2 # -*- coding: utf-8 -*-
5 'Ricardo Garcia Gonzalez',
13 'Philipp Hagemeister',
17 __license__ = 'Public Domain'
18 __version__ = '2011.09.13'
20 UPDATE_URL = 'https://raw.github.com/phihag/youtube-dl/master/youtube-dl'
48 except ImportError: # Python 2.4
51 import cStringIO as StringIO
55 # parse_qs was moved from the cgi module to the urlparse module recently.
57 from urlparse import parse_qs
59 from cgi import parse_qs
67 import xml.etree.ElementTree
68 except ImportError: # Python<2.5
69 pass # Not officially supported, but let it slip
72 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
73 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
74 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
75 'Accept-Encoding': 'gzip, deflate',
76 'Accept-Language': 'en-us,en;q=0.5',
79 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
83 except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
89 def raiseError(msg, i):
90 raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]))
91 def skipSpace(i, expectMore=True):
92 while i < len(s) and s[i] in ' \t\r\n':
96 raiseError('Premature end', i)
98 def decodeEscape(match):
114 return unichr(int(esc[1:5], 16))
115 if len(esc) == 5+6 and esc[5:7] == '\\u':
116 hi = int(esc[1:5], 16)
117 low = int(esc[7:11], 16)
118 return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000)
119 raise ValueError('Unknown escape ' + str(esc))
126 while s[e-bslashes-1] == '\\':
128 if bslashes % 2 == 1:
132 rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)')
133 stri = rexp.sub(decodeEscape, s[i:e])
139 if s[i] == '}': # Empty dictionary
143 raiseError('Expected a string object key', i)
144 i,key = parseString(i)
146 if i >= len(s) or s[i] != ':':
147 raiseError('Expected a colon', i)
154 raiseError('Expected comma or closing curly brace', i)
159 if s[i] == ']': # Empty array
164 i = skipSpace(i) # Raise exception if premature end
168 raiseError('Expected a comma or closing bracket', i)
170 def parseDiscrete(i):
171 for k,v in {'true': True, 'false': False, 'null': None}.items():
172 if s.startswith(k, i):
174 raiseError('Not a boolean (or null)', i)
176 mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:])
178 raiseError('Not a number', i)
180 if '.' in nums or 'e' in nums or 'E' in nums:
181 return (i+len(nums), float(nums))
182 return (i+len(nums), int(nums))
183 CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete}
186 i,res = CHARMAP.get(s[i], parseNumber)(i)
187 i = skipSpace(i, False)
191 raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')')
194 def preferredencoding():
195 """Get preferred encoding.
197 Returns the best encoding scheme for the system, based on
198 locale.getpreferredencoding() and some further tweaks.
200 def yield_preferredencoding():
202 pref = locale.getpreferredencoding()
208 return yield_preferredencoding().next()
211 def htmlentity_transform(matchobj):
212 """Transforms an HTML entity to a Unicode character.
214 This function receives a match object and is intended to be used with
215 the re.sub() function.
217 entity = matchobj.group(1)
219 # Known non-numeric HTML entity
220 if entity in htmlentitydefs.name2codepoint:
221 return unichr(htmlentitydefs.name2codepoint[entity])
224 mobj = re.match(ur'(?u)#(x?\d+)', entity)
226 numstr = mobj.group(1)
227 if numstr.startswith(u'x'):
229 numstr = u'0%s' % numstr
232 return unichr(long(numstr, base))
234 # Unknown entity in name, return its literal representation
235 return (u'&%s;' % entity)
238 def sanitize_title(utitle):
239 """Sanitizes a video title so it could be used as part of a filename."""
240 utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
241 return utitle.replace(unicode(os.sep), u'%')
244 def sanitize_open(filename, open_mode):
245 """Try to open the given filename, and slightly tweak it if this fails.
247 Attempts to open the given filename. If this fails, it tries to change
248 the filename slightly, step by step, until it's either able to open it
249 or it fails and raises a final exception, like the standard open()
252 It returns the tuple (stream, definitive_file_name).
256 if sys.platform == 'win32':
258 msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
259 return (sys.stdout, filename)
260 stream = open(filename, open_mode)
261 return (stream, filename)
262 except (IOError, OSError), err:
263 # In case of error, try to remove win32 forbidden chars
264 filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
266 # An exception here should be caught in the caller
267 stream = open(filename, open_mode)
268 return (stream, filename)
271 def timeconvert(timestr):
272 """Convert RFC 2822 defined time string into system timestamp"""
274 timetuple = email.utils.parsedate_tz(timestr)
275 if timetuple is not None:
276 timestamp = email.utils.mktime_tz(timetuple)
280 class DownloadError(Exception):
281 """Download Error exception.
283 This exception may be thrown by FileDownloader objects if they are not
284 configured to continue on errors. They will contain the appropriate
290 class SameFileError(Exception):
291 """Same File exception.
293 This exception will be thrown by FileDownloader objects if they detect
294 multiple files would have to be downloaded to the same file on disk.
299 class PostProcessingError(Exception):
300 """Post Processing exception.
302 This exception may be raised by PostProcessor's .run() method to
303 indicate an error in the postprocessing task.
308 class UnavailableVideoError(Exception):
309 """Unavailable Format exception.
311 This exception will be thrown when a video is requested
312 in a format that is not available for that video.
317 class ContentTooShortError(Exception):
318 """Content Too Short exception.
320 This exception may be raised by FileDownloader objects when a file they
321 download is too small for what the server announced first, indicating
322 the connection was probably interrupted.
328 def __init__(self, downloaded, expected):
329 self.downloaded = downloaded
330 self.expected = expected
333 class YoutubeDLHandler(urllib2.HTTPHandler):
334 """Handler for HTTP requests and responses.
336 This class, when installed with an OpenerDirector, automatically adds
337 the standard headers to every HTTP request and handles gzipped and
338 deflated responses from web servers. If compression is to be avoided in
339 a particular request, the original request in the program code only has
340 to include the HTTP header "Youtubedl-No-Compression", which will be
341 removed before making the real request.
343 Part of this code was copied from:
345 http://techknack.net/python-urllib2-handlers/
347 Andrew Rowls, the author of that code, agreed to release it to the
354 return zlib.decompress(data, -zlib.MAX_WBITS)
356 return zlib.decompress(data)
359 def addinfourl_wrapper(stream, headers, url, code):
360 if hasattr(urllib2.addinfourl, 'getcode'):
361 return urllib2.addinfourl(stream, headers, url, code)
362 ret = urllib2.addinfourl(stream, headers, url)
366 def http_request(self, req):
367 for h in std_headers:
370 req.add_header(h, std_headers[h])
371 if 'Youtubedl-no-compression' in req.headers:
372 if 'Accept-encoding' in req.headers:
373 del req.headers['Accept-encoding']
374 del req.headers['Youtubedl-no-compression']
377 def http_response(self, req, resp):
380 if resp.headers.get('Content-encoding', '') == 'gzip':
381 gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
382 resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
383 resp.msg = old_resp.msg
385 if resp.headers.get('Content-encoding', '') == 'deflate':
386 gz = StringIO.StringIO(self.deflate(resp.read()))
387 resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
388 resp.msg = old_resp.msg
392 class FileDownloader(object):
393 """File Downloader class.
395 File downloader objects are the ones responsible of downloading the
396 actual video file and writing it to disk if the user has requested
397 it, among some other tasks. In most cases there should be one per
398 program. As, given a video URL, the downloader doesn't know how to
399 extract all the needed information, task that InfoExtractors do, it
400 has to pass the URL to one of them.
402 For this, file downloader objects have a method that allows
403 InfoExtractors to be registered in a given order. When it is passed
404 a URL, the file downloader handles it to the first InfoExtractor it
405 finds that reports being able to handle it. The InfoExtractor extracts
406 all the information about the video or videos the URL refers to, and
407 asks the FileDownloader to process the video information, possibly
408 downloading the video.
410 File downloaders accept a lot of parameters. In order not to saturate
411 the object constructor with arguments, it receives a dictionary of
412 options instead. These options are available through the params
413 attribute for the InfoExtractors to use. The FileDownloader also
414 registers itself as the downloader in charge for the InfoExtractors
415 that are added to it, so this is a "mutual registration".
419 username: Username for authentication purposes.
420 password: Password for authentication purposes.
421 usenetrc: Use netrc for authentication instead.
422 quiet: Do not print messages to stdout.
423 forceurl: Force printing final URL.
424 forcetitle: Force printing title.
425 forcethumbnail: Force printing thumbnail URL.
426 forcedescription: Force printing description.
427 forcefilename: Force printing final filename.
428 simulate: Do not download the video files.
429 format: Video format code.
430 format_limit: Highest quality format to try.
431 outtmpl: Template for output names.
432 ignoreerrors: Do not stop on download errors.
433 ratelimit: Download speed limit, in bytes/sec.
434 nooverwrites: Prevent overwriting files.
435 retries: Number of times to retry for HTTP error 5xx
436 continuedl: Try to continue downloads if possible.
437 noprogress: Do not print the progress bar.
438 playliststart: Playlist item to start at.
439 playlistend: Playlist item to end at.
440 logtostderr: Log messages to stderr instead of stdout.
441 consoletitle: Display progress in console window's titlebar.
442 nopart: Do not use temporary .part files.
443 updatetime: Use the Last-modified header to set output file timestamps.
444 writedescription: Write the video description to a .description file
445 writeinfojson: Write the video description to a .info.json file
451 _download_retcode = None
452 _num_downloads = None
455 def __init__(self, params):
456 """Create a FileDownloader object with the given options."""
459 self._download_retcode = 0
460 self._num_downloads = 0
461 self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
465 def format_bytes(bytes):
468 if type(bytes) is str:
473 exponent = long(math.log(bytes, 1024.0))
474 suffix = 'bkMGTPEZY'[exponent]
475 converted = float(bytes) / float(1024 ** exponent)
476 return '%.2f%s' % (converted, suffix)
479 def calc_percent(byte_counter, data_len):
482 return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
485 def calc_eta(start, now, total, current):
489 if current == 0 or dif < 0.001: # One millisecond
491 rate = float(current) / dif
492 eta = long((float(total) - float(current)) / rate)
493 (eta_mins, eta_secs) = divmod(eta, 60)
496 return '%02d:%02d' % (eta_mins, eta_secs)
499 def calc_speed(start, now, bytes):
501 if bytes == 0 or dif < 0.001: # One millisecond
502 return '%10s' % '---b/s'
503 return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
506 def best_block_size(elapsed_time, bytes):
507 new_min = max(bytes / 2.0, 1.0)
508 new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
509 if elapsed_time < 0.001:
511 rate = bytes / elapsed_time
519 def parse_bytes(bytestr):
520 """Parse a string indicating a byte quantity into a long integer."""
521 matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
524 number = float(matchobj.group(1))
525 multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
526 return long(round(number * multiplier))
528 def add_info_extractor(self, ie):
529 """Add an InfoExtractor object to the end of the list."""
531 ie.set_downloader(self)
533 def add_post_processor(self, pp):
534 """Add a PostProcessor object to the end of the chain."""
536 pp.set_downloader(self)
538 def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
539 """Print message to stdout if not in quiet mode."""
541 if not self.params.get('quiet', False):
542 terminator = [u'\n', u''][skip_eol]
543 print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
544 self._screen_file.flush()
545 except (UnicodeEncodeError), err:
546 if not ignore_encoding_errors:
549 def to_stderr(self, message):
550 """Print message to stderr."""
551 print >>sys.stderr, message.encode(preferredencoding())
553 def to_cons_title(self, message):
554 """Set console/terminal window title to message."""
555 if not self.params.get('consoletitle', False):
557 if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
558 # c_wchar_p() might not be necessary if `message` is
559 # already of type unicode()
560 ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
561 elif 'TERM' in os.environ:
562 sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
564 def fixed_template(self):
565 """Checks if the output template is fixed."""
566 return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
568 def trouble(self, message=None):
569 """Determine action to take when a download problem appears.
571 Depending on if the downloader has been configured to ignore
572 download errors or not, this method may throw an exception or
573 not when errors are found, after printing the message.
575 if message is not None:
576 self.to_stderr(message)
577 if not self.params.get('ignoreerrors', False):
578 raise DownloadError(message)
579 self._download_retcode = 1
581 def slow_down(self, start_time, byte_counter):
582 """Sleep if the download speed is over the rate limit."""
583 rate_limit = self.params.get('ratelimit', None)
584 if rate_limit is None or byte_counter == 0:
587 elapsed = now - start_time
590 speed = float(byte_counter) / elapsed
591 if speed > rate_limit:
592 time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
594 def temp_name(self, filename):
595 """Returns a temporary filename for the given filename."""
596 if self.params.get('nopart', False) or filename == u'-' or \
597 (os.path.exists(filename) and not os.path.isfile(filename)):
599 return filename + u'.part'
601 def undo_temp_name(self, filename):
602 if filename.endswith(u'.part'):
603 return filename[:-len(u'.part')]
606 def try_rename(self, old_filename, new_filename):
608 if old_filename == new_filename:
610 os.rename(old_filename, new_filename)
611 except (IOError, OSError), err:
612 self.trouble(u'ERROR: unable to rename file')
614 def try_utime(self, filename, last_modified_hdr):
615 """Try to set the last-modified time of the given file."""
616 if last_modified_hdr is None:
618 if not os.path.isfile(filename):
620 timestr = last_modified_hdr
623 filetime = timeconvert(timestr)
627 os.utime(filename, (time.time(), filetime))
631 def report_writedescription(self, descfn):
632 """ Report that the description file is being written """
633 self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
635 def report_writeinfojson(self, infofn):
636 """ Report that the metadata file has been written """
637 self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
639 def report_destination(self, filename):
640 """Report destination filename."""
641 self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
643 def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
644 """Report download progress."""
645 if self.params.get('noprogress', False):
647 self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
648 (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
649 self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
650 (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
652 def report_resuming_byte(self, resume_len):
653 """Report attempt to resume at given byte."""
654 self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
656 def report_retry(self, count, retries):
657 """Report retry in case of HTTP error 5xx"""
658 self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
660 def report_file_already_downloaded(self, file_name):
661 """Report file has already been fully downloaded."""
663 self.to_screen(u'[download] %s has already been downloaded' % file_name)
664 except (UnicodeEncodeError), err:
665 self.to_screen(u'[download] The file has already been downloaded')
667 def report_unable_to_resume(self):
668 """Report it was impossible to resume download."""
669 self.to_screen(u'[download] Unable to resume')
671 def report_finish(self):
672 """Report download finished."""
673 if self.params.get('noprogress', False):
674 self.to_screen(u'[download] Download completed')
678 def increment_downloads(self):
679 """Increment the ordinal that assigns a number to each file."""
680 self._num_downloads += 1
682 def prepare_filename(self, info_dict):
683 """Generate the output filename."""
685 template_dict = dict(info_dict)
686 template_dict['epoch'] = unicode(long(time.time()))
687 template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
688 filename = self.params['outtmpl'] % template_dict
690 except (ValueError, KeyError), err:
691 self.trouble(u'ERROR: invalid system charset or erroneous output template')
694 def process_info(self, info_dict):
695 """Process a single dictionary returned by an InfoExtractor."""
696 filename = self.prepare_filename(info_dict)
697 # Do nothing else if in simulate mode
698 if self.params.get('simulate', False):
700 if self.params.get('forcetitle', False):
701 print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
702 if self.params.get('forceurl', False):
703 print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
704 if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
705 print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
706 if self.params.get('forcedescription', False) and 'description' in info_dict:
707 print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
708 if self.params.get('forcefilename', False) and filename is not None:
709 print filename.encode(preferredencoding(), 'xmlcharrefreplace')
715 if self.params.get('nooverwrites', False) and os.path.exists(filename):
716 self.to_stderr(u'WARNING: file exists and will be skipped')
720 dn = os.path.dirname(filename)
721 if dn != '' and not os.path.exists(dn):
723 except (OSError, IOError), err:
724 self.trouble(u'ERROR: unable to create directory ' + unicode(err))
727 if self.params.get('writedescription', False):
729 descfn = filename + '.description'
730 self.report_writedescription(descfn)
731 descfile = open(descfn, 'wb')
733 descfile.write(info_dict['description'].encode('utf-8'))
736 except (OSError, IOError):
737 self.trouble(u'ERROR: Cannot write description file ' + descfn)
740 if self.params.get('writeinfojson', False):
741 infofn = filename + '.info.json'
742 self.report_writeinfojson(infofn)
745 except (NameError,AttributeError):
746 self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
749 infof = open(infofn, 'wb')
751 json.dump(info_dict, infof)
754 except (OSError, IOError):
755 self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
759 success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
760 except (OSError, IOError), err:
761 raise UnavailableVideoError
762 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
763 self.trouble(u'ERROR: unable to download video data: %s' % str(err))
765 except (ContentTooShortError, ), err:
766 self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
771 self.post_process(filename, info_dict)
772 except (PostProcessingError), err:
773 self.trouble(u'ERROR: postprocessing: %s' % str(err))
776 def download(self, url_list):
777 """Download a given list of URLs."""
778 if len(url_list) > 1 and self.fixed_template():
779 raise SameFileError(self.params['outtmpl'])
782 suitable_found = False
784 # Go to next InfoExtractor if not suitable
785 if not ie.suitable(url):
788 # Suitable InfoExtractor found
789 suitable_found = True
791 # Extract information from URL and process it
794 # Suitable InfoExtractor had been found; go to next URL
797 if not suitable_found:
798 self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
800 return self._download_retcode
802 def post_process(self, filename, ie_info):
803 """Run the postprocessing chain on the given file."""
805 info['filepath'] = filename
811 def _download_with_rtmpdump(self, filename, url, player_url):
812 self.report_destination(filename)
813 tmpfilename = self.temp_name(filename)
815 # Check for rtmpdump first
817 subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
818 except (OSError, IOError):
819 self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
822 # Download using rtmpdump. rtmpdump returns exit code 2 when
823 # the connection was interrumpted and resuming appears to be
824 # possible. This is part of rtmpdump's normal usage, AFAIK.
825 basic_args = ['rtmpdump'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
826 retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
827 while retval == 2 or retval == 1:
828 prevsize = os.path.getsize(tmpfilename)
829 self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
830 time.sleep(5.0) # This seems to be needed
831 retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
832 cursize = os.path.getsize(tmpfilename)
833 if prevsize == cursize and retval == 1:
836 self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
837 self.try_rename(tmpfilename, filename)
840 self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
843 def _do_download(self, filename, url, player_url):
844 # Check file already present
845 if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
846 self.report_file_already_downloaded(filename)
849 # Attempt to download using rtmpdump
850 if url.startswith('rtmp'):
851 return self._download_with_rtmpdump(filename, url, player_url)
853 tmpfilename = self.temp_name(filename)
857 # Do not include the Accept-Encoding header
858 headers = {'Youtubedl-no-compression': 'True'}
859 basic_request = urllib2.Request(url, None, headers)
860 request = urllib2.Request(url, None, headers)
862 # Establish possible resume length
863 if os.path.isfile(tmpfilename):
864 resume_len = os.path.getsize(tmpfilename)
868 # Request parameters in case of being able to resume
869 if self.params.get('continuedl', False) and resume_len != 0:
870 self.report_resuming_byte(resume_len)
871 request.add_header('Range', 'bytes=%d-' % resume_len)
875 retries = self.params.get('retries', 0)
876 while count <= retries:
877 # Establish connection
879 data = urllib2.urlopen(request)
881 except (urllib2.HTTPError, ), err:
882 if (err.code < 500 or err.code >= 600) and err.code != 416:
883 # Unexpected HTTP error
885 elif err.code == 416:
886 # Unable to resume (requested range not satisfiable)
888 # Open the connection again without the range header
889 data = urllib2.urlopen(basic_request)
890 content_length = data.info()['Content-Length']
891 except (urllib2.HTTPError, ), err:
892 if err.code < 500 or err.code >= 600:
895 # Examine the reported length
896 if (content_length is not None and
897 (resume_len - 100 < long(content_length) < resume_len + 100)):
898 # The file had already been fully downloaded.
899 # Explanation to the above condition: in issue #175 it was revealed that
900 # YouTube sometimes adds or removes a few bytes from the end of the file,
901 # changing the file size slightly and causing problems for some users. So
902 # I decided to implement a suggested change and consider the file
903 # completely downloaded if the file size differs less than 100 bytes from
904 # the one in the hard drive.
905 self.report_file_already_downloaded(filename)
906 self.try_rename(tmpfilename, filename)
909 # The length does not match, we start the download over
910 self.report_unable_to_resume()
916 self.report_retry(count, retries)
919 self.trouble(u'ERROR: giving up after %s retries' % retries)
922 data_len = data.info().get('Content-length', None)
923 if data_len is not None:
924 data_len = long(data_len) + resume_len
925 data_len_str = self.format_bytes(data_len)
926 byte_counter = 0 + resume_len
932 data_block = data.read(block_size)
934 if len(data_block) == 0:
936 byte_counter += len(data_block)
938 # Open file just in time
941 (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
942 assert stream is not None
943 filename = self.undo_temp_name(tmpfilename)
944 self.report_destination(filename)
945 except (OSError, IOError), err:
946 self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
949 stream.write(data_block)
950 except (IOError, OSError), err:
951 self.trouble(u'\nERROR: unable to write data: %s' % str(err))
953 block_size = self.best_block_size(after - before, len(data_block))
956 percent_str = self.calc_percent(byte_counter, data_len)
957 eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
958 speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
959 self.report_progress(percent_str, data_len_str, speed_str, eta_str)
962 self.slow_down(start, byte_counter - resume_len)
965 self.trouble(u'\nERROR: Did not get any data blocks')
969 if data_len is not None and byte_counter != data_len:
970 raise ContentTooShortError(byte_counter, long(data_len))
971 self.try_rename(tmpfilename, filename)
973 # Update file modification time
974 if self.params.get('updatetime', True):
975 self.try_utime(filename, data.info().get('last-modified', None))
980 class InfoExtractor(object):
981 """Information Extractor class.
983 Information extractors are the classes that, given a URL, extract
984 information from the video (or videos) the URL refers to. This
985 information includes the real video URL, the video title and simplified
986 title, author and others. The information is stored in a dictionary
987 which is then passed to the FileDownloader. The FileDownloader
988 processes this information possibly downloading the video to the file
989 system, among other possible outcomes. The dictionaries must include
990 the following fields:
992 id: Video identifier.
993 url: Final video URL.
994 uploader: Nickname of the video uploader.
995 title: Literal title.
996 stitle: Simplified title.
997 ext: Video filename extension.
998 format: Video format.
999 player_url: SWF Player URL (may be None).
1001 The following fields are optional. Their primary purpose is to allow
1002 youtube-dl to serve as the backend for a video search function, such
1003 as the one in youtube2mp3. They are only used when their respective
1004 forced printing functions are called:
1006 thumbnail: Full URL to a video thumbnail image.
1007 description: One-line video description.
1009 Subclasses of this one should re-define the _real_initialize() and
1010 _real_extract() methods, as well as the suitable() static method.
1011 Probably, they should also be instantiated and added to the main
1018 def __init__(self, downloader=None):
1019 """Constructor. Receives an optional downloader."""
1021 self.set_downloader(downloader)
1025 """Receives a URL and returns True if suitable for this IE."""
1028 def initialize(self):
1029 """Initializes an instance (authentication, etc)."""
1031 self._real_initialize()
1034 def extract(self, url):
1035 """Extracts URL information and returns it in list of dicts."""
1037 return self._real_extract(url)
1039 def set_downloader(self, downloader):
1040 """Sets the downloader for this IE."""
1041 self._downloader = downloader
1043 def _real_initialize(self):
1044 """Real initialization process. Redefine in subclasses."""
1047 def _real_extract(self, url):
1048 """Real extraction process. Redefine in subclasses."""
1052 class YoutubeIE(InfoExtractor):
1053 """Information extractor for youtube.com."""
1055 _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
1056 _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
1057 _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
1058 _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
1059 _NETRC_MACHINE = 'youtube'
1060 # Listed in order of quality
1061 _available_formats = ['38', '37', '45', '22', '43', '35', '34', '18', '6', '5', '17', '13']
1062 _video_extensions = {
1068 '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
1075 return (re.match(YoutubeIE._VALID_URL, url) is not None)
1077 def report_lang(self):
1078 """Report attempt to set language."""
1079 self._downloader.to_screen(u'[youtube] Setting language')
1081 def report_login(self):
1082 """Report attempt to log in."""
1083 self._downloader.to_screen(u'[youtube] Logging in')
1085 def report_age_confirmation(self):
1086 """Report attempt to confirm age."""
1087 self._downloader.to_screen(u'[youtube] Confirming age')
1089 def report_video_webpage_download(self, video_id):
1090 """Report attempt to download video webpage."""
1091 self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
1093 def report_video_info_webpage_download(self, video_id):
1094 """Report attempt to download video info webpage."""
1095 self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
1097 def report_information_extraction(self, video_id):
1098 """Report attempt to extract video information."""
1099 self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
1101 def report_unavailable_format(self, video_id, format):
1102 """Report extracted video URL."""
1103 self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
1105 def report_rtmp_download(self):
1106 """Indicate the download will use the RTMP protocol."""
1107 self._downloader.to_screen(u'[youtube] RTMP download detected')
1109 def _real_initialize(self):
1110 if self._downloader is None:
1115 downloader_params = self._downloader.params
1117 # Attempt to use provided username and password or .netrc data
1118 if downloader_params.get('username', None) is not None:
1119 username = downloader_params['username']
1120 password = downloader_params['password']
1121 elif downloader_params.get('usenetrc', False):
1123 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
1124 if info is not None:
1128 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
1129 except (IOError, netrc.NetrcParseError), err:
1130 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
1134 request = urllib2.Request(self._LANG_URL)
1137 urllib2.urlopen(request).read()
1138 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1139 self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
1142 # No authentication to be performed
1143 if username is None:
1148 'current_form': 'loginForm',
1150 'action_login': 'Log In',
1151 'username': username,
1152 'password': password,
1154 request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
1157 login_results = urllib2.urlopen(request).read()
1158 if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
1159 self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
1161 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1162 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
1168 'action_confirm': 'Confirm',
1170 request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))
1172 self.report_age_confirmation()
1173 age_results = urllib2.urlopen(request).read()
1174 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1175 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
1178 def _real_extract(self, url):
1179 # Extract video id from URL
1180 mobj = re.match(self._VALID_URL, url)
1182 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1184 video_id = mobj.group(2)
1187 self.report_video_webpage_download(video_id)
1188 request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
1190 video_webpage = urllib2.urlopen(request).read()
1191 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1192 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
1195 # Attempt to extract SWF player URL
1196 mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1197 if mobj is not None:
1198 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1203 self.report_video_info_webpage_download(video_id)
1204 for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
1205 video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1206 % (video_id, el_type))
1207 request = urllib2.Request(video_info_url)
1209 video_info_webpage = urllib2.urlopen(request).read()
1210 video_info = parse_qs(video_info_webpage)
1211 if 'token' in video_info:
1213 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1214 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
1216 if 'token' not in video_info:
1217 if 'reason' in video_info:
1218 self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
1220 self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
1223 # Start extracting information
1224 self.report_information_extraction(video_id)
1227 if 'author' not in video_info:
1228 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1230 video_uploader = urllib.unquote_plus(video_info['author'][0])
1233 if 'title' not in video_info:
1234 self._downloader.trouble(u'ERROR: unable to extract video title')
1236 video_title = urllib.unquote_plus(video_info['title'][0])
1237 video_title = video_title.decode('utf-8')
1238 video_title = sanitize_title(video_title)
1241 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1242 simple_title = simple_title.strip(ur'_')
1245 if 'thumbnail_url' not in video_info:
1246 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
1247 video_thumbnail = ''
1248 else: # don't panic if we can't find it
1249 video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
1253 mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
1254 if mobj is not None:
1255 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1256 format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
1257 for expression in format_expressions:
1259 upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
1267 video_description = u'No description available.'
1268 if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False):
1269 mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
1270 if mobj is not None:
1271 video_description = mobj.group(1).decode('utf-8')
1273 html_parser = lxml.etree.HTMLParser(encoding='utf-8')
1274 vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser)
1275 video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()'))
1276 # TODO use another parser
1279 video_token = urllib.unquote_plus(video_info['token'][0])
1281 # Decide which formats to download
1282 req_format = self._downloader.params.get('format', None)
1284 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1285 self.report_rtmp_download()
1286 video_url_list = [(None, video_info['conn'][0])]
1287 elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
1288 url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
1289 url_data = [parse_qs(uds) for uds in url_data_strs]
1290 url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
1291 url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
1293 format_limit = self._downloader.params.get('format_limit', None)
1294 if format_limit is not None and format_limit in self._available_formats:
1295 format_list = self._available_formats[self._available_formats.index(format_limit):]
1297 format_list = self._available_formats
1298 existing_formats = [x for x in format_list if x in url_map]
1299 if len(existing_formats) == 0:
1300 self._downloader.trouble(u'ERROR: no known formats available for video')
1302 if req_format is None:
1303 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
1304 elif req_format == '-1':
1305 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
1308 if req_format not in url_map:
1309 self._downloader.trouble(u'ERROR: requested format not available')
1311 video_url_list = [(req_format, url_map[req_format])] # Specific format
1313 self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
1316 for format_param, video_real_url in video_url_list:
1317 # At this point we have a new video
1318 self._downloader.increment_downloads()
1321 video_extension = self._video_extensions.get(format_param, 'flv')
1324 # Process video information
1325 self._downloader.process_info({
1326 'id': video_id.decode('utf-8'),
1327 'url': video_real_url.decode('utf-8'),
1328 'uploader': video_uploader.decode('utf-8'),
1329 'upload_date': upload_date,
1330 'title': video_title,
1331 'stitle': simple_title,
1332 'ext': video_extension.decode('utf-8'),
1333 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
1334 'thumbnail': video_thumbnail.decode('utf-8'),
1335 'description': video_description,
1336 'player_url': player_url,
1338 except UnavailableVideoError, err:
1339 self._downloader.trouble(u'\nERROR: unable to download video')
1342 class MetacafeIE(InfoExtractor):
1343 """Information Extractor for metacafe.com."""
1345 _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
1346 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
1347 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
1350 def __init__(self, youtube_ie, downloader=None):
1351 InfoExtractor.__init__(self, downloader)
1352 self._youtube_ie = youtube_ie
1356 return (re.match(MetacafeIE._VALID_URL, url) is not None)
1358 def report_disclaimer(self):
1359 """Report disclaimer retrieval."""
1360 self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
1362 def report_age_confirmation(self):
1363 """Report attempt to confirm age."""
1364 self._downloader.to_screen(u'[metacafe] Confirming age')
1366 def report_download_webpage(self, video_id):
1367 """Report webpage download."""
1368 self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
1370 def report_extraction(self, video_id):
1371 """Report information extraction."""
1372 self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
1374 def _real_initialize(self):
1375 # Retrieve disclaimer
1376 request = urllib2.Request(self._DISCLAIMER)
1378 self.report_disclaimer()
1379 disclaimer = urllib2.urlopen(request).read()
1380 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1381 self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
1387 'submit': "Continue - I'm over 18",
1389 request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))
1391 self.report_age_confirmation()
1392 disclaimer = urllib2.urlopen(request).read()
1393 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1394 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
1397 def _real_extract(self, url):
1398 # Extract id and simplified title from URL
1399 mobj = re.match(self._VALID_URL, url)
1401 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1404 video_id = mobj.group(1)
1406 # Check if video comes from YouTube
1407 mobj2 = re.match(r'^yt-(.*)$', video_id)
1408 if mobj2 is not None:
1409 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
1412 # At this point we have a new video
1413 self._downloader.increment_downloads()
1415 simple_title = mobj.group(2).decode('utf-8')
1417 # Retrieve video webpage to extract further information
1418 request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
1420 self.report_download_webpage(video_id)
1421 webpage = urllib2.urlopen(request).read()
1422 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1423 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
1426 # Extract URL, uploader and title from webpage
1427 self.report_extraction(video_id)
1428 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
1429 if mobj is not None:
1430 mediaURL = urllib.unquote(mobj.group(1))
1431 video_extension = mediaURL[-3:]
1433 # Extract gdaKey if available
1434 mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
1436 video_url = mediaURL
1438 gdaKey = mobj.group(1)
1439 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
1441 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
1443 self._downloader.trouble(u'ERROR: unable to extract media URL')
1445 vardict = parse_qs(mobj.group(1))
1446 if 'mediaData' not in vardict:
1447 self._downloader.trouble(u'ERROR: unable to extract media URL')
1449 mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
1451 self._downloader.trouble(u'ERROR: unable to extract media URL')
1453 mediaURL = mobj.group(1).replace('\\/', '/')
1454 video_extension = mediaURL[-3:]
1455 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
1457 mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
1459 self._downloader.trouble(u'ERROR: unable to extract title')
1461 video_title = mobj.group(1).decode('utf-8')
1462 video_title = sanitize_title(video_title)
1464 mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
1466 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1468 video_uploader = mobj.group(1)
1471 # Process video information
1472 self._downloader.process_info({
1473 'id': video_id.decode('utf-8'),
1474 'url': video_url.decode('utf-8'),
1475 'uploader': video_uploader.decode('utf-8'),
1476 'upload_date': u'NA',
1477 'title': video_title,
1478 'stitle': simple_title,
1479 'ext': video_extension.decode('utf-8'),
1483 except UnavailableVideoError:
1484 self._downloader.trouble(u'\nERROR: unable to download video')
1487 class DailymotionIE(InfoExtractor):
1488 """Information Extractor for Dailymotion"""
1490 _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
1492 def __init__(self, downloader=None):
1493 InfoExtractor.__init__(self, downloader)
1497 return (re.match(DailymotionIE._VALID_URL, url) is not None)
1499 def report_download_webpage(self, video_id):
1500 """Report webpage download."""
1501 self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
1503 def report_extraction(self, video_id):
1504 """Report information extraction."""
1505 self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
1507 def _real_initialize(self):
1510 def _real_extract(self, url):
1511 # Extract id and simplified title from URL
1512 mobj = re.match(self._VALID_URL, url)
1514 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1517 # At this point we have a new video
1518 self._downloader.increment_downloads()
1519 video_id = mobj.group(1)
1521 simple_title = mobj.group(2).decode('utf-8')
1522 video_extension = 'flv'
1524 # Retrieve video webpage to extract further information
1525 request = urllib2.Request(url)
1527 self.report_download_webpage(video_id)
1528 webpage = urllib2.urlopen(request).read()
1529 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1530 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
1533 # Extract URL, uploader and title from webpage
1534 self.report_extraction(video_id)
1535 mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
1537 self._downloader.trouble(u'ERROR: unable to extract media URL')
1539 mediaURL = urllib.unquote(mobj.group(1))
1541 # if needed add http://www.dailymotion.com/ if relative URL
1543 video_url = mediaURL
1545 # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
1546 mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
1548 self._downloader.trouble(u'ERROR: unable to extract title')
1550 video_title = mobj.group(1).decode('utf-8')
1551 video_title = sanitize_title(video_title)
1553 mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
1555 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1557 video_uploader = mobj.group(1)
1560 # Process video information
1561 self._downloader.process_info({
1562 'id': video_id.decode('utf-8'),
1563 'url': video_url.decode('utf-8'),
1564 'uploader': video_uploader.decode('utf-8'),
1565 'upload_date': u'NA',
1566 'title': video_title,
1567 'stitle': simple_title,
1568 'ext': video_extension.decode('utf-8'),
1572 except UnavailableVideoError:
1573 self._downloader.trouble(u'\nERROR: unable to download video')
1576 class GoogleIE(InfoExtractor):
1577 """Information extractor for video.google.com."""
1579 _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
1581 def __init__(self, downloader=None):
1582 InfoExtractor.__init__(self, downloader)
1586 return (re.match(GoogleIE._VALID_URL, url) is not None)
1588 def report_download_webpage(self, video_id):
1589 """Report webpage download."""
1590 self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
1592 def report_extraction(self, video_id):
1593 """Report information extraction."""
1594 self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
1596 def _real_initialize(self):
1599 def _real_extract(self, url):
1600 # Extract id from URL
1601 mobj = re.match(self._VALID_URL, url)
1603 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1606 # At this point we have a new video
1607 self._downloader.increment_downloads()
1608 video_id = mobj.group(1)
1610 video_extension = 'mp4'
1612 # Retrieve video webpage to extract further information
1613 request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
1615 self.report_download_webpage(video_id)
1616 webpage = urllib2.urlopen(request).read()
1617 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1618 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1621 # Extract URL, uploader, and title from webpage
1622 self.report_extraction(video_id)
1623 mobj = re.search(r"download_url:'([^']+)'", webpage)
1625 video_extension = 'flv'
1626 mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
1628 self._downloader.trouble(u'ERROR: unable to extract media URL')
1630 mediaURL = urllib.unquote(mobj.group(1))
1631 mediaURL = mediaURL.replace('\\x3d', '\x3d')
1632 mediaURL = mediaURL.replace('\\x26', '\x26')
1634 video_url = mediaURL
1636 mobj = re.search(r'<title>(.*)</title>', webpage)
1638 self._downloader.trouble(u'ERROR: unable to extract title')
1640 video_title = mobj.group(1).decode('utf-8')
1641 video_title = sanitize_title(video_title)
1642 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1644 # Extract video description
1645 mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
1647 self._downloader.trouble(u'ERROR: unable to extract video description')
1649 video_description = mobj.group(1).decode('utf-8')
1650 if not video_description:
1651 video_description = 'No description available.'
1653 # Extract video thumbnail
1654 if self._downloader.params.get('forcethumbnail', False):
1655 request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
1657 webpage = urllib2.urlopen(request).read()
1658 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1659 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1661 mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
1663 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1665 video_thumbnail = mobj.group(1)
1666 else: # we need something to pass to process_info
1667 video_thumbnail = ''
1670 # Process video information
1671 self._downloader.process_info({
1672 'id': video_id.decode('utf-8'),
1673 'url': video_url.decode('utf-8'),
1675 'upload_date': u'NA',
1676 'title': video_title,
1677 'stitle': simple_title,
1678 'ext': video_extension.decode('utf-8'),
1682 except UnavailableVideoError:
1683 self._downloader.trouble(u'\nERROR: unable to download video')
1686 class PhotobucketIE(InfoExtractor):
1687 """Information extractor for photobucket.com."""
1689 _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
1691 def __init__(self, downloader=None):
1692 InfoExtractor.__init__(self, downloader)
1696 return (re.match(PhotobucketIE._VALID_URL, url) is not None)
1698 def report_download_webpage(self, video_id):
1699 """Report webpage download."""
1700 self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
1702 def report_extraction(self, video_id):
1703 """Report information extraction."""
1704 self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
1706 def _real_initialize(self):
1709 def _real_extract(self, url):
1710 # Extract id from URL
1711 mobj = re.match(self._VALID_URL, url)
1713 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1716 # At this point we have a new video
1717 self._downloader.increment_downloads()
1718 video_id = mobj.group(1)
1720 video_extension = 'flv'
1722 # Retrieve video webpage to extract further information
1723 request = urllib2.Request(url)
1725 self.report_download_webpage(video_id)
1726 webpage = urllib2.urlopen(request).read()
1727 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1728 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1731 # Extract URL, uploader, and title from webpage
1732 self.report_extraction(video_id)
1733 mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
1735 self._downloader.trouble(u'ERROR: unable to extract media URL')
1737 mediaURL = urllib.unquote(mobj.group(1))
1739 video_url = mediaURL
1741 mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
1743 self._downloader.trouble(u'ERROR: unable to extract title')
1745 video_title = mobj.group(1).decode('utf-8')
1746 video_title = sanitize_title(video_title)
1747 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1749 video_uploader = mobj.group(2).decode('utf-8')
1752 # Process video information
1753 self._downloader.process_info({
1754 'id': video_id.decode('utf-8'),
1755 'url': video_url.decode('utf-8'),
1756 'uploader': video_uploader,
1757 'upload_date': u'NA',
1758 'title': video_title,
1759 'stitle': simple_title,
1760 'ext': video_extension.decode('utf-8'),
1764 except UnavailableVideoError:
1765 self._downloader.trouble(u'\nERROR: unable to download video')
1768 class YahooIE(InfoExtractor):
1769 """Information extractor for video.yahoo.com."""
1771 # _VALID_URL matches all Yahoo! Video URLs
1772 # _VPAGE_URL matches only the extractable '/watch/' URLs
1773 _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
1774 _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
1776 def __init__(self, downloader=None):
1777 InfoExtractor.__init__(self, downloader)
1781 return (re.match(YahooIE._VALID_URL, url) is not None)
1783 def report_download_webpage(self, video_id):
1784 """Report webpage download."""
1785 self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
1787 def report_extraction(self, video_id):
1788 """Report information extraction."""
1789 self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
1791 def _real_initialize(self):
1794 def _real_extract(self, url, new_video=True):
1795 # Extract ID from URL
1796 mobj = re.match(self._VALID_URL, url)
1798 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1801 # At this point we have a new video
1802 self._downloader.increment_downloads()
1803 video_id = mobj.group(2)
1804 video_extension = 'flv'
1806 # Rewrite valid but non-extractable URLs as
1807 # extractable English language /watch/ URLs
1808 if re.match(self._VPAGE_URL, url) is None:
1809 request = urllib2.Request(url)
1811 webpage = urllib2.urlopen(request).read()
1812 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1813 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1816 mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
1818 self._downloader.trouble(u'ERROR: Unable to extract id field')
1820 yahoo_id = mobj.group(1)
1822 mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
1824 self._downloader.trouble(u'ERROR: Unable to extract vid field')
1826 yahoo_vid = mobj.group(1)
1828 url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
1829 return self._real_extract(url, new_video=False)
1831 # Retrieve video webpage to extract further information
1832 request = urllib2.Request(url)
1834 self.report_download_webpage(video_id)
1835 webpage = urllib2.urlopen(request).read()
1836 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1837 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1840 # Extract uploader and title from webpage
1841 self.report_extraction(video_id)
1842 mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
1844 self._downloader.trouble(u'ERROR: unable to extract video title')
1846 video_title = mobj.group(1).decode('utf-8')
1847 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1849 mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
1851 self._downloader.trouble(u'ERROR: unable to extract video uploader')
1853 video_uploader = mobj.group(1).decode('utf-8')
1855 # Extract video thumbnail
1856 mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
1858 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1860 video_thumbnail = mobj.group(1).decode('utf-8')
1862 # Extract video description
1863 mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
1865 self._downloader.trouble(u'ERROR: unable to extract video description')
1867 video_description = mobj.group(1).decode('utf-8')
1868 if not video_description:
1869 video_description = 'No description available.'
1871 # Extract video height and width
1872 mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
1874 self._downloader.trouble(u'ERROR: unable to extract video height')
1876 yv_video_height = mobj.group(1)
1878 mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
1880 self._downloader.trouble(u'ERROR: unable to extract video width')
1882 yv_video_width = mobj.group(1)
1884 # Retrieve video playlist to extract media URL
1885 # I'm not completely sure what all these options are, but we
1886 # seem to need most of them, otherwise the server sends a 401.
1887 yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
1888 yv_bitrate = '700' # according to Wikipedia this is hard-coded
1889 request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
1890 '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
1891 '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
1893 self.report_download_webpage(video_id)
1894 webpage = urllib2.urlopen(request).read()
1895 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1896 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1899 # Extract media URL from playlist XML
1900 mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
1902 self._downloader.trouble(u'ERROR: Unable to extract media URL')
1904 video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
1905 video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
1908 # Process video information
1909 self._downloader.process_info({
1910 'id': video_id.decode('utf-8'),
1912 'uploader': video_uploader,
1913 'upload_date': u'NA',
1914 'title': video_title,
1915 'stitle': simple_title,
1916 'ext': video_extension.decode('utf-8'),
1917 'thumbnail': video_thumbnail.decode('utf-8'),
1918 'description': video_description,
1919 'thumbnail': video_thumbnail,
1922 except UnavailableVideoError:
1923 self._downloader.trouble(u'\nERROR: unable to download video')
1926 class VimeoIE(InfoExtractor):
1927 """Information extractor for vimeo.com."""
1929 # _VALID_URL matches Vimeo URLs
1930 _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
1932 def __init__(self, downloader=None):
1933 InfoExtractor.__init__(self, downloader)
1937 return (re.match(VimeoIE._VALID_URL, url) is not None)
1939 def report_download_webpage(self, video_id):
1940 """Report webpage download."""
1941 self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
1943 def report_extraction(self, video_id):
1944 """Report information extraction."""
1945 self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
1947 def _real_initialize(self):
1950 def _real_extract(self, url, new_video=True):
1951 # Extract ID from URL
1952 mobj = re.match(self._VALID_URL, url)
1954 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1957 # At this point we have a new video
1958 self._downloader.increment_downloads()
1959 video_id = mobj.group(1)
1961 # Retrieve video webpage to extract further information
1962 request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)
1964 self.report_download_webpage(video_id)
1965 webpage = urllib2.urlopen(request).read()
1966 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1967 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1970 # Now we begin extracting as much information as we can from what we
1971 # retrieved. First we extract the information common to all extractors,
1972 # and latter we extract those that are Vimeo specific.
1973 self.report_extraction(video_id)
1976 mobj = re.search(r'<caption>(.*?)</caption>', webpage)
1978 self._downloader.trouble(u'ERROR: unable to extract video title')
1980 video_title = mobj.group(1).decode('utf-8')
1981 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1984 mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
1986 self._downloader.trouble(u'ERROR: unable to extract video uploader')
1988 video_uploader = mobj.group(1).decode('utf-8')
1990 # Extract video thumbnail
1991 mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage)
1993 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1995 video_thumbnail = mobj.group(1).decode('utf-8')
1997 # # Extract video description
1998 # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage)
2000 # self._downloader.trouble(u'ERROR: unable to extract video description')
2002 # video_description = mobj.group(1).decode('utf-8')
2003 # if not video_description: video_description = 'No description available.'
2004 video_description = 'Foo.'
2006 # Vimeo specific: extract request signature
2007 mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
2009 self._downloader.trouble(u'ERROR: unable to extract request signature')
2011 sig = mobj.group(1).decode('utf-8')
2013 # Vimeo specific: Extract request signature expiration
2014 mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
2016 self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
2018 sig_exp = mobj.group(1).decode('utf-8')
2020 video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
2023 # Process video information
2024 self._downloader.process_info({
2025 'id': video_id.decode('utf-8'),
2027 'uploader': video_uploader,
2028 'upload_date': u'NA',
2029 'title': video_title,
2030 'stitle': simple_title,
2032 'thumbnail': video_thumbnail.decode('utf-8'),
2033 'description': video_description,
2034 'thumbnail': video_thumbnail,
2035 'description': video_description,
2038 except UnavailableVideoError:
2039 self._downloader.trouble(u'ERROR: unable to download video')
2042 class GenericIE(InfoExtractor):
2043 """Generic last-resort information extractor."""
2045 def __init__(self, downloader=None):
2046 InfoExtractor.__init__(self, downloader)
2052 def report_download_webpage(self, video_id):
2053 """Report webpage download."""
2054 self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
2055 self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
2057 def report_extraction(self, video_id):
2058 """Report information extraction."""
2059 self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
2061 def _real_initialize(self):
2064 def _real_extract(self, url):
2065 # At this point we have a new video
2066 self._downloader.increment_downloads()
2068 video_id = url.split('/')[-1]
2069 request = urllib2.Request(url)
2071 self.report_download_webpage(video_id)
2072 webpage = urllib2.urlopen(request).read()
2073 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2074 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
2076 except ValueError, err:
2077 # since this is the last-resort InfoExtractor, if
2078 # this error is thrown, it'll be thrown here
2079 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
2082 self.report_extraction(video_id)
2083 # Start with something easy: JW Player in SWFObject
2084 mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
2086 # Broaden the search a little bit
2087 mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
2089 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
2092 # It's possible that one of the regexes
2093 # matched, but returned an empty group:
2094 if mobj.group(1) is None:
2095 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
2098 video_url = urllib.unquote(mobj.group(1))
2099 video_id = os.path.basename(video_url)
2101 # here's a fun little line of code for you:
2102 video_extension = os.path.splitext(video_id)[1][1:]
2103 video_id = os.path.splitext(video_id)[0]
2105 # it's tempting to parse this further, but you would
2106 # have to take into account all the variations like
2107 # Video Title - Site Name
2108 # Site Name | Video Title
2109 # Video Title - Tagline | Site Name
2110 # and so on and so forth; it's just not practical
2111 mobj = re.search(r'<title>(.*)</title>', webpage)
2113 self._downloader.trouble(u'ERROR: unable to extract title')
2115 video_title = mobj.group(1).decode('utf-8')
2116 video_title = sanitize_title(video_title)
2117 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
2119 # video uploader is domain name
2120 mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
2122 self._downloader.trouble(u'ERROR: unable to extract title')
2124 video_uploader = mobj.group(1).decode('utf-8')
2127 # Process video information
2128 self._downloader.process_info({
2129 'id': video_id.decode('utf-8'),
2130 'url': video_url.decode('utf-8'),
2131 'uploader': video_uploader,
2132 'upload_date': u'NA',
2133 'title': video_title,
2134 'stitle': simple_title,
2135 'ext': video_extension.decode('utf-8'),
2139 except UnavailableVideoError, err:
2140 self._downloader.trouble(u'\nERROR: unable to download video')
2143 class YoutubeSearchIE(InfoExtractor):
2144 """Information Extractor for YouTube search queries."""
2145 _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
2146 _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
2147 _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
2148 _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
2150 _max_youtube_results = 1000
2152 def __init__(self, youtube_ie, downloader=None):
2153 InfoExtractor.__init__(self, downloader)
2154 self._youtube_ie = youtube_ie
2158 return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
2160 def report_download_page(self, query, pagenum):
2161 """Report attempt to download playlist page with given number."""
2162 query = query.decode(preferredencoding())
2163 self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
2165 def _real_initialize(self):
2166 self._youtube_ie.initialize()
2168 def _real_extract(self, query):
2169 mobj = re.match(self._VALID_QUERY, query)
2171 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
2174 prefix, query = query.split(':')
2176 query = query.encode('utf-8')
2178 self._download_n_results(query, 1)
2180 elif prefix == 'all':
2181 self._download_n_results(query, self._max_youtube_results)
2187 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
2189 elif n > self._max_youtube_results:
2190 self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
2191 n = self._max_youtube_results
2192 self._download_n_results(query, n)
2194 except ValueError: # parsing prefix as integer fails
2195 self._download_n_results(query, 1)
2198 def _download_n_results(self, query, n):
2199 """Downloads a specified number of results for a query"""
2202 already_seen = set()
2206 self.report_download_page(query, pagenum)
2207 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2208 request = urllib2.Request(result_url)
2210 page = urllib2.urlopen(request).read()
2211 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2212 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2215 # Extract video identifiers
2216 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2217 video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
2218 if video_id not in already_seen:
2219 video_ids.append(video_id)
2220 already_seen.add(video_id)
2221 if len(video_ids) == n:
2222 # Specified n videos reached
2223 for id in video_ids:
2224 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2227 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2228 for id in video_ids:
2229 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2232 pagenum = pagenum + 1
2235 class GoogleSearchIE(InfoExtractor):
2236 """Information Extractor for Google Video search queries."""
2237 _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
2238 _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
2239 _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
2240 _MORE_PAGES_INDICATOR = r'<span>Next</span>'
2242 _max_google_results = 1000
2244 def __init__(self, google_ie, downloader=None):
2245 InfoExtractor.__init__(self, downloader)
2246 self._google_ie = google_ie
2250 return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
2252 def report_download_page(self, query, pagenum):
2253 """Report attempt to download playlist page with given number."""
2254 query = query.decode(preferredencoding())
2255 self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
2257 def _real_initialize(self):
2258 self._google_ie.initialize()
2260 def _real_extract(self, query):
2261 mobj = re.match(self._VALID_QUERY, query)
2263 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
2266 prefix, query = query.split(':')
2268 query = query.encode('utf-8')
2270 self._download_n_results(query, 1)
2272 elif prefix == 'all':
2273 self._download_n_results(query, self._max_google_results)
2279 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
2281 elif n > self._max_google_results:
2282 self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
2283 n = self._max_google_results
2284 self._download_n_results(query, n)
2286 except ValueError: # parsing prefix as integer fails
2287 self._download_n_results(query, 1)
2290 def _download_n_results(self, query, n):
2291 """Downloads a specified number of results for a query"""
2294 already_seen = set()
2298 self.report_download_page(query, pagenum)
2299 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2300 request = urllib2.Request(result_url)
2302 page = urllib2.urlopen(request).read()
2303 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2304 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2307 # Extract video identifiers
2308 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2309 video_id = mobj.group(1)
2310 if video_id not in already_seen:
2311 video_ids.append(video_id)
2312 already_seen.add(video_id)
2313 if len(video_ids) == n:
2314 # Specified n videos reached
2315 for id in video_ids:
2316 self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
2319 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2320 for id in video_ids:
2321 self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
2324 pagenum = pagenum + 1
2327 class YahooSearchIE(InfoExtractor):
2328 """Information Extractor for Yahoo! Video search queries."""
2329 _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
2330 _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
2331 _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
2332 _MORE_PAGES_INDICATOR = r'\s*Next'
2334 _max_yahoo_results = 1000
2336 def __init__(self, yahoo_ie, downloader=None):
2337 InfoExtractor.__init__(self, downloader)
2338 self._yahoo_ie = yahoo_ie
2342 return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
2344 def report_download_page(self, query, pagenum):
2345 """Report attempt to download playlist page with given number."""
2346 query = query.decode(preferredencoding())
2347 self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
2349 def _real_initialize(self):
2350 self._yahoo_ie.initialize()
2352 def _real_extract(self, query):
2353 mobj = re.match(self._VALID_QUERY, query)
2355 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
2358 prefix, query = query.split(':')
2360 query = query.encode('utf-8')
2362 self._download_n_results(query, 1)
2364 elif prefix == 'all':
2365 self._download_n_results(query, self._max_yahoo_results)
2371 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
2373 elif n > self._max_yahoo_results:
2374 self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
2375 n = self._max_yahoo_results
2376 self._download_n_results(query, n)
2378 except ValueError: # parsing prefix as integer fails
2379 self._download_n_results(query, 1)
2382 def _download_n_results(self, query, n):
2383 """Downloads a specified number of results for a query"""
2386 already_seen = set()
2390 self.report_download_page(query, pagenum)
2391 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2392 request = urllib2.Request(result_url)
2394 page = urllib2.urlopen(request).read()
2395 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2396 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2399 # Extract video identifiers
2400 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2401 video_id = mobj.group(1)
2402 if video_id not in already_seen:
2403 video_ids.append(video_id)
2404 already_seen.add(video_id)
2405 if len(video_ids) == n:
2406 # Specified n videos reached
2407 for id in video_ids:
2408 self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
2411 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2412 for id in video_ids:
2413 self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
2416 pagenum = pagenum + 1
2419 class YoutubePlaylistIE(InfoExtractor):
2420 """Information Extractor for YouTube playlists."""
2422 _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
2423 _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
2424 _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
2425 _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
2428 def __init__(self, youtube_ie, downloader=None):
2429 InfoExtractor.__init__(self, downloader)
2430 self._youtube_ie = youtube_ie
2434 return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
2436 def report_download_page(self, playlist_id, pagenum):
2437 """Report attempt to download playlist page with given number."""
2438 self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
2440 def _real_initialize(self):
2441 self._youtube_ie.initialize()
2443 def _real_extract(self, url):
2444 # Extract playlist id
2445 mobj = re.match(self._VALID_URL, url)
2447 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
2451 if mobj.group(3) is not None:
2452 self._youtube_ie.extract(mobj.group(3))
2455 # Download playlist pages
2456 # prefix is 'p' as default for playlists but there are other types that need extra care
2457 playlist_prefix = mobj.group(1)
2458 if playlist_prefix == 'a':
2459 playlist_access = 'artist'
2461 playlist_prefix = 'p'
2462 playlist_access = 'view_play_list'
2463 playlist_id = mobj.group(2)
2468 self.report_download_page(playlist_id, pagenum)
2469 request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
2471 page = urllib2.urlopen(request).read()
2472 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2473 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2476 # Extract video identifiers
2478 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2479 if mobj.group(1) not in ids_in_page:
2480 ids_in_page.append(mobj.group(1))
2481 video_ids.extend(ids_in_page)
2483 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2485 pagenum = pagenum + 1
2487 playliststart = self._downloader.params.get('playliststart', 1) - 1
2488 playlistend = self._downloader.params.get('playlistend', -1)
2489 video_ids = video_ids[playliststart:playlistend]
2491 for id in video_ids:
2492 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2496 class YoutubeUserIE(InfoExtractor):
2497 """Information Extractor for YouTube users."""
2499 _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
2500 _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
2501 _GDATA_PAGE_SIZE = 50
2502 _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
2503 _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
2506 def __init__(self, youtube_ie, downloader=None):
2507 InfoExtractor.__init__(self, downloader)
2508 self._youtube_ie = youtube_ie
2512 return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
2514 def report_download_page(self, username, start_index):
2515 """Report attempt to download user page."""
2516 self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
2517 (username, start_index, start_index + self._GDATA_PAGE_SIZE))
2519 def _real_initialize(self):
2520 self._youtube_ie.initialize()
2522 def _real_extract(self, url):
2524 mobj = re.match(self._VALID_URL, url)
2526 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
2529 username = mobj.group(1)
2531 # Download video ids using YouTube Data API. Result size per
2532 # query is limited (currently to 50 videos) so we need to query
2533 # page by page until there are no video ids - it means we got
2540 start_index = pagenum * self._GDATA_PAGE_SIZE + 1
2541 self.report_download_page(username, start_index)
2543 request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
2546 page = urllib2.urlopen(request).read()
2547 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2548 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2551 # Extract video identifiers
2554 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2555 if mobj.group(1) not in ids_in_page:
2556 ids_in_page.append(mobj.group(1))
2558 video_ids.extend(ids_in_page)
2560 # A little optimization - if current page is not
2561 # "full", ie. does not contain PAGE_SIZE video ids then
2562 # we can assume that this page is the last one - there
2563 # are no more ids on further pages - no need to query
2566 if len(ids_in_page) < self._GDATA_PAGE_SIZE:
2571 all_ids_count = len(video_ids)
2572 playliststart = self._downloader.params.get('playliststart', 1) - 1
2573 playlistend = self._downloader.params.get('playlistend', -1)
2575 if playlistend == -1:
2576 video_ids = video_ids[playliststart:]
2578 video_ids = video_ids[playliststart:playlistend]
2580 self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
2581 (username, all_ids_count, len(video_ids)))
2583 for video_id in video_ids:
2584 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
2587 class DepositFilesIE(InfoExtractor):
2588 """Information extractor for depositfiles.com"""
2590 _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
2592 def __init__(self, downloader=None):
2593 InfoExtractor.__init__(self, downloader)
2597 return (re.match(DepositFilesIE._VALID_URL, url) is not None)
2599 def report_download_webpage(self, file_id):
2600 """Report webpage download."""
2601 self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
2603 def report_extraction(self, file_id):
2604 """Report information extraction."""
2605 self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
2607 def _real_initialize(self):
2610 def _real_extract(self, url):
2611 # At this point we have a new file
2612 self._downloader.increment_downloads()
2614 file_id = url.split('/')[-1]
2615 # Rebuild url in english locale
2616 url = 'http://depositfiles.com/en/files/' + file_id
2618 # Retrieve file webpage with 'Free download' button pressed
2619 free_download_indication = { 'gateway_result' : '1' }
2620 request = urllib2.Request(url, urllib.urlencode(free_download_indication))
2622 self.report_download_webpage(file_id)
2623 webpage = urllib2.urlopen(request).read()
2624 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2625 self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
2628 # Search for the real file URL
2629 mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
2630 if (mobj is None) or (mobj.group(1) is None):
2631 # Try to figure out reason of the error.
2632 mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
2633 if (mobj is not None) and (mobj.group(1) is not None):
2634 restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
2635 self._downloader.trouble(u'ERROR: %s' % restriction_message)
2637 self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
2640 file_url = mobj.group(1)
2641 file_extension = os.path.splitext(file_url)[1][1:]
2643 # Search for file title
2644 mobj = re.search(r'<b title="(.*?)">', webpage)
2646 self._downloader.trouble(u'ERROR: unable to extract title')
2648 file_title = mobj.group(1).decode('utf-8')
2651 # Process file information
2652 self._downloader.process_info({
2653 'id': file_id.decode('utf-8'),
2654 'url': file_url.decode('utf-8'),
2656 'upload_date': u'NA',
2657 'title': file_title,
2658 'stitle': file_title,
2659 'ext': file_extension.decode('utf-8'),
2663 except UnavailableVideoError, err:
2664 self._downloader.trouble(u'ERROR: unable to download file')
2667 class FacebookIE(InfoExtractor):
2668 """Information Extractor for Facebook"""
2670 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
2671 _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
2672 _NETRC_MACHINE = 'facebook'
2673 _available_formats = ['highqual', 'lowqual']
2674 _video_extensions = {
2679 def __init__(self, downloader=None):
2680 InfoExtractor.__init__(self, downloader)
2684 return (re.match(FacebookIE._VALID_URL, url) is not None)
2686 def _reporter(self, message):
2687 """Add header and report message."""
2688 self._downloader.to_screen(u'[facebook] %s' % message)
2690 def report_login(self):
2691 """Report attempt to log in."""
2692 self._reporter(u'Logging in')
2694 def report_video_webpage_download(self, video_id):
2695 """Report attempt to download video webpage."""
2696 self._reporter(u'%s: Downloading video webpage' % video_id)
2698 def report_information_extraction(self, video_id):
2699 """Report attempt to extract video information."""
2700 self._reporter(u'%s: Extracting video information' % video_id)
2702 def _parse_page(self, video_webpage):
2703 """Extract video information from page"""
2705 data = {'title': r'class="video_title datawrap">(.*?)</',
2706 'description': r'<div class="datawrap">(.*?)</div>',
2707 'owner': r'\("video_owner_name", "(.*?)"\)',
2708 'upload_date': r'data-date="(.*?)"',
2709 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
2712 for piece in data.keys():
2713 mobj = re.search(data[piece], video_webpage)
2714 if mobj is not None:
2715 video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
2719 for fmt in self._available_formats:
2720 mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
2721 if mobj is not None:
2722 # URL is in a Javascript segment inside an escaped Unicode format within
2723 # the generally utf-8 page
2724 video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
2725 video_info['video_urls'] = video_urls
2729 def _real_initialize(self):
2730 if self._downloader is None:
2735 downloader_params = self._downloader.params
2737 # Attempt to use provided username and password or .netrc data
2738 if downloader_params.get('username', None) is not None:
2739 useremail = downloader_params['username']
2740 password = downloader_params['password']
2741 elif downloader_params.get('usenetrc', False):
2743 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
2744 if info is not None:
2748 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
2749 except (IOError, netrc.NetrcParseError), err:
2750 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
2753 if useremail is None:
2762 request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
2765 login_results = urllib2.urlopen(request).read()
2766 if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
2767 self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
2769 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2770 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
2773 def _real_extract(self, url):
2774 mobj = re.match(self._VALID_URL, url)
2776 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2778 video_id = mobj.group('ID')
2781 self.report_video_webpage_download(video_id)
2782 request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
2784 page = urllib2.urlopen(request)
2785 video_webpage = page.read()
2786 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2787 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
2790 # Start extracting information
2791 self.report_information_extraction(video_id)
2793 # Extract information
2794 video_info = self._parse_page(video_webpage)
2797 if 'owner' not in video_info:
2798 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
2800 video_uploader = video_info['owner']
2803 if 'title' not in video_info:
2804 self._downloader.trouble(u'ERROR: unable to extract video title')
2806 video_title = video_info['title']
2807 video_title = video_title.decode('utf-8')
2808 video_title = sanitize_title(video_title)
2811 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
2812 simple_title = simple_title.strip(ur'_')
2815 if 'thumbnail' not in video_info:
2816 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
2817 video_thumbnail = ''
2819 video_thumbnail = video_info['thumbnail']
2823 if 'upload_date' in video_info:
2824 upload_time = video_info['upload_date']
2825 timetuple = email.utils.parsedate_tz(upload_time)
2826 if timetuple is not None:
2828 upload_date = time.strftime('%Y%m%d', timetuple[0:9])
2833 video_description = video_info.get('description', 'No description available.')
2835 url_map = video_info['video_urls']
2836 if len(url_map.keys()) > 0:
2837 # Decide which formats to download
2838 req_format = self._downloader.params.get('format', None)
2839 format_limit = self._downloader.params.get('format_limit', None)
2841 if format_limit is not None and format_limit in self._available_formats:
2842 format_list = self._available_formats[self._available_formats.index(format_limit):]
2844 format_list = self._available_formats
2845 existing_formats = [x for x in format_list if x in url_map]
2846 if len(existing_formats) == 0:
2847 self._downloader.trouble(u'ERROR: no known formats available for video')
2849 if req_format is None:
2850 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
2851 elif req_format == '-1':
2852 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
2855 if req_format not in url_map:
2856 self._downloader.trouble(u'ERROR: requested format not available')
2858 video_url_list = [(req_format, url_map[req_format])] # Specific format
2860 for format_param, video_real_url in video_url_list:
2862 # At this point we have a new video
2863 self._downloader.increment_downloads()
2866 video_extension = self._video_extensions.get(format_param, 'mp4')
2869 # Process video information
2870 self._downloader.process_info({
2871 'id': video_id.decode('utf-8'),
2872 'url': video_real_url.decode('utf-8'),
2873 'uploader': video_uploader.decode('utf-8'),
2874 'upload_date': upload_date,
2875 'title': video_title,
2876 'stitle': simple_title,
2877 'ext': video_extension.decode('utf-8'),
2878 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
2879 'thumbnail': video_thumbnail.decode('utf-8'),
2880 'description': video_description.decode('utf-8'),
2883 except UnavailableVideoError, err:
2884 self._downloader.trouble(u'\nERROR: unable to download video')
2886 class BlipTVIE(InfoExtractor):
2887 """Information extractor for blip.tv"""
2889 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
2890 _URL_EXT = r'^.*\.([a-z0-9]+)$'
2894 return (re.match(BlipTVIE._VALID_URL, url) is not None)
2896 def report_extraction(self, file_id):
2897 """Report information extraction."""
2898 self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
2900 def _simplify_title(self, title):
2901 res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
2902 res = res.strip(ur'_')
2905 def _real_extract(self, url):
2906 mobj = re.match(self._VALID_URL, url)
2908 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2915 json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
2916 request = urllib2.Request(json_url)
2917 self.report_extraction(mobj.group(1))
2919 json_code = urllib2.urlopen(request).read()
2920 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2921 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
2924 json_data = json.loads(json_code)
2925 if 'Post' in json_data:
2926 data = json_data['Post']
2930 upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
2931 video_url = data['media']['url']
2932 umobj = re.match(self._URL_EXT, video_url)
2934 raise ValueError('Can not determine filename extension')
2935 ext = umobj.group(1)
2937 self._downloader.increment_downloads()
2940 'id': data['item_id'],
2942 'uploader': data['display_name'],
2943 'upload_date': upload_date,
2944 'title': data['title'],
2945 'stitle': self._simplify_title(data['title']),
2947 'format': data['media']['mimeType'],
2948 'thumbnail': data['thumbnailUrl'],
2949 'description': data['description'],
2950 'player_url': data['embedUrl']
2952 except (ValueError,KeyError), err:
2953 self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
2957 self._downloader.process_info(info)
2958 except UnavailableVideoError, err:
2959 self._downloader.trouble(u'\nERROR: unable to download video')
2962 class MyVideoIE(InfoExtractor):
2963 """Information Extractor for myvideo.de."""
2965 _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
2967 def __init__(self, downloader=None):
2968 InfoExtractor.__init__(self, downloader)
2972 return (re.match(MyVideoIE._VALID_URL, url) is not None)
2974 def report_download_webpage(self, video_id):
2975 """Report webpage download."""
2976 self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
2978 def report_extraction(self, video_id):
2979 """Report information extraction."""
2980 self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
2982 def _real_initialize(self):
2985 def _real_extract(self,url):
2986 mobj = re.match(self._VALID_URL, url)
2988 self._download.trouble(u'ERROR: invalid URL: %s' % url)
2991 video_id = mobj.group(1)
2992 simple_title = mobj.group(2).decode('utf-8')
2993 # should actually not be necessary
2994 simple_title = sanitize_title(simple_title)
2995 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
2998 request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
3000 self.report_download_webpage(video_id)
3001 webpage = urllib2.urlopen(request).read()
3002 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
3003 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
3006 self.report_extraction(video_id)
3007 mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
3010 self._downloader.trouble(u'ERROR: unable to extract media URL')
3012 video_url = mobj.group(1) + ('/%s.flv' % video_id)
3014 mobj = re.search('<title>([^<]+)</title>', webpage)
3016 self._downloader.trouble(u'ERROR: unable to extract title')
3019 video_title = mobj.group(1)
3020 video_title = sanitize_title(video_title)
3024 self._downloader.process_info({
3028 'upload_date': u'NA',
3029 'title': video_title,
3030 'stitle': simple_title,
3035 except UnavailableVideoError:
3036 self._downloader.trouble(u'\nERROR: Unable to download video')
3038 class ComedyCentralIE(InfoExtractor):
3039 """Information extractor for The Daily Show and Colbert Report """
3041 _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
3045 return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
3047 def report_extraction(self, episode_id):
3048 self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
3050 def report_config_download(self, episode_id):
3051 self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
3053 def report_player_url(self, episode_id):
3054 self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
3056 def _simplify_title(self, title):
3057 res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
3058 res = res.strip(ur'_')
3061 def _real_extract(self, url):
3062 mobj = re.match(self._VALID_URL, url)
3064 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3067 if mobj.group('shortname'):
3068 if mobj.group('shortname') in ('tds', 'thedailyshow'):
3069 url = 'http://www.thedailyshow.com/full-episodes/'
3071 url = 'http://www.colbertnation.com/full-episodes/'
3072 mobj = re.match(self._VALID_URL, url)
3073 assert mobj is not None
3075 dlNewest = not mobj.group('episode')
3077 epTitle = mobj.group('showname')
3079 epTitle = mobj.group('episode')
3081 req = urllib2.Request(url)
3082 self.report_extraction(epTitle)
3084 htmlHandle = urllib2.urlopen(req)
3085 html = htmlHandle.read()
3086 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
3087 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
3090 url = htmlHandle.geturl()
3091 mobj = re.match(self._VALID_URL, url)
3093 self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
3095 if mobj.group('episode') == '':
3096 self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
3098 epTitle = mobj.group('episode')
3100 mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:([^:]*):)(.*?))"/>', html)
3101 if len(mMovieParams) == 0:
3102 self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
3104 show_id = mMovieParams[0][2]
3105 ACT_COUNT = { # TODO: Detect this dynamically
3106 'thedailyshow.com': 4,
3107 'colbertnation.com': 3,
3110 'thedailyshow.com': 1,
3111 'colbertnation.com': 1,
3114 first_player_url = mMovieParams[0][0]
3115 startMediaNum = int(mMovieParams[0][3]) + OFFSET
3116 movieId = mMovieParams[0][1]
3118 playerReq = urllib2.Request(first_player_url)
3119 self.report_player_url(epTitle)
3121 playerResponse = urllib2.urlopen(playerReq)
3122 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
3123 self._downloader.trouble(u'ERROR: unable to download player: %s' % unicode(err))
3125 player_url = playerResponse.geturl()
3127 for actNum in range(ACT_COUNT):
3128 mediaNum = startMediaNum + actNum
3129 mediaId = movieId + str(mediaNum)
3130 configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
3131 urllib.urlencode({'uri': mediaId}))
3132 configReq = urllib2.Request(configUrl)
3133 self.report_config_download(epTitle)
3135 configXml = urllib2.urlopen(configReq).read()
3136 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
3137 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
3140 cdoc = xml.etree.ElementTree.fromstring(configXml)
3142 for rendition in cdoc.findall('.//rendition'):
3143 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
3147 self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum) + ': No videos found')
3150 # For now, just pick the highest bitrate
3151 format,video_url = turls[-1]
3153 self._downloader.increment_downloads()
3155 effTitle = show_id.replace('.com', '') + '-' + epTitle
3157 'id': str(mediaNum),
3159 'uploader': show_id,
3160 'upload_date': 'NA',
3162 'stitle': self._simplify_title(effTitle),
3166 'description': 'TODO: Not yet supported',
3167 'player_url': player_url
3171 self._downloader.process_info(info)
3172 except UnavailableVideoError, err:
3173 self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum))
3177 class PostProcessor(object):
3178 """Post Processor class.
3180 PostProcessor objects can be added to downloaders with their
3181 add_post_processor() method. When the downloader has finished a
3182 successful download, it will take its internal chain of PostProcessors
3183 and start calling the run() method on each one of them, first with
3184 an initial argument and then with the returned value of the previous
3187 The chain will be stopped if one of them ever returns None or the end
3188 of the chain is reached.
3190 PostProcessor objects follow a "mutual registration" process similar
3191 to InfoExtractor objects.
3196 def __init__(self, downloader=None):
3197 self._downloader = downloader
3199 def set_downloader(self, downloader):
3200 """Sets the downloader for this PP."""
3201 self._downloader = downloader
3203 def run(self, information):
3204 """Run the PostProcessor.
3206 The "information" argument is a dictionary like the ones
3207 composed by InfoExtractors. The only difference is that this
3208 one has an extra field called "filepath" that points to the
3211 When this method returns None, the postprocessing chain is
3212 stopped. However, this method may return an information
3213 dictionary that will be passed to the next postprocessing
3214 object in the chain. It can be the one it received after
3215 changing some fields.
3217 In addition, this method may raise a PostProcessingError
3218 exception that will be taken into account by the downloader
3221 return information # by default, do nothing
3224 class FFmpegExtractAudioPP(PostProcessor):
3226 def __init__(self, downloader=None, preferredcodec=None):
3227 PostProcessor.__init__(self, downloader)
3228 if preferredcodec is None:
3229 preferredcodec = 'best'
3230 self._preferredcodec = preferredcodec
3233 def get_audio_codec(path):
3235 cmd = ['ffprobe', '-show_streams', '--', path]
3236 handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
3237 output = handle.communicate()[0]
3238 if handle.wait() != 0:
3240 except (IOError, OSError):
3243 for line in output.split('\n'):
3244 if line.startswith('codec_name='):
3245 audio_codec = line.split('=')[1].strip()
3246 elif line.strip() == 'codec_type=audio' and audio_codec is not None:
3251 def run_ffmpeg(path, out_path, codec, more_opts):
3253 cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
3254 ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
3256 except (IOError, OSError):
3259 def run(self, information):
3260 path = information['filepath']
3262 filecodec = self.get_audio_codec(path)
3263 if filecodec is None:
3264 self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
3268 if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
3269 if filecodec == 'aac' or filecodec == 'mp3':
3270 # Lossless if possible
3272 extension = filecodec
3273 if filecodec == 'aac':
3274 more_opts = ['-f', 'adts']
3277 acodec = 'libmp3lame'
3279 more_opts = ['-ab', '128k']
3281 # We convert the audio (lossy)
3282 acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
3283 extension = self._preferredcodec
3284 more_opts = ['-ab', '128k']
3285 if self._preferredcodec == 'aac':
3286 more_opts += ['-f', 'adts']
3288 (prefix, ext) = os.path.splitext(path)
3289 new_path = prefix + '.' + extension
3290 self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path)
3291 status = self.run_ffmpeg(path, new_path, acodec, more_opts)
3294 self._downloader.to_stderr(u'WARNING: error running ffmpeg')
3299 except (IOError, OSError):
3300 self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
3303 information['filepath'] = new_path
3307 def updateSelf(downloader, filename):
3308 ''' Update the program file with the latest version from the repository '''
3309 # Note: downloader only used for options
3310 if not os.access(filename, os.W_OK):
3311 sys.exit('ERROR: no write permissions on %s' % filename)
3313 downloader.to_screen('Updating to latest version...')
3317 urlh = urllib.urlopen(UPDATE_URL)
3318 newcontent = urlh.read()
3321 except (IOError, OSError), err:
3322 sys.exit('ERROR: unable to download latest version')
3325 outf = open(filename, 'wb')
3327 outf.write(newcontent)
3330 except (IOError, OSError), err:
3331 sys.exit('ERROR: unable to overwrite current version')
3333 downloader.to_screen('Updated youtube-dl. Restart to use the new version.')
3340 def _format_option_string(option):
3341 ''' ('-o', '--option') -> -o, --format METAVAR'''
3345 if option._short_opts: opts.append(option._short_opts[0])
3346 if option._long_opts: opts.append(option._long_opts[0])
3347 if len(opts) > 1: opts.insert(1, ', ')
3349 if option.takes_value(): opts.append(' %s' % option.metavar)
3351 return "".join(opts)
3353 def _find_term_columns():
3354 columns = os.environ.get('COLUMNS', None)
3359 sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
3360 out,err = sp.communicate()
3361 return int(out.split()[1])
3367 max_help_position = 80
3369 # No need to wrap help messages if we're on a wide console
3370 columns = _find_term_columns()
3371 if columns: max_width = columns
3373 fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
3374 fmt.format_option_strings = _format_option_string
3377 'version' : __version__,
3379 'usage' : '%prog [options] url...',
3380 'conflict_handler' : 'resolve',
3383 parser = optparse.OptionParser(**kw)
3386 general = optparse.OptionGroup(parser, 'General Options')
3387 authentication = optparse.OptionGroup(parser, 'Authentication Options')
3388 video_format = optparse.OptionGroup(parser, 'Video Format Options')
3389 postproc = optparse.OptionGroup(parser, 'Post-processing Options')
3390 filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
3391 verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
3393 general.add_option('-h', '--help',
3394 action='help', help='print this help text and exit')
3395 general.add_option('-v', '--version',
3396 action='version', help='print program version and exit')
3397 general.add_option('-U', '--update',
3398 action='store_true', dest='update_self', help='update this program to latest version')
3399 general.add_option('-i', '--ignore-errors',
3400 action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
3401 general.add_option('-r', '--rate-limit',
3402 dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
3403 general.add_option('-R', '--retries',
3404 dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
3405 general.add_option('--playlist-start',
3406 dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
3407 general.add_option('--playlist-end',
3408 dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
3409 general.add_option('--dump-user-agent',
3410 action='store_true', dest='dump_user_agent',
3411 help='display the current browser identification', default=False)
3413 authentication.add_option('-u', '--username',
3414 dest='username', metavar='USERNAME', help='account username')
3415 authentication.add_option('-p', '--password',
3416 dest='password', metavar='PASSWORD', help='account password')
3417 authentication.add_option('-n', '--netrc',
3418 action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
3421 video_format.add_option('-f', '--format',
3422 action='store', dest='format', metavar='FORMAT', help='video format code')
3423 video_format.add_option('--all-formats',
3424 action='store_const', dest='format', help='download all available video formats', const='-1')
3425 video_format.add_option('--max-quality',
3426 action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
3429 verbosity.add_option('-q', '--quiet',
3430 action='store_true', dest='quiet', help='activates quiet mode', default=False)
3431 verbosity.add_option('-s', '--simulate',
3432 action='store_true', dest='simulate', help='do not download video', default=False)
3433 verbosity.add_option('-g', '--get-url',
3434 action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
3435 verbosity.add_option('-e', '--get-title',
3436 action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
3437 verbosity.add_option('--get-thumbnail',
3438 action='store_true', dest='getthumbnail',
3439 help='simulate, quiet but print thumbnail URL', default=False)
3440 verbosity.add_option('--get-description',
3441 action='store_true', dest='getdescription',
3442 help='simulate, quiet but print video description', default=False)
3443 verbosity.add_option('--get-filename',
3444 action='store_true', dest='getfilename',
3445 help='simulate, quiet but print output filename', default=False)
3446 verbosity.add_option('--no-progress',
3447 action='store_true', dest='noprogress', help='do not print progress bar', default=False)
3448 verbosity.add_option('--console-title',
3449 action='store_true', dest='consoletitle',
3450 help='display progress in console titlebar', default=False)
3453 filesystem.add_option('-t', '--title',
3454 action='store_true', dest='usetitle', help='use title in file name', default=False)
3455 filesystem.add_option('-l', '--literal',
3456 action='store_true', dest='useliteral', help='use literal title in file name', default=False)
3457 filesystem.add_option('-A', '--auto-number',
3458 action='store_true', dest='autonumber',
3459 help='number downloaded files starting from 00000', default=False)
3460 filesystem.add_option('-o', '--output',
3461 dest='outtmpl', metavar='TEMPLATE', help='output filename template')
3462 filesystem.add_option('-a', '--batch-file',
3463 dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
3464 filesystem.add_option('-w', '--no-overwrites',
3465 action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
3466 filesystem.add_option('-c', '--continue',
3467 action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
3468 filesystem.add_option('--cookies',
3469 dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
3470 filesystem.add_option('--no-part',
3471 action='store_true', dest='nopart', help='do not use .part files', default=False)
3472 filesystem.add_option('--no-mtime',
3473 action='store_false', dest='updatetime',
3474 help='do not use the Last-modified header to set the file modification time', default=True)
3475 filesystem.add_option('--write-description',
3476 action='store_true', dest='writedescription',
3477 help='write video description to a .description file', default=False)
3478 filesystem.add_option('--write-info-json',
3479 action='store_true', dest='writeinfojson',
3480 help='write video metadata to a .info.json file', default=False)
3483 postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
3484 help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
3485 postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
3486 help='"best", "aac" or "mp3"; best by default')
3489 parser.add_option_group(general)
3490 parser.add_option_group(filesystem)
3491 parser.add_option_group(verbosity)
3492 parser.add_option_group(video_format)
3493 parser.add_option_group(authentication)
3494 parser.add_option_group(postproc)
3496 opts, args = parser.parse_args()
3498 return parser, opts, args
3501 parser, opts, args = parseOpts()
3503 # Open appropriate CookieJar
3504 if opts.cookiefile is None:
3505 jar = cookielib.CookieJar()
3508 jar = cookielib.MozillaCookieJar(opts.cookiefile)
3509 if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
3511 except (IOError, OSError), err:
3512 sys.exit(u'ERROR: unable to open cookie file')
3515 if opts.dump_user_agent:
3516 print std_headers['User-Agent']
3519 # General configuration
3520 cookie_processor = urllib2.HTTPCookieProcessor(jar)
3521 opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
3522 urllib2.install_opener(opener)
3523 socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
3525 # Batch file verification
3527 if opts.batchfile is not None:
3529 if opts.batchfile == '-':
3532 batchfd = open(opts.batchfile, 'r')
3533 batchurls = batchfd.readlines()
3534 batchurls = [x.strip() for x in batchurls]
3535 batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
3537 sys.exit(u'ERROR: batch file could not be read')
3538 all_urls = batchurls + args
3540 # Conflicting, missing and erroneous options
3541 if opts.usenetrc and (opts.username is not None or opts.password is not None):
3542 parser.error(u'using .netrc conflicts with giving username/password')
3543 if opts.password is not None and opts.username is None:
3544 parser.error(u'account username missing')
3545 if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
3546 parser.error(u'using output template conflicts with using title, literal title or auto number')
3547 if opts.usetitle and opts.useliteral:
3548 parser.error(u'using title conflicts with using literal title')
3549 if opts.username is not None and opts.password is None:
3550 opts.password = getpass.getpass(u'Type account password and press return:')
3551 if opts.ratelimit is not None:
3552 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
3553 if numeric_limit is None:
3554 parser.error(u'invalid rate limit specified')
3555 opts.ratelimit = numeric_limit
3556 if opts.retries is not None:
3558 opts.retries = long(opts.retries)
3559 except (TypeError, ValueError), err:
3560 parser.error(u'invalid retry count specified')
3562 opts.playliststart = int(opts.playliststart)
3563 if opts.playliststart <= 0:
3564 raise ValueError(u'Playlist start must be positive')
3565 except (TypeError, ValueError), err:
3566 parser.error(u'invalid playlist start number specified')
3568 opts.playlistend = int(opts.playlistend)
3569 if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
3570 raise ValueError(u'Playlist end must be greater than playlist start')
3571 except (TypeError, ValueError), err:
3572 parser.error(u'invalid playlist end number specified')
3573 if opts.extractaudio:
3574 if opts.audioformat not in ['best', 'aac', 'mp3']:
3575 parser.error(u'invalid audio format specified')
3577 # Information extractors
3578 youtube_ie = YoutubeIE()
3579 metacafe_ie = MetacafeIE(youtube_ie)
3580 dailymotion_ie = DailymotionIE()
3581 youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
3582 youtube_user_ie = YoutubeUserIE(youtube_ie)
3583 youtube_search_ie = YoutubeSearchIE(youtube_ie)
3584 google_ie = GoogleIE()
3585 google_search_ie = GoogleSearchIE(google_ie)
3586 photobucket_ie = PhotobucketIE()
3587 yahoo_ie = YahooIE()
3588 yahoo_search_ie = YahooSearchIE(yahoo_ie)
3589 deposit_files_ie = DepositFilesIE()
3590 facebook_ie = FacebookIE()
3591 bliptv_ie = BlipTVIE()
3592 vimeo_ie = VimeoIE()
3593 myvideo_ie = MyVideoIE()
3594 comedycentral_ie = ComedyCentralIE()
3596 generic_ie = GenericIE()
3599 fd = FileDownloader({
3600 'usenetrc': opts.usenetrc,
3601 'username': opts.username,
3602 'password': opts.password,
3603 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
3604 'forceurl': opts.geturl,
3605 'forcetitle': opts.gettitle,
3606 'forcethumbnail': opts.getthumbnail,
3607 'forcedescription': opts.getdescription,
3608 'forcefilename': opts.getfilename,
3609 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
3610 'format': opts.format,
3611 'format_limit': opts.format_limit,
3612 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
3613 or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
3614 or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
3615 or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
3616 or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
3617 or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
3618 or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
3619 or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
3620 or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
3621 or u'%(id)s.%(ext)s'),
3622 'ignoreerrors': opts.ignoreerrors,
3623 'ratelimit': opts.ratelimit,
3624 'nooverwrites': opts.nooverwrites,
3625 'retries': opts.retries,
3626 'continuedl': opts.continue_dl,
3627 'noprogress': opts.noprogress,
3628 'playliststart': opts.playliststart,
3629 'playlistend': opts.playlistend,
3630 'logtostderr': opts.outtmpl == '-',
3631 'consoletitle': opts.consoletitle,
3632 'nopart': opts.nopart,
3633 'updatetime': opts.updatetime,
3634 'writedescription': opts.writedescription,
3635 'writeinfojson': opts.writeinfojson,
3637 fd.add_info_extractor(youtube_search_ie)
3638 fd.add_info_extractor(youtube_pl_ie)
3639 fd.add_info_extractor(youtube_user_ie)
3640 fd.add_info_extractor(metacafe_ie)
3641 fd.add_info_extractor(dailymotion_ie)
3642 fd.add_info_extractor(youtube_ie)
3643 fd.add_info_extractor(google_ie)
3644 fd.add_info_extractor(google_search_ie)
3645 fd.add_info_extractor(photobucket_ie)
3646 fd.add_info_extractor(yahoo_ie)
3647 fd.add_info_extractor(yahoo_search_ie)
3648 fd.add_info_extractor(deposit_files_ie)
3649 fd.add_info_extractor(facebook_ie)
3650 fd.add_info_extractor(bliptv_ie)
3651 fd.add_info_extractor(vimeo_ie)
3652 fd.add_info_extractor(myvideo_ie)
3653 fd.add_info_extractor(comedycentral_ie)
3655 # This must come last since it's the
3656 # fallback if none of the others work
3657 fd.add_info_extractor(generic_ie)
3660 if opts.extractaudio:
3661 fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
3664 if opts.update_self:
3665 updateSelf(fd, sys.argv[0])
3668 if len(all_urls) < 1:
3669 if not opts.update_self:
3670 parser.error(u'you must provide at least one URL')
3673 retcode = fd.download(all_urls)
3675 # Dump cookie jar if requested
3676 if opts.cookiefile is not None:
3679 except (IOError, OSError), err:
3680 sys.exit(u'ERROR: unable to save cookie jar')
3685 if __name__ == '__main__':
3688 except DownloadError:
3690 except SameFileError:
3691 sys.exit(u'ERROR: fixed output name but more than one file to download')
3692 except KeyboardInterrupt:
3693 sys.exit(u'\nERROR: Interrupted by user')
3695 # vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: