2 # -*- coding: utf-8 -*-
3 # Author: Ricardo Garcia Gonzalez
4 # Author: Danny Colligan
5 # Author: Benjamin Johnson
6 # Author: Vasyl' Vavrychuk
7 # Author: Witold Baryluk
8 # Author: Paweł Paprota
9 # Author: Gergely Imreh
10 # Author: Philipp Hagemeister <phihag@phihag.de>
11 # License: Public domain code
12 from __future__ import with_statement
38 import cStringIO as StringIO
42 # parse_qs was moved from the cgi module to the urlparse module recently.
44 from urlparse import parse_qs
46 from cgi import parse_qs
50 except ImportError: # Python < 2.6
54 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:2.0b11) Gecko/20100101 Firefox/4.0b11',
55 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
56 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
57 'Accept-Encoding': 'gzip, deflate',
58 'Accept-Language': 'en-us,en;q=0.5',
61 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
65 except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
71 def raiseError(msg, i):
72 raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]))
73 def skipSpace(i, expectMore=True):
74 while i < len(s) and s[i] in ' \t\r\n':
78 raiseError('Premature end', i)
80 def decodeEscape(match):
96 return unichr(int(esc[1:5], 16))
97 if len(esc) == 5+6 and esc[5:7] == '\\u':
98 hi = int(esc[1:5], 16)
99 low = int(esc[7:11], 16)
100 return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000)
101 raise ValueError('Unknown escape ' + str(esc))
108 while s[e-bslashes-1] == '\\':
110 if bslashes % 2 == 1:
114 rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)')
115 stri = rexp.sub(decodeEscape, s[i:e])
121 if s[i] == '}': # Empty dictionary
125 raiseError('Expected a string object key', i)
126 i,key = parseString(i)
128 if i >= len(s) or s[i] != ':':
129 raiseError('Expected a colon', i)
136 raiseError('Expected comma or closing curly brace', i)
141 if s[i] == ']': # Empty array
146 i = skipSpace(i) # Raise exception if premature end
150 raiseError('Expected a comma or closing bracket', i)
152 def parseDiscrete(i):
153 for k,v in {'true': True, 'false': False, 'null': None}.items():
154 if s.startswith(k, i):
156 raiseError('Not a boolean (or null)', i)
158 mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:])
160 raiseError('Not a number', i)
162 if '.' in nums or 'e' in nums or 'E' in nums:
163 return (i+len(nums), float(nums))
164 return (i+len(nums), int(nums))
165 CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete}
168 i,res = CHARMAP.get(s[i], parseNumber)(i)
169 i = skipSpace(i, False)
173 raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')')
176 def preferredencoding():
177 """Get preferred encoding.
179 Returns the best encoding scheme for the system, based on
180 locale.getpreferredencoding() and some further tweaks.
182 def yield_preferredencoding():
184 pref = locale.getpreferredencoding()
190 return yield_preferredencoding().next()
192 def htmlentity_transform(matchobj):
193 """Transforms an HTML entity to a Unicode character.
195 This function receives a match object and is intended to be used with
196 the re.sub() function.
198 entity = matchobj.group(1)
200 # Known non-numeric HTML entity
201 if entity in htmlentitydefs.name2codepoint:
202 return unichr(htmlentitydefs.name2codepoint[entity])
205 mobj = re.match(ur'(?u)#(x?\d+)', entity)
207 numstr = mobj.group(1)
208 if numstr.startswith(u'x'):
210 numstr = u'0%s' % numstr
213 return unichr(long(numstr, base))
215 # Unknown entity in name, return its literal representation
216 return (u'&%s;' % entity)
218 def sanitize_title(utitle):
219 """Sanitizes a video title so it could be used as part of a filename."""
220 utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
221 return utitle.replace(unicode(os.sep), u'%')
223 def sanitize_open(filename, open_mode):
224 """Try to open the given filename, and slightly tweak it if this fails.
226 Attempts to open the given filename. If this fails, it tries to change
227 the filename slightly, step by step, until it's either able to open it
228 or it fails and raises a final exception, like the standard open()
231 It returns the tuple (stream, definitive_file_name).
235 if sys.platform == 'win32':
237 msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
238 return (sys.stdout, filename)
239 stream = open(filename, open_mode)
240 return (stream, filename)
241 except (IOError, OSError), err:
242 # In case of error, try to remove win32 forbidden chars
243 filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
245 # An exception here should be caught in the caller
246 stream = open(filename, open_mode)
247 return (stream, filename)
249 def timeconvert(timestr):
250 """Convert RFC 2822 defined time string into system timestamp"""
252 timetuple = email.utils.parsedate_tz(timestr)
253 if timetuple is not None:
254 timestamp = email.utils.mktime_tz(timetuple)
257 class DownloadError(Exception):
258 """Download Error exception.
260 This exception may be thrown by FileDownloader objects if they are not
261 configured to continue on errors. They will contain the appropriate
266 class SameFileError(Exception):
267 """Same File exception.
269 This exception will be thrown by FileDownloader objects if they detect
270 multiple files would have to be downloaded to the same file on disk.
274 class PostProcessingError(Exception):
275 """Post Processing exception.
277 This exception may be raised by PostProcessor's .run() method to
278 indicate an error in the postprocessing task.
282 class UnavailableVideoError(Exception):
283 """Unavailable Format exception.
285 This exception will be thrown when a video is requested
286 in a format that is not available for that video.
290 class ContentTooShortError(Exception):
291 """Content Too Short exception.
293 This exception may be raised by FileDownloader objects when a file they
294 download is too small for what the server announced first, indicating
295 the connection was probably interrupted.
301 def __init__(self, downloaded, expected):
302 self.downloaded = downloaded
303 self.expected = expected
305 class YoutubeDLHandler(urllib2.HTTPHandler):
306 """Handler for HTTP requests and responses.
308 This class, when installed with an OpenerDirector, automatically adds
309 the standard headers to every HTTP request and handles gzipped and
310 deflated responses from web servers. If compression is to be avoided in
311 a particular request, the original request in the program code only has
312 to include the HTTP header "Youtubedl-No-Compression", which will be
313 removed before making the real request.
315 Part of this code was copied from:
317 http://techknack.net/python-urllib2-handlers/
319 Andrew Rowls, the author of that code, agreed to release it to the
326 return zlib.decompress(data, -zlib.MAX_WBITS)
328 return zlib.decompress(data)
331 def addinfourl_wrapper(stream, headers, url, code):
332 if hasattr(urllib2.addinfourl, 'getcode'):
333 return urllib2.addinfourl(stream, headers, url, code)
334 ret = urllib2.addinfourl(stream, headers, url)
338 def http_request(self, req):
339 for h in std_headers:
342 req.add_header(h, std_headers[h])
343 if 'Youtubedl-no-compression' in req.headers:
344 if 'Accept-encoding' in req.headers:
345 del req.headers['Accept-encoding']
346 del req.headers['Youtubedl-no-compression']
349 def http_response(self, req, resp):
352 if resp.headers.get('Content-encoding', '') == 'gzip':
353 gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
354 resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
355 resp.msg = old_resp.msg
357 if resp.headers.get('Content-encoding', '') == 'deflate':
358 gz = StringIO.StringIO(self.deflate(resp.read()))
359 resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
360 resp.msg = old_resp.msg
363 class FileDownloader(object):
364 """File Downloader class.
366 File downloader objects are the ones responsible of downloading the
367 actual video file and writing it to disk if the user has requested
368 it, among some other tasks. In most cases there should be one per
369 program. As, given a video URL, the downloader doesn't know how to
370 extract all the needed information, task that InfoExtractors do, it
371 has to pass the URL to one of them.
373 For this, file downloader objects have a method that allows
374 InfoExtractors to be registered in a given order. When it is passed
375 a URL, the file downloader handles it to the first InfoExtractor it
376 finds that reports being able to handle it. The InfoExtractor extracts
377 all the information about the video or videos the URL refers to, and
378 asks the FileDownloader to process the video information, possibly
379 downloading the video.
381 File downloaders accept a lot of parameters. In order not to saturate
382 the object constructor with arguments, it receives a dictionary of
383 options instead. These options are available through the params
384 attribute for the InfoExtractors to use. The FileDownloader also
385 registers itself as the downloader in charge for the InfoExtractors
386 that are added to it, so this is a "mutual registration".
390 username: Username for authentication purposes.
391 password: Password for authentication purposes.
392 usenetrc: Use netrc for authentication instead.
393 quiet: Do not print messages to stdout.
394 forceurl: Force printing final URL.
395 forcetitle: Force printing title.
396 forcethumbnail: Force printing thumbnail URL.
397 forcedescription: Force printing description.
398 forcefilename: Force printing final filename.
399 simulate: Do not download the video files.
400 format: Video format code.
401 format_limit: Highest quality format to try.
402 outtmpl: Template for output names.
403 ignoreerrors: Do not stop on download errors.
404 ratelimit: Download speed limit, in bytes/sec.
405 nooverwrites: Prevent overwriting files.
406 retries: Number of times to retry for HTTP error 5xx
407 continuedl: Try to continue downloads if possible.
408 noprogress: Do not print the progress bar.
409 playliststart: Playlist item to start at.
410 playlistend: Playlist item to end at.
411 logtostderr: Log messages to stderr instead of stdout.
412 consoletitle: Display progress in console window's titlebar.
413 nopart: Do not use temporary .part files.
414 updatetime: Use the Last-modified header to set output file timestamps.
415 writedescription: Write the video description to a .description file
416 writeinfojson: Write the video description to a .info.json file
422 _download_retcode = None
423 _num_downloads = None
426 def __init__(self, params):
427 """Create a FileDownloader object with the given options."""
430 self._download_retcode = 0
431 self._num_downloads = 0
432 self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
436 def pmkdir(filename):
437 """Create directory components in filename. Similar to Unix "mkdir -p"."""
438 components = filename.split(os.sep)
439 aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
440 aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
441 for dir in aggregate:
442 if not os.path.exists(dir):
446 def format_bytes(bytes):
449 if type(bytes) is str:
454 exponent = long(math.log(bytes, 1024.0))
455 suffix = 'bkMGTPEZY'[exponent]
456 converted = float(bytes) / float(1024**exponent)
457 return '%.2f%s' % (converted, suffix)
460 def calc_percent(byte_counter, data_len):
463 return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
466 def calc_eta(start, now, total, current):
470 if current == 0 or dif < 0.001: # One millisecond
472 rate = float(current) / dif
473 eta = long((float(total) - float(current)) / rate)
474 (eta_mins, eta_secs) = divmod(eta, 60)
477 return '%02d:%02d' % (eta_mins, eta_secs)
480 def calc_speed(start, now, bytes):
482 if bytes == 0 or dif < 0.001: # One millisecond
483 return '%10s' % '---b/s'
484 return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
487 def best_block_size(elapsed_time, bytes):
488 new_min = max(bytes / 2.0, 1.0)
489 new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
490 if elapsed_time < 0.001:
492 rate = bytes / elapsed_time
500 def parse_bytes(bytestr):
501 """Parse a string indicating a byte quantity into a long integer."""
502 matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
505 number = float(matchobj.group(1))
506 multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
507 return long(round(number * multiplier))
509 def add_info_extractor(self, ie):
510 """Add an InfoExtractor object to the end of the list."""
512 ie.set_downloader(self)
514 def add_post_processor(self, pp):
515 """Add a PostProcessor object to the end of the chain."""
517 pp.set_downloader(self)
519 def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
520 """Print message to stdout if not in quiet mode."""
522 if not self.params.get('quiet', False):
523 terminator = [u'\n', u''][skip_eol]
524 print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
525 self._screen_file.flush()
526 except (UnicodeEncodeError), err:
527 if not ignore_encoding_errors:
530 def to_stderr(self, message):
531 """Print message to stderr."""
532 print >>sys.stderr, message.encode(preferredencoding())
534 def to_cons_title(self, message):
535 """Set console/terminal window title to message."""
536 if not self.params.get('consoletitle', False):
538 if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
539 # c_wchar_p() might not be necessary if `message` is
540 # already of type unicode()
541 ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
542 elif 'TERM' in os.environ:
543 sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
545 def fixed_template(self):
546 """Checks if the output template is fixed."""
547 return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
549 def trouble(self, message=None):
550 """Determine action to take when a download problem appears.
552 Depending on if the downloader has been configured to ignore
553 download errors or not, this method may throw an exception or
554 not when errors are found, after printing the message.
556 if message is not None:
557 self.to_stderr(message)
558 if not self.params.get('ignoreerrors', False):
559 raise DownloadError(message)
560 self._download_retcode = 1
562 def slow_down(self, start_time, byte_counter):
563 """Sleep if the download speed is over the rate limit."""
564 rate_limit = self.params.get('ratelimit', None)
565 if rate_limit is None or byte_counter == 0:
568 elapsed = now - start_time
571 speed = float(byte_counter) / elapsed
572 if speed > rate_limit:
573 time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
575 def temp_name(self, filename):
576 """Returns a temporary filename for the given filename."""
577 if self.params.get('nopart', False) or filename == u'-' or \
578 (os.path.exists(filename) and not os.path.isfile(filename)):
580 return filename + u'.part'
582 def undo_temp_name(self, filename):
583 if filename.endswith(u'.part'):
584 return filename[:-len(u'.part')]
587 def try_rename(self, old_filename, new_filename):
589 if old_filename == new_filename:
591 os.rename(old_filename, new_filename)
592 except (IOError, OSError), err:
593 self.trouble(u'ERROR: unable to rename file')
595 def try_utime(self, filename, last_modified_hdr):
596 """Try to set the last-modified time of the given file."""
597 if last_modified_hdr is None:
599 if not os.path.isfile(filename):
601 timestr = last_modified_hdr
604 filetime = timeconvert(timestr)
608 os.utime(filename,(time.time(), filetime))
612 def report_writedescription(self, descfn):
613 """ Report that the description file is being written """
614 self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
616 def report_writeinfojson(self, infofn):
617 """ Report that the metadata file has been written """
618 self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
620 def report_destination(self, filename):
621 """Report destination filename."""
622 self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
624 def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
625 """Report download progress."""
626 if self.params.get('noprogress', False):
628 self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
629 (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
630 self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
631 (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
633 def report_resuming_byte(self, resume_len):
634 """Report attempt to resume at given byte."""
635 self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
637 def report_retry(self, count, retries):
638 """Report retry in case of HTTP error 5xx"""
639 self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
641 def report_file_already_downloaded(self, file_name):
642 """Report file has already been fully downloaded."""
644 self.to_screen(u'[download] %s has already been downloaded' % file_name)
645 except (UnicodeEncodeError), err:
646 self.to_screen(u'[download] The file has already been downloaded')
648 def report_unable_to_resume(self):
649 """Report it was impossible to resume download."""
650 self.to_screen(u'[download] Unable to resume')
652 def report_finish(self):
653 """Report download finished."""
654 if self.params.get('noprogress', False):
655 self.to_screen(u'[download] Download completed')
659 def increment_downloads(self):
660 """Increment the ordinal that assigns a number to each file."""
661 self._num_downloads += 1
663 def prepare_filename(self, info_dict):
664 """Generate the output filename."""
666 template_dict = dict(info_dict)
667 template_dict['epoch'] = unicode(long(time.time()))
668 template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
669 filename = self.params['outtmpl'] % template_dict
671 except (ValueError, KeyError), err:
672 self.trouble(u'ERROR: invalid system charset or erroneous output template')
675 def process_info(self, info_dict):
676 """Process a single dictionary returned by an InfoExtractor."""
677 filename = self.prepare_filename(info_dict)
678 # Do nothing else if in simulate mode
679 if self.params.get('simulate', False):
681 if self.params.get('forcetitle', False):
682 print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
683 if self.params.get('forceurl', False):
684 print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
685 if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
686 print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
687 if self.params.get('forcedescription', False) and 'description' in info_dict:
688 print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
689 if self.params.get('forcefilename', False) and filename is not None:
690 print filename.encode(preferredencoding(), 'xmlcharrefreplace')
696 if self.params.get('nooverwrites', False) and os.path.exists(filename):
697 self.to_stderr(u'WARNING: file exists and will be skipped')
701 self.pmkdir(filename)
702 except (OSError, IOError), err:
703 self.trouble(u'ERROR: unable to create directories: %s' % str(err))
706 if self.params.get('writedescription', False):
708 descfn = filename + '.description'
709 self.report_writedescription(descfn)
710 with contextlib.closing(open(descfn, 'wb')) as descfile:
711 descfile.write(info_dict['description'].encode('utf-8'))
712 except (OSError, IOError):
713 self.trouble(u'ERROR: Cannot write description file: %s' % str(descfn))
716 if self.params.get('writeinfojson', False):
717 infofn = filename + '.info.json'
718 self.report_writeinfojson(infofn)
721 except (NameError,AttributeError):
722 self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
725 with contextlib.closing(open(infofn, 'wb')) as infof:
726 json.dump(info_dict, infof)
727 except (OSError, IOError):
728 self.trouble(u'ERROR: Cannot write metadata to JSON file: %s' % str(infofn))
732 success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
733 except (OSError, IOError), err:
734 raise UnavailableVideoError
735 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
736 self.trouble(u'ERROR: unable to download video data: %s' % str(err))
738 except (ContentTooShortError, ), err:
739 self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
744 self.post_process(filename, info_dict)
745 except (PostProcessingError), err:
746 self.trouble(u'ERROR: postprocessing: %s' % str(err))
749 def download(self, url_list):
750 """Download a given list of URLs."""
751 if len(url_list) > 1 and self.fixed_template():
752 raise SameFileError(self.params['outtmpl'])
755 suitable_found = False
757 # Go to next InfoExtractor if not suitable
758 if not ie.suitable(url):
761 # Suitable InfoExtractor found
762 suitable_found = True
764 # Extract information from URL and process it
767 # Suitable InfoExtractor had been found; go to next URL
770 if not suitable_found:
771 self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
773 return self._download_retcode
775 def post_process(self, filename, ie_info):
776 """Run the postprocessing chain on the given file."""
778 info['filepath'] = filename
784 def _download_with_rtmpdump(self, filename, url, player_url):
785 self.report_destination(filename)
786 tmpfilename = self.temp_name(filename)
788 # Check for rtmpdump first
790 subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
791 except (OSError, IOError):
792 self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
795 # Download using rtmpdump. rtmpdump returns exit code 2 when
796 # the connection was interrumpted and resuming appears to be
797 # possible. This is part of rtmpdump's normal usage, AFAIK.
798 basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
799 retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
800 while retval == 2 or retval == 1:
801 prevsize = os.path.getsize(tmpfilename)
802 self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
803 time.sleep(5.0) # This seems to be needed
804 retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
805 cursize = os.path.getsize(tmpfilename)
806 if prevsize == cursize and retval == 1:
809 self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
810 self.try_rename(tmpfilename, filename)
813 self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
816 def _do_download(self, filename, url, player_url):
817 # Check file already present
818 if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
819 self.report_file_already_downloaded(filename)
822 # Attempt to download using rtmpdump
823 if url.startswith('rtmp'):
824 return self._download_with_rtmpdump(filename, url, player_url)
826 tmpfilename = self.temp_name(filename)
830 # Do not include the Accept-Encoding header
831 headers = {'Youtubedl-no-compression': 'True'}
832 basic_request = urllib2.Request(url, None, headers)
833 request = urllib2.Request(url, None, headers)
835 # Establish possible resume length
836 if os.path.isfile(tmpfilename):
837 resume_len = os.path.getsize(tmpfilename)
841 # Request parameters in case of being able to resume
842 if self.params.get('continuedl', False) and resume_len != 0:
843 self.report_resuming_byte(resume_len)
844 request.add_header('Range','bytes=%d-' % resume_len)
848 retries = self.params.get('retries', 0)
849 while count <= retries:
850 # Establish connection
852 data = urllib2.urlopen(request)
854 except (urllib2.HTTPError, ), err:
855 if (err.code < 500 or err.code >= 600) and err.code != 416:
856 # Unexpected HTTP error
858 elif err.code == 416:
859 # Unable to resume (requested range not satisfiable)
861 # Open the connection again without the range header
862 data = urllib2.urlopen(basic_request)
863 content_length = data.info()['Content-Length']
864 except (urllib2.HTTPError, ), err:
865 if err.code < 500 or err.code >= 600:
868 # Examine the reported length
869 if (content_length is not None and
870 (resume_len - 100 < long(content_length) < resume_len + 100)):
871 # The file had already been fully downloaded.
872 # Explanation to the above condition: in issue #175 it was revealed that
873 # YouTube sometimes adds or removes a few bytes from the end of the file,
874 # changing the file size slightly and causing problems for some users. So
875 # I decided to implement a suggested change and consider the file
876 # completely downloaded if the file size differs less than 100 bytes from
877 # the one in the hard drive.
878 self.report_file_already_downloaded(filename)
879 self.try_rename(tmpfilename, filename)
882 # The length does not match, we start the download over
883 self.report_unable_to_resume()
889 self.report_retry(count, retries)
892 self.trouble(u'ERROR: giving up after %s retries' % retries)
895 data_len = data.info().get('Content-length', None)
896 if data_len is not None:
897 data_len = long(data_len) + resume_len
898 data_len_str = self.format_bytes(data_len)
899 byte_counter = 0 + resume_len
905 data_block = data.read(block_size)
907 if len(data_block) == 0:
909 byte_counter += len(data_block)
911 # Open file just in time
914 (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
915 filename = self.undo_temp_name(tmpfilename)
916 self.report_destination(filename)
917 except (OSError, IOError), err:
918 self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
921 stream.write(data_block)
922 except (IOError, OSError), err:
923 self.trouble(u'\nERROR: unable to write data: %s' % str(err))
925 block_size = self.best_block_size(after - before, len(data_block))
928 percent_str = self.calc_percent(byte_counter, data_len)
929 eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
930 speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
931 self.report_progress(percent_str, data_len_str, speed_str, eta_str)
934 self.slow_down(start, byte_counter - resume_len)
938 if data_len is not None and byte_counter != data_len:
939 raise ContentTooShortError(byte_counter, long(data_len))
940 self.try_rename(tmpfilename, filename)
942 # Update file modification time
943 if self.params.get('updatetime', True):
944 self.try_utime(filename, data.info().get('last-modified', None))
948 class InfoExtractor(object):
949 """Information Extractor class.
951 Information extractors are the classes that, given a URL, extract
952 information from the video (or videos) the URL refers to. This
953 information includes the real video URL, the video title and simplified
954 title, author and others. The information is stored in a dictionary
955 which is then passed to the FileDownloader. The FileDownloader
956 processes this information possibly downloading the video to the file
957 system, among other possible outcomes. The dictionaries must include
958 the following fields:
960 id: Video identifier.
961 url: Final video URL.
962 uploader: Nickname of the video uploader.
963 title: Literal title.
964 stitle: Simplified title.
965 ext: Video filename extension.
966 format: Video format.
967 player_url: SWF Player URL (may be None).
969 The following fields are optional. Their primary purpose is to allow
970 youtube-dl to serve as the backend for a video search function, such
971 as the one in youtube2mp3. They are only used when their respective
972 forced printing functions are called:
974 thumbnail: Full URL to a video thumbnail image.
975 description: One-line video description.
977 Subclasses of this one should re-define the _real_initialize() and
978 _real_extract() methods, as well as the suitable() static method.
979 Probably, they should also be instantiated and added to the main
986 def __init__(self, downloader=None):
987 """Constructor. Receives an optional downloader."""
989 self.set_downloader(downloader)
993 """Receives a URL and returns True if suitable for this IE."""
996 def initialize(self):
997 """Initializes an instance (authentication, etc)."""
999 self._real_initialize()
1002 def extract(self, url):
1003 """Extracts URL information and returns it in list of dicts."""
1005 return self._real_extract(url)
1007 def set_downloader(self, downloader):
1008 """Sets the downloader for this IE."""
1009 self._downloader = downloader
1011 def _real_initialize(self):
1012 """Real initialization process. Redefine in subclasses."""
1015 def _real_extract(self, url):
1016 """Real extraction process. Redefine in subclasses."""
1019 class YoutubeIE(InfoExtractor):
1020 """Information extractor for youtube.com."""
1022 _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
1023 _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
1024 _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
1025 _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
1026 _NETRC_MACHINE = 'youtube'
1027 # Listed in order of quality
1028 _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
1029 _video_extensions = {
1035 '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
1042 return (re.match(YoutubeIE._VALID_URL, url) is not None)
1044 def report_lang(self):
1045 """Report attempt to set language."""
1046 self._downloader.to_screen(u'[youtube] Setting language')
1048 def report_login(self):
1049 """Report attempt to log in."""
1050 self._downloader.to_screen(u'[youtube] Logging in')
1052 def report_age_confirmation(self):
1053 """Report attempt to confirm age."""
1054 self._downloader.to_screen(u'[youtube] Confirming age')
1056 def report_video_webpage_download(self, video_id):
1057 """Report attempt to download video webpage."""
1058 self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
1060 def report_video_info_webpage_download(self, video_id):
1061 """Report attempt to download video info webpage."""
1062 self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
1064 def report_information_extraction(self, video_id):
1065 """Report attempt to extract video information."""
1066 self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
1068 def report_unavailable_format(self, video_id, format):
1069 """Report extracted video URL."""
1070 self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
1072 def report_rtmp_download(self):
1073 """Indicate the download will use the RTMP protocol."""
1074 self._downloader.to_screen(u'[youtube] RTMP download detected')
1076 def _real_initialize(self):
1077 if self._downloader is None:
1082 downloader_params = self._downloader.params
1084 # Attempt to use provided username and password or .netrc data
1085 if downloader_params.get('username', None) is not None:
1086 username = downloader_params['username']
1087 password = downloader_params['password']
1088 elif downloader_params.get('usenetrc', False):
1090 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
1091 if info is not None:
1095 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
1096 except (IOError, netrc.NetrcParseError), err:
1097 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
1101 request = urllib2.Request(self._LANG_URL)
1104 urllib2.urlopen(request).read()
1105 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1106 self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
1109 # No authentication to be performed
1110 if username is None:
1115 'current_form': 'loginForm',
1117 'action_login': 'Log In',
1118 'username': username,
1119 'password': password,
1121 request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
1124 login_results = urllib2.urlopen(request).read()
1125 if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
1126 self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
1128 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1129 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
1135 'action_confirm': 'Confirm',
1137 request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))
1139 self.report_age_confirmation()
1140 age_results = urllib2.urlopen(request).read()
1141 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1142 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
1145 def _real_extract(self, url):
1146 # Extract video id from URL
1147 mobj = re.match(self._VALID_URL, url)
1149 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1151 video_id = mobj.group(2)
1154 self.report_video_webpage_download(video_id)
1155 request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
1157 video_webpage = urllib2.urlopen(request).read()
1158 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1159 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
1162 # Attempt to extract SWF player URL
1163 mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1164 if mobj is not None:
1165 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1170 self.report_video_info_webpage_download(video_id)
1171 for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
1172 video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1173 % (video_id, el_type))
1174 request = urllib2.Request(video_info_url)
1176 video_info_webpage = urllib2.urlopen(request).read()
1177 video_info = parse_qs(video_info_webpage)
1178 if 'token' in video_info:
1180 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1181 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
1183 if 'token' not in video_info:
1184 if 'reason' in video_info:
1185 self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
1187 self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
1190 # Start extracting information
1191 self.report_information_extraction(video_id)
1194 if 'author' not in video_info:
1195 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1197 video_uploader = urllib.unquote_plus(video_info['author'][0])
1200 if 'title' not in video_info:
1201 self._downloader.trouble(u'ERROR: unable to extract video title')
1203 video_title = urllib.unquote_plus(video_info['title'][0])
1204 video_title = video_title.decode('utf-8')
1205 video_title = sanitize_title(video_title)
1208 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1209 simple_title = simple_title.strip(ur'_')
1212 if 'thumbnail_url' not in video_info:
1213 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
1214 video_thumbnail = ''
1215 else: # don't panic if we can't find it
1216 video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
1220 mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
1221 if mobj is not None:
1222 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1223 format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
1224 for expression in format_expressions:
1226 upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
1234 video_description = u'No description available.'
1235 if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False):
1236 warnings.warn(u'You are using an old Python version, install Python 2.6+ or lxml. Falling back to old video description extractor.')
1237 mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
1238 if mobj is not None:
1239 video_description = mobj.group(1).decode('utf-8')
1241 html_parser = lxml.etree.HTMLParser(encoding='utf-8')
1242 vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser)
1243 video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()'))
1244 # TODO use another parser
1247 video_token = urllib.unquote_plus(video_info['token'][0])
1249 # Decide which formats to download
1250 req_format = self._downloader.params.get('format', None)
1252 if 'fmt_url_map' in video_info and len(video_info['fmt_url_map']) >= 1:
1253 url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
1254 format_limit = self._downloader.params.get('format_limit', None)
1255 if format_limit is not None and format_limit in self._available_formats:
1256 format_list = self._available_formats[self._available_formats.index(format_limit):]
1258 format_list = self._available_formats
1259 existing_formats = [x for x in format_list if x in url_map]
1260 if len(existing_formats) == 0:
1261 self._downloader.trouble(u'ERROR: no known formats available for video')
1263 if req_format is None:
1264 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
1265 elif req_format == '-1':
1266 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
1269 if req_format not in url_map:
1270 self._downloader.trouble(u'ERROR: requested format not available')
1272 video_url_list = [(req_format, url_map[req_format])] # Specific format
1274 elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1275 self.report_rtmp_download()
1276 video_url_list = [(None, video_info['conn'][0])]
1279 self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
1282 for format_param, video_real_url in video_url_list:
1283 # At this point we have a new video
1284 self._downloader.increment_downloads()
1287 video_extension = self._video_extensions.get(format_param, 'flv')
1289 # Find the video URL in fmt_url_map or conn paramters
1291 # Process video information
1292 self._downloader.process_info({
1293 'id': video_id.decode('utf-8'),
1294 'url': video_real_url.decode('utf-8'),
1295 'uploader': video_uploader.decode('utf-8'),
1296 'upload_date': upload_date,
1297 'title': video_title,
1298 'stitle': simple_title,
1299 'ext': video_extension.decode('utf-8'),
1300 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
1301 'thumbnail': video_thumbnail.decode('utf-8'),
1302 'description': video_description,
1303 'player_url': player_url,
1305 except UnavailableVideoError, err:
1306 self._downloader.trouble(u'\nERROR: unable to download video')
1309 class MetacafeIE(InfoExtractor):
1310 """Information Extractor for metacafe.com."""
1312 _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
1313 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
1314 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
1317 def __init__(self, youtube_ie, downloader=None):
1318 InfoExtractor.__init__(self, downloader)
1319 self._youtube_ie = youtube_ie
1323 return (re.match(MetacafeIE._VALID_URL, url) is not None)
1325 def report_disclaimer(self):
1326 """Report disclaimer retrieval."""
1327 self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
1329 def report_age_confirmation(self):
1330 """Report attempt to confirm age."""
1331 self._downloader.to_screen(u'[metacafe] Confirming age')
1333 def report_download_webpage(self, video_id):
1334 """Report webpage download."""
1335 self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
1337 def report_extraction(self, video_id):
1338 """Report information extraction."""
1339 self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
1341 def _real_initialize(self):
1342 # Retrieve disclaimer
1343 request = urllib2.Request(self._DISCLAIMER)
1345 self.report_disclaimer()
1346 disclaimer = urllib2.urlopen(request).read()
1347 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1348 self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
1354 'submit': "Continue - I'm over 18",
1356 request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))
1358 self.report_age_confirmation()
1359 disclaimer = urllib2.urlopen(request).read()
1360 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1361 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
1364 def _real_extract(self, url):
1365 # Extract id and simplified title from URL
1366 mobj = re.match(self._VALID_URL, url)
1368 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1371 video_id = mobj.group(1)
1373 # Check if video comes from YouTube
1374 mobj2 = re.match(r'^yt-(.*)$', video_id)
1375 if mobj2 is not None:
1376 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
1379 # At this point we have a new video
1380 self._downloader.increment_downloads()
1382 simple_title = mobj.group(2).decode('utf-8')
1384 # Retrieve video webpage to extract further information
1385 request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
1387 self.report_download_webpage(video_id)
1388 webpage = urllib2.urlopen(request).read()
1389 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1390 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
1393 # Extract URL, uploader and title from webpage
1394 self.report_extraction(video_id)
1395 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
1396 if mobj is not None:
1397 mediaURL = urllib.unquote(mobj.group(1))
1398 video_extension = mediaURL[-3:]
1400 # Extract gdaKey if available
1401 mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
1403 video_url = mediaURL
1405 gdaKey = mobj.group(1)
1406 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
1408 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
1410 self._downloader.trouble(u'ERROR: unable to extract media URL')
1412 vardict = parse_qs(mobj.group(1))
1413 if 'mediaData' not in vardict:
1414 self._downloader.trouble(u'ERROR: unable to extract media URL')
1416 mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
1418 self._downloader.trouble(u'ERROR: unable to extract media URL')
1420 mediaURL = mobj.group(1).replace('\\/', '/')
1421 video_extension = mediaURL[-3:]
1422 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
1424 mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
1426 self._downloader.trouble(u'ERROR: unable to extract title')
1428 video_title = mobj.group(1).decode('utf-8')
1429 video_title = sanitize_title(video_title)
1431 mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
1433 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1435 video_uploader = mobj.group(1)
1438 # Process video information
1439 self._downloader.process_info({
1440 'id': video_id.decode('utf-8'),
1441 'url': video_url.decode('utf-8'),
1442 'uploader': video_uploader.decode('utf-8'),
1443 'upload_date': u'NA',
1444 'title': video_title,
1445 'stitle': simple_title,
1446 'ext': video_extension.decode('utf-8'),
1450 except UnavailableVideoError:
1451 self._downloader.trouble(u'\nERROR: unable to download video')
1454 class DailymotionIE(InfoExtractor):
1455 """Information Extractor for Dailymotion"""
1457 _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
1459 def __init__(self, downloader=None):
1460 InfoExtractor.__init__(self, downloader)
1464 return (re.match(DailymotionIE._VALID_URL, url) is not None)
1466 def report_download_webpage(self, video_id):
1467 """Report webpage download."""
1468 self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
1470 def report_extraction(self, video_id):
1471 """Report information extraction."""
1472 self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
1474 def _real_initialize(self):
1477 def _real_extract(self, url):
1478 # Extract id and simplified title from URL
1479 mobj = re.match(self._VALID_URL, url)
1481 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1484 # At this point we have a new video
1485 self._downloader.increment_downloads()
1486 video_id = mobj.group(1)
1488 simple_title = mobj.group(2).decode('utf-8')
1489 video_extension = 'flv'
1491 # Retrieve video webpage to extract further information
1492 request = urllib2.Request(url)
1494 self.report_download_webpage(video_id)
1495 webpage = urllib2.urlopen(request).read()
1496 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1497 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
1500 # Extract URL, uploader and title from webpage
1501 self.report_extraction(video_id)
1502 mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
1504 self._downloader.trouble(u'ERROR: unable to extract media URL')
1506 mediaURL = urllib.unquote(mobj.group(1))
1508 # if needed add http://www.dailymotion.com/ if relative URL
1510 video_url = mediaURL
1512 # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
1513 mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
1515 self._downloader.trouble(u'ERROR: unable to extract title')
1517 video_title = mobj.group(1).decode('utf-8')
1518 video_title = sanitize_title(video_title)
1520 mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
1522 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1524 video_uploader = mobj.group(1)
1527 # Process video information
1528 self._downloader.process_info({
1529 'id': video_id.decode('utf-8'),
1530 'url': video_url.decode('utf-8'),
1531 'uploader': video_uploader.decode('utf-8'),
1532 'upload_date': u'NA',
1533 'title': video_title,
1534 'stitle': simple_title,
1535 'ext': video_extension.decode('utf-8'),
1539 except UnavailableVideoError:
1540 self._downloader.trouble(u'\nERROR: unable to download video')
1542 class GoogleIE(InfoExtractor):
1543 """Information extractor for video.google.com."""
1545 _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
1547 def __init__(self, downloader=None):
1548 InfoExtractor.__init__(self, downloader)
1552 return (re.match(GoogleIE._VALID_URL, url) is not None)
1554 def report_download_webpage(self, video_id):
1555 """Report webpage download."""
1556 self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
1558 def report_extraction(self, video_id):
1559 """Report information extraction."""
1560 self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
1562 def _real_initialize(self):
1565 def _real_extract(self, url):
1566 # Extract id from URL
1567 mobj = re.match(self._VALID_URL, url)
1569 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1572 # At this point we have a new video
1573 self._downloader.increment_downloads()
1574 video_id = mobj.group(1)
1576 video_extension = 'mp4'
1578 # Retrieve video webpage to extract further information
1579 request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
1581 self.report_download_webpage(video_id)
1582 webpage = urllib2.urlopen(request).read()
1583 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1584 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1587 # Extract URL, uploader, and title from webpage
1588 self.report_extraction(video_id)
1589 mobj = re.search(r"download_url:'([^']+)'", webpage)
1591 video_extension = 'flv'
1592 mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
1594 self._downloader.trouble(u'ERROR: unable to extract media URL')
1596 mediaURL = urllib.unquote(mobj.group(1))
1597 mediaURL = mediaURL.replace('\\x3d', '\x3d')
1598 mediaURL = mediaURL.replace('\\x26', '\x26')
1600 video_url = mediaURL
1602 mobj = re.search(r'<title>(.*)</title>', webpage)
1604 self._downloader.trouble(u'ERROR: unable to extract title')
1606 video_title = mobj.group(1).decode('utf-8')
1607 video_title = sanitize_title(video_title)
1608 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1610 # Extract video description
1611 mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
1613 self._downloader.trouble(u'ERROR: unable to extract video description')
1615 video_description = mobj.group(1).decode('utf-8')
1616 if not video_description:
1617 video_description = 'No description available.'
1619 # Extract video thumbnail
1620 if self._downloader.params.get('forcethumbnail', False):
1621 request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
1623 webpage = urllib2.urlopen(request).read()
1624 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1625 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1627 mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
1629 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1631 video_thumbnail = mobj.group(1)
1632 else: # we need something to pass to process_info
1633 video_thumbnail = ''
1637 # Process video information
1638 self._downloader.process_info({
1639 'id': video_id.decode('utf-8'),
1640 'url': video_url.decode('utf-8'),
1642 'upload_date': u'NA',
1643 'title': video_title,
1644 'stitle': simple_title,
1645 'ext': video_extension.decode('utf-8'),
1649 except UnavailableVideoError:
1650 self._downloader.trouble(u'\nERROR: unable to download video')
1653 class PhotobucketIE(InfoExtractor):
1654 """Information extractor for photobucket.com."""
1656 _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
1658 def __init__(self, downloader=None):
1659 InfoExtractor.__init__(self, downloader)
1663 return (re.match(PhotobucketIE._VALID_URL, url) is not None)
1665 def report_download_webpage(self, video_id):
1666 """Report webpage download."""
1667 self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
1669 def report_extraction(self, video_id):
1670 """Report information extraction."""
1671 self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
1673 def _real_initialize(self):
1676 def _real_extract(self, url):
1677 # Extract id from URL
1678 mobj = re.match(self._VALID_URL, url)
1680 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1683 # At this point we have a new video
1684 self._downloader.increment_downloads()
1685 video_id = mobj.group(1)
1687 video_extension = 'flv'
1689 # Retrieve video webpage to extract further information
1690 request = urllib2.Request(url)
1692 self.report_download_webpage(video_id)
1693 webpage = urllib2.urlopen(request).read()
1694 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1695 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1698 # Extract URL, uploader, and title from webpage
1699 self.report_extraction(video_id)
1700 mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
1702 self._downloader.trouble(u'ERROR: unable to extract media URL')
1704 mediaURL = urllib.unquote(mobj.group(1))
1706 video_url = mediaURL
1708 mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
1710 self._downloader.trouble(u'ERROR: unable to extract title')
1712 video_title = mobj.group(1).decode('utf-8')
1713 video_title = sanitize_title(video_title)
1714 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1716 video_uploader = mobj.group(2).decode('utf-8')
1719 # Process video information
1720 self._downloader.process_info({
1721 'id': video_id.decode('utf-8'),
1722 'url': video_url.decode('utf-8'),
1723 'uploader': video_uploader,
1724 'upload_date': u'NA',
1725 'title': video_title,
1726 'stitle': simple_title,
1727 'ext': video_extension.decode('utf-8'),
1731 except UnavailableVideoError:
1732 self._downloader.trouble(u'\nERROR: unable to download video')
1735 class YahooIE(InfoExtractor):
1736 """Information extractor for video.yahoo.com."""
1738 # _VALID_URL matches all Yahoo! Video URLs
1739 # _VPAGE_URL matches only the extractable '/watch/' URLs
1740 _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
1741 _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
1743 def __init__(self, downloader=None):
1744 InfoExtractor.__init__(self, downloader)
1748 return (re.match(YahooIE._VALID_URL, url) is not None)
1750 def report_download_webpage(self, video_id):
1751 """Report webpage download."""
1752 self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
1754 def report_extraction(self, video_id):
1755 """Report information extraction."""
1756 self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
1758 def _real_initialize(self):
1761 def _real_extract(self, url, new_video=True):
1762 # Extract ID from URL
1763 mobj = re.match(self._VALID_URL, url)
1765 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1768 # At this point we have a new video
1769 self._downloader.increment_downloads()
1770 video_id = mobj.group(2)
1771 video_extension = 'flv'
1773 # Rewrite valid but non-extractable URLs as
1774 # extractable English language /watch/ URLs
1775 if re.match(self._VPAGE_URL, url) is None:
1776 request = urllib2.Request(url)
1778 webpage = urllib2.urlopen(request).read()
1779 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1780 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1783 mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
1785 self._downloader.trouble(u'ERROR: Unable to extract id field')
1787 yahoo_id = mobj.group(1)
1789 mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
1791 self._downloader.trouble(u'ERROR: Unable to extract vid field')
1793 yahoo_vid = mobj.group(1)
1795 url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
1796 return self._real_extract(url, new_video=False)
1798 # Retrieve video webpage to extract further information
1799 request = urllib2.Request(url)
1801 self.report_download_webpage(video_id)
1802 webpage = urllib2.urlopen(request).read()
1803 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1804 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1807 # Extract uploader and title from webpage
1808 self.report_extraction(video_id)
1809 mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
1811 self._downloader.trouble(u'ERROR: unable to extract video title')
1813 video_title = mobj.group(1).decode('utf-8')
1814 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1816 mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
1818 self._downloader.trouble(u'ERROR: unable to extract video uploader')
1820 video_uploader = mobj.group(1).decode('utf-8')
1822 # Extract video thumbnail
1823 mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
1825 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1827 video_thumbnail = mobj.group(1).decode('utf-8')
1829 # Extract video description
1830 mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
1832 self._downloader.trouble(u'ERROR: unable to extract video description')
1834 video_description = mobj.group(1).decode('utf-8')
1835 if not video_description: video_description = 'No description available.'
1837 # Extract video height and width
1838 mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
1840 self._downloader.trouble(u'ERROR: unable to extract video height')
1842 yv_video_height = mobj.group(1)
1844 mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
1846 self._downloader.trouble(u'ERROR: unable to extract video width')
1848 yv_video_width = mobj.group(1)
1850 # Retrieve video playlist to extract media URL
1851 # I'm not completely sure what all these options are, but we
1852 # seem to need most of them, otherwise the server sends a 401.
1853 yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
1854 yv_bitrate = '700' # according to Wikipedia this is hard-coded
1855 request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
1856 '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
1857 '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
1859 self.report_download_webpage(video_id)
1860 webpage = urllib2.urlopen(request).read()
1861 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1862 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1865 # Extract media URL from playlist XML
1866 mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
1868 self._downloader.trouble(u'ERROR: Unable to extract media URL')
1870 video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
1871 video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
1874 # Process video information
1875 self._downloader.process_info({
1876 'id': video_id.decode('utf-8'),
1878 'uploader': video_uploader,
1879 'upload_date': u'NA',
1880 'title': video_title,
1881 'stitle': simple_title,
1882 'ext': video_extension.decode('utf-8'),
1883 'thumbnail': video_thumbnail.decode('utf-8'),
1884 'description': video_description,
1885 'thumbnail': video_thumbnail,
1886 'description': video_description,
1889 except UnavailableVideoError:
1890 self._downloader.trouble(u'\nERROR: unable to download video')
1893 class GenericIE(InfoExtractor):
1894 """Generic last-resort information extractor."""
1896 def __init__(self, downloader=None):
1897 InfoExtractor.__init__(self, downloader)
1903 def report_download_webpage(self, video_id):
1904 """Report webpage download."""
1905 self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
1906 self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
1908 def report_extraction(self, video_id):
1909 """Report information extraction."""
1910 self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
1912 def _real_initialize(self):
1915 def _real_extract(self, url):
1916 # At this point we have a new video
1917 self._downloader.increment_downloads()
1919 video_id = url.split('/')[-1]
1920 request = urllib2.Request(url)
1922 self.report_download_webpage(video_id)
1923 webpage = urllib2.urlopen(request).read()
1924 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1925 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1927 except ValueError, err:
1928 # since this is the last-resort InfoExtractor, if
1929 # this error is thrown, it'll be thrown here
1930 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1933 self.report_extraction(video_id)
1934 # Start with something easy: JW Player in SWFObject
1935 mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
1937 # Broaden the search a little bit
1938 mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
1940 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1943 # It's possible that one of the regexes
1944 # matched, but returned an empty group:
1945 if mobj.group(1) is None:
1946 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1949 video_url = urllib.unquote(mobj.group(1))
1950 video_id = os.path.basename(video_url)
1952 # here's a fun little line of code for you:
1953 video_extension = os.path.splitext(video_id)[1][1:]
1954 video_id = os.path.splitext(video_id)[0]
1956 # it's tempting to parse this further, but you would
1957 # have to take into account all the variations like
1958 # Video Title - Site Name
1959 # Site Name | Video Title
1960 # Video Title - Tagline | Site Name
1961 # and so on and so forth; it's just not practical
1962 mobj = re.search(r'<title>(.*)</title>', webpage)
1964 self._downloader.trouble(u'ERROR: unable to extract title')
1966 video_title = mobj.group(1).decode('utf-8')
1967 video_title = sanitize_title(video_title)
1968 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1970 # video uploader is domain name
1971 mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
1973 self._downloader.trouble(u'ERROR: unable to extract title')
1975 video_uploader = mobj.group(1).decode('utf-8')
1978 # Process video information
1979 self._downloader.process_info({
1980 'id': video_id.decode('utf-8'),
1981 'url': video_url.decode('utf-8'),
1982 'uploader': video_uploader,
1983 'upload_date': u'NA',
1984 'title': video_title,
1985 'stitle': simple_title,
1986 'ext': video_extension.decode('utf-8'),
1990 except UnavailableVideoError, err:
1991 self._downloader.trouble(u'\nERROR: unable to download video')
1994 class YoutubeSearchIE(InfoExtractor):
1995 """Information Extractor for YouTube search queries."""
1996 _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
1997 _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
1998 _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
1999 _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
2001 _max_youtube_results = 1000
2003 def __init__(self, youtube_ie, downloader=None):
2004 InfoExtractor.__init__(self, downloader)
2005 self._youtube_ie = youtube_ie
2009 return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
2011 def report_download_page(self, query, pagenum):
2012 """Report attempt to download playlist page with given number."""
2013 query = query.decode(preferredencoding())
2014 self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
2016 def _real_initialize(self):
2017 self._youtube_ie.initialize()
2019 def _real_extract(self, query):
2020 mobj = re.match(self._VALID_QUERY, query)
2022 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
2025 prefix, query = query.split(':')
2027 query = query.encode('utf-8')
2029 self._download_n_results(query, 1)
2031 elif prefix == 'all':
2032 self._download_n_results(query, self._max_youtube_results)
2038 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
2040 elif n > self._max_youtube_results:
2041 self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
2042 n = self._max_youtube_results
2043 self._download_n_results(query, n)
2045 except ValueError: # parsing prefix as integer fails
2046 self._download_n_results(query, 1)
2049 def _download_n_results(self, query, n):
2050 """Downloads a specified number of results for a query"""
2053 already_seen = set()
2057 self.report_download_page(query, pagenum)
2058 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2059 request = urllib2.Request(result_url)
2061 page = urllib2.urlopen(request).read()
2062 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2063 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2066 # Extract video identifiers
2067 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2068 video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
2069 if video_id not in already_seen:
2070 video_ids.append(video_id)
2071 already_seen.add(video_id)
2072 if len(video_ids) == n:
2073 # Specified n videos reached
2074 for id in video_ids:
2075 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2078 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2079 for id in video_ids:
2080 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2083 pagenum = pagenum + 1
2085 class GoogleSearchIE(InfoExtractor):
2086 """Information Extractor for Google Video search queries."""
2087 _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
2088 _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
2089 _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
2090 _MORE_PAGES_INDICATOR = r'<span>Next</span>'
2092 _max_google_results = 1000
2094 def __init__(self, google_ie, downloader=None):
2095 InfoExtractor.__init__(self, downloader)
2096 self._google_ie = google_ie
2100 return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
2102 def report_download_page(self, query, pagenum):
2103 """Report attempt to download playlist page with given number."""
2104 query = query.decode(preferredencoding())
2105 self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
2107 def _real_initialize(self):
2108 self._google_ie.initialize()
2110 def _real_extract(self, query):
2111 mobj = re.match(self._VALID_QUERY, query)
2113 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
2116 prefix, query = query.split(':')
2118 query = query.encode('utf-8')
2120 self._download_n_results(query, 1)
2122 elif prefix == 'all':
2123 self._download_n_results(query, self._max_google_results)
2129 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
2131 elif n > self._max_google_results:
2132 self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
2133 n = self._max_google_results
2134 self._download_n_results(query, n)
2136 except ValueError: # parsing prefix as integer fails
2137 self._download_n_results(query, 1)
2140 def _download_n_results(self, query, n):
2141 """Downloads a specified number of results for a query"""
2144 already_seen = set()
2148 self.report_download_page(query, pagenum)
2149 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2150 request = urllib2.Request(result_url)
2152 page = urllib2.urlopen(request).read()
2153 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2154 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2157 # Extract video identifiers
2158 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2159 video_id = mobj.group(1)
2160 if video_id not in already_seen:
2161 video_ids.append(video_id)
2162 already_seen.add(video_id)
2163 if len(video_ids) == n:
2164 # Specified n videos reached
2165 for id in video_ids:
2166 self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
2169 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2170 for id in video_ids:
2171 self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
2174 pagenum = pagenum + 1
2176 class YahooSearchIE(InfoExtractor):
2177 """Information Extractor for Yahoo! Video search queries."""
2178 _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
2179 _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
2180 _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
2181 _MORE_PAGES_INDICATOR = r'\s*Next'
2183 _max_yahoo_results = 1000
2185 def __init__(self, yahoo_ie, downloader=None):
2186 InfoExtractor.__init__(self, downloader)
2187 self._yahoo_ie = yahoo_ie
2191 return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
2193 def report_download_page(self, query, pagenum):
2194 """Report attempt to download playlist page with given number."""
2195 query = query.decode(preferredencoding())
2196 self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
2198 def _real_initialize(self):
2199 self._yahoo_ie.initialize()
2201 def _real_extract(self, query):
2202 mobj = re.match(self._VALID_QUERY, query)
2204 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
2207 prefix, query = query.split(':')
2209 query = query.encode('utf-8')
2211 self._download_n_results(query, 1)
2213 elif prefix == 'all':
2214 self._download_n_results(query, self._max_yahoo_results)
2220 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
2222 elif n > self._max_yahoo_results:
2223 self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
2224 n = self._max_yahoo_results
2225 self._download_n_results(query, n)
2227 except ValueError: # parsing prefix as integer fails
2228 self._download_n_results(query, 1)
2231 def _download_n_results(self, query, n):
2232 """Downloads a specified number of results for a query"""
2235 already_seen = set()
2239 self.report_download_page(query, pagenum)
2240 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2241 request = urllib2.Request(result_url)
2243 page = urllib2.urlopen(request).read()
2244 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2245 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2248 # Extract video identifiers
2249 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2250 video_id = mobj.group(1)
2251 if video_id not in already_seen:
2252 video_ids.append(video_id)
2253 already_seen.add(video_id)
2254 if len(video_ids) == n:
2255 # Specified n videos reached
2256 for id in video_ids:
2257 self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
2260 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2261 for id in video_ids:
2262 self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
2265 pagenum = pagenum + 1
2267 class YoutubePlaylistIE(InfoExtractor):
2268 """Information Extractor for YouTube playlists."""
2270 _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
2271 _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
2272 _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
2273 _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
2276 def __init__(self, youtube_ie, downloader=None):
2277 InfoExtractor.__init__(self, downloader)
2278 self._youtube_ie = youtube_ie
2282 return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
2284 def report_download_page(self, playlist_id, pagenum):
2285 """Report attempt to download playlist page with given number."""
2286 self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
2288 def _real_initialize(self):
2289 self._youtube_ie.initialize()
2291 def _real_extract(self, url):
2292 # Extract playlist id
2293 mobj = re.match(self._VALID_URL, url)
2295 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
2299 if mobj.group(3) is not None:
2300 self._youtube_ie.extract(mobj.group(3))
2303 # Download playlist pages
2304 # prefix is 'p' as default for playlists but there are other types that need extra care
2305 playlist_prefix = mobj.group(1)
2306 if playlist_prefix == 'a':
2307 playlist_access = 'artist'
2309 playlist_prefix = 'p'
2310 playlist_access = 'view_play_list'
2311 playlist_id = mobj.group(2)
2316 self.report_download_page(playlist_id, pagenum)
2317 request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
2319 page = urllib2.urlopen(request).read()
2320 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2321 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2324 # Extract video identifiers
2326 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2327 if mobj.group(1) not in ids_in_page:
2328 ids_in_page.append(mobj.group(1))
2329 video_ids.extend(ids_in_page)
2331 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2333 pagenum = pagenum + 1
2335 playliststart = self._downloader.params.get('playliststart', 1) - 1
2336 playlistend = self._downloader.params.get('playlistend', -1)
2337 video_ids = video_ids[playliststart:playlistend]
2339 for id in video_ids:
2340 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2343 class YoutubeUserIE(InfoExtractor):
2344 """Information Extractor for YouTube users."""
2346 _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
2347 _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
2348 _GDATA_PAGE_SIZE = 50
2349 _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
2350 _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
2353 def __init__(self, youtube_ie, downloader=None):
2354 InfoExtractor.__init__(self, downloader)
2355 self._youtube_ie = youtube_ie
2359 return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
2361 def report_download_page(self, username, start_index):
2362 """Report attempt to download user page."""
2363 self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
2364 (username, start_index, start_index + self._GDATA_PAGE_SIZE))
2366 def _real_initialize(self):
2367 self._youtube_ie.initialize()
2369 def _real_extract(self, url):
2371 mobj = re.match(self._VALID_URL, url)
2373 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
2376 username = mobj.group(1)
2378 # Download video ids using YouTube Data API. Result size per
2379 # query is limited (currently to 50 videos) so we need to query
2380 # page by page until there are no video ids - it means we got
2387 start_index = pagenum * self._GDATA_PAGE_SIZE + 1
2388 self.report_download_page(username, start_index)
2390 request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
2393 page = urllib2.urlopen(request).read()
2394 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2395 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2398 # Extract video identifiers
2401 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2402 if mobj.group(1) not in ids_in_page:
2403 ids_in_page.append(mobj.group(1))
2405 video_ids.extend(ids_in_page)
2407 # A little optimization - if current page is not
2408 # "full", ie. does not contain PAGE_SIZE video ids then
2409 # we can assume that this page is the last one - there
2410 # are no more ids on further pages - no need to query
2413 if len(ids_in_page) < self._GDATA_PAGE_SIZE:
2418 all_ids_count = len(video_ids)
2419 playliststart = self._downloader.params.get('playliststart', 1) - 1
2420 playlistend = self._downloader.params.get('playlistend', -1)
2422 if playlistend == -1:
2423 video_ids = video_ids[playliststart:]
2425 video_ids = video_ids[playliststart:playlistend]
2427 self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
2428 (username, all_ids_count, len(video_ids)))
2430 for video_id in video_ids:
2431 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
2434 class DepositFilesIE(InfoExtractor):
2435 """Information extractor for depositfiles.com"""
2437 _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
2439 def __init__(self, downloader=None):
2440 InfoExtractor.__init__(self, downloader)
2444 return (re.match(DepositFilesIE._VALID_URL, url) is not None)
2446 def report_download_webpage(self, file_id):
2447 """Report webpage download."""
2448 self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
2450 def report_extraction(self, file_id):
2451 """Report information extraction."""
2452 self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
2454 def _real_initialize(self):
2457 def _real_extract(self, url):
2458 # At this point we have a new file
2459 self._downloader.increment_downloads()
2461 file_id = url.split('/')[-1]
2462 # Rebuild url in english locale
2463 url = 'http://depositfiles.com/en/files/' + file_id
2465 # Retrieve file webpage with 'Free download' button pressed
2466 free_download_indication = { 'gateway_result' : '1' }
2467 request = urllib2.Request(url, urllib.urlencode(free_download_indication))
2469 self.report_download_webpage(file_id)
2470 webpage = urllib2.urlopen(request).read()
2471 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2472 self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
2475 # Search for the real file URL
2476 mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
2477 if (mobj is None) or (mobj.group(1) is None):
2478 # Try to figure out reason of the error.
2479 mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
2480 if (mobj is not None) and (mobj.group(1) is not None):
2481 restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
2482 self._downloader.trouble(u'ERROR: %s' % restriction_message)
2484 self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
2487 file_url = mobj.group(1)
2488 file_extension = os.path.splitext(file_url)[1][1:]
2490 # Search for file title
2491 mobj = re.search(r'<b title="(.*?)">', webpage)
2493 self._downloader.trouble(u'ERROR: unable to extract title')
2495 file_title = mobj.group(1).decode('utf-8')
2498 # Process file information
2499 self._downloader.process_info({
2500 'id': file_id.decode('utf-8'),
2501 'url': file_url.decode('utf-8'),
2503 'upload_date': u'NA',
2504 'title': file_title,
2505 'stitle': file_title,
2506 'ext': file_extension.decode('utf-8'),
2510 except UnavailableVideoError, err:
2511 self._downloader.trouble(u'ERROR: unable to download file')
2513 class FacebookIE(InfoExtractor):
2514 """Information Extractor for Facebook"""
2516 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
2517 _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
2518 _NETRC_MACHINE = 'facebook'
2519 _available_formats = ['highqual', 'lowqual']
2520 _video_extensions = {
2525 def __init__(self, downloader=None):
2526 InfoExtractor.__init__(self, downloader)
2530 return (re.match(FacebookIE._VALID_URL, url) is not None)
2532 def _reporter(self, message):
2533 """Add header and report message."""
2534 self._downloader.to_screen(u'[facebook] %s' % message)
2536 def report_login(self):
2537 """Report attempt to log in."""
2538 self._reporter(u'Logging in')
2540 def report_video_webpage_download(self, video_id):
2541 """Report attempt to download video webpage."""
2542 self._reporter(u'%s: Downloading video webpage' % video_id)
2544 def report_information_extraction(self, video_id):
2545 """Report attempt to extract video information."""
2546 self._reporter(u'%s: Extracting video information' % video_id)
2548 def _parse_page(self, video_webpage):
2549 """Extract video information from page"""
2551 data = {'title': r'class="video_title datawrap">(.*?)</',
2552 'description': r'<div class="datawrap">(.*?)</div>',
2553 'owner': r'\("video_owner_name", "(.*?)"\)',
2554 'upload_date': r'data-date="(.*?)"',
2555 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
2558 for piece in data.keys():
2559 mobj = re.search(data[piece], video_webpage)
2560 if mobj is not None:
2561 video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
2565 for fmt in self._available_formats:
2566 mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
2567 if mobj is not None:
2568 # URL is in a Javascript segment inside an escaped Unicode format within
2569 # the generally utf-8 page
2570 video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
2571 video_info['video_urls'] = video_urls
2575 def _real_initialize(self):
2576 if self._downloader is None:
2581 downloader_params = self._downloader.params
2583 # Attempt to use provided username and password or .netrc data
2584 if downloader_params.get('username', None) is not None:
2585 useremail = downloader_params['username']
2586 password = downloader_params['password']
2587 elif downloader_params.get('usenetrc', False):
2589 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
2590 if info is not None:
2594 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
2595 except (IOError, netrc.NetrcParseError), err:
2596 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
2599 if useremail is None:
2608 request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
2611 login_results = urllib2.urlopen(request).read()
2612 if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
2613 self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
2615 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2616 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
2619 def _real_extract(self, url):
2620 mobj = re.match(self._VALID_URL, url)
2622 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2624 video_id = mobj.group('ID')
2627 self.report_video_webpage_download(video_id)
2628 request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
2630 page = urllib2.urlopen(request)
2631 video_webpage = page.read()
2632 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2633 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
2636 # Start extracting information
2637 self.report_information_extraction(video_id)
2639 # Extract information
2640 video_info = self._parse_page(video_webpage)
2643 if 'owner' not in video_info:
2644 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
2646 video_uploader = video_info['owner']
2649 if 'title' not in video_info:
2650 self._downloader.trouble(u'ERROR: unable to extract video title')
2652 video_title = video_info['title']
2653 video_title = video_title.decode('utf-8')
2654 video_title = sanitize_title(video_title)
2657 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
2658 simple_title = simple_title.strip(ur'_')
2661 if 'thumbnail' not in video_info:
2662 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
2663 video_thumbnail = ''
2665 video_thumbnail = video_info['thumbnail']
2669 if 'upload_date' in video_info:
2670 upload_time = video_info['upload_date']
2671 timetuple = email.utils.parsedate_tz(upload_time)
2672 if timetuple is not None:
2674 upload_date = time.strftime('%Y%m%d', timetuple[0:9])
2679 video_description = video_info.get('description', 'No description available.')
2681 url_map = video_info['video_urls']
2682 if len(url_map.keys()) > 0:
2683 # Decide which formats to download
2684 req_format = self._downloader.params.get('format', None)
2685 format_limit = self._downloader.params.get('format_limit', None)
2687 if format_limit is not None and format_limit in self._available_formats:
2688 format_list = self._available_formats[self._available_formats.index(format_limit):]
2690 format_list = self._available_formats
2691 existing_formats = [x for x in format_list if x in url_map]
2692 if len(existing_formats) == 0:
2693 self._downloader.trouble(u'ERROR: no known formats available for video')
2695 if req_format is None:
2696 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
2697 elif req_format == '-1':
2698 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
2701 if req_format not in url_map:
2702 self._downloader.trouble(u'ERROR: requested format not available')
2704 video_url_list = [(req_format, url_map[req_format])] # Specific format
2706 for format_param, video_real_url in video_url_list:
2708 # At this point we have a new video
2709 self._downloader.increment_downloads()
2712 video_extension = self._video_extensions.get(format_param, 'mp4')
2714 # Find the video URL in fmt_url_map or conn paramters
2716 # Process video information
2717 self._downloader.process_info({
2718 'id': video_id.decode('utf-8'),
2719 'url': video_real_url.decode('utf-8'),
2720 'uploader': video_uploader.decode('utf-8'),
2721 'upload_date': upload_date,
2722 'title': video_title,
2723 'stitle': simple_title,
2724 'ext': video_extension.decode('utf-8'),
2725 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
2726 'thumbnail': video_thumbnail.decode('utf-8'),
2727 'description': video_description.decode('utf-8'),
2730 except UnavailableVideoError, err:
2731 self._downloader.trouble(u'\nERROR: unable to download video')
2733 class BlipTVIE(InfoExtractor):
2734 """Information extractor for blip.tv"""
2736 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip.tv(/.+)$'
2737 _URL_EXT = r'^.*\.([a-z0-9]+)$'
2741 return (re.match(BlipTVIE._VALID_URL, url) is not None)
2743 def report_extraction(self, file_id):
2744 """Report information extraction."""
2745 self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
2747 def _simplify_title(self, title):
2748 res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
2749 res = res.strip(ur'_')
2752 def _real_extract(self, url):
2753 mobj = re.match(self._VALID_URL, url)
2755 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2758 json_url = url + ('&' if '?' in url else '?') + 'skin=json&version=2&no_wrap=1'
2759 request = urllib2.Request(json_url)
2760 self.report_extraction(mobj.group(1))
2762 json_code = urllib2.urlopen(request).read()
2763 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2764 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
2767 json_data = json.loads(json_code)
2768 data = json_data['Post'] if 'Post' in json_data else json_data
2770 upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
2771 video_url = data['media']['url']
2772 umobj = re.match(self._URL_EXT, video_url)
2774 raise ValueError('Can not determine filename extension')
2775 ext = umobj.group(1)
2777 self._downloader.increment_downloads()
2780 'id': data['item_id'],
2782 'uploader': data['display_name'],
2783 'upload_date': upload_date,
2784 'title': data['title'],
2785 'stitle': self._simplify_title(data['title']),
2787 'format': data['media']['mimeType'],
2788 'thumbnail': data['thumbnailUrl'],
2789 'description': data['description'],
2790 'player_url': data['embedUrl']
2792 except (ValueError,KeyError), err:
2793 self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
2797 self._downloader.process_info(info)
2798 except UnavailableVideoError, err:
2799 self._downloader.trouble(u'\nERROR: unable to download video')
2802 class PostProcessor(object):
2803 """Post Processor class.
2805 PostProcessor objects can be added to downloaders with their
2806 add_post_processor() method. When the downloader has finished a
2807 successful download, it will take its internal chain of PostProcessors
2808 and start calling the run() method on each one of them, first with
2809 an initial argument and then with the returned value of the previous
2812 The chain will be stopped if one of them ever returns None or the end
2813 of the chain is reached.
2815 PostProcessor objects follow a "mutual registration" process similar
2816 to InfoExtractor objects.
2821 def __init__(self, downloader=None):
2822 self._downloader = downloader
2824 def set_downloader(self, downloader):
2825 """Sets the downloader for this PP."""
2826 self._downloader = downloader
2828 def run(self, information):
2829 """Run the PostProcessor.
2831 The "information" argument is a dictionary like the ones
2832 composed by InfoExtractors. The only difference is that this
2833 one has an extra field called "filepath" that points to the
2836 When this method returns None, the postprocessing chain is
2837 stopped. However, this method may return an information
2838 dictionary that will be passed to the next postprocessing
2839 object in the chain. It can be the one it received after
2840 changing some fields.
2842 In addition, this method may raise a PostProcessingError
2843 exception that will be taken into account by the downloader
2846 return information # by default, do nothing
2848 class FFmpegExtractAudioPP(PostProcessor):
2850 def __init__(self, downloader=None, preferredcodec=None):
2851 PostProcessor.__init__(self, downloader)
2852 if preferredcodec is None:
2853 preferredcodec = 'best'
2854 self._preferredcodec = preferredcodec
2857 def get_audio_codec(path):
2859 cmd = ['ffprobe', '-show_streams', '--', path]
2860 handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
2861 output = handle.communicate()[0]
2862 if handle.wait() != 0:
2864 except (IOError, OSError):
2867 for line in output.split('\n'):
2868 if line.startswith('codec_name='):
2869 audio_codec = line.split('=')[1].strip()
2870 elif line.strip() == 'codec_type=audio' and audio_codec is not None:
2875 def run_ffmpeg(path, out_path, codec, more_opts):
2877 cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
2878 ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
2880 except (IOError, OSError):
2883 def run(self, information):
2884 path = information['filepath']
2886 filecodec = self.get_audio_codec(path)
2887 if filecodec is None:
2888 self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
2892 if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
2893 if filecodec == 'aac' or filecodec == 'mp3':
2894 # Lossless if possible
2896 extension = filecodec
2897 if filecodec == 'aac':
2898 more_opts = ['-f', 'adts']
2901 acodec = 'libmp3lame'
2903 more_opts = ['-ab', '128k']
2905 # We convert the audio (lossy)
2906 acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
2907 extension = self._preferredcodec
2908 more_opts = ['-ab', '128k']
2909 if self._preferredcodec == 'aac':
2910 more_opts += ['-f', 'adts']
2912 (prefix, ext) = os.path.splitext(path)
2913 new_path = prefix + '.' + extension
2914 self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path)
2915 status = self.run_ffmpeg(path, new_path, acodec, more_opts)
2918 self._downloader.to_stderr(u'WARNING: error running ffmpeg')
2923 except (IOError, OSError):
2924 self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
2927 information['filepath'] = new_path
2930 ### MAIN PROGRAM ###
2931 if __name__ == '__main__':
2933 # Modules needed only when running the main program
2937 # Function to update the program file with the latest version from the repository.
2938 def update_self(downloader, filename):
2939 # Note: downloader only used for options
2940 if not os.access(filename, os.W_OK):
2941 sys.exit('ERROR: no write permissions on %s' % filename)
2943 downloader.to_screen('Updating to latest stable version...')
2945 latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
2946 latest_version = urllib.urlopen(latest_url).read().strip()
2947 prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
2948 newcontent = urllib.urlopen(prog_url).read()
2949 except (IOError, OSError), err:
2950 sys.exit('ERROR: unable to download latest version')
2952 stream = open(filename, 'w')
2953 stream.write(newcontent)
2955 except (IOError, OSError), err:
2956 sys.exit('ERROR: unable to overwrite current version')
2957 downloader.to_screen('Updated to version %s' % latest_version)
2959 # Parse command line
2960 parser = optparse.OptionParser(
2961 usage='Usage: %prog [options] url...',
2962 version='2011.07.09-phihag',
2963 conflict_handler='resolve',
2966 parser.add_option('-h', '--help',
2967 action='help', help='print this help text and exit')
2968 parser.add_option('-v', '--version',
2969 action='version', help='print program version and exit')
2970 parser.add_option('-U', '--update',
2971 action='store_true', dest='update_self', help='update this program to latest stable version')
2972 parser.add_option('-i', '--ignore-errors',
2973 action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
2974 parser.add_option('-r', '--rate-limit',
2975 dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
2976 parser.add_option('-R', '--retries',
2977 dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
2978 parser.add_option('--playlist-start',
2979 dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
2980 parser.add_option('--playlist-end',
2981 dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
2982 parser.add_option('--dump-user-agent',
2983 action='store_true', dest='dump_user_agent',
2984 help='display the current browser identification', default=False)
2986 authentication = optparse.OptionGroup(parser, 'Authentication Options')
2987 authentication.add_option('-u', '--username',
2988 dest='username', metavar='USERNAME', help='account username')
2989 authentication.add_option('-p', '--password',
2990 dest='password', metavar='PASSWORD', help='account password')
2991 authentication.add_option('-n', '--netrc',
2992 action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
2993 parser.add_option_group(authentication)
2995 video_format = optparse.OptionGroup(parser, 'Video Format Options')
2996 video_format.add_option('-f', '--format',
2997 action='store', dest='format', metavar='FORMAT', help='video format code')
2998 video_format.add_option('--all-formats',
2999 action='store_const', dest='format', help='download all available video formats', const='-1')
3000 video_format.add_option('--max-quality',
3001 action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
3002 parser.add_option_group(video_format)
3004 verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
3005 verbosity.add_option('-q', '--quiet',
3006 action='store_true', dest='quiet', help='activates quiet mode', default=False)
3007 verbosity.add_option('-s', '--simulate',
3008 action='store_true', dest='simulate', help='do not download video', default=False)
3009 verbosity.add_option('-g', '--get-url',
3010 action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
3011 verbosity.add_option('-e', '--get-title',
3012 action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
3013 verbosity.add_option('--get-thumbnail',
3014 action='store_true', dest='getthumbnail',
3015 help='simulate, quiet but print thumbnail URL', default=False)
3016 verbosity.add_option('--get-description',
3017 action='store_true', dest='getdescription',
3018 help='simulate, quiet but print video description', default=False)
3019 verbosity.add_option('--get-filename',
3020 action='store_true', dest='getfilename',
3021 help='simulate, quiet but print output filename', default=False)
3022 verbosity.add_option('--no-progress',
3023 action='store_true', dest='noprogress', help='do not print progress bar', default=False)
3024 verbosity.add_option('--console-title',
3025 action='store_true', dest='consoletitle',
3026 help='display progress in console titlebar', default=False)
3027 parser.add_option_group(verbosity)
3029 filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
3030 filesystem.add_option('-t', '--title',
3031 action='store_true', dest='usetitle', help='use title in file name', default=False)
3032 filesystem.add_option('-l', '--literal',
3033 action='store_true', dest='useliteral', help='use literal title in file name', default=False)
3034 filesystem.add_option('-A', '--auto-number',
3035 action='store_true', dest='autonumber',
3036 help='number downloaded files starting from 00000', default=False)
3037 filesystem.add_option('-o', '--output',
3038 dest='outtmpl', metavar='TEMPLATE', help='output filename template')
3039 filesystem.add_option('-a', '--batch-file',
3040 dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
3041 filesystem.add_option('-w', '--no-overwrites',
3042 action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
3043 filesystem.add_option('-c', '--continue',
3044 action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
3045 filesystem.add_option('--cookies',
3046 dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
3047 filesystem.add_option('--no-part',
3048 action='store_true', dest='nopart', help='do not use .part files', default=False)
3049 filesystem.add_option('--no-mtime',
3050 action='store_false', dest='updatetime',
3051 help='do not use the Last-modified header to set the file modification time', default=True)
3052 filesystem.add_option('--write-description',
3053 action='store_true', dest='writedescription',
3054 help='write video description to a .description file', default=False)
3055 filesystem.add_option('--write-info-json',
3056 action='store_true', dest='writeinfojson',
3057 help='write video metadata to a .info.json file', default=False)
3058 parser.add_option_group(filesystem)
3060 postproc = optparse.OptionGroup(parser, 'Post-processing Options')
3061 postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
3062 help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
3063 postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
3064 help='"best", "aac" or "mp3"; best by default')
3065 parser.add_option_group(postproc)
3067 (opts, args) = parser.parse_args()
3069 # Open appropriate CookieJar
3070 if opts.cookiefile is None:
3071 jar = cookielib.CookieJar()
3074 jar = cookielib.MozillaCookieJar(opts.cookiefile)
3075 if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
3077 except (IOError, OSError), err:
3078 sys.exit(u'ERROR: unable to open cookie file')
3081 if opts.dump_user_agent:
3082 print std_headers['User-Agent']
3085 # General configuration
3086 cookie_processor = urllib2.HTTPCookieProcessor(jar)
3087 urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()))
3088 socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
3090 # Batch file verification
3092 if opts.batchfile is not None:
3094 if opts.batchfile == '-':
3097 batchfd = open(opts.batchfile, 'r')
3098 batchurls = batchfd.readlines()
3099 batchurls = [x.strip() for x in batchurls]
3100 batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
3102 sys.exit(u'ERROR: batch file could not be read')
3103 all_urls = batchurls + args
3105 # Conflicting, missing and erroneous options
3106 if opts.usenetrc and (opts.username is not None or opts.password is not None):
3107 parser.error(u'using .netrc conflicts with giving username/password')
3108 if opts.password is not None and opts.username is None:
3109 parser.error(u'account username missing')
3110 if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
3111 parser.error(u'using output template conflicts with using title, literal title or auto number')
3112 if opts.usetitle and opts.useliteral:
3113 parser.error(u'using title conflicts with using literal title')
3114 if opts.username is not None and opts.password is None:
3115 opts.password = getpass.getpass(u'Type account password and press return:')
3116 if opts.ratelimit is not None:
3117 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
3118 if numeric_limit is None:
3119 parser.error(u'invalid rate limit specified')
3120 opts.ratelimit = numeric_limit
3121 if opts.retries is not None:
3123 opts.retries = long(opts.retries)
3124 except (TypeError, ValueError), err:
3125 parser.error(u'invalid retry count specified')
3127 opts.playliststart = long(opts.playliststart)
3128 if opts.playliststart <= 0:
3130 except (TypeError, ValueError), err:
3131 parser.error(u'invalid playlist start number specified')
3133 opts.playlistend = long(opts.playlistend)
3134 if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
3136 except (TypeError, ValueError), err:
3137 parser.error(u'invalid playlist end number specified')
3138 if opts.extractaudio:
3139 if opts.audioformat not in ['best', 'aac', 'mp3']:
3140 parser.error(u'invalid audio format specified')
3142 # Information extractors
3143 youtube_ie = YoutubeIE()
3144 metacafe_ie = MetacafeIE(youtube_ie)
3145 dailymotion_ie = DailymotionIE()
3146 youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
3147 youtube_user_ie = YoutubeUserIE(youtube_ie)
3148 youtube_search_ie = YoutubeSearchIE(youtube_ie)
3149 google_ie = GoogleIE()
3150 google_search_ie = GoogleSearchIE(google_ie)
3151 photobucket_ie = PhotobucketIE()
3152 yahoo_ie = YahooIE()
3153 yahoo_search_ie = YahooSearchIE(yahoo_ie)
3154 deposit_files_ie = DepositFilesIE()
3155 facebook_ie = FacebookIE()
3156 bliptv_ie = BlipTVIE()
3157 generic_ie = GenericIE()
3160 fd = FileDownloader({
3161 'usenetrc': opts.usenetrc,
3162 'username': opts.username,
3163 'password': opts.password,
3164 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
3165 'forceurl': opts.geturl,
3166 'forcetitle': opts.gettitle,
3167 'forcethumbnail': opts.getthumbnail,
3168 'forcedescription': opts.getdescription,
3169 'forcefilename': opts.getfilename,
3170 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
3171 'format': opts.format,
3172 'format_limit': opts.format_limit,
3173 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
3174 or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
3175 or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
3176 or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
3177 or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
3178 or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
3179 or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
3180 or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
3181 or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
3182 or u'%(id)s.%(ext)s'),
3183 'ignoreerrors': opts.ignoreerrors,
3184 'ratelimit': opts.ratelimit,
3185 'nooverwrites': opts.nooverwrites,
3186 'retries': opts.retries,
3187 'continuedl': opts.continue_dl,
3188 'noprogress': opts.noprogress,
3189 'playliststart': opts.playliststart,
3190 'playlistend': opts.playlistend,
3191 'logtostderr': opts.outtmpl == '-',
3192 'consoletitle': opts.consoletitle,
3193 'nopart': opts.nopart,
3194 'updatetime': opts.updatetime,
3195 'writedescription': opts.writedescription,
3196 'writeinfojson': opts.writeinfojson,
3198 fd.add_info_extractor(youtube_search_ie)
3199 fd.add_info_extractor(youtube_pl_ie)
3200 fd.add_info_extractor(youtube_user_ie)
3201 fd.add_info_extractor(metacafe_ie)
3202 fd.add_info_extractor(dailymotion_ie)
3203 fd.add_info_extractor(youtube_ie)
3204 fd.add_info_extractor(google_ie)
3205 fd.add_info_extractor(google_search_ie)
3206 fd.add_info_extractor(photobucket_ie)
3207 fd.add_info_extractor(yahoo_ie)
3208 fd.add_info_extractor(yahoo_search_ie)
3209 fd.add_info_extractor(deposit_files_ie)
3210 fd.add_info_extractor(facebook_ie)
3211 fd.add_info_extractor(bliptv_ie)
3213 # This must come last since it's the
3214 # fallback if none of the others work
3215 fd.add_info_extractor(generic_ie)
3218 if opts.extractaudio:
3219 fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
3222 if opts.update_self:
3223 update_self(fd, sys.argv[0])
3226 if len(all_urls) < 1:
3227 if not opts.update_self:
3228 parser.error(u'you must provide at least one URL')
3231 retcode = fd.download(all_urls)
3233 # Dump cookie jar if requested
3234 if opts.cookiefile is not None:
3237 except (IOError, OSError), err:
3238 sys.exit(u'ERROR: unable to save cookie jar')
3242 except DownloadError:
3244 except SameFileError:
3245 sys.exit(u'ERROR: fixed output name but more than one file to download')
3246 except KeyboardInterrupt:
3247 sys.exit(u'\nERROR: Interrupted by user')