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 # License: Public domain code
34 # parse_qs was moved from the cgi module to the urlparse module recently.
36 from urlparse import parse_qs
38 from cgi import parse_qs
41 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:2.0b11) Gecko/20100101 Firefox/4.0b11',
42 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
43 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
44 'Accept-Encoding': 'gzip, deflate',
45 'Accept-Language': 'en-us,en;q=0.5',
48 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
50 def preferredencoding():
51 """Get preferred encoding.
53 Returns the best encoding scheme for the system, based on
54 locale.getpreferredencoding() and some further tweaks.
56 def yield_preferredencoding():
58 pref = locale.getpreferredencoding()
64 return yield_preferredencoding().next()
66 def htmlentity_transform(matchobj):
67 """Transforms an HTML entity to a Unicode character.
69 This function receives a match object and is intended to be used with
70 the re.sub() function.
72 entity = matchobj.group(1)
74 # Known non-numeric HTML entity
75 if entity in htmlentitydefs.name2codepoint:
76 return unichr(htmlentitydefs.name2codepoint[entity])
79 mobj = re.match(ur'(?u)#(x?\d+)', entity)
81 numstr = mobj.group(1)
82 if numstr.startswith(u'x'):
84 numstr = u'0%s' % numstr
87 return unichr(long(numstr, base))
89 # Unknown entity in name, return its literal representation
90 return (u'&%s;' % entity)
92 def sanitize_title(utitle):
93 """Sanitizes a video title so it could be used as part of a filename."""
94 utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
95 return utitle.replace(unicode(os.sep), u'%')
97 def sanitize_open(filename, open_mode):
98 """Try to open the given filename, and slightly tweak it if this fails.
100 Attempts to open the given filename. If this fails, it tries to change
101 the filename slightly, step by step, until it's either able to open it
102 or it fails and raises a final exception, like the standard open()
105 It returns the tuple (stream, definitive_file_name).
109 if sys.platform == 'win32':
111 msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
112 return (sys.stdout, filename)
113 stream = open(filename, open_mode)
114 return (stream, filename)
115 except (IOError, OSError), err:
116 # In case of error, try to remove win32 forbidden chars
117 filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
119 # An exception here should be caught in the caller
120 stream = open(filename, open_mode)
121 return (stream, filename)
123 def timeconvert(timestr):
124 """Convert RFC 2822 defined time string into system timestamp"""
126 timetuple = email.utils.parsedate_tz(timestr)
127 if timetuple is not None:
128 timestamp = email.utils.mktime_tz(timetuple)
131 class DownloadError(Exception):
132 """Download Error exception.
134 This exception may be thrown by FileDownloader objects if they are not
135 configured to continue on errors. They will contain the appropriate
140 class SameFileError(Exception):
141 """Same File exception.
143 This exception will be thrown by FileDownloader objects if they detect
144 multiple files would have to be downloaded to the same file on disk.
148 class PostProcessingError(Exception):
149 """Post Processing exception.
151 This exception may be raised by PostProcessor's .run() method to
152 indicate an error in the postprocessing task.
156 class UnavailableVideoError(Exception):
157 """Unavailable Format exception.
159 This exception will be thrown when a video is requested
160 in a format that is not available for that video.
164 class ContentTooShortError(Exception):
165 """Content Too Short exception.
167 This exception may be raised by FileDownloader objects when a file they
168 download is too small for what the server announced first, indicating
169 the connection was probably interrupted.
175 def __init__(self, downloaded, expected):
176 self.downloaded = downloaded
177 self.expected = expected
179 class YoutubeDLHandler(urllib2.HTTPHandler):
180 """Handler for HTTP requests and responses.
182 This class, when installed with an OpenerDirector, automatically adds
183 the standard headers to every HTTP request and handles gzipped and
184 deflated responses from web servers. If compression is to be avoided in
185 a particular request, the original request in the program code only has
186 to include the HTTP header "Youtubedl-No-Compression", which will be
187 removed before making the real request.
189 Part of this code was copied from:
191 http://techknack.net/python-urllib2-handlers/
193 Andrew Rowls, the author of that code, agreed to release it to the
200 return zlib.decompress(data, -zlib.MAX_WBITS)
202 return zlib.decompress(data)
205 def addinfourl_wrapper(stream, headers, url, code):
206 if hasattr(urllib2.addinfourl, 'getcode'):
207 return urllib2.addinfourl(stream, headers, url, code)
208 ret = urllib2.addinfourl(stream, headers, url)
212 def http_request(self, req):
213 for h in std_headers:
216 req.add_header(h, std_headers[h])
217 if 'Youtubedl-no-compression' in req.headers:
218 if 'Accept-encoding' in req.headers:
219 del req.headers['Accept-encoding']
220 del req.headers['Youtubedl-no-compression']
223 def http_response(self, req, resp):
226 if resp.headers.get('Content-encoding', '') == 'gzip':
227 gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
228 resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
229 resp.msg = old_resp.msg
231 if resp.headers.get('Content-encoding', '') == 'deflate':
232 gz = StringIO.StringIO(self.deflate(resp.read()))
233 resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
234 resp.msg = old_resp.msg
237 class FileDownloader(object):
238 """File Downloader class.
240 File downloader objects are the ones responsible of downloading the
241 actual video file and writing it to disk if the user has requested
242 it, among some other tasks. In most cases there should be one per
243 program. As, given a video URL, the downloader doesn't know how to
244 extract all the needed information, task that InfoExtractors do, it
245 has to pass the URL to one of them.
247 For this, file downloader objects have a method that allows
248 InfoExtractors to be registered in a given order. When it is passed
249 a URL, the file downloader handles it to the first InfoExtractor it
250 finds that reports being able to handle it. The InfoExtractor extracts
251 all the information about the video or videos the URL refers to, and
252 asks the FileDownloader to process the video information, possibly
253 downloading the video.
255 File downloaders accept a lot of parameters. In order not to saturate
256 the object constructor with arguments, it receives a dictionary of
257 options instead. These options are available through the params
258 attribute for the InfoExtractors to use. The FileDownloader also
259 registers itself as the downloader in charge for the InfoExtractors
260 that are added to it, so this is a "mutual registration".
264 username: Username for authentication purposes.
265 password: Password for authentication purposes.
266 usenetrc: Use netrc for authentication instead.
267 quiet: Do not print messages to stdout.
268 forceurl: Force printing final URL.
269 forcetitle: Force printing title.
270 forcethumbnail: Force printing thumbnail URL.
271 forcedescription: Force printing description.
272 forcefilename: Force printing final filename.
273 simulate: Do not download the video files.
274 format: Video format code.
275 format_limit: Highest quality format to try.
276 outtmpl: Template for output names.
277 ignoreerrors: Do not stop on download errors.
278 ratelimit: Download speed limit, in bytes/sec.
279 nooverwrites: Prevent overwriting files.
280 retries: Number of times to retry for HTTP error 5xx
281 continuedl: Try to continue downloads if possible.
282 noprogress: Do not print the progress bar.
283 playliststart: Playlist item to start at.
284 playlistend: Playlist item to end at.
285 logtostderr: Log messages to stderr instead of stdout.
286 consoletitle: Display progress in console window's titlebar.
287 nopart: Do not use temporary .part files.
288 updatetime: Use the Last-modified header to set output file timestamps.
294 _download_retcode = None
295 _num_downloads = None
298 def __init__(self, params):
299 """Create a FileDownloader object with the given options."""
302 self._download_retcode = 0
303 self._num_downloads = 0
304 self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
308 def pmkdir(filename):
309 """Create directory components in filename. Similar to Unix "mkdir -p"."""
310 components = filename.split(os.sep)
311 aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
312 aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
313 for dir in aggregate:
314 if not os.path.exists(dir):
318 def format_bytes(bytes):
321 if type(bytes) is str:
326 exponent = long(math.log(bytes, 1024.0))
327 suffix = 'bkMGTPEZY'[exponent]
328 converted = float(bytes) / float(1024**exponent)
329 return '%.2f%s' % (converted, suffix)
332 def calc_percent(byte_counter, data_len):
335 return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
338 def calc_eta(start, now, total, current):
342 if current == 0 or dif < 0.001: # One millisecond
344 rate = float(current) / dif
345 eta = long((float(total) - float(current)) / rate)
346 (eta_mins, eta_secs) = divmod(eta, 60)
349 return '%02d:%02d' % (eta_mins, eta_secs)
352 def calc_speed(start, now, bytes):
354 if bytes == 0 or dif < 0.001: # One millisecond
355 return '%10s' % '---b/s'
356 return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
359 def best_block_size(elapsed_time, bytes):
360 new_min = max(bytes / 2.0, 1.0)
361 new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
362 if elapsed_time < 0.001:
364 rate = bytes / elapsed_time
372 def parse_bytes(bytestr):
373 """Parse a string indicating a byte quantity into a long integer."""
374 matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
377 number = float(matchobj.group(1))
378 multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
379 return long(round(number * multiplier))
381 def add_info_extractor(self, ie):
382 """Add an InfoExtractor object to the end of the list."""
384 ie.set_downloader(self)
386 def add_post_processor(self, pp):
387 """Add a PostProcessor object to the end of the chain."""
389 pp.set_downloader(self)
391 def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
392 """Print message to stdout if not in quiet mode."""
394 if not self.params.get('quiet', False):
395 terminator = [u'\n', u''][skip_eol]
396 print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
397 self._screen_file.flush()
398 except (UnicodeEncodeError), err:
399 if not ignore_encoding_errors:
402 def to_stderr(self, message):
403 """Print message to stderr."""
404 print >>sys.stderr, message.encode(preferredencoding())
406 def to_cons_title(self, message):
407 """Set console/terminal window title to message."""
408 if not self.params.get('consoletitle', False):
410 if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
411 # c_wchar_p() might not be necessary if `message` is
412 # already of type unicode()
413 ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
414 elif 'TERM' in os.environ:
415 sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
417 def fixed_template(self):
418 """Checks if the output template is fixed."""
419 return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
421 def trouble(self, message=None):
422 """Determine action to take when a download problem appears.
424 Depending on if the downloader has been configured to ignore
425 download errors or not, this method may throw an exception or
426 not when errors are found, after printing the message.
428 if message is not None:
429 self.to_stderr(message)
430 if not self.params.get('ignoreerrors', False):
431 raise DownloadError(message)
432 self._download_retcode = 1
434 def slow_down(self, start_time, byte_counter):
435 """Sleep if the download speed is over the rate limit."""
436 rate_limit = self.params.get('ratelimit', None)
437 if rate_limit is None or byte_counter == 0:
440 elapsed = now - start_time
443 speed = float(byte_counter) / elapsed
444 if speed > rate_limit:
445 time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
447 def temp_name(self, filename):
448 """Returns a temporary filename for the given filename."""
449 if self.params.get('nopart', False) or filename == u'-' or \
450 (os.path.exists(filename) and not os.path.isfile(filename)):
452 return filename + u'.part'
454 def undo_temp_name(self, filename):
455 if filename.endswith(u'.part'):
456 return filename[:-len(u'.part')]
459 def try_rename(self, old_filename, new_filename):
461 if old_filename == new_filename:
463 os.rename(old_filename, new_filename)
464 except (IOError, OSError), err:
465 self.trouble(u'ERROR: unable to rename file')
467 def try_utime(self, filename, last_modified_hdr):
468 """Try to set the last-modified time of the given file."""
469 if last_modified_hdr is None:
471 if not os.path.isfile(filename):
473 timestr = last_modified_hdr
476 filetime = timeconvert(timestr)
480 os.utime(filename,(time.time(), filetime))
484 def report_destination(self, filename):
485 """Report destination filename."""
486 self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
488 def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
489 """Report download progress."""
490 if self.params.get('noprogress', False):
492 self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
493 (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
494 self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
495 (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
497 def report_resuming_byte(self, resume_len):
498 """Report attempt to resume at given byte."""
499 self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
501 def report_retry(self, count, retries):
502 """Report retry in case of HTTP error 5xx"""
503 self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
505 def report_file_already_downloaded(self, file_name):
506 """Report file has already been fully downloaded."""
508 self.to_screen(u'[download] %s has already been downloaded' % file_name)
509 except (UnicodeEncodeError), err:
510 self.to_screen(u'[download] The file has already been downloaded')
512 def report_unable_to_resume(self):
513 """Report it was impossible to resume download."""
514 self.to_screen(u'[download] Unable to resume')
516 def report_finish(self):
517 """Report download finished."""
518 if self.params.get('noprogress', False):
519 self.to_screen(u'[download] Download completed')
523 def increment_downloads(self):
524 """Increment the ordinal that assigns a number to each file."""
525 self._num_downloads += 1
527 def prepare_filename(self, info_dict):
528 """Generate the output filename."""
530 template_dict = dict(info_dict)
531 template_dict['epoch'] = unicode(long(time.time()))
532 template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
533 filename = self.params['outtmpl'] % template_dict
535 except (ValueError, KeyError), err:
536 self.trouble(u'ERROR: invalid system charset or erroneous output template')
539 def process_info(self, info_dict):
540 """Process a single dictionary returned by an InfoExtractor."""
541 filename = self.prepare_filename(info_dict)
542 # Do nothing else if in simulate mode
543 if self.params.get('simulate', False):
545 if self.params.get('forcetitle', False):
546 print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
547 if self.params.get('forceurl', False):
548 print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
549 if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
550 print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
551 if self.params.get('forcedescription', False) and 'description' in info_dict:
552 print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
553 if self.params.get('forcefilename', False) and filename is not None:
554 print filename.encode(preferredencoding(), 'xmlcharrefreplace')
560 if self.params.get('nooverwrites', False) and os.path.exists(filename):
561 self.to_stderr(u'WARNING: file exists and will be skipped')
565 self.pmkdir(filename)
566 except (OSError, IOError), err:
567 self.trouble(u'ERROR: unable to create directories: %s' % str(err))
571 success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
572 except (OSError, IOError), err:
573 raise UnavailableVideoError
574 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
575 self.trouble(u'ERROR: unable to download video data: %s' % str(err))
577 except (ContentTooShortError, ), err:
578 self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
583 self.post_process(filename, info_dict)
584 except (PostProcessingError), err:
585 self.trouble(u'ERROR: postprocessing: %s' % str(err))
588 def download(self, url_list):
589 """Download a given list of URLs."""
590 if len(url_list) > 1 and self.fixed_template():
591 raise SameFileError(self.params['outtmpl'])
594 suitable_found = False
596 # Go to next InfoExtractor if not suitable
597 if not ie.suitable(url):
600 # Suitable InfoExtractor found
601 suitable_found = True
603 # Extract information from URL and process it
606 # Suitable InfoExtractor had been found; go to next URL
609 if not suitable_found:
610 self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
612 return self._download_retcode
614 def post_process(self, filename, ie_info):
615 """Run the postprocessing chain on the given file."""
617 info['filepath'] = filename
623 def _download_with_rtmpdump(self, filename, url, player_url):
624 self.report_destination(filename)
625 tmpfilename = self.temp_name(filename)
627 # Check for rtmpdump first
629 subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
630 except (OSError, IOError):
631 self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
634 # Download using rtmpdump. rtmpdump returns exit code 2 when
635 # the connection was interrumpted and resuming appears to be
636 # possible. This is part of rtmpdump's normal usage, AFAIK.
637 basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
638 retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
639 while retval == 2 or retval == 1:
640 prevsize = os.path.getsize(tmpfilename)
641 self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
642 time.sleep(5.0) # This seems to be needed
643 retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
644 cursize = os.path.getsize(tmpfilename)
645 if prevsize == cursize and retval == 1:
648 self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
649 self.try_rename(tmpfilename, filename)
652 self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
655 def _do_download(self, filename, url, player_url):
656 # Check file already present
657 if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
658 self.report_file_already_downloaded(filename)
661 # Attempt to download using rtmpdump
662 if url.startswith('rtmp'):
663 return self._download_with_rtmpdump(filename, url, player_url)
665 tmpfilename = self.temp_name(filename)
669 # Do not include the Accept-Encoding header
670 headers = {'Youtubedl-no-compression': 'True'}
671 basic_request = urllib2.Request(url, None, headers)
672 request = urllib2.Request(url, None, headers)
674 # Establish possible resume length
675 if os.path.isfile(tmpfilename):
676 resume_len = os.path.getsize(tmpfilename)
680 # Request parameters in case of being able to resume
681 if self.params.get('continuedl', False) and resume_len != 0:
682 self.report_resuming_byte(resume_len)
683 request.add_header('Range','bytes=%d-' % resume_len)
687 retries = self.params.get('retries', 0)
688 while count <= retries:
689 # Establish connection
691 data = urllib2.urlopen(request)
693 except (urllib2.HTTPError, ), err:
694 if (err.code < 500 or err.code >= 600) and err.code != 416:
695 # Unexpected HTTP error
697 elif err.code == 416:
698 # Unable to resume (requested range not satisfiable)
700 # Open the connection again without the range header
701 data = urllib2.urlopen(basic_request)
702 content_length = data.info()['Content-Length']
703 except (urllib2.HTTPError, ), err:
704 if err.code < 500 or err.code >= 600:
707 # Examine the reported length
708 if (content_length is not None and
709 (resume_len - 100 < long(content_length) < resume_len + 100)):
710 # The file had already been fully downloaded.
711 # Explanation to the above condition: in issue #175 it was revealed that
712 # YouTube sometimes adds or removes a few bytes from the end of the file,
713 # changing the file size slightly and causing problems for some users. So
714 # I decided to implement a suggested change and consider the file
715 # completely downloaded if the file size differs less than 100 bytes from
716 # the one in the hard drive.
717 self.report_file_already_downloaded(filename)
718 self.try_rename(tmpfilename, filename)
721 # The length does not match, we start the download over
722 self.report_unable_to_resume()
728 self.report_retry(count, retries)
731 self.trouble(u'ERROR: giving up after %s retries' % retries)
734 data_len = data.info().get('Content-length', None)
735 if data_len is not None:
736 data_len = long(data_len) + resume_len
737 data_len_str = self.format_bytes(data_len)
738 byte_counter = 0 + resume_len
744 data_block = data.read(block_size)
746 if len(data_block) == 0:
748 byte_counter += len(data_block)
750 # Open file just in time
753 (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
754 filename = self.undo_temp_name(tmpfilename)
755 self.report_destination(filename)
756 except (OSError, IOError), err:
757 self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
760 stream.write(data_block)
761 except (IOError, OSError), err:
762 self.trouble(u'\nERROR: unable to write data: %s' % str(err))
764 block_size = self.best_block_size(after - before, len(data_block))
767 percent_str = self.calc_percent(byte_counter, data_len)
768 eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
769 speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
770 self.report_progress(percent_str, data_len_str, speed_str, eta_str)
773 self.slow_down(start, byte_counter - resume_len)
777 if data_len is not None and byte_counter != data_len:
778 raise ContentTooShortError(byte_counter, long(data_len))
779 self.try_rename(tmpfilename, filename)
781 # Update file modification time
782 if self.params.get('updatetime', True):
783 self.try_utime(filename, data.info().get('last-modified', None))
787 class InfoExtractor(object):
788 """Information Extractor class.
790 Information extractors are the classes that, given a URL, extract
791 information from the video (or videos) the URL refers to. This
792 information includes the real video URL, the video title and simplified
793 title, author and others. The information is stored in a dictionary
794 which is then passed to the FileDownloader. The FileDownloader
795 processes this information possibly downloading the video to the file
796 system, among other possible outcomes. The dictionaries must include
797 the following fields:
799 id: Video identifier.
800 url: Final video URL.
801 uploader: Nickname of the video uploader.
802 title: Literal title.
803 stitle: Simplified title.
804 ext: Video filename extension.
805 format: Video format.
806 player_url: SWF Player URL (may be None).
808 The following fields are optional. Their primary purpose is to allow
809 youtube-dl to serve as the backend for a video search function, such
810 as the one in youtube2mp3. They are only used when their respective
811 forced printing functions are called:
813 thumbnail: Full URL to a video thumbnail image.
814 description: One-line video description.
816 Subclasses of this one should re-define the _real_initialize() and
817 _real_extract() methods, as well as the suitable() static method.
818 Probably, they should also be instantiated and added to the main
825 def __init__(self, downloader=None):
826 """Constructor. Receives an optional downloader."""
828 self.set_downloader(downloader)
832 """Receives a URL and returns True if suitable for this IE."""
835 def initialize(self):
836 """Initializes an instance (authentication, etc)."""
838 self._real_initialize()
841 def extract(self, url):
842 """Extracts URL information and returns it in list of dicts."""
844 return self._real_extract(url)
846 def set_downloader(self, downloader):
847 """Sets the downloader for this IE."""
848 self._downloader = downloader
850 def _real_initialize(self):
851 """Real initialization process. Redefine in subclasses."""
854 def _real_extract(self, url):
855 """Real extraction process. Redefine in subclasses."""
858 class YoutubeIE(InfoExtractor):
859 """Information extractor for youtube.com."""
861 _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
862 _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
863 _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
864 _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
865 _NETRC_MACHINE = 'youtube'
866 # Listed in order of quality
867 _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
868 _video_extensions = {
874 '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
881 return (re.match(YoutubeIE._VALID_URL, url) is not None)
883 def report_lang(self):
884 """Report attempt to set language."""
885 self._downloader.to_screen(u'[youtube] Setting language')
887 def report_login(self):
888 """Report attempt to log in."""
889 self._downloader.to_screen(u'[youtube] Logging in')
891 def report_age_confirmation(self):
892 """Report attempt to confirm age."""
893 self._downloader.to_screen(u'[youtube] Confirming age')
895 def report_video_webpage_download(self, video_id):
896 """Report attempt to download video webpage."""
897 self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
899 def report_video_info_webpage_download(self, video_id):
900 """Report attempt to download video info webpage."""
901 self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
903 def report_information_extraction(self, video_id):
904 """Report attempt to extract video information."""
905 self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
907 def report_unavailable_format(self, video_id, format):
908 """Report extracted video URL."""
909 self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
911 def report_rtmp_download(self):
912 """Indicate the download will use the RTMP protocol."""
913 self._downloader.to_screen(u'[youtube] RTMP download detected')
915 def _real_initialize(self):
916 if self._downloader is None:
921 downloader_params = self._downloader.params
923 # Attempt to use provided username and password or .netrc data
924 if downloader_params.get('username', None) is not None:
925 username = downloader_params['username']
926 password = downloader_params['password']
927 elif downloader_params.get('usenetrc', False):
929 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
934 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
935 except (IOError, netrc.NetrcParseError), err:
936 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
940 request = urllib2.Request(self._LANG_URL)
943 urllib2.urlopen(request).read()
944 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
945 self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
948 # No authentication to be performed
954 'current_form': 'loginForm',
956 'action_login': 'Log In',
957 'username': username,
958 'password': password,
960 request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
963 login_results = urllib2.urlopen(request).read()
964 if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
965 self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
967 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
968 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
974 'action_confirm': 'Confirm',
976 request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))
978 self.report_age_confirmation()
979 age_results = urllib2.urlopen(request).read()
980 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
981 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
984 def _real_extract(self, url):
985 # Extract video id from URL
986 mobj = re.match(self._VALID_URL, url)
988 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
990 video_id = mobj.group(2)
993 self.report_video_webpage_download(video_id)
994 request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
996 video_webpage = urllib2.urlopen(request).read()
997 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
998 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
1001 # Attempt to extract SWF player URL
1002 mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1003 if mobj is not None:
1004 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1009 self.report_video_info_webpage_download(video_id)
1010 for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
1011 video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1012 % (video_id, el_type))
1013 request = urllib2.Request(video_info_url)
1015 video_info_webpage = urllib2.urlopen(request).read()
1016 video_info = parse_qs(video_info_webpage)
1017 if 'token' in video_info:
1019 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1020 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
1022 if 'token' not in video_info:
1023 if 'reason' in video_info:
1024 self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
1026 self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
1029 # Start extracting information
1030 self.report_information_extraction(video_id)
1033 if 'author' not in video_info:
1034 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1036 video_uploader = urllib.unquote_plus(video_info['author'][0])
1039 if 'title' not in video_info:
1040 self._downloader.trouble(u'ERROR: unable to extract video title')
1042 video_title = urllib.unquote_plus(video_info['title'][0])
1043 video_title = video_title.decode('utf-8')
1044 video_title = sanitize_title(video_title)
1047 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1048 simple_title = simple_title.strip(ur'_')
1051 if 'thumbnail_url' not in video_info:
1052 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
1053 video_thumbnail = ''
1054 else: # don't panic if we can't find it
1055 video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
1059 mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
1060 if mobj is not None:
1061 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1062 format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
1063 for expression in format_expressions:
1065 upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
1070 video_description = 'No description available.'
1071 if self._downloader.params.get('forcedescription', False):
1072 mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
1073 if mobj is not None:
1074 video_description = mobj.group(1)
1077 video_token = urllib.unquote_plus(video_info['token'][0])
1079 # Decide which formats to download
1080 req_format = self._downloader.params.get('format', None)
1082 if 'fmt_url_map' in video_info and len(video_info['fmt_url_map']) >= 1 and ',' in video_info['fmt_url_map'][0]:
1083 url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
1084 format_limit = self._downloader.params.get('format_limit', None)
1085 if format_limit is not None and format_limit in self._available_formats:
1086 format_list = self._available_formats[self._available_formats.index(format_limit):]
1088 format_list = self._available_formats
1089 existing_formats = [x for x in format_list if x in url_map]
1090 if len(existing_formats) == 0:
1091 self._downloader.trouble(u'ERROR: no known formats available for video')
1093 if req_format is None:
1094 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
1095 elif req_format == '-1':
1096 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
1099 if req_format not in url_map:
1100 self._downloader.trouble(u'ERROR: requested format not available')
1102 video_url_list = [(req_format, url_map[req_format])] # Specific format
1104 elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1105 self.report_rtmp_download()
1106 video_url_list = [(None, video_info['conn'][0])]
1109 self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
1112 for format_param, video_real_url in video_url_list:
1113 # At this point we have a new video
1114 self._downloader.increment_downloads()
1117 video_extension = self._video_extensions.get(format_param, 'flv')
1119 # Find the video URL in fmt_url_map or conn paramters
1121 # Process video information
1122 self._downloader.process_info({
1123 'id': video_id.decode('utf-8'),
1124 'url': video_real_url.decode('utf-8'),
1125 'uploader': video_uploader.decode('utf-8'),
1126 'upload_date': upload_date,
1127 'title': video_title,
1128 'stitle': simple_title,
1129 'ext': video_extension.decode('utf-8'),
1130 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
1131 'thumbnail': video_thumbnail.decode('utf-8'),
1132 'description': video_description.decode('utf-8'),
1133 'player_url': player_url,
1135 except UnavailableVideoError, err:
1136 self._downloader.trouble(u'\nERROR: unable to download video')
1139 class MetacafeIE(InfoExtractor):
1140 """Information Extractor for metacafe.com."""
1142 _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
1143 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
1144 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
1147 def __init__(self, youtube_ie, downloader=None):
1148 InfoExtractor.__init__(self, downloader)
1149 self._youtube_ie = youtube_ie
1153 return (re.match(MetacafeIE._VALID_URL, url) is not None)
1155 def report_disclaimer(self):
1156 """Report disclaimer retrieval."""
1157 self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
1159 def report_age_confirmation(self):
1160 """Report attempt to confirm age."""
1161 self._downloader.to_screen(u'[metacafe] Confirming age')
1163 def report_download_webpage(self, video_id):
1164 """Report webpage download."""
1165 self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
1167 def report_extraction(self, video_id):
1168 """Report information extraction."""
1169 self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
1171 def _real_initialize(self):
1172 # Retrieve disclaimer
1173 request = urllib2.Request(self._DISCLAIMER)
1175 self.report_disclaimer()
1176 disclaimer = urllib2.urlopen(request).read()
1177 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1178 self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
1184 'submit': "Continue - I'm over 18",
1186 request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))
1188 self.report_age_confirmation()
1189 disclaimer = urllib2.urlopen(request).read()
1190 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1191 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
1194 def _real_extract(self, url):
1195 # Extract id and simplified title from URL
1196 mobj = re.match(self._VALID_URL, url)
1198 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1201 video_id = mobj.group(1)
1203 # Check if video comes from YouTube
1204 mobj2 = re.match(r'^yt-(.*)$', video_id)
1205 if mobj2 is not None:
1206 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
1209 # At this point we have a new video
1210 self._downloader.increment_downloads()
1212 simple_title = mobj.group(2).decode('utf-8')
1214 # Retrieve video webpage to extract further information
1215 request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
1217 self.report_download_webpage(video_id)
1218 webpage = urllib2.urlopen(request).read()
1219 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1220 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
1223 # Extract URL, uploader and title from webpage
1224 self.report_extraction(video_id)
1225 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
1226 if mobj is not None:
1227 mediaURL = urllib.unquote(mobj.group(1))
1228 video_extension = mediaURL[-3:]
1230 # Extract gdaKey if available
1231 mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
1233 video_url = mediaURL
1235 gdaKey = mobj.group(1)
1236 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
1238 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
1240 self._downloader.trouble(u'ERROR: unable to extract media URL')
1242 vardict = parse_qs(mobj.group(1))
1243 if 'mediaData' not in vardict:
1244 self._downloader.trouble(u'ERROR: unable to extract media URL')
1246 mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
1248 self._downloader.trouble(u'ERROR: unable to extract media URL')
1250 mediaURL = mobj.group(1).replace('\\/', '/')
1251 video_extension = mediaURL[-3:]
1252 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
1254 mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
1256 self._downloader.trouble(u'ERROR: unable to extract title')
1258 video_title = mobj.group(1).decode('utf-8')
1259 video_title = sanitize_title(video_title)
1261 mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
1263 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1265 video_uploader = mobj.group(1)
1268 # Process video information
1269 self._downloader.process_info({
1270 'id': video_id.decode('utf-8'),
1271 'url': video_url.decode('utf-8'),
1272 'uploader': video_uploader.decode('utf-8'),
1273 'upload_date': u'NA',
1274 'title': video_title,
1275 'stitle': simple_title,
1276 'ext': video_extension.decode('utf-8'),
1280 except UnavailableVideoError:
1281 self._downloader.trouble(u'\nERROR: unable to download video')
1284 class DailymotionIE(InfoExtractor):
1285 """Information Extractor for Dailymotion"""
1287 _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
1289 def __init__(self, downloader=None):
1290 InfoExtractor.__init__(self, downloader)
1294 return (re.match(DailymotionIE._VALID_URL, url) is not None)
1296 def report_download_webpage(self, video_id):
1297 """Report webpage download."""
1298 self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
1300 def report_extraction(self, video_id):
1301 """Report information extraction."""
1302 self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
1304 def _real_initialize(self):
1307 def _real_extract(self, url):
1308 # Extract id and simplified title from URL
1309 mobj = re.match(self._VALID_URL, url)
1311 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1314 # At this point we have a new video
1315 self._downloader.increment_downloads()
1316 video_id = mobj.group(1)
1318 simple_title = mobj.group(2).decode('utf-8')
1319 video_extension = 'flv'
1321 # Retrieve video webpage to extract further information
1322 request = urllib2.Request(url)
1324 self.report_download_webpage(video_id)
1325 webpage = urllib2.urlopen(request).read()
1326 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1327 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
1330 # Extract URL, uploader and title from webpage
1331 self.report_extraction(video_id)
1332 mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
1334 self._downloader.trouble(u'ERROR: unable to extract media URL')
1336 mediaURL = urllib.unquote(mobj.group(1))
1338 # if needed add http://www.dailymotion.com/ if relative URL
1340 video_url = mediaURL
1342 # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
1343 mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
1345 self._downloader.trouble(u'ERROR: unable to extract title')
1347 video_title = mobj.group(1).decode('utf-8')
1348 video_title = sanitize_title(video_title)
1350 mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
1352 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1354 video_uploader = mobj.group(1)
1357 # Process video information
1358 self._downloader.process_info({
1359 'id': video_id.decode('utf-8'),
1360 'url': video_url.decode('utf-8'),
1361 'uploader': video_uploader.decode('utf-8'),
1362 'upload_date': u'NA',
1363 'title': video_title,
1364 'stitle': simple_title,
1365 'ext': video_extension.decode('utf-8'),
1369 except UnavailableVideoError:
1370 self._downloader.trouble(u'\nERROR: unable to download video')
1372 class GoogleIE(InfoExtractor):
1373 """Information extractor for video.google.com."""
1375 _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
1377 def __init__(self, downloader=None):
1378 InfoExtractor.__init__(self, downloader)
1382 return (re.match(GoogleIE._VALID_URL, url) is not None)
1384 def report_download_webpage(self, video_id):
1385 """Report webpage download."""
1386 self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
1388 def report_extraction(self, video_id):
1389 """Report information extraction."""
1390 self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
1392 def _real_initialize(self):
1395 def _real_extract(self, url):
1396 # Extract id from URL
1397 mobj = re.match(self._VALID_URL, url)
1399 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1402 # At this point we have a new video
1403 self._downloader.increment_downloads()
1404 video_id = mobj.group(1)
1406 video_extension = 'mp4'
1408 # Retrieve video webpage to extract further information
1409 request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
1411 self.report_download_webpage(video_id)
1412 webpage = urllib2.urlopen(request).read()
1413 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1414 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1417 # Extract URL, uploader, and title from webpage
1418 self.report_extraction(video_id)
1419 mobj = re.search(r"download_url:'([^']+)'", webpage)
1421 video_extension = 'flv'
1422 mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
1424 self._downloader.trouble(u'ERROR: unable to extract media URL')
1426 mediaURL = urllib.unquote(mobj.group(1))
1427 mediaURL = mediaURL.replace('\\x3d', '\x3d')
1428 mediaURL = mediaURL.replace('\\x26', '\x26')
1430 video_url = mediaURL
1432 mobj = re.search(r'<title>(.*)</title>', webpage)
1434 self._downloader.trouble(u'ERROR: unable to extract title')
1436 video_title = mobj.group(1).decode('utf-8')
1437 video_title = sanitize_title(video_title)
1438 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1440 # Extract video description
1441 mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
1443 self._downloader.trouble(u'ERROR: unable to extract video description')
1445 video_description = mobj.group(1).decode('utf-8')
1446 if not video_description:
1447 video_description = 'No description available.'
1449 # Extract video thumbnail
1450 if self._downloader.params.get('forcethumbnail', False):
1451 request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
1453 webpage = urllib2.urlopen(request).read()
1454 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1455 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1457 mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
1459 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1461 video_thumbnail = mobj.group(1)
1462 else: # we need something to pass to process_info
1463 video_thumbnail = ''
1467 # Process video information
1468 self._downloader.process_info({
1469 'id': video_id.decode('utf-8'),
1470 'url': video_url.decode('utf-8'),
1472 'upload_date': u'NA',
1473 'title': video_title,
1474 'stitle': simple_title,
1475 'ext': video_extension.decode('utf-8'),
1479 except UnavailableVideoError:
1480 self._downloader.trouble(u'\nERROR: unable to download video')
1483 class PhotobucketIE(InfoExtractor):
1484 """Information extractor for photobucket.com."""
1486 _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
1488 def __init__(self, downloader=None):
1489 InfoExtractor.__init__(self, downloader)
1493 return (re.match(PhotobucketIE._VALID_URL, url) is not None)
1495 def report_download_webpage(self, video_id):
1496 """Report webpage download."""
1497 self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
1499 def report_extraction(self, video_id):
1500 """Report information extraction."""
1501 self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
1503 def _real_initialize(self):
1506 def _real_extract(self, url):
1507 # Extract id from URL
1508 mobj = re.match(self._VALID_URL, url)
1510 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1513 # At this point we have a new video
1514 self._downloader.increment_downloads()
1515 video_id = mobj.group(1)
1517 video_extension = 'flv'
1519 # Retrieve video webpage to extract further information
1520 request = urllib2.Request(url)
1522 self.report_download_webpage(video_id)
1523 webpage = urllib2.urlopen(request).read()
1524 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1525 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1528 # Extract URL, uploader, and title from webpage
1529 self.report_extraction(video_id)
1530 mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
1532 self._downloader.trouble(u'ERROR: unable to extract media URL')
1534 mediaURL = urllib.unquote(mobj.group(1))
1536 video_url = mediaURL
1538 mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
1540 self._downloader.trouble(u'ERROR: unable to extract title')
1542 video_title = mobj.group(1).decode('utf-8')
1543 video_title = sanitize_title(video_title)
1544 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1546 video_uploader = mobj.group(2).decode('utf-8')
1549 # Process video information
1550 self._downloader.process_info({
1551 'id': video_id.decode('utf-8'),
1552 'url': video_url.decode('utf-8'),
1553 'uploader': video_uploader,
1554 'upload_date': u'NA',
1555 'title': video_title,
1556 'stitle': simple_title,
1557 'ext': video_extension.decode('utf-8'),
1561 except UnavailableVideoError:
1562 self._downloader.trouble(u'\nERROR: unable to download video')
1565 class YahooIE(InfoExtractor):
1566 """Information extractor for video.yahoo.com."""
1568 # _VALID_URL matches all Yahoo! Video URLs
1569 # _VPAGE_URL matches only the extractable '/watch/' URLs
1570 _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
1571 _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
1573 def __init__(self, downloader=None):
1574 InfoExtractor.__init__(self, downloader)
1578 return (re.match(YahooIE._VALID_URL, url) is not None)
1580 def report_download_webpage(self, video_id):
1581 """Report webpage download."""
1582 self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
1584 def report_extraction(self, video_id):
1585 """Report information extraction."""
1586 self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
1588 def _real_initialize(self):
1591 def _real_extract(self, url, new_video=True):
1592 # Extract ID from URL
1593 mobj = re.match(self._VALID_URL, url)
1595 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1598 # At this point we have a new video
1599 self._downloader.increment_downloads()
1600 video_id = mobj.group(2)
1601 video_extension = 'flv'
1603 # Rewrite valid but non-extractable URLs as
1604 # extractable English language /watch/ URLs
1605 if re.match(self._VPAGE_URL, url) is None:
1606 request = urllib2.Request(url)
1608 webpage = urllib2.urlopen(request).read()
1609 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1610 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1613 mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
1615 self._downloader.trouble(u'ERROR: Unable to extract id field')
1617 yahoo_id = mobj.group(1)
1619 mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
1621 self._downloader.trouble(u'ERROR: Unable to extract vid field')
1623 yahoo_vid = mobj.group(1)
1625 url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
1626 return self._real_extract(url, new_video=False)
1628 # Retrieve video webpage to extract further information
1629 request = urllib2.Request(url)
1631 self.report_download_webpage(video_id)
1632 webpage = urllib2.urlopen(request).read()
1633 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1634 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1637 # Extract uploader and title from webpage
1638 self.report_extraction(video_id)
1639 mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
1641 self._downloader.trouble(u'ERROR: unable to extract video title')
1643 video_title = mobj.group(1).decode('utf-8')
1644 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1646 mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
1648 self._downloader.trouble(u'ERROR: unable to extract video uploader')
1650 video_uploader = mobj.group(1).decode('utf-8')
1652 # Extract video thumbnail
1653 mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
1655 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1657 video_thumbnail = mobj.group(1).decode('utf-8')
1659 # Extract video description
1660 mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
1662 self._downloader.trouble(u'ERROR: unable to extract video description')
1664 video_description = mobj.group(1).decode('utf-8')
1665 if not video_description: video_description = 'No description available.'
1667 # Extract video height and width
1668 mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
1670 self._downloader.trouble(u'ERROR: unable to extract video height')
1672 yv_video_height = mobj.group(1)
1674 mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
1676 self._downloader.trouble(u'ERROR: unable to extract video width')
1678 yv_video_width = mobj.group(1)
1680 # Retrieve video playlist to extract media URL
1681 # I'm not completely sure what all these options are, but we
1682 # seem to need most of them, otherwise the server sends a 401.
1683 yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
1684 yv_bitrate = '700' # according to Wikipedia this is hard-coded
1685 request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
1686 '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
1687 '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
1689 self.report_download_webpage(video_id)
1690 webpage = urllib2.urlopen(request).read()
1691 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1692 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1695 # Extract media URL from playlist XML
1696 mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
1698 self._downloader.trouble(u'ERROR: Unable to extract media URL')
1700 video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
1701 video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
1704 # Process video information
1705 self._downloader.process_info({
1706 'id': video_id.decode('utf-8'),
1708 'uploader': video_uploader,
1709 'upload_date': u'NA',
1710 'title': video_title,
1711 'stitle': simple_title,
1712 'ext': video_extension.decode('utf-8'),
1713 'thumbnail': video_thumbnail.decode('utf-8'),
1714 'description': video_description,
1715 'thumbnail': video_thumbnail,
1716 'description': video_description,
1719 except UnavailableVideoError:
1720 self._downloader.trouble(u'\nERROR: unable to download video')
1723 class VimeoIE(InfoExtractor):
1724 """Information extractor for vimeo.com."""
1726 # _VALID_URL matches Vimeo URLs
1727 _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
1729 def __init__(self, downloader=None):
1730 InfoExtractor.__init__(self, downloader)
1734 return (re.match(VimeoIE._VALID_URL, url) is not None)
1736 def report_download_webpage(self, video_id):
1737 """Report webpage download."""
1738 self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
1740 def report_extraction(self, video_id):
1741 """Report information extraction."""
1742 self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
1744 def _real_initialize(self):
1747 def _real_extract(self, url, new_video=True):
1748 # Extract ID from URL
1749 mobj = re.match(self._VALID_URL, url)
1751 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1754 # At this point we have a new video
1755 self._downloader.increment_downloads()
1756 video_id = mobj.group(1)
1758 # Retrieve video webpage to extract further information
1759 request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)
1761 self.report_download_webpage(video_id)
1762 webpage = urllib2.urlopen(request).read()
1763 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1764 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1767 # Now we begin extracting as much information as we can from what we
1768 # retrieved. First we extract the information common to all extractors,
1769 # and latter we extract those that are Vimeo specific.
1770 self.report_extraction(video_id)
1773 mobj = re.search(r'<caption>(.*?)</caption>', webpage)
1775 self._downloader.trouble(u'ERROR: unable to extract video title')
1777 video_title = mobj.group(1).decode('utf-8')
1778 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1781 mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
1783 self._downloader.trouble(u'ERROR: unable to extract video uploader')
1785 video_uploader = mobj.group(1).decode('utf-8')
1787 # Extract video thumbnail
1788 mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage)
1790 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1792 video_thumbnail = mobj.group(1).decode('utf-8')
1794 # # Extract video description
1795 # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage)
1797 # self._downloader.trouble(u'ERROR: unable to extract video description')
1799 # video_description = mobj.group(1).decode('utf-8')
1800 # if not video_description: video_description = 'No description available.'
1801 video_description = 'Foo.'
1803 # Vimeo specific: extract request signature
1804 mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
1806 self._downloader.trouble(u'ERROR: unable to extract request signature')
1808 sig = mobj.group(1).decode('utf-8')
1810 # Vimeo specific: Extract request signature expiration
1811 mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
1813 self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
1815 sig_exp = mobj.group(1).decode('utf-8')
1817 video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
1820 # Process video information
1821 self._downloader.process_info({
1822 'id': video_id.decode('utf-8'),
1824 'uploader': video_uploader,
1825 'upload_date': u'NA',
1826 'title': video_title,
1827 'stitle': simple_title,
1829 'thumbnail': video_thumbnail.decode('utf-8'),
1830 'description': video_description,
1831 'thumbnail': video_thumbnail,
1832 'description': video_description,
1835 except UnavailableVideoError:
1836 self._downloader.trouble(u'ERROR: unable to download video')
1839 class GenericIE(InfoExtractor):
1840 """Generic last-resort information extractor."""
1842 def __init__(self, downloader=None):
1843 InfoExtractor.__init__(self, downloader)
1849 def report_download_webpage(self, video_id):
1850 """Report webpage download."""
1851 self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
1852 self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
1854 def report_extraction(self, video_id):
1855 """Report information extraction."""
1856 self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
1858 def _real_initialize(self):
1861 def _real_extract(self, url):
1862 # At this point we have a new video
1863 self._downloader.increment_downloads()
1865 video_id = url.split('/')[-1]
1866 request = urllib2.Request(url)
1868 self.report_download_webpage(video_id)
1869 webpage = urllib2.urlopen(request).read()
1870 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1871 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1873 except ValueError, err:
1874 # since this is the last-resort InfoExtractor, if
1875 # this error is thrown, it'll be thrown here
1876 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1879 self.report_extraction(video_id)
1880 # Start with something easy: JW Player in SWFObject
1881 mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
1883 # Broaden the search a little bit
1884 mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
1886 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1889 # It's possible that one of the regexes
1890 # matched, but returned an empty group:
1891 if mobj.group(1) is None:
1892 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1895 video_url = urllib.unquote(mobj.group(1))
1896 video_id = os.path.basename(video_url)
1898 # here's a fun little line of code for you:
1899 video_extension = os.path.splitext(video_id)[1][1:]
1900 video_id = os.path.splitext(video_id)[0]
1902 # it's tempting to parse this further, but you would
1903 # have to take into account all the variations like
1904 # Video Title - Site Name
1905 # Site Name | Video Title
1906 # Video Title - Tagline | Site Name
1907 # and so on and so forth; it's just not practical
1908 mobj = re.search(r'<title>(.*)</title>', webpage)
1910 self._downloader.trouble(u'ERROR: unable to extract title')
1912 video_title = mobj.group(1).decode('utf-8')
1913 video_title = sanitize_title(video_title)
1914 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1916 # video uploader is domain name
1917 mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
1919 self._downloader.trouble(u'ERROR: unable to extract title')
1921 video_uploader = mobj.group(1).decode('utf-8')
1924 # Process video information
1925 self._downloader.process_info({
1926 'id': video_id.decode('utf-8'),
1927 'url': video_url.decode('utf-8'),
1928 'uploader': video_uploader,
1929 'upload_date': u'NA',
1930 'title': video_title,
1931 'stitle': simple_title,
1932 'ext': video_extension.decode('utf-8'),
1936 except UnavailableVideoError, err:
1937 self._downloader.trouble(u'\nERROR: unable to download video')
1940 class YoutubeSearchIE(InfoExtractor):
1941 """Information Extractor for YouTube search queries."""
1942 _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
1943 _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
1944 _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
1945 _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
1947 _max_youtube_results = 1000
1949 def __init__(self, youtube_ie, downloader=None):
1950 InfoExtractor.__init__(self, downloader)
1951 self._youtube_ie = youtube_ie
1955 return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
1957 def report_download_page(self, query, pagenum):
1958 """Report attempt to download playlist page with given number."""
1959 query = query.decode(preferredencoding())
1960 self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
1962 def _real_initialize(self):
1963 self._youtube_ie.initialize()
1965 def _real_extract(self, query):
1966 mobj = re.match(self._VALID_QUERY, query)
1968 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1971 prefix, query = query.split(':')
1973 query = query.encode('utf-8')
1975 self._download_n_results(query, 1)
1977 elif prefix == 'all':
1978 self._download_n_results(query, self._max_youtube_results)
1984 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1986 elif n > self._max_youtube_results:
1987 self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
1988 n = self._max_youtube_results
1989 self._download_n_results(query, n)
1991 except ValueError: # parsing prefix as integer fails
1992 self._download_n_results(query, 1)
1995 def _download_n_results(self, query, n):
1996 """Downloads a specified number of results for a query"""
1999 already_seen = set()
2003 self.report_download_page(query, pagenum)
2004 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2005 request = urllib2.Request(result_url)
2007 page = urllib2.urlopen(request).read()
2008 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2009 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2012 # Extract video identifiers
2013 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2014 video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
2015 if video_id not in already_seen:
2016 video_ids.append(video_id)
2017 already_seen.add(video_id)
2018 if len(video_ids) == n:
2019 # Specified n videos reached
2020 for id in video_ids:
2021 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2024 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2025 for id in video_ids:
2026 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2029 pagenum = pagenum + 1
2031 class GoogleSearchIE(InfoExtractor):
2032 """Information Extractor for Google Video search queries."""
2033 _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
2034 _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
2035 _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
2036 _MORE_PAGES_INDICATOR = r'<span>Next</span>'
2038 _max_google_results = 1000
2040 def __init__(self, google_ie, downloader=None):
2041 InfoExtractor.__init__(self, downloader)
2042 self._google_ie = google_ie
2046 return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
2048 def report_download_page(self, query, pagenum):
2049 """Report attempt to download playlist page with given number."""
2050 query = query.decode(preferredencoding())
2051 self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
2053 def _real_initialize(self):
2054 self._google_ie.initialize()
2056 def _real_extract(self, query):
2057 mobj = re.match(self._VALID_QUERY, query)
2059 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
2062 prefix, query = query.split(':')
2064 query = query.encode('utf-8')
2066 self._download_n_results(query, 1)
2068 elif prefix == 'all':
2069 self._download_n_results(query, self._max_google_results)
2075 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
2077 elif n > self._max_google_results:
2078 self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
2079 n = self._max_google_results
2080 self._download_n_results(query, n)
2082 except ValueError: # parsing prefix as integer fails
2083 self._download_n_results(query, 1)
2086 def _download_n_results(self, query, n):
2087 """Downloads a specified number of results for a query"""
2090 already_seen = set()
2094 self.report_download_page(query, pagenum)
2095 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2096 request = urllib2.Request(result_url)
2098 page = urllib2.urlopen(request).read()
2099 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2100 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2103 # Extract video identifiers
2104 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2105 video_id = mobj.group(1)
2106 if video_id not in already_seen:
2107 video_ids.append(video_id)
2108 already_seen.add(video_id)
2109 if len(video_ids) == n:
2110 # Specified n videos reached
2111 for id in video_ids:
2112 self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
2115 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2116 for id in video_ids:
2117 self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
2120 pagenum = pagenum + 1
2122 class YahooSearchIE(InfoExtractor):
2123 """Information Extractor for Yahoo! Video search queries."""
2124 _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
2125 _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
2126 _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
2127 _MORE_PAGES_INDICATOR = r'\s*Next'
2129 _max_yahoo_results = 1000
2131 def __init__(self, yahoo_ie, downloader=None):
2132 InfoExtractor.__init__(self, downloader)
2133 self._yahoo_ie = yahoo_ie
2137 return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
2139 def report_download_page(self, query, pagenum):
2140 """Report attempt to download playlist page with given number."""
2141 query = query.decode(preferredencoding())
2142 self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
2144 def _real_initialize(self):
2145 self._yahoo_ie.initialize()
2147 def _real_extract(self, query):
2148 mobj = re.match(self._VALID_QUERY, query)
2150 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
2153 prefix, query = query.split(':')
2155 query = query.encode('utf-8')
2157 self._download_n_results(query, 1)
2159 elif prefix == 'all':
2160 self._download_n_results(query, self._max_yahoo_results)
2166 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
2168 elif n > self._max_yahoo_results:
2169 self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
2170 n = self._max_yahoo_results
2171 self._download_n_results(query, n)
2173 except ValueError: # parsing prefix as integer fails
2174 self._download_n_results(query, 1)
2177 def _download_n_results(self, query, n):
2178 """Downloads a specified number of results for a query"""
2181 already_seen = set()
2185 self.report_download_page(query, pagenum)
2186 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
2187 request = urllib2.Request(result_url)
2189 page = urllib2.urlopen(request).read()
2190 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2191 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2194 # Extract video identifiers
2195 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2196 video_id = mobj.group(1)
2197 if video_id not in already_seen:
2198 video_ids.append(video_id)
2199 already_seen.add(video_id)
2200 if len(video_ids) == n:
2201 # Specified n videos reached
2202 for id in video_ids:
2203 self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
2206 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2207 for id in video_ids:
2208 self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
2211 pagenum = pagenum + 1
2213 class YoutubePlaylistIE(InfoExtractor):
2214 """Information Extractor for YouTube playlists."""
2216 _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_-]+))?.*'
2217 _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
2218 _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
2219 _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
2222 def __init__(self, youtube_ie, downloader=None):
2223 InfoExtractor.__init__(self, downloader)
2224 self._youtube_ie = youtube_ie
2228 return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
2230 def report_download_page(self, playlist_id, pagenum):
2231 """Report attempt to download playlist page with given number."""
2232 self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
2234 def _real_initialize(self):
2235 self._youtube_ie.initialize()
2237 def _real_extract(self, url):
2238 # Extract playlist id
2239 mobj = re.match(self._VALID_URL, url)
2241 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
2245 if mobj.group(3) is not None:
2246 self._youtube_ie.extract(mobj.group(3))
2249 # Download playlist pages
2250 # prefix is 'p' as default for playlists but there are other types that need extra care
2251 playlist_prefix = mobj.group(1)
2252 if playlist_prefix == 'a':
2253 playlist_access = 'artist'
2255 playlist_prefix = 'p'
2256 playlist_access = 'view_play_list'
2257 playlist_id = mobj.group(2)
2262 self.report_download_page(playlist_id, pagenum)
2263 request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
2265 page = urllib2.urlopen(request).read()
2266 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2267 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2270 # Extract video identifiers
2272 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2273 if mobj.group(1) not in ids_in_page:
2274 ids_in_page.append(mobj.group(1))
2275 video_ids.extend(ids_in_page)
2277 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
2279 pagenum = pagenum + 1
2281 playliststart = self._downloader.params.get('playliststart', 1) - 1
2282 playlistend = self._downloader.params.get('playlistend', -1)
2283 video_ids = video_ids[playliststart:playlistend]
2285 for id in video_ids:
2286 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2289 class YoutubeUserIE(InfoExtractor):
2290 """Information Extractor for YouTube users."""
2292 _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
2293 _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
2294 _GDATA_PAGE_SIZE = 50
2295 _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
2296 _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
2299 def __init__(self, youtube_ie, downloader=None):
2300 InfoExtractor.__init__(self, downloader)
2301 self._youtube_ie = youtube_ie
2305 return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
2307 def report_download_page(self, username, start_index):
2308 """Report attempt to download user page."""
2309 self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
2310 (username, start_index, start_index + self._GDATA_PAGE_SIZE))
2312 def _real_initialize(self):
2313 self._youtube_ie.initialize()
2315 def _real_extract(self, url):
2317 mobj = re.match(self._VALID_URL, url)
2319 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
2322 username = mobj.group(1)
2324 # Download video ids using YouTube Data API. Result size per
2325 # query is limited (currently to 50 videos) so we need to query
2326 # page by page until there are no video ids - it means we got
2333 start_index = pagenum * self._GDATA_PAGE_SIZE + 1
2334 self.report_download_page(username, start_index)
2336 request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
2339 page = urllib2.urlopen(request).read()
2340 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2341 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2344 # Extract video identifiers
2347 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2348 if mobj.group(1) not in ids_in_page:
2349 ids_in_page.append(mobj.group(1))
2351 video_ids.extend(ids_in_page)
2353 # A little optimization - if current page is not
2354 # "full", ie. does not contain PAGE_SIZE video ids then
2355 # we can assume that this page is the last one - there
2356 # are no more ids on further pages - no need to query
2359 if len(ids_in_page) < self._GDATA_PAGE_SIZE:
2364 all_ids_count = len(video_ids)
2365 playliststart = self._downloader.params.get('playliststart', 1) - 1
2366 playlistend = self._downloader.params.get('playlistend', -1)
2368 if playlistend == -1:
2369 video_ids = video_ids[playliststart:]
2371 video_ids = video_ids[playliststart:playlistend]
2373 self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
2374 (username, all_ids_count, len(video_ids)))
2376 for video_id in video_ids:
2377 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
2380 class DepositFilesIE(InfoExtractor):
2381 """Information extractor for depositfiles.com"""
2383 _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
2385 def __init__(self, downloader=None):
2386 InfoExtractor.__init__(self, downloader)
2390 return (re.match(DepositFilesIE._VALID_URL, url) is not None)
2392 def report_download_webpage(self, file_id):
2393 """Report webpage download."""
2394 self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
2396 def report_extraction(self, file_id):
2397 """Report information extraction."""
2398 self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
2400 def _real_initialize(self):
2403 def _real_extract(self, url):
2404 # At this point we have a new file
2405 self._downloader.increment_downloads()
2407 file_id = url.split('/')[-1]
2408 # Rebuild url in english locale
2409 url = 'http://depositfiles.com/en/files/' + file_id
2411 # Retrieve file webpage with 'Free download' button pressed
2412 free_download_indication = { 'gateway_result' : '1' }
2413 request = urllib2.Request(url, urllib.urlencode(free_download_indication))
2415 self.report_download_webpage(file_id)
2416 webpage = urllib2.urlopen(request).read()
2417 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2418 self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
2421 # Search for the real file URL
2422 mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
2423 if (mobj is None) or (mobj.group(1) is None):
2424 # Try to figure out reason of the error.
2425 mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
2426 if (mobj is not None) and (mobj.group(1) is not None):
2427 restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
2428 self._downloader.trouble(u'ERROR: %s' % restriction_message)
2430 self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
2433 file_url = mobj.group(1)
2434 file_extension = os.path.splitext(file_url)[1][1:]
2436 # Search for file title
2437 mobj = re.search(r'<b title="(.*?)">', webpage)
2439 self._downloader.trouble(u'ERROR: unable to extract title')
2441 file_title = mobj.group(1).decode('utf-8')
2444 # Process file information
2445 self._downloader.process_info({
2446 'id': file_id.decode('utf-8'),
2447 'url': file_url.decode('utf-8'),
2449 'upload_date': u'NA',
2450 'title': file_title,
2451 'stitle': file_title,
2452 'ext': file_extension.decode('utf-8'),
2456 except UnavailableVideoError, err:
2457 self._downloader.trouble(u'ERROR: unable to download file')
2459 class FacebookIE(InfoExtractor):
2460 """Information Extractor for Facebook"""
2462 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
2463 _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
2464 _NETRC_MACHINE = 'facebook'
2465 _available_formats = ['highqual', 'lowqual']
2466 _video_extensions = {
2471 def __init__(self, downloader=None):
2472 InfoExtractor.__init__(self, downloader)
2476 return (re.match(FacebookIE._VALID_URL, url) is not None)
2478 def _reporter(self, message):
2479 """Add header and report message."""
2480 self._downloader.to_screen(u'[facebook] %s' % message)
2482 def report_login(self):
2483 """Report attempt to log in."""
2484 self._reporter(u'Logging in')
2486 def report_video_webpage_download(self, video_id):
2487 """Report attempt to download video webpage."""
2488 self._reporter(u'%s: Downloading video webpage' % video_id)
2490 def report_information_extraction(self, video_id):
2491 """Report attempt to extract video information."""
2492 self._reporter(u'%s: Extracting video information' % video_id)
2494 def _parse_page(self, video_webpage):
2495 """Extract video information from page"""
2497 data = {'title': r'class="video_title datawrap">(.*?)</',
2498 'description': r'<div class="datawrap">(.*?)</div>',
2499 'owner': r'\("video_owner_name", "(.*?)"\)',
2500 'upload_date': r'data-date="(.*?)"',
2501 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
2504 for piece in data.keys():
2505 mobj = re.search(data[piece], video_webpage)
2506 if mobj is not None:
2507 video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
2511 for fmt in self._available_formats:
2512 mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
2513 if mobj is not None:
2514 # URL is in a Javascript segment inside an escaped Unicode format within
2515 # the generally utf-8 page
2516 video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
2517 video_info['video_urls'] = video_urls
2521 def _real_initialize(self):
2522 if self._downloader is None:
2527 downloader_params = self._downloader.params
2529 # Attempt to use provided username and password or .netrc data
2530 if downloader_params.get('username', None) is not None:
2531 useremail = downloader_params['username']
2532 password = downloader_params['password']
2533 elif downloader_params.get('usenetrc', False):
2535 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
2536 if info is not None:
2540 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
2541 except (IOError, netrc.NetrcParseError), err:
2542 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
2545 if useremail is None:
2554 request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
2557 login_results = urllib2.urlopen(request).read()
2558 if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
2559 self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
2561 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2562 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
2565 def _real_extract(self, url):
2566 mobj = re.match(self._VALID_URL, url)
2568 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2570 video_id = mobj.group('ID')
2573 self.report_video_webpage_download(video_id)
2574 request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
2576 page = urllib2.urlopen(request)
2577 video_webpage = page.read()
2578 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2579 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
2582 # Start extracting information
2583 self.report_information_extraction(video_id)
2585 # Extract information
2586 video_info = self._parse_page(video_webpage)
2589 if 'owner' not in video_info:
2590 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
2592 video_uploader = video_info['owner']
2595 if 'title' not in video_info:
2596 self._downloader.trouble(u'ERROR: unable to extract video title')
2598 video_title = video_info['title']
2599 video_title = video_title.decode('utf-8')
2600 video_title = sanitize_title(video_title)
2603 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
2604 simple_title = simple_title.strip(ur'_')
2607 if 'thumbnail' not in video_info:
2608 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
2609 video_thumbnail = ''
2611 video_thumbnail = video_info['thumbnail']
2615 if 'upload_date' in video_info:
2616 upload_time = video_info['upload_date']
2617 timetuple = email.utils.parsedate_tz(upload_time)
2618 if timetuple is not None:
2620 upload_date = time.strftime('%Y%m%d', timetuple[0:9])
2625 video_description = 'No description available.'
2626 if (self._downloader.params.get('forcedescription', False) and
2627 'description' in video_info):
2628 video_description = video_info['description']
2630 url_map = video_info['video_urls']
2631 if len(url_map.keys()) > 0:
2632 # Decide which formats to download
2633 req_format = self._downloader.params.get('format', None)
2634 format_limit = self._downloader.params.get('format_limit', None)
2636 if format_limit is not None and format_limit in self._available_formats:
2637 format_list = self._available_formats[self._available_formats.index(format_limit):]
2639 format_list = self._available_formats
2640 existing_formats = [x for x in format_list if x in url_map]
2641 if len(existing_formats) == 0:
2642 self._downloader.trouble(u'ERROR: no known formats available for video')
2644 if req_format is None:
2645 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
2646 elif req_format == '-1':
2647 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
2650 if req_format not in url_map:
2651 self._downloader.trouble(u'ERROR: requested format not available')
2653 video_url_list = [(req_format, url_map[req_format])] # Specific format
2655 for format_param, video_real_url in video_url_list:
2657 # At this point we have a new video
2658 self._downloader.increment_downloads()
2661 video_extension = self._video_extensions.get(format_param, 'mp4')
2663 # Find the video URL in fmt_url_map or conn paramters
2665 # Process video information
2666 self._downloader.process_info({
2667 'id': video_id.decode('utf-8'),
2668 'url': video_real_url.decode('utf-8'),
2669 'uploader': video_uploader.decode('utf-8'),
2670 'upload_date': upload_date,
2671 'title': video_title,
2672 'stitle': simple_title,
2673 'ext': video_extension.decode('utf-8'),
2674 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
2675 'thumbnail': video_thumbnail.decode('utf-8'),
2676 'description': video_description.decode('utf-8'),
2679 except UnavailableVideoError, err:
2680 self._downloader.trouble(u'\nERROR: unable to download video')
2682 class PostProcessor(object):
2683 """Post Processor class.
2685 PostProcessor objects can be added to downloaders with their
2686 add_post_processor() method. When the downloader has finished a
2687 successful download, it will take its internal chain of PostProcessors
2688 and start calling the run() method on each one of them, first with
2689 an initial argument and then with the returned value of the previous
2692 The chain will be stopped if one of them ever returns None or the end
2693 of the chain is reached.
2695 PostProcessor objects follow a "mutual registration" process similar
2696 to InfoExtractor objects.
2701 def __init__(self, downloader=None):
2702 self._downloader = downloader
2704 def set_downloader(self, downloader):
2705 """Sets the downloader for this PP."""
2706 self._downloader = downloader
2708 def run(self, information):
2709 """Run the PostProcessor.
2711 The "information" argument is a dictionary like the ones
2712 composed by InfoExtractors. The only difference is that this
2713 one has an extra field called "filepath" that points to the
2716 When this method returns None, the postprocessing chain is
2717 stopped. However, this method may return an information
2718 dictionary that will be passed to the next postprocessing
2719 object in the chain. It can be the one it received after
2720 changing some fields.
2722 In addition, this method may raise a PostProcessingError
2723 exception that will be taken into account by the downloader
2726 return information # by default, do nothing
2728 class FFmpegExtractAudioPP(PostProcessor):
2730 def __init__(self, downloader=None, preferredcodec=None):
2731 PostProcessor.__init__(self, downloader)
2732 if preferredcodec is None:
2733 preferredcodec = 'best'
2734 self._preferredcodec = preferredcodec
2737 def get_audio_codec(path):
2739 cmd = ['ffprobe', '-show_streams', '--', path]
2740 handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
2741 output = handle.communicate()[0]
2742 if handle.wait() != 0:
2744 except (IOError, OSError):
2747 for line in output.split('\n'):
2748 if line.startswith('codec_name='):
2749 audio_codec = line.split('=')[1].strip()
2750 elif line.strip() == 'codec_type=audio' and audio_codec is not None:
2755 def run_ffmpeg(path, out_path, codec, more_opts):
2757 cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
2758 ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
2760 except (IOError, OSError):
2763 def run(self, information):
2764 path = information['filepath']
2766 filecodec = self.get_audio_codec(path)
2767 if filecodec is None:
2768 self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
2772 if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
2773 if filecodec == 'aac' or filecodec == 'mp3':
2774 # Lossless if possible
2776 extension = filecodec
2777 if filecodec == 'aac':
2778 more_opts = ['-f', 'adts']
2781 acodec = 'libmp3lame'
2783 more_opts = ['-ab', '128k']
2785 # We convert the audio (lossy)
2786 acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
2787 extension = self._preferredcodec
2788 more_opts = ['-ab', '128k']
2789 if self._preferredcodec == 'aac':
2790 more_opts += ['-f', 'adts']
2792 (prefix, ext) = os.path.splitext(path)
2793 new_path = prefix + '.' + extension
2794 self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path)
2795 status = self.run_ffmpeg(path, new_path, acodec, more_opts)
2798 self._downloader.to_stderr(u'WARNING: error running ffmpeg')
2803 except (IOError, OSError):
2804 self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
2807 information['filepath'] = new_path
2810 ### MAIN PROGRAM ###
2811 if __name__ == '__main__':
2813 # Modules needed only when running the main program
2817 # Function to update the program file with the latest version from the repository.
2818 def update_self(downloader, filename):
2819 # Note: downloader only used for options
2820 if not os.access(filename, os.W_OK):
2821 sys.exit('ERROR: no write permissions on %s' % filename)
2823 downloader.to_screen('Updating to latest stable version...')
2825 latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
2826 latest_version = urllib.urlopen(latest_url).read().strip()
2827 prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
2828 newcontent = urllib.urlopen(prog_url).read()
2829 except (IOError, OSError), err:
2830 sys.exit('ERROR: unable to download latest version')
2832 stream = open(filename, 'w')
2833 stream.write(newcontent)
2835 except (IOError, OSError), err:
2836 sys.exit('ERROR: unable to overwrite current version')
2837 downloader.to_screen('Updated to version %s' % latest_version)
2839 # Parse command line
2840 parser = optparse.OptionParser(
2841 usage='Usage: %prog [options] url...',
2842 version='2011.03.29',
2843 conflict_handler='resolve',
2846 parser.add_option('-h', '--help',
2847 action='help', help='print this help text and exit')
2848 parser.add_option('-v', '--version',
2849 action='version', help='print program version and exit')
2850 parser.add_option('-U', '--update',
2851 action='store_true', dest='update_self', help='update this program to latest stable version')
2852 parser.add_option('-i', '--ignore-errors',
2853 action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
2854 parser.add_option('-r', '--rate-limit',
2855 dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
2856 parser.add_option('-R', '--retries',
2857 dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
2858 parser.add_option('--playlist-start',
2859 dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
2860 parser.add_option('--playlist-end',
2861 dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
2862 parser.add_option('--dump-user-agent',
2863 action='store_true', dest='dump_user_agent',
2864 help='display the current browser identification', default=False)
2866 authentication = optparse.OptionGroup(parser, 'Authentication Options')
2867 authentication.add_option('-u', '--username',
2868 dest='username', metavar='USERNAME', help='account username')
2869 authentication.add_option('-p', '--password',
2870 dest='password', metavar='PASSWORD', help='account password')
2871 authentication.add_option('-n', '--netrc',
2872 action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
2873 parser.add_option_group(authentication)
2875 video_format = optparse.OptionGroup(parser, 'Video Format Options')
2876 video_format.add_option('-f', '--format',
2877 action='store', dest='format', metavar='FORMAT', help='video format code')
2878 video_format.add_option('--all-formats',
2879 action='store_const', dest='format', help='download all available video formats', const='-1')
2880 video_format.add_option('--max-quality',
2881 action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
2882 parser.add_option_group(video_format)
2884 verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
2885 verbosity.add_option('-q', '--quiet',
2886 action='store_true', dest='quiet', help='activates quiet mode', default=False)
2887 verbosity.add_option('-s', '--simulate',
2888 action='store_true', dest='simulate', help='do not download video', default=False)
2889 verbosity.add_option('-g', '--get-url',
2890 action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
2891 verbosity.add_option('-e', '--get-title',
2892 action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
2893 verbosity.add_option('--get-thumbnail',
2894 action='store_true', dest='getthumbnail',
2895 help='simulate, quiet but print thumbnail URL', default=False)
2896 verbosity.add_option('--get-description',
2897 action='store_true', dest='getdescription',
2898 help='simulate, quiet but print video description', default=False)
2899 verbosity.add_option('--get-filename',
2900 action='store_true', dest='getfilename',
2901 help='simulate, quiet but print output filename', default=False)
2902 verbosity.add_option('--no-progress',
2903 action='store_true', dest='noprogress', help='do not print progress bar', default=False)
2904 verbosity.add_option('--console-title',
2905 action='store_true', dest='consoletitle',
2906 help='display progress in console titlebar', default=False)
2907 parser.add_option_group(verbosity)
2909 filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
2910 filesystem.add_option('-t', '--title',
2911 action='store_true', dest='usetitle', help='use title in file name', default=False)
2912 filesystem.add_option('-l', '--literal',
2913 action='store_true', dest='useliteral', help='use literal title in file name', default=False)
2914 filesystem.add_option('-A', '--auto-number',
2915 action='store_true', dest='autonumber',
2916 help='number downloaded files starting from 00000', default=False)
2917 filesystem.add_option('-o', '--output',
2918 dest='outtmpl', metavar='TEMPLATE', help='output filename template')
2919 filesystem.add_option('-a', '--batch-file',
2920 dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
2921 filesystem.add_option('-w', '--no-overwrites',
2922 action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
2923 filesystem.add_option('-c', '--continue',
2924 action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
2925 filesystem.add_option('--cookies',
2926 dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
2927 filesystem.add_option('--no-part',
2928 action='store_true', dest='nopart', help='do not use .part files', default=False)
2929 filesystem.add_option('--no-mtime',
2930 action='store_false', dest='updatetime',
2931 help='do not use the Last-modified header to set the file modification time', default=True)
2932 parser.add_option_group(filesystem)
2934 postproc = optparse.OptionGroup(parser, 'Post-processing Options')
2935 postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
2936 help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
2937 postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
2938 help='"best", "aac" or "mp3"; best by default')
2939 parser.add_option_group(postproc)
2941 (opts, args) = parser.parse_args()
2943 # Open appropriate CookieJar
2944 if opts.cookiefile is None:
2945 jar = cookielib.CookieJar()
2948 jar = cookielib.MozillaCookieJar(opts.cookiefile)
2949 if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
2951 except (IOError, OSError), err:
2952 sys.exit(u'ERROR: unable to open cookie file')
2955 if opts.dump_user_agent:
2956 print std_headers['User-Agent']
2959 # General configuration
2960 cookie_processor = urllib2.HTTPCookieProcessor(jar)
2961 urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()))
2962 socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
2964 # Batch file verification
2966 if opts.batchfile is not None:
2968 if opts.batchfile == '-':
2971 batchfd = open(opts.batchfile, 'r')
2972 batchurls = batchfd.readlines()
2973 batchurls = [x.strip() for x in batchurls]
2974 batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
2976 sys.exit(u'ERROR: batch file could not be read')
2977 all_urls = batchurls + args
2979 # Conflicting, missing and erroneous options
2980 if opts.usenetrc and (opts.username is not None or opts.password is not None):
2981 parser.error(u'using .netrc conflicts with giving username/password')
2982 if opts.password is not None and opts.username is None:
2983 parser.error(u'account username missing')
2984 if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
2985 parser.error(u'using output template conflicts with using title, literal title or auto number')
2986 if opts.usetitle and opts.useliteral:
2987 parser.error(u'using title conflicts with using literal title')
2988 if opts.username is not None and opts.password is None:
2989 opts.password = getpass.getpass(u'Type account password and press return:')
2990 if opts.ratelimit is not None:
2991 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
2992 if numeric_limit is None:
2993 parser.error(u'invalid rate limit specified')
2994 opts.ratelimit = numeric_limit
2995 if opts.retries is not None:
2997 opts.retries = long(opts.retries)
2998 except (TypeError, ValueError), err:
2999 parser.error(u'invalid retry count specified')
3001 opts.playliststart = long(opts.playliststart)
3002 if opts.playliststart <= 0:
3004 except (TypeError, ValueError), err:
3005 parser.error(u'invalid playlist start number specified')
3007 opts.playlistend = long(opts.playlistend)
3008 if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
3010 except (TypeError, ValueError), err:
3011 parser.error(u'invalid playlist end number specified')
3012 if opts.extractaudio:
3013 if opts.audioformat not in ['best', 'aac', 'mp3']:
3014 parser.error(u'invalid audio format specified')
3016 # Information extractors
3017 vimeo_ie = VimeoIE()
3018 youtube_ie = YoutubeIE()
3019 metacafe_ie = MetacafeIE(youtube_ie)
3020 dailymotion_ie = DailymotionIE()
3021 youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
3022 youtube_user_ie = YoutubeUserIE(youtube_ie)
3023 youtube_search_ie = YoutubeSearchIE(youtube_ie)
3024 google_ie = GoogleIE()
3025 google_search_ie = GoogleSearchIE(google_ie)
3026 photobucket_ie = PhotobucketIE()
3027 yahoo_ie = YahooIE()
3028 yahoo_search_ie = YahooSearchIE(yahoo_ie)
3029 deposit_files_ie = DepositFilesIE()
3030 facebook_ie = FacebookIE()
3031 generic_ie = GenericIE()
3034 fd = FileDownloader({
3035 'usenetrc': opts.usenetrc,
3036 'username': opts.username,
3037 'password': opts.password,
3038 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
3039 'forceurl': opts.geturl,
3040 'forcetitle': opts.gettitle,
3041 'forcethumbnail': opts.getthumbnail,
3042 'forcedescription': opts.getdescription,
3043 'forcefilename': opts.getfilename,
3044 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
3045 'format': opts.format,
3046 'format_limit': opts.format_limit,
3047 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
3048 or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
3049 or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
3050 or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
3051 or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
3052 or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
3053 or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
3054 or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
3055 or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
3056 or u'%(id)s.%(ext)s'),
3057 'ignoreerrors': opts.ignoreerrors,
3058 'ratelimit': opts.ratelimit,
3059 'nooverwrites': opts.nooverwrites,
3060 'retries': opts.retries,
3061 'continuedl': opts.continue_dl,
3062 'noprogress': opts.noprogress,
3063 'playliststart': opts.playliststart,
3064 'playlistend': opts.playlistend,
3065 'logtostderr': opts.outtmpl == '-',
3066 'consoletitle': opts.consoletitle,
3067 'nopart': opts.nopart,
3068 'updatetime': opts.updatetime,
3070 fd.add_info_extractor(vimeo_ie)
3071 fd.add_info_extractor(youtube_search_ie)
3072 fd.add_info_extractor(youtube_pl_ie)
3073 fd.add_info_extractor(youtube_user_ie)
3074 fd.add_info_extractor(metacafe_ie)
3075 fd.add_info_extractor(dailymotion_ie)
3076 fd.add_info_extractor(youtube_ie)
3077 fd.add_info_extractor(google_ie)
3078 fd.add_info_extractor(google_search_ie)
3079 fd.add_info_extractor(photobucket_ie)
3080 fd.add_info_extractor(yahoo_ie)
3081 fd.add_info_extractor(yahoo_search_ie)
3082 fd.add_info_extractor(deposit_files_ie)
3083 fd.add_info_extractor(facebook_ie)
3085 # This must come last since it's the
3086 # fallback if none of the others work
3087 fd.add_info_extractor(generic_ie)
3090 if opts.extractaudio:
3091 fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
3094 if opts.update_self:
3095 update_self(fd, sys.argv[0])
3098 if len(all_urls) < 1:
3099 if not opts.update_self:
3100 parser.error(u'you must provide at least one URL')
3103 retcode = fd.download(all_urls)
3105 # Dump cookie jar if requested
3106 if opts.cookiefile is not None:
3109 except (IOError, OSError), err:
3110 sys.exit(u'ERROR: unable to save cookie jar')
3114 except DownloadError:
3116 except SameFileError:
3117 sys.exit(u'ERROR: fixed output name but more than one file to download')
3118 except KeyboardInterrupt:
3119 sys.exit(u'\nERROR: Interrupted by user')