.git
diff --git a/youtube-dl b/youtube-dl
index 1b2ccae..c2511e8 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -12,17 +12,21 @@ __author__ = (
'Rogério Brito',
'Philipp Hagemeister',
'Sören Schulze',
+ 'Kevin Ngo',
+ 'Ori Avtalion',
+ 'shizeeg',
)
__license__ = 'Public Domain'
-__version__ = '2011.09.09-phihag'
+__version__ = '2011.12.15'
-UPDATE_URL = 'https://raw.github.com/phihag/youtube-dl/master/youtube-dl'
+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
@@ -65,8 +69,8 @@ except ImportError:
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',
@@ -76,8 +80,6 @@ std_headers = {
'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):
@@ -276,6 +278,17 @@ def timeconvert(timestr):
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'_')
+
+def _orderedSet(iterable):
+ """ Remove all duplicates from the input iterable """
+ res = []
+ for el in iterable:
+ if el not in res:
+ res.append(el)
+ return res
class DownloadError(Exception):
"""Download Error exception.
@@ -304,6 +317,10 @@ class PostProcessingError(Exception):
"""
pass
+class MaxDownloadsReached(Exception):
+ """ --max-downloads limit has been reached. """
+ pass
+
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
@@ -437,6 +454,8 @@ class FileDownloader(object):
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.
@@ -622,11 +641,12 @@ class FileDownloader(object):
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 """
@@ -691,27 +711,54 @@ class FileDownloader(object):
self.trouble(u'ERROR: invalid system charset or erroneous output template')
return None
+ def _match_entry(self, info_dict):
+ """ Returns None iff the file should be downloaded """
+
+ title = info_dict['title']
+ matchtitle = self.params.get('matchtitle', False)
+ if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
+ return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+ rejecttitle = self.params.get('rejecttitle', False)
+ if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
+ return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+ return None
+
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
+
+ reason = self._match_entry(info_dict)
+ if reason is not None:
+ self.to_screen(u'[download] ' + reason)
+ return
+
+ max_downloads = self.params.get('max_downloads')
+ if max_downloads is not None:
+ if self._num_downloads > int(max_downloads):
+ raise MaxDownloadsReached()
+
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
+
if self.params.get('nooverwrites', False) and os.path.exists(filename):
self.to_stderr(u'WARNING: file exists and will be skipped')
return
@@ -748,30 +795,32 @@ class FileDownloader(object):
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."""
@@ -822,7 +871,7 @@ class FileDownloader(object):
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
- basic_args = ['rtmpdump'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
+ basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
while retval == 2 or retval == 1:
prevsize = os.path.getsize(tmpfilename)
@@ -832,6 +881,11 @@ class FileDownloader(object):
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)
@@ -840,7 +894,10 @@ class FileDownloader(object):
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)
@@ -852,7 +909,6 @@ class FileDownloader(object):
tmpfilename = self.temp_name(filename)
stream = None
- open_mode = 'wb'
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
@@ -865,17 +921,22 @@ class FileDownloader(object):
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:
@@ -953,10 +1014,13 @@ class FileDownloader(object):
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)
@@ -972,7 +1036,7 @@ class FileDownloader(object):
# 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
@@ -1007,9 +1071,8 @@ class InfoExtractor(object):
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
@@ -1020,10 +1083,9 @@ class InfoExtractor(object):
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)."""
@@ -1052,13 +1114,14 @@ class InfoExtractor(object):
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']
+ _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
@@ -1067,12 +1130,25 @@ class YoutubeIE(InfoExtractor):
'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."""
@@ -1106,6 +1182,11 @@ class YoutubeIE(InfoExtractor):
"""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
@@ -1185,7 +1266,7 @@ class YoutubeIE(InfoExtractor):
# 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:
@@ -1238,8 +1319,7 @@ class YoutubeIE(InfoExtractor):
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:
@@ -1291,24 +1371,36 @@ class YoutubeIE(InfoExtractor):
url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
format_limit = self._downloader.params.get('format_limit', None)
- if format_limit is not None and format_limit in self._available_formats:
- format_list = self._available_formats[self._available_formats.index(format_limit):]
+ available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
+ if format_limit is not None and format_limit in available_formats:
+ format_list = available_formats[available_formats.index(format_limit):]
else:
- format_list = self._available_formats
+ format_list = available_formats
existing_formats = [x for x in format_list if x in url_map]
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
@@ -1346,15 +1438,12 @@ class MetacafeIE(InfoExtractor):
_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')
@@ -1488,14 +1577,11 @@ class DailymotionIE(InfoExtractor):
"""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)
@@ -1504,10 +1590,9 @@ class DailymotionIE(InfoExtractor):
"""Report information extraction."""
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
@@ -1518,11 +1603,11 @@ class DailymotionIE(InfoExtractor):
self._downloader.increment_downloads()
video_id = mobj.group(1)
- simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
# 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()
@@ -1532,25 +1617,30 @@ class DailymotionIE(InfoExtractor):
# 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
- # ''
- mobj = re.search(r'(?im)
Dailymotion\s*[\-:]\s*(.+?)', webpage)
+ mobj = re.search(r'', 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 = htmlParser.unescape(mobj.group('title')).decode('utf-8')
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
- mobj = re.search(r'(?im)(.+?)', webpage)
+ mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
@@ -1577,14 +1667,11 @@ 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)
@@ -1593,9 +1680,6 @@ class GoogleIE(InfoExtractor):
"""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)
@@ -1639,7 +1723,7 @@ class GoogleIE(InfoExtractor):
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'([^<]*)', webpage)
@@ -1687,14 +1771,11 @@ class PhotobucketIE(InfoExtractor):
"""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)
@@ -1703,9 +1784,6 @@ class PhotobucketIE(InfoExtractor):
"""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)
@@ -1744,7 +1822,7 @@ class PhotobucketIE(InfoExtractor):
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')
@@ -1772,14 +1850,11 @@ class YahooIE(InfoExtractor):
# _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)
@@ -1788,9 +1863,6 @@ class YahooIE(InfoExtractor):
"""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)
@@ -1844,7 +1916,7 @@ class YahooIE(InfoExtractor):
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'', webpage)
if mobj is None:
@@ -1917,7 +1989,6 @@ class YahooIE(InfoExtractor):
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'thumbnail': video_thumbnail,
- 'description': video_description,
'player_url': None,
})
except UnavailableVideoError:
@@ -1929,14 +2000,11 @@ class VimeoIE(InfoExtractor):
# _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)
@@ -1945,9 +2013,6 @@ class VimeoIE(InfoExtractor):
"""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)
@@ -1979,7 +2044,7 @@ class VimeoIE(InfoExtractor):
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)
# Extract uploader
mobj = re.search(r'http://vimeo.com/(.*?)', webpage)
@@ -2011,6 +2076,18 @@ class VimeoIE(InfoExtractor):
return
sig = mobj.group(1).decode('utf-8')
+ # Vimeo specific: extract video quality information
+ mobj = re.search(r'(\d+)', 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'(.*?)', webpage)
if mobj is None:
@@ -2018,7 +2095,7 @@ class VimeoIE(InfoExtractor):
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
@@ -2043,13 +2120,12 @@ class VimeoIE(InfoExtractor):
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.')
@@ -2059,9 +2135,6 @@ class GenericIE(InfoExtractor):
"""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()
@@ -2115,7 +2188,7 @@ class GenericIE(InfoExtractor):
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)
@@ -2143,21 +2216,18 @@ class GenericIE(InfoExtractor):
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*'
_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())
@@ -2167,7 +2237,7 @@ class YoutubeSearchIE(InfoExtractor):
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
@@ -2235,21 +2305,18 @@ class YoutubeSearchIE(InfoExtractor):
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'Next'
_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())
@@ -2259,7 +2326,7 @@ class GoogleSearchIE(InfoExtractor):
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
@@ -2327,21 +2394,18 @@ class GoogleSearchIE(InfoExtractor):
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())
@@ -2351,7 +2415,7 @@ class YahooSearchIE(InfoExtractor):
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
@@ -2420,20 +2484,17 @@ class YahooSearchIE(InfoExtractor):
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*'
_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))
@@ -2467,7 +2528,8 @@ class YoutubePlaylistIE(InfoExtractor):
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:
@@ -2497,21 +2559,18 @@ class YoutubePlaylistIE(InfoExtractor):
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' %
@@ -2588,15 +2647,12 @@ class YoutubeUserIE(InfoExtractor):
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)
@@ -2605,9 +2661,6 @@ class DepositFilesIE(InfoExtractor):
"""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()
@@ -2668,22 +2721,20 @@ class DepositFilesIE(InfoExtractor):
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P\d+)(?:.*)'
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P\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)
@@ -2703,10 +2754,9 @@ class FacebookIE(InfoExtractor):
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'(.*?)
',
'owner': r'\("video_owner_name", "(.*?)"\)',
- 'upload_date': r'data-date="(.*?)"',
'thumbnail': r'\("thumb_url", "(?P.*?)"\)',
}
video_info = {}
@@ -2808,9 +2858,7 @@ class FacebookIE(InfoExtractor):
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:
@@ -2849,6 +2897,8 @@ class FacebookIE(InfoExtractor):
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:
@@ -2889,19 +2939,15 @@ class BlipTVIE(InfoExtractor):
_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)
@@ -2916,43 +2962,65 @@ class BlipTVIE(InfoExtractor):
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)
@@ -2964,14 +3032,11 @@ 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)
- @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)
@@ -2980,9 +3045,6 @@ class MyVideoIE(InfoExtractor):
"""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:
@@ -2990,10 +3052,6 @@ class MyVideoIE(InfoExtractor):
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)
@@ -3020,8 +3078,9 @@ class MyVideoIE(InfoExtractor):
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,
@@ -3037,13 +3096,10 @@ class MyVideoIE(InfoExtractor):
self._downloader.trouble(u'\nERROR: Unable to download video')
class ComedyCentralIE(InfoExtractor):
- """Information extractor for blip.tv"""
+ """Information extractor for The Daily Show and Colbert Report """
- _VALID_URL = r'^(?:https?://)?(www\.)?(thedailyshow|colbertnation)\.com/full-episodes/(.*)$'
-
- @staticmethod
- def suitable(url):
- return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
+ _VALID_URL = r'^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?Pthedailyshow|colbertnation)\.com/full-episodes/(?P.*)$'
+ IE_NAME = u'comedycentral'
def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
@@ -3051,59 +3107,83 @@ class ComedyCentralIE(InfoExtractor):
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
- epTitle = mobj.group(3)
+
+ if mobj.group('shortname'):
+ if mobj.group('shortname') in ('tds', 'thedailyshow'):
+ url = u'http://www.thedailyshow.com/full-episodes/'
+ else:
+ url = u'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:
- html = urllib2.urlopen(req).read()
+ 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('', html)
+ mMovieParams = re.findall('', html)
if len(mMovieParams) == 0:
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
return
- show_id = mMovieParams[0][2]
- ACT_COUNT = { # TODO: Detect this dynamically
- 'thedailyshow.com': 4,
- 'colbertnation.com': 3,
- }.get(show_id, 4)
- OFFSET = {
- 'thedailyshow.com': 1,
- 'colbertnation.com': 1,
- }.get(show_id, 1)
-
- first_player_url = mMovieParams[0][0]
- startMediaNum = int(mMovieParams[0][3]) + OFFSET
- movieId = mMovieParams[0][1]
-
- playerReq = urllib2.Request(first_player_url)
+
+ playerUrl_raw = mMovieParams[0][0]
self.report_player_url(epTitle)
try:
- playerResponse = urllib2.urlopen(playerReq)
+ 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 player: %s' % unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err))
return
- player_url = playerResponse.geturl()
- for actNum in range(ACT_COUNT):
- mediaNum = startMediaNum + actNum
- mediaId = movieId + str(mediaNum)
+ 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)
@@ -3121,7 +3201,7 @@ class ComedyCentralIE(InfoExtractor):
turls.append(finfo)
if len(turls) == 0:
- self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum) + ': No videos found')
+ self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
continue
# For now, just pick the highest bitrate
@@ -3129,138 +3209,803 @@ class ComedyCentralIE(InfoExtractor):
self._downloader.increment_downloads()
- effTitle = show_id.replace('.com', '') + '-' + epTitle
+ effTitle = showId + u'-' + epTitle
info = {
- 'id': str(mediaNum),
+ 'id': shortMediaId,
'url': video_url,
- 'uploader': show_id,
- 'upload_date': 'NA',
+ 'uploader': showId,
+ 'upload_date': officialDate,
'title': effTitle,
- 'stitle': self._simplify_title(effTitle),
+ 'stitle': _simplify_title(effTitle),
'ext': 'mp4',
'format': format,
'thumbnail': None,
- 'description': 'TODO: Not yet supported',
- 'player_url': player_url
+ 'description': officialTitle,
+ 'player_url': playerUrl
}
try:
self._downloader.process_info(info)
except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum))
+ self._downloader.trouble(u'\nERROR: unable to download ' + mediaId)
continue
-class PostProcessor(object):
- """Post Processor class.
-
- PostProcessor objects can be added to downloaders with their
- add_post_processor() method. When the downloader has finished a
- successful download, it will take its internal chain of PostProcessors
- and start calling the run() method on each one of them, first with
- an initial argument and then with the returned value of the previous
- PostProcessor.
+class EscapistIE(InfoExtractor):
+ """Information extractor for The Escapist """
- The chain will be stopped if one of them ever returns None or the end
- of the chain is reached.
+ _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P[^/]+)/(?P[^/?]+)[/?]?.*$'
+ IE_NAME = u'escapist'
- PostProcessor objects follow a "mutual registration" process similar
- to InfoExtractor objects.
- """
+ def report_extraction(self, showName):
+ self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
- _downloader = None
+ def report_config_download(self, showName):
+ self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
- def __init__(self, downloader=None):
- self._downloader = downloader
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
- def set_downloader(self, downloader):
- """Sets the downloader for this PP."""
- self._downloader = downloader
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ showName = mobj.group('showname')
+ videoId = mobj.group('episode')
- def run(self, information):
- """Run the PostProcessor.
+ self.report_extraction(showName)
+ try:
+ webPage = urllib2.urlopen(url).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
+ return
- The "information" argument is a dictionary like the ones
- composed by InfoExtractors. The only difference is that this
- one has an extra field called "filepath" that points to the
- downloaded file.
+ descMatch = re.search('[0-9]+)/(?P.*)$'
+ IE_NAME = u'collegehumor'
- more_opts = []
- if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
- if filecodec == 'aac' or filecodec == 'mp3':
- # Lossless if possible
- acodec = 'copy'
- extension = filecodec
- if filecodec == 'aac':
- more_opts = ['-f', 'adts']
- else:
- # MP3 otherwise.
- acodec = 'libmp3lame'
+ 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[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'(.*?)\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">(.*?)
', webpage)
+ if mobj:
+ description = mobj.group(1)
+
+ # upload date
+ upload_date = None
+ mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)", webpage)
+ if mobj:
+ try:
+ upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
+ except Exception, 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'', 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 MixcloudIE(InfoExtractor):
+ """Information extractor for www.mixcloud.com"""
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+ IE_NAME = u'mixcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_json(self, file_id):
+ """Report JSON download."""
+ self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+
+ def get_urls(self, jsonData, fmt, bitrate='best'):
+ """Get urls from 'audio_formats' section in json"""
+ file_url = None
+ try:
+ bitrate_list = jsonData[fmt]
+ if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
+ bitrate = max(bitrate_list) # select highest
+
+ url_list = jsonData[fmt][bitrate]
+ except TypeError: # we have no bitrate info.
+ url_list = jsonData[fmt]
+
+ return url_list
+
+ def check_urls(self, url_list):
+ """Returns 1st active url from list"""
+ for url in url_list:
+ try:
+ urllib2.urlopen(url)
+ return url
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ url = None
+
+ return None
+
+ def _print_formats(self, formats):
+ print 'Available formats:'
+ for fmt in formats.keys():
+ for b in formats[fmt]:
+ try:
+ ext = formats[fmt][b][0]
+ print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])
+ except TypeError: # we have no bitrate info
+ ext = formats[fmt][0]
+ print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])
+ break
+
+ 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
+ # extract uploader & filename from url
+ uploader = mobj.group(1).decode('utf-8')
+ file_id = uploader + "-" + mobj.group(2).decode('utf-8')
+
+ # construct API request
+ file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
+ # retrieve .json file with links to files
+ request = urllib2.Request(file_url)
+ try:
+ self.report_download_json(file_url)
+ jsonData = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err))
+ return
+
+ # parse JSON
+ json_data = json.loads(jsonData)
+ player_url = json_data['player_swf_url']
+ formats = dict(json_data['audio_formats'])
+
+ req_format = self._downloader.params.get('format', None)
+ bitrate = None
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(formats)
+ return
+
+ if req_format is None or req_format == 'best':
+ for format_param in formats.keys():
+ url_list = self.get_urls(formats, format_param)
+ # check urls
+ file_url = self.check_urls(url_list)
+ if file_url is not None:
+ break # got it!
+ else:
+ if req_format not in formats.keys():
+ self._downloader.trouble(u'ERROR: format is not available')
+ return
+
+ url_list = self.get_urls(formats, req_format)
+ file_url = self.check_urls(url_list)
+ format_param = req_format
+
+ # We have audio
+ self._downloader.increment_downloads()
+ try:
+ # Process file information
+ self._downloader.process_info({
+ 'id': file_id.decode('utf-8'),
+ 'url': file_url.decode('utf-8'),
+ 'uploader': uploader.decode('utf-8'),
+ 'upload_date': u'NA',
+ 'title': json_data['name'],
+ 'stitle': _simplify_title(json_data['name']),
+ 'ext': file_url.split('.')[-1].decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': json_data['thumbnail_url'],
+ 'description': json_data['description'],
+ 'player_url': player_url.decode('utf-8'),
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download file')
+
+class StanfordOpenClassroomIE(InfoExtractor):
+ """Information extractor for Stanford's Open ClassRoom"""
+
+ _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P[^&]+)(&video=(?P