"""Information Extractor class.
Information extractors are the classes that, given a URL, extract
- information from the video (or videos) the URL refers to. This
- information includes the real video URL, the video title and simplified
- title, author and others. The information is stored in a dictionary
- which is then passed to the FileDownloader. The FileDownloader
- processes this information possibly downloading the video to the file
- system, among other possible outcomes. The dictionaries must include
- the following fields:
-
- id: Video identifier.
- url: Final video URL.
- uploader: Nickname of the video uploader.
- title: Literal title.
- ext: Video filename extension.
- format: Video format.
- player_url: SWF Player URL (may be None).
-
- The following fields are optional. Their primary purpose is to allow
- youtube-dl to serve as the backend for a video search function, such
- as the one in youtube2mp3. They are only used when their respective
- forced printing functions are called:
-
- thumbnail: Full URL to a video thumbnail image.
- description: One-line video description.
+ information about the video (or videos) the URL refers to. This
+ information includes the real video URL, the video title, author and
+ others. The information is stored in a dictionary which is then
+ passed to the FileDownloader. The FileDownloader processes this
+ information possibly downloading the video to the file system, among
+ other possible outcomes.
+
+ The dictionaries must include the following fields:
+
+ id: Video identifier.
+ url: Final video URL.
+ uploader: Nickname of the video uploader, unescaped.
+ upload_date: Video upload date (YYYYMMDD).
+ title: Video title, unescaped.
+ ext: Video filename extension.
+
+ The following fields are optional:
+
+ format: The video format, defaults to ext (used for --get-format)
+ thumbnail: Full URL to a video thumbnail image.
+ description: One-line video description.
+ player_url: SWF Player URL (used for rtmpdump).
+ subtitles: The .srt file contents.
+ urlhandle: [internal] The urlHandle to be used to download the file,
+ like returned by urllib2.urlopen
+
+ The fields should all be Unicode strings.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods and define a _VALID_URL regexp.
Probably, they should also be added to the list of extractors.
+
+ _real_extract() must return a *list* of information dictionaries as
+ described above.
+
+ Finally, the _WORKING attribute should be set to False for broken IEs
+ in order to warn the users and skip the tests.
"""
_ready = False
_downloader = None
+ _WORKING = True
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""
"""Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url) is not None
+ def working(self):
+ """Getter method for _WORKING."""
+ return self._WORKING
+
def initialize(self):
"""Initializes an instance (authentication, etc)."""
if not self._ready:
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _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).+)?$'
+ _VALID_URL = r"""^
+ (
+ (?:https?://)? # http(s):// (optional)
+ (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
+ tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
+ (?:.*?\#/)? # handle anchor (#/) redirect urls
+ (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
+ (?: # the various things that can precede the ID:
+ (?:(?:v|embed|e)/) # v/ or embed/ or e/
+ |(?: # or the v= param in all its forms
+ (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
+ (?:\?|\#!?) # the params delimiter ? or # or #!
+ (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx)
+ v=
+ )
+ )? # optional -> youtube.com/xxxx is OK
+ )? # all until now is optional -> you can pass the naked ID
+ ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
+ (?(1).+)? # if we found the ID, everything can follow
+ $"""
_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'
}
IE_NAME = u'youtube'
+ def suitable(self, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+
def report_lang(self):
"""Report attempt to set language."""
self._downloader.to_screen(u'[youtube] Setting language')
return srt
def _print_formats(self, formats):
- print 'Available 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, '???'))
+ 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:
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+ self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % u(err))
return
# Set language
self.report_lang()
urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
+ self._downloader.to_stderr(u'WARNING: unable to set language: %s' % u(err))
return
# No authentication to be performed
self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
return
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+ self._downloader.to_stderr(u'WARNING: unable to log in: %s' % u(err))
return
# Confirm age
self.report_age_confirmation()
age_results = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to confirm age: %s' % u(err))
return
def _real_extract(self, url):
url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/')
# Extract video id from URL
- mobj = re.match(self._VALID_URL, url)
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
try:
video_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))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return
# Attempt to extract SWF player URL
if 'token' in video_info:
break
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % u(err))
return
if 'token' not in video_info:
if 'reason' in video_info:
video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
# upload date
- upload_date = u'NA'
+ upload_date = None
mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
try:
srt_list = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
+ raise Trouble(u'WARNING: unable to download video subtitles: %s' % u(err))
srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
if not srt_lang_list:
try:
srt_xml = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
+ raise Trouble(u'WARNING: unable to download video subtitles: %s' % u(err))
if not srt_xml:
raise Trouble(u'WARNING: unable to download video subtitles')
video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
except Trouble as trouble:
self._downloader.trouble(trouble[0])
+ if 'length_seconds' not in video_info:
+ self._downloader.trouble(u'WARNING: unable to extract video duration')
+ video_duration = ''
+ else:
+ video_duration = urllib.unquote_plus(video_info['length_seconds'][0])
+
# token
video_token = urllib.unquote_plus(video_info['token'][0])
url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
url_data = [parse_qs(uds) for uds in url_data_strs]
url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
- url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
+ url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
format_limit = self._downloader.params.get('format_limit', None)
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
# Extension
video_extension = self._video_extensions.get(format_param, 'flv')
+ video_format = '{} - {}'.format(format_param.decode('utf-8') if format_param else video_extension.decode('utf-8'),
+ self._video_dimensions.get(format_param, '???'))
+
results.append({
'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'),
'upload_date': upload_date,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'format': video_format,
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'player_url': player_url,
- 'subtitles': video_subtitles
+ 'subtitles': video_subtitles,
+ 'duration': video_duration
})
return results
self.report_disclaimer()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % u(err))
return
# Confirm age
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to confirm age: %s' % u(err))
return
def _real_extract(self, url):
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % u(err))
return
# Extract URL, uploader and title from webpage
return
video_title = mobj.group(1).decode('utf-8')
- mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
+ mobj = re.search(r'submitter=(.*?);', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+ _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
IE_NAME = u'dailymotion'
def __init__(self, downloader=None):
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- video_id = mobj.group(1)
+ video_id = mobj.group(1).split('_')[0].split('?')[0]
- video_extension = 'flv'
+ video_extension = 'mp4'
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % u(err))
return
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
+ mobj = re.search(r'\s*var flashvars = (.*)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- sequence = urllib.unquote(mobj.group(1))
- mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+ flashvars = urllib.unquote(mobj.group(1))
+
+ for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
+ if key in flashvars:
+ max_quality = key
+ self._downloader.to_screen(u'[dailymotion] Using %s' % key)
+ break
+ else:
+ self._downloader.trouble(u'ERROR: unable to extract video URL')
+ return
+
+ mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
+ self._downloader.trouble(u'ERROR: unable to extract video URL')
return
- mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
- # if needed add http://www.dailymotion.com/ if relative URL
+ video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/')
- video_url = mediaURL
+ # TODO: support choosing qualities
mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
if mobj is None:
return
video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
- mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
+ video_uploader = None
+ mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
+ # lookin for official user
+ mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
+ if mobj_official is None:
+ self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+ else:
+ video_uploader = mobj_official.group(1)
+ else:
+ video_uploader = mobj.group(1)
+
+ video_upload_date = None
+ mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
+ if mobj is not None:
+ video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
return [{
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
- 'upload_date': u'NA',
+ 'upload_date': video_upload_date,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
# Extract URL, uploader, and title from webpage
try:
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
if mobj is None:
return [{
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
- 'uploader': u'NA',
- 'upload_date': u'NA',
+ 'uploader': None,
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
# Extract URL, uploader, and title from webpage
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
try:
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
# Extract uploader and title from webpage
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
# Extract media URL from playlist XML
'id': video_id.decode('utf-8'),
'url': video_url,
'uploader': video_uploader,
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
- 'thumbnail': video_thumbnail,
- 'player_url': None,
}]
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+ _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
IE_NAME = u'vimeo'
def __init__(self, downloader=None):
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
# Now we begin extracting as much information as we can from what we
else: video_description = ''
# Extract upload date
- video_upload_date = u'NA'
+ video_upload_date = None
mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage)
if mobj is not None:
video_upload_date = mobj.group(1)
timestamp = config['request']['timestamp']
# Vimeo specific: extract video codec and quality information
+ # First consider quality, then codecs, then take everything
# TODO bind to format param
codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
- for codec in codecs:
- if codec[0] in config["video"]["files"]:
- video_codec = codec[0]
- video_extension = codec[1]
- if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd'
- else: quality = 'sd'
+ files = { 'hd': [], 'sd': [], 'other': []}
+ for codec_name, codec_extension in codecs:
+ if codec_name in config["video"]["files"]:
+ if 'hd' in config["video"]["files"][codec_name]:
+ files['hd'].append((codec_name, codec_extension, 'hd'))
+ elif 'sd' in config["video"]["files"][codec_name]:
+ files['sd'].append((codec_name, codec_extension, 'sd'))
+ else:
+ files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
+
+ for quality in ('hd', 'sd', 'other'):
+ if len(files[quality]) > 0:
+ video_quality = files[quality][0][2]
+ video_codec = files[quality][0][0]
+ video_extension = files[quality][0][1]
+ self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
break
else:
self._downloader.trouble(u'ERROR: no known codec found')
return
video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
- %(video_id, sig, timestamp, quality, video_codec.upper())
+ %(video_id, sig, timestamp, video_quality, video_codec.upper())
return [{
'id': video_id,
'ext': video_extension,
'thumbnail': video_thumbnail,
'description': video_description,
- 'player_url': None,
}]
+class ArteTvIE(InfoExtractor):
+ """arte.tv information extractor."""
+
+ _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
+ _LIVE_URL = r'index-[0-9]+\.html$'
+
+ IE_NAME = u'arte.tv'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
+
+ def fetch_webpage(self, url):
+ self._downloader.increment_downloads()
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(url)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
+ return
+ except ValueError, err:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+ return webpage
+
+ def grep_webpage(self, url, regex, regexFlags, matchTuples):
+ page = self.fetch_webpage(url)
+ mobj = re.search(regex, page, regexFlags)
+ info = {}
+
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ for (i, key, err) in matchTuples:
+ if mobj.group(i) is None:
+ self._downloader.trouble(err)
+ return
+ else:
+ info[key] = mobj.group(i)
+
+ return info
+
+ def extractLiveStream(self, url):
+ video_lang = url.split('/')[-4]
+ info = self.grep_webpage(
+ url,
+ r'src="(.*?/videothek_js.*?\.js)',
+ 0,
+ [
+ (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ ]
+ )
+ http_host = url.split('/')[2]
+ next_url = 'http://%s%s' % (http_host, urllib.unquote(info.get('url')))
+ info = self.grep_webpage(
+ next_url,
+ r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
+ '(http://.*?\.swf).*?' +
+ '(rtmp://.*?)\'',
+ re.DOTALL,
+ [
+ (1, 'path', u'ERROR: could not extract video path: %s' % url),
+ (2, 'player', u'ERROR: could not extract video player: %s' % url),
+ (3, 'url', u'ERROR: could not extract video url: %s' % url)
+ ]
+ )
+ video_url = u'%s/%s' % (info.get('url'), info.get('path'))
+
+ def extractPlus7Stream(self, url):
+ video_lang = url.split('/')[-3]
+ info = self.grep_webpage(
+ url,
+ r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
+ 0,
+ [
+ (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ ]
+ )
+ next_url = urllib.unquote(info.get('url'))
+ info = self.grep_webpage(
+ next_url,
+ r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
+ 0,
+ [
+ (1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
+ ]
+ )
+ next_url = urllib.unquote(info.get('url'))
+
+ info = self.grep_webpage(
+ next_url,
+ r'<video id="(.*?)".*?>.*?' +
+ '<name>(.*?)</name>.*?' +
+ '<dateVideo>(.*?)</dateVideo>.*?' +
+ '<url quality="hd">(.*?)</url>',
+ re.DOTALL,
+ [
+ (1, 'id', u'ERROR: could not extract video id: %s' % url),
+ (2, 'title', u'ERROR: could not extract video title: %s' % url),
+ (3, 'date', u'ERROR: could not extract video date: %s' % url),
+ (4, 'url', u'ERROR: could not extract video url: %s' % url)
+ ]
+ )
+
+ return {
+ 'id': info.get('id'),
+ 'url': urllib.unquote(info.get('url')),
+ 'uploader': u'arte.tv',
+ 'upload_date': info.get('date'),
+ 'title': info.get('title'),
+ 'ext': u'mp4',
+ 'format': u'NA',
+ 'player_url': None,
+ }
+
+ def _real_extract(self, url):
+ video_id = url.split('/')[-1]
+ self.report_extraction(video_id)
+
+ if re.search(self._LIVE_URL, video_id) is not None:
+ self.extractLiveStream(url)
+ return
+ else:
+ info = self.extractPlus7Stream(url)
+
+ return [info]
+
+
class GenericIE(InfoExtractor):
"""Generic last-resort information extractor."""
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
except ValueError, err:
# since this is the last-resort InfoExtractor, if
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
- 'upload_date': u'NA',
+ 'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
return
else:
try:
- n = long(prefix)
+ n = int(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
try:
data = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download API page: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download API page: %s' % u(err))
return
api_response = json.loads(data)['data']
return
else:
try:
- n = long(prefix)
+ n = int(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return
# Extract video identifiers
return
else:
try:
- n = long(prefix)
+ n = int(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return
# Extract video identifiers
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _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_-]+))?.*'
+ _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|EC)?|PL|EC)([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_TEMPLATE = r'/watch\?v=(.+?)&list=(PL)?%s&'
+ _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s'
_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
IE_NAME = u'youtube:playlist'
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return
# Extract video identifiers
return
+class YoutubeChannelIE(InfoExtractor):
+ """Information Extractor for YouTube channels."""
+
+ _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
+ _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
+ _MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO
+ IE_NAME = u'youtube:channel'
+
+ def report_download_page(self, channel_id, pagenum):
+ """Report attempt to download channel page with given number."""
+ self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
+
+ def _real_extract(self, url):
+ # Extract channel id
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # Download channel pages
+ channel_id = mobj.group(1)
+ video_ids = []
+ pagenum = 1
+
+ while True:
+ self.report_download_page(channel_id, pagenum)
+ url = self._TEMPLATE_URL % (channel_id, pagenum)
+ request = urllib2.Request(url)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+ for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ break
+ pagenum = pagenum + 1
+
+ for id in video_ids:
+ self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
+ return
+
+
class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users."""
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return
# Extract video identifiers
mobj = re.search(r'data-users-id="([^"]+)"', page)
page_base = page_base % mobj.group(1)
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return
self.report_download_webpage(file_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % u(err))
return
# Search for the real file URL
return [{
'id': file_id.decode('utf-8'),
'url': file_url.decode('utf-8'),
- 'uploader': u'NA',
- 'upload_date': u'NA',
+ 'uploader': None,
+ 'upload_date': None,
'title': file_title,
'ext': file_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
}]
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
+ _WORKING = False
_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'
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+ self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % u(err))
return
if useremail is None:
self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
return
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+ self._downloader.to_stderr(u'WARNING: unable to log in: %s' % u(err))
return
def _real_extract(self, url):
page = urllib2.urlopen(request)
video_webpage = page.read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return
# Start extracting information
video_thumbnail = video_info['thumbnail']
# upload date
- upload_date = u'NA'
+ upload_date = None
if 'upload_date' in video_info:
upload_time = video_info['upload_date']
timetuple = email.utils.parsedate_tz(upload_time)
'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description.decode('utf-8'),
- 'player_url': None,
})
return results
info = {
'id': title,
'url': url,
+ 'uploader': None,
+ 'upload_date': None,
'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))
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % u(err))
return
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))
+ self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % u(err))
return
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
self.report_extraction(video_id)
return [{
'id': video_id,
'url': video_url,
- 'uploader': u'NA',
- 'upload_date': u'NA',
+ 'uploader': None,
+ 'upload_date': None,
'title': video_title,
'ext': u'flv',
- 'format': u'NA',
- 'player_url': None,
}]
class ComedyCentralIE(InfoExtractor):
_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'
+ _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
+
+ _video_extensions = {
+ '3500': 'mp4',
+ '2200': 'mp4',
+ '1700': 'mp4',
+ '1200': 'mp4',
+ '750': 'mp4',
+ '400': 'mp4',
+ }
+ _video_dimensions = {
+ '3500': '1280x720',
+ '2200': '960x540',
+ '1700': '768x432',
+ '1200': '640x360',
+ '750': '512x288',
+ '400': '384x216',
+ }
+
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 _print_formats(self, formats):
+ print('Available formats:')
+ for x in formats:
+ print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
+
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
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))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return
if dlNewest:
url = htmlHandle.geturl()
epTitle = mobj.group('episode')
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html)
+
if len(mMovieParams) == 0:
- self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
- return
+ # The Colbert Report embeds the information in a without
+ # a URL prefix; so extract the alternate reference
+ # and then add the URL prefix manually.
+ altMovieParams = re.findall('data-mgid="([^"]*episode.*?:.*?)"', html)
+ if len(altMovieParams) == 0:
+ self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+ return
+ else:
+ mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
+
playerUrl_raw = mMovieParams[0][0]
self.report_player_url(epTitle)
try:
urlHandle = urllib2.urlopen(playerUrl_raw)
playerUrl = urlHandle.geturl()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err))
+ self._downloader.trouble(u'ERROR: unable to find out player URL: ' + u(err))
return
uri = mMovieParams[0][1]
try:
indexXml = urllib2.urlopen(indexUrl).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download episode index: ' + u(err))
return
results = []
try:
configXml = urllib2.urlopen(configReq).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return
cdoc = xml.etree.ElementTree.fromstring(configXml)
if len(turls) == 0:
self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
continue
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats([i[0] for i in turls])
+ return
# For now, just pick the highest bitrate
format,video_url = turls[-1]
+ # Get the format arg from the arg stream
+ req_format = self._downloader.params.get('format', None)
+
+ # Select format if we can find one
+ for f,v in turls:
+ if f == req_format:
+ format, video_url = f, v
+ break
+
+ # Patch to download from alternative CDN, which does not
+ # break on current RTMPDump builds
+ broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/"
+ better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/"
+
+ if video_url.startswith(broken_cdn):
+ video_url = video_url.replace(broken_cdn, better_cdn)
+
effTitle = showId + u'-' + epTitle
info = {
'id': shortMediaId,
'format': format,
'thumbnail': None,
'description': officialTitle,
- 'player_url': playerUrl
+ 'player_url': None #playerUrl
}
results.append(info)
m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: ' + u(err))
return
descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
try:
configJSON = urllib2.urlopen(configUrl).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download configuration: ' + u(err))
return
# Technically, it's JavaScript, not JSON
try:
config = json.loads(configJSON)
except (ValueError,), err:
- self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err))
+ self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + u(err))
return
playlist = config['playlist']
'upload_date': None,
'title': showName,
'ext': 'flv',
- 'format': 'flv',
'thumbnail': imgUrl,
'description': description,
'player_url': playerUrl,
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))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return
m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
info = {
'id': video_id,
'internal_id': internal_video_id,
+ 'uploader': None,
+ 'upload_date': None,
}
self.report_extraction(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))
+ self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % u(err))
return
mdoc = xml.etree.ElementTree.fromstring(metaXml)
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
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))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return
self.report_extraction(video_id)
'upload_date': None,
'title': video_title,
'ext': 'flv',
- 'format': 'flv',
'thumbnail': video_thumbnail,
'description': None,
- 'player_url': None,
}
return [info]
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))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return
self.report_extraction('%s/%s' % (uploader, slug_title))
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)
try:
upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
except Exception, e:
- self._downloader.to_stderr(str(e))
+ self._downloader.to_stderr(u(e))
# for soundcloud, a request to a cross domain is required for cookies
request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
'upload_date': upload_date,
'title': title,
'ext': u'mp3',
- 'format': u'NA',
- 'player_url': None,
'description': description.decode('utf-8')
}]
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))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return
self.report_extraction(url)
'uploader': None,
'upload_date': None,
'title': video_title,
- 'ext': extension,
- 'format': extension, # Extension is always(?) mp4, but seems to be flv
+ 'ext': extension, # Extension is always(?) mp4, but seems to be flv
'thumbnail': None,
'description': video_description,
- 'player_url': None,
}
return [info]
return None
def _print_formats(self, formats):
- print 'Available 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])
+ 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])
+ print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
break
def _real_extract(self, url):
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))
+ self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % u(err))
return
# parse JSON
'id': file_id.decode('utf-8'),
'url': file_url.decode('utf-8'),
'uploader': uploader.decode('utf-8'),
- 'upload_date': u'NA',
+ 'upload_date': None,
'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')),
video = mobj.group('video')
info = {
'id': course + '_' + video,
+ 'uploader': None,
+ 'upload_date': None,
}
self.report_extraction(info['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' % unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % u(err))
return
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
return
info['ext'] = info['url'].rpartition('.')[2]
- info['format'] = info['ext']
return [info]
elif mobj.group('course'): # A course page
course = mobj.group('course')
info = {
'id': course,
'type': 'playlist',
+ 'uploader': None,
+ 'upload_date': None,
}
self.report_download_webpage(info['id'])
try:
coursepage = urllib2.urlopen(url).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download course info page: ' + u(err))
return
m = re.search('<h1>([^<]+)</h1>', coursepage)
info = {
'id': 'Stanford OpenClassroom',
'type': 'playlist',
+ 'uploader': None,
+ 'upload_date': None,
}
self.report_download_webpage(info['id'])
try:
rootpage = urllib2.urlopen(rootURL).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download course info page: ' + u(err))
return
info['title'] = info['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))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return
mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
try:
metadataXml = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % u(err))
return
mdoc = xml.etree.ElementTree.fromstring(metadataXml)
'id': video_id,
'url': video_url,
'uploader': performer,
+ 'upload_date': None,
'title': video_title,
'ext': ext,
'format': format,
return [info]
-
class YoukuIE(InfoExtractor):
_VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
#return ''.join(mixed)
return mixed
-
def _get_file_id(self, fileId, seed):
mixed = self._get_file_ID_mix_string(seed)
ids = fileId.split('*')
realId = []
for ch in ids:
- if ch is not '':
+ if ch:
realId.append(mixed[int(ch)])
return ''.join(realId)
- def _gen_key(self, key1, key2):
- pass
-
-
-
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self.report_download_webpage(video_id)
jsondata = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return
self.report_extraction(video_id)
temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
- print download_url
+
info = {
'id': '%s_part%02d' % (video_id, index),
'url': download_url,
'uploader': None,
+ 'upload_date': None,
'title': video_title,
'ext': ext,
- 'format': u'NA'
}
files_info.append(info)
return files_info
+
+
+class XNXXIE(InfoExtractor):
+ """Information extractor for xnxx.com"""
+
+ _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)'
+ IE_NAME = u'xnxx'
+ VIDEO_URL_RE = r'flv_url=(.*?)&'
+ VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
+ VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
+
+ 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):
+ 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)
+
+ # Get webpage content
+ try:
+ webpage = urllib2.urlopen(url).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
+ return
+
+ result = re.search(self.VIDEO_URL_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = urllib.unquote(result.group(1).decode('utf-8'))
+
+ result = re.search(self.VIDEO_TITLE_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = result.group(1).decode('utf-8')
+
+ result = re.search(self.VIDEO_THUMB_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = result.group(1).decode('utf-8')
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'thumbnail': video_thumbnail,
+ 'description': None,
+ }]
+
+
+class GooglePlusIE(InfoExtractor):
+ """Information extractor for plus.google.com."""
+
+ _VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)'
+ IE_NAME = u'plus.google'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_extract_entry(self, url):
+ """Report downloading extry"""
+ self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8'))
+
+ def report_date(self, upload_date):
+ """Report downloading extry"""
+ self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date)
+
+ def report_uploader(self, uploader):
+ """Report downloading extry"""
+ self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8'))
+
+ def report_title(self, video_title):
+ """Report downloading extry"""
+ self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8'))
+
+ def report_extract_vid_page(self, video_page):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8'))
+
+ def _real_extract(self, url):
+ # Extract id from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ post_url = mobj.group(0)
+ video_id = mobj.group(2)
+
+ video_extension = 'flv'
+
+ # Step 1, Retrieve post webpage to extract further information
+ self.report_extract_entry(post_url)
+ request = urllib2.Request(post_url)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % u(err))
+ return
+
+ # Extract update date
+ upload_date = None
+ pattern = 'title="Timestamp">(.*?)</a>'
+ mobj = re.search(pattern, webpage)
+ if mobj:
+ upload_date = mobj.group(1)
+ # Convert timestring to a format suitable for filename
+ upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
+ upload_date = upload_date.strftime('%Y%m%d')
+ self.report_date(upload_date)
+
+ # Extract uploader
+ uploader = None
+ pattern = r'rel\="author".*?>(.*?)</a>'
+ mobj = re.search(pattern, webpage)
+ if mobj:
+ uploader = mobj.group(1)
+ self.report_uploader(uploader)
+
+ # Extract title
+ # Get the first line for title
+ video_title = u'NA'
+ pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
+ mobj = re.search(pattern, webpage)
+ if mobj:
+ video_title = mobj.group(1)
+ self.report_title(video_title)
+
+ # Step 2, Stimulate clicking the image box to launch video
+ pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
+ mobj = re.search(pattern, webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video page URL')
+
+ video_page = mobj.group(1)
+ request = urllib2.Request(video_page)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
+ return
+ self.report_extract_vid_page(video_page)
+
+
+ # Extract video links on video page
+ """Extract video links of all sizes"""
+ pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
+ mobj = re.findall(pattern, webpage)
+ if len(mobj) == 0:
+ self._downloader.trouble(u'ERROR: unable to extract video links')
+
+ # Sort in resolution
+ links = sorted(mobj)
+
+ # Choose the lowest of the sort, i.e. highest resolution
+ video_url = links[-1]
+ # Only get the url. The resolution part in the tuple has no use anymore
+ video_url = video_url[-1]
+ # Treat escaped \u0026 style hex
+ video_url = unicode(video_url, "unicode_escape")
+
+
+ return [{
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url,
+ 'uploader': uploader.decode('utf-8'),
+ 'upload_date': upload_date.decode('utf-8'),
+ 'title': video_title.decode('utf-8'),
+ 'ext': video_extension.decode('utf-8'),
+ }]