-# parse_qs was moved from the cgi module to the urlparse module recently.
-try:
- from urlparse import parse_qs
-except ImportError:
- from cgi import parse_qs
-
-std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12',
- 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
- 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
- 'Accept-Language': 'en-us,en;q=0.5',
-}
-
-simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
-
-def preferredencoding():
- """Get preferred encoding.
-
- Returns the best encoding scheme for the system, based on
- locale.getpreferredencoding() and some further tweaks.
- """
- def yield_preferredencoding():
- try:
- pref = locale.getpreferredencoding()
- u'TEST'.encode(pref)
- except:
- pref = 'UTF-8'
- while True:
- yield pref
- return yield_preferredencoding().next()
-
-def htmlentity_transform(matchobj):
- """Transforms an HTML entity to a Unicode character.
-
- This function receives a match object and is intended to be used with
- the re.sub() function.
- """
- entity = matchobj.group(1)
-
- # Known non-numeric HTML entity
- if entity in htmlentitydefs.name2codepoint:
- return unichr(htmlentitydefs.name2codepoint[entity])
-
- # Unicode character
- mobj = re.match(ur'(?u)#(x?\d+)', entity)
- if mobj is not None:
- numstr = mobj.group(1)
- if numstr.startswith(u'x'):
- base = 16
- numstr = u'0%s' % numstr
- else:
- base = 10
- return unichr(long(numstr, base))
-
- # Unknown entity in name, return its literal representation
- return (u'&%s;' % entity)
-
-def sanitize_title(utitle):
- """Sanitizes a video title so it could be used as part of a filename."""
- utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
- return utitle.replace(unicode(os.sep), u'%')
-
-def sanitize_open(filename, open_mode):
- """Try to open the given filename, and slightly tweak it if this fails.
-
- Attempts to open the given filename. If this fails, it tries to change
- the filename slightly, step by step, until it's either able to open it
- or it fails and raises a final exception, like the standard open()
- function.
-
- It returns the tuple (stream, definitive_file_name).
- """
- try:
- if filename == u'-':
- if sys.platform == 'win32':
- import msvcrt
- msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
- return (sys.stdout, filename)
- stream = open(filename, open_mode)
- return (stream, filename)
- except (IOError, OSError), err:
- # In case of error, try to remove win32 forbidden chars
- filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
-
- # An exception here should be caught in the caller
- stream = open(filename, open_mode)
- return (stream, filename)
-
-class DownloadError(Exception):
- """Download Error exception.
-
- This exception may be thrown by FileDownloader objects if they are not
- configured to continue on errors. They will contain the appropriate
- error message.
- """
- pass
-
-class SameFileError(Exception):
- """Same File exception.
-
- This exception will be thrown by FileDownloader objects if they detect
- multiple files would have to be downloaded to the same file on disk.
- """
- pass
-
-class PostProcessingError(Exception):
- """Post Processing exception.
-
- This exception may be raised by PostProcessor's .run() method to
- indicate an error in the postprocessing task.
- """
- pass
-
-class UnavailableVideoError(Exception):
- """Unavailable Format exception.
-
- This exception will be thrown when a video is requested
- in a format that is not available for that video.
- """
- pass
-
-class ContentTooShortError(Exception):
- """Content Too Short exception.
-
- This exception may be raised by FileDownloader objects when a file they
- download is too small for what the server announced first, indicating
- the connection was probably interrupted.
- """
- # Both in bytes
- downloaded = None
- expected = None
-
- def __init__(self, downloaded, expected):
- self.downloaded = downloaded
- self.expected = expected
-
-class FileDownloader(object):
- """File Downloader class.
-
- File downloader objects are the ones responsible of downloading the
- actual video file and writing it to disk if the user has requested
- it, among some other tasks. In most cases there should be one per
- program. As, given a video URL, the downloader doesn't know how to
- extract all the needed information, task that InfoExtractors do, it
- has to pass the URL to one of them.
-
- For this, file downloader objects have a method that allows
- InfoExtractors to be registered in a given order. When it is passed
- a URL, the file downloader handles it to the first InfoExtractor it
- finds that reports being able to handle it. The InfoExtractor extracts
- all the information about the video or videos the URL refers to, and
- asks the FileDownloader to process the video information, possibly
- downloading the video.
-
- File downloaders accept a lot of parameters. In order not to saturate
- the object constructor with arguments, it receives a dictionary of
- options instead. These options are available through the params
- attribute for the InfoExtractors to use. The FileDownloader also
- registers itself as the downloader in charge for the InfoExtractors
- that are added to it, so this is a "mutual registration".
-
- Available options:
-
- username: Username for authentication purposes.
- password: Password for authentication purposes.
- usenetrc: Use netrc for authentication instead.
- quiet: Do not print messages to stdout.
- forceurl: Force printing final URL.
- forcetitle: Force printing title.
- forcethumbnail: Force printing thumbnail URL.
- forcedescription: Force printing description.
- simulate: Do not download the video files.
- format: Video format code.
- format_limit: Highest quality format to try.
- outtmpl: Template for output names.
- ignoreerrors: Do not stop on download errors.
- ratelimit: Download speed limit, in bytes/sec.
- nooverwrites: Prevent overwriting files.
- retries: Number of times to retry for HTTP error 5xx
- continuedl: Try to continue downloads if possible.
- noprogress: Do not print the progress bar.
- playliststart: Playlist item to start at.
- playlistend: Playlist item to end at.
- logtostderr: Log messages to stderr instead of stdout.
- """
-
- params = None
- _ies = []
- _pps = []
- _download_retcode = None
- _num_downloads = None
- _screen_file = None
-
- def __init__(self, params):
- """Create a FileDownloader object with the given options."""
- self._ies = []
- self._pps = []
- self._download_retcode = 0
- self._num_downloads = 0
- self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
- self.params = params
-
- @staticmethod
- def pmkdir(filename):
- """Create directory components in filename. Similar to Unix "mkdir -p"."""
- components = filename.split(os.sep)
- aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
- aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
- for dir in aggregate:
- if not os.path.exists(dir):
- os.mkdir(dir)
-
- @staticmethod
- def temp_name(filename):
- """Returns a temporary filename for the given filename."""
- if filename == u'-' or (os.path.exists(filename) and not os.path.isfile(filename)):
- return filename
- return filename + u'.part'
-
- @staticmethod
- def format_bytes(bytes):
- if bytes is None:
- return 'N/A'
- if type(bytes) is str:
- bytes = float(bytes)
- if bytes == 0.0:
- exponent = 0
- else:
- exponent = long(math.log(bytes, 1024.0))
- suffix = 'bkMGTPEZY'[exponent]
- converted = float(bytes) / float(1024**exponent)
- return '%.2f%s' % (converted, suffix)
-
- @staticmethod
- def calc_percent(byte_counter, data_len):
- if data_len is None:
- return '---.-%'
- return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
-
- @staticmethod
- def calc_eta(start, now, total, current):
- if total is None:
- return '--:--'
- dif = now - start
- if current == 0 or dif < 0.001: # One millisecond
- return '--:--'
- rate = float(current) / dif
- eta = long((float(total) - float(current)) / rate)
- (eta_mins, eta_secs) = divmod(eta, 60)
- if eta_mins > 99:
- return '--:--'
- return '%02d:%02d' % (eta_mins, eta_secs)
-
- @staticmethod
- def calc_speed(start, now, bytes):
- dif = now - start
- if bytes == 0 or dif < 0.001: # One millisecond
- return '%10s' % '---b/s'
- return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
-
- @staticmethod
- def best_block_size(elapsed_time, bytes):
- new_min = max(bytes / 2.0, 1.0)
- new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
- if elapsed_time < 0.001:
- return long(new_max)
- rate = bytes / elapsed_time
- if rate > new_max:
- return long(new_max)
- if rate < new_min:
- return long(new_min)
- return long(rate)
-
- @staticmethod
- def parse_bytes(bytestr):
- """Parse a string indicating a byte quantity into a long integer."""
- matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
- if matchobj is None:
- return None
- number = float(matchobj.group(1))
- multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
- return long(round(number * multiplier))
-
- def add_info_extractor(self, ie):
- """Add an InfoExtractor object to the end of the list."""
- self._ies.append(ie)
- ie.set_downloader(self)
-
- def add_post_processor(self, pp):
- """Add a PostProcessor object to the end of the chain."""
- self._pps.append(pp)
- pp.set_downloader(self)
-
- def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
- """Print message to stdout if not in quiet mode."""
- try:
- if not self.params.get('quiet', False):
- terminator = [u'\n', u''][skip_eol]
- print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
- self._screen_file.flush()
- except (UnicodeEncodeError), err:
- if not ignore_encoding_errors:
- raise
-
- def to_stderr(self, message):
- """Print message to stderr."""
- print >>sys.stderr, message.encode(preferredencoding())
-
- def fixed_template(self):
- """Checks if the output template is fixed."""
- return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
-
- def trouble(self, message=None):
- """Determine action to take when a download problem appears.
-
- Depending on if the downloader has been configured to ignore
- download errors or not, this method may throw an exception or
- not when errors are found, after printing the message.
- """
- if message is not None:
- self.to_stderr(message)
- if not self.params.get('ignoreerrors', False):
- raise DownloadError(message)
- self._download_retcode = 1
-
- def slow_down(self, start_time, byte_counter):
- """Sleep if the download speed is over the rate limit."""
- rate_limit = self.params.get('ratelimit', None)
- if rate_limit is None or byte_counter == 0:
- return
- now = time.time()
- elapsed = now - start_time
- if elapsed <= 0.0:
- return
- speed = float(byte_counter) / elapsed
- if speed > rate_limit:
- time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
-
- def try_rename(self, old_filename, new_filename):
- try:
- if old_filename == new_filename:
- return
- os.rename(old_filename, new_filename)
- except (IOError, OSError), err:
- self.trouble(u'ERROR: unable to rename file')
-
- def report_destination(self, filename):
- """Report destination filename."""
- self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
-
- def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
- """Report download progress."""
- if self.params.get('noprogress', False):
- return
- self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
- (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
-
- def report_resuming_byte(self, resume_len):
- """Report attempt to resume at given byte."""
- self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
-
- def report_retry(self, count, retries):
- """Report retry in case of HTTP error 5xx"""
- self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
-
- def report_file_already_downloaded(self, file_name):
- """Report file has already been fully downloaded."""
- try:
- self.to_screen(u'[download] %s has already been downloaded' % file_name)
- except (UnicodeEncodeError), err:
- self.to_screen(u'[download] The file has already been downloaded')
-
- def report_unable_to_resume(self):
- """Report it was impossible to resume download."""
- self.to_screen(u'[download] Unable to resume')
-
- def report_finish(self):
- """Report download finished."""
- if self.params.get('noprogress', False):
- self.to_screen(u'[download] Download completed')
- else:
- self.to_screen(u'')
-
- def increment_downloads(self):
- """Increment the ordinal that assigns a number to each file."""
- self._num_downloads += 1
-
- def process_info(self, info_dict):
- """Process a single dictionary returned by an InfoExtractor."""
- # 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')
-
- return
-
- try:
- template_dict = dict(info_dict)
- template_dict['epoch'] = unicode(long(time.time()))
- template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
- filename = self.params['outtmpl'] % template_dict
- except (ValueError, KeyError), err:
- self.trouble(u'ERROR: invalid system charset or erroneous output template')
- return
- if self.params.get('nooverwrites', False) and os.path.exists(filename):
- self.to_stderr(u'WARNING: file exists and will be skipped')
- return
-
- try:
- self.pmkdir(filename)
- except (OSError, IOError), err:
- self.trouble(u'ERROR: unable to create directories: %s' % str(err))
- 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:
- 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."""
- if len(url_list) > 1 and self.fixed_template():
- raise SameFileError(self.params['outtmpl'])
-
- for url in url_list:
- suitable_found = False
- for ie in self._ies:
- # Go to next InfoExtractor if not suitable
- if not ie.suitable(url):
- continue
-
- # Suitable InfoExtractor found
- suitable_found = True
-
- # Extract information from URL and process it
- ie.extract(url)
-
- # Suitable InfoExtractor had been found; go to next URL
- break
-
- if not suitable_found:
- self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
-
- return self._download_retcode
-
- def post_process(self, filename, ie_info):
- """Run the postprocessing chain on the given file."""
- info = dict(ie_info)
- info['filepath'] = filename
- for pp in self._pps:
- info = pp.run(info)
- if info is None:
- break
-
- def _download_with_rtmpdump(self, filename, url, player_url):
- self.report_destination(filename)
- tmpfilename = self.temp_name(filename)
-
- # Check for rtmpdump first
- try:
- subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
- except (OSError, IOError):
- self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
- return False
-
- # 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', '-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)
- self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
- time.sleep(5.0) # This seems to be needed
- retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
- cursize = os.path.getsize(tmpfilename)
- if prevsize == cursize and retval == 1:
- break
- if retval == 0:
- self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
- self.try_rename(tmpfilename, filename)
- return True
- else:
- self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
- return False
-
- def _do_download(self, filename, url, player_url):
- # Check file already present
- if self.params.get('continuedl', False) and os.path.isfile(filename):
- self.report_file_already_downloaded(filename)
- return True
-
- # Attempt to download using rtmpdump
- if url.startswith('rtmp'):
- return self._download_with_rtmpdump(filename, url, player_url)
-
- tmpfilename = self.temp_name(filename)
- stream = None
- open_mode = 'wb'
- basic_request = urllib2.Request(url, None, std_headers)
- request = urllib2.Request(url, None, std_headers)
-
- # Establish possible resume length
- if os.path.isfile(tmpfilename):
- resume_len = os.path.getsize(tmpfilename)
- 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'
-
- count = 0
- retries = self.params.get('retries', 0)
- while count <= retries:
- # Establish connection
- try:
- data = urllib2.urlopen(request)
- break
- except (urllib2.HTTPError, ), err:
- if (err.code < 500 or err.code >= 600) and err.code != 416:
- # Unexpected HTTP error
- raise
- elif err.code == 416:
- # Unable to resume (requested range not satisfiable)
- try:
- # Open the connection again without the range header
- data = urllib2.urlopen(basic_request)
- content_length = data.info()['Content-Length']
- except (urllib2.HTTPError, ), err:
- if err.code < 500 or err.code >= 600:
- raise
- else:
- # Examine the reported length
- if (content_length is not None and
- (resume_len - 100 < long(content_length) < resume_len + 100)):
- # The file had already been fully downloaded.
- # Explanation to the above condition: in issue #175 it was revealed that
- # YouTube sometimes adds or removes a few bytes from the end of the file,
- # changing the file size slightly and causing problems for some users. So
- # I decided to implement a suggested change and consider the file
- # completely downloaded if the file size differs less than 100 bytes from
- # the one in the hard drive.
- self.report_file_already_downloaded(filename)
- self.try_rename(tmpfilename, filename)
- return True
- else:
- # The length does not match, we start the download over
- self.report_unable_to_resume()
- open_mode = 'wb'
- break
- # Retry
- count += 1
- if count <= retries:
- self.report_retry(count, retries)
-
- if count > retries:
- self.trouble(u'ERROR: giving up after %s retries' % retries)
- return False
-
- data_len = data.info().get('Content-length', None)
- data_len_str = self.format_bytes(data_len)
- byte_counter = 0
- block_size = 1024
- start = time.time()
- while True:
- # Download and write
- before = time.time()
- data_block = data.read(block_size)
- after = time.time()
- data_block_len = len(data_block)
- if data_block_len == 0:
- break
- byte_counter += data_block_len
-
- # Open file just in time
- if stream is None:
- try:
- (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
- self.report_destination(filename)
- except (OSError, IOError), err:
- self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
- return False
- try:
- stream.write(data_block)
- except (IOError, OSError), err:
- self.trouble(u'\nERROR: unable to write data: %s' % str(err))
- return False
- block_size = self.best_block_size(after - before, data_block_len)
-
- # Progress message
- percent_str = self.calc_percent(byte_counter, data_len)
- eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
- speed_str = self.calc_speed(start, time.time(), byte_counter)
- self.report_progress(percent_str, data_len_str, speed_str, eta_str)
-
- # Apply rate limit
- self.slow_down(start, byte_counter)
-
- stream.close()
- self.report_finish()
- if data_len is not None and str(byte_counter) != data_len:
- raise ContentTooShortError(byte_counter, long(data_len))
- self.try_rename(tmpfilename, filename)
- return True
-
-class InfoExtractor(object):
- """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.
- stitle: Simplified 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.
-
- 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.
- """
-
- _ready = False
- _downloader = None
-
- def __init__(self, downloader=None):
- """Constructor. Receives an optional downloader."""
- self._ready = False
- self.set_downloader(downloader)
-
- @staticmethod
- def suitable(url):
- """Receives a URL and returns True if suitable for this IE."""
- return False
-
- def initialize(self):
- """Initializes an instance (authentication, etc)."""
- if not self._ready:
- self._real_initialize()
- self._ready = True
-
- def extract(self, url):
- """Extracts URL information and returns it in list of dicts."""
- self.initialize()
- return self._real_extract(url)
-
- def set_downloader(self, downloader):
- """Sets the downloader for this IE."""
- self._downloader = downloader
-
- def _real_initialize(self):
- """Real initialization process. Redefine in subclasses."""
- pass
-
- def _real_extract(self, url):
- """Real extraction process. Redefine in subclasses."""
- pass
-
-class YoutubeIE(InfoExtractor):
- """Information extractor for youtube.com."""
-
- _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
- _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
- _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
- _NETRC_MACHINE = 'youtube'
- # Listed in order of quality
- _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
- _video_extensions = {
- '13': '3gp',
- '17': 'mp4',
- '18': 'mp4',
- '22': 'mp4',
- '37': 'mp4',
- '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
- '43': 'webm',
- '45': 'webm',
- }
-
- @staticmethod
- def suitable(url):
- return (re.match(YoutubeIE._VALID_URL, url) is not None)
-
- def report_lang(self):
- """Report attempt to set language."""
- self._downloader.to_screen(u'[youtube] Setting language')
-
- def report_login(self):
- """Report attempt to log in."""
- self._downloader.to_screen(u'[youtube] Logging in')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[youtube] Confirming age')
-
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
-
- def report_video_info_webpage_download(self, video_id):
- """Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
-
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
-
- def report_unavailable_format(self, video_id, format):
- """Report extracted video URL."""
- self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
-
- def report_rtmp_download(self):
- """Indicate the download will use the RTMP protocol."""
- self._downloader.to_screen(u'[youtube] RTMP download detected')
-
- def _real_initialize(self):
- if self._downloader is None:
- return
-
- username = None
- password = None
- downloader_params = self._downloader.params
-
- # Attempt to use provided username and password or .netrc data
- if downloader_params.get('username', None) is not None:
- username = downloader_params['username']
- password = downloader_params['password']
- elif downloader_params.get('usenetrc', False):
- try:
- info = netrc.netrc().authenticators(self._NETRC_MACHINE)
- if info is not None:
- username = info[0]
- password = info[2]
- 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))
- return
-
- # Set language
- request = urllib2.Request(self._LANG_URL, None, std_headers)
- try:
- 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))
- return
-
- # No authentication to be performed
- if username is None:
- return
-
- # Log in
- login_form = {
- 'current_form': 'loginForm',
- 'next': '/',
- 'action_login': 'Log In',
- 'username': username,
- 'password': password,
- }
- request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
- try:
- self.report_login()
- login_results = urllib2.urlopen(request).read()
- if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
- 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))
- return
-
- # Confirm age
- age_form = {
- 'next_url': '/',
- 'action_confirm': 'Confirm',
- }
- request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
- try:
- 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))
- return
-
- def _real_extract(self, url):
- # Extract video id from 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(2)
-
- # 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, None, std_headers)
- 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))
- return
-
- # Attempt to extract SWF player URL
- mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
- if mobj is not None:
- player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
- else:
- player_url = None
-
- # Get video info
- self.report_video_info_webpage_download(video_id)
- for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
- request = urllib2.Request(video_info_url, None, std_headers)
- try:
- video_info_webpage = urllib2.urlopen(request).read()
- video_info = parse_qs(video_info_webpage)
- 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))
- return
- if 'token' not in video_info:
- if 'reason' in video_info:
- self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
- else:
- self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
- return
-
- # Start extracting information
- self.report_information_extraction(video_id)
-
- # uploader
- if 'author' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = urllib.unquote_plus(video_info['author'][0])
-
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = urllib.unquote_plus(video_info['title'][0])
- 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'_')
-
- # thumbnail image
- if 'thumbnail_url' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
- video_thumbnail = ''
- else: # don't panic if we can't find it
- video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
-
- # upload date
- upload_date = u'NA'
- 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())
- format_expressions = ['%d %B %Y', '%B %d %Y']
- for expression in format_expressions:
- try:
- upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
- except:
- pass
-
- # description
- video_description = 'No description available.'
- if self._downloader.params.get('forcedescription', False):
- mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
- if mobj is not None:
- video_description = mobj.group(1)
-
- # token
- video_token = urllib.unquote_plus(video_info['token'][0])
-
- # Decide which formats to download
- req_format = self._downloader.params.get('format', None)
- get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token)
-
- if 'fmt_url_map' in video_info:
- url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
- 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):]
- else:
- format_list = self._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:
- video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
- elif req_format == '-1':
- video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
- else:
- if req_format in url_map:
- video_url_list = [(req_format, url_map[req_format])] # Specific format
- else:
- video_url_list = [(req_format, get_video_template % req_format)] # Specific format
-
- elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
- self.report_rtmp_download()
- video_url_list = [(None, video_info['conn'][0])]
-
- else:
- self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
- return
-
- for format_param, video_real_url in video_url_list:
- # At this point we have a new video
- self._downloader.increment_downloads()
-
- # Extension
- video_extension = self._video_extensions.get(format_param, 'flv')
-
- # Find the video URL in fmt_url_map or conn paramters
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_real_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': upload_date,
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- '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': player_url,
- })
- except UnavailableVideoError, err:
- self._downloader.trouble(u'ERROR: unable to download video (format may not be available)')
-
-
-class MetacafeIE(InfoExtractor):
- """Information Extractor for metacafe.com."""
-
- _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
- _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
- _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
- _youtube_ie = None
-
- 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')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[metacafe] Confirming age')
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- # Retrieve disclaimer
- request = urllib2.Request(self._DISCLAIMER, None, std_headers)
- try:
- 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))
- return
-
- # Confirm age
- disclaimer_form = {
- 'filters': '0',
- 'submit': "Continue - I'm over 18",
- }
- request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
- try:
- 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))
- return
-
- def _real_extract(self, url):
- # Extract id and simplified title from 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)
-
- # Check if video comes from YouTube
- mobj2 = re.match(r'^yt-(.*)$', video_id)
- if mobj2 is not None:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
- return
-
- # At this point we have a new video
- self._downloader.increment_downloads()
-
- simple_title = mobj.group(2).decode('utf-8')
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
- return
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
- if mobj is not None:
- mediaURL = urllib.unquote(mobj.group(1))
- video_extension = mediaURL[-3:]
-
- # Extract gdaKey if available
- mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
- if mobj is None:
- video_url = mediaURL
- else:
- gdaKey = mobj.group(1)
- video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
- else:
- mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- vardict = parse_qs(mobj.group(1))
- if 'mediaData' not in vardict:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = mobj.group(1).replace('\\/', '/')
- video_extension = mediaURL[-3:]
- video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
-
- mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
- video_title = sanitize_title(video_title)
-
- mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
-
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- })
- except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
-
-
-class DailymotionIE(InfoExtractor):
- """Information Extractor for Dailymotion"""
-
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
-
- 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)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- return
-
- def _real_extract(self, url):
- # Extract id and simplified title from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- # At this point we have a new video
- self._downloader.increment_downloads()
- video_id = mobj.group(1)
-
- simple_title = mobj.group(2).decode('utf-8')
- video_extension = 'flv'
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request(url)
- 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 retrieve video webpage: %s' % str(err))
- return
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = urllib.unquote(mobj.group(1))
-
- # if needed add http://www.dailymotion.com/ if relative URL
-
- video_url = mediaURL
-
- # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
- mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
- video_title = sanitize_title(video_title)
-
- mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
-
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- })
- except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
-
-class GoogleIE(InfoExtractor):
- """Information extractor for video.google.com."""
-
- _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
-
- 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)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- return
-
- def _real_extract(self, url):
- # Extract id from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- # At this point we have a new video
- self._downloader.increment_downloads()
- video_id = mobj.group(1)
-
- video_extension = 'mp4'
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- # Extract URL, uploader, and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r"download_url:'([^']+)'", webpage)
- if mobj is None:
- video_extension = 'flv'
- mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = urllib.unquote(mobj.group(1))
- mediaURL = mediaURL.replace('\\x3d', '\x3d')
- mediaURL = mediaURL.replace('\\x26', '\x26')
Rapsys Git / youtubedl / blobdiff