2 # -*- coding: utf-8 -*-
3 # Author: Ricardo Garcia Gonzalez
4 # Author: Danny Colligan
5 # Author: Benjamin Johnson
6 # License: Public domain code
23 # parse_qs was moved from the cgi module to the urlparse module recently.
25 from urlparse import parse_qs
27 from cgi import parse_qs
30 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.8) Gecko/20100723 Firefox/3.6.8',
31 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
32 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
33 'Accept-Language': 'en-us,en;q=0.5',
36 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
38 def preferredencoding():
39 """Get preferred encoding.
41 Returns the best encoding scheme for the system, based on
42 locale.getpreferredencoding() and some further tweaks.
44 def yield_preferredencoding():
46 pref = locale.getpreferredencoding()
52 return yield_preferredencoding().next()
54 def htmlentity_transform(matchobj):
55 """Transforms an HTML entity to a Unicode character.
57 This function receives a match object and is intended to be used with
58 the re.sub() function.
60 entity = matchobj.group(1)
62 # Known non-numeric HTML entity
63 if entity in htmlentitydefs.name2codepoint:
64 return unichr(htmlentitydefs.name2codepoint[entity])
67 mobj = re.match(ur'(?u)#(x?\d+)', entity)
69 numstr = mobj.group(1)
70 if numstr.startswith(u'x'):
72 numstr = u'0%s' % numstr
75 return unichr(long(numstr, base))
77 # Unknown entity in name, return its literal representation
78 return (u'&%s;' % entity)
80 def sanitize_title(utitle):
81 """Sanitizes a video title so it could be used as part of a filename."""
82 utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
83 return utitle.replace(unicode(os.sep), u'%')
85 def sanitize_open(filename, open_mode):
86 """Try to open the given filename, and slightly tweak it if this fails.
88 Attempts to open the given filename. If this fails, it tries to change
89 the filename slightly, step by step, until it's either able to open it
90 or it fails and raises a final exception, like the standard open()
93 It returns the tuple (stream, definitive_file_name).
97 if sys.platform == 'win32':
99 msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
100 return (sys.stdout, filename)
101 stream = open(filename, open_mode)
102 return (stream, filename)
103 except (IOError, OSError), err:
104 # In case of error, try to remove win32 forbidden chars
105 filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
107 # An exception here should be caught in the caller
108 stream = open(filename, open_mode)
109 return (stream, filename)
112 class DownloadError(Exception):
113 """Download Error exception.
115 This exception may be thrown by FileDownloader objects if they are not
116 configured to continue on errors. They will contain the appropriate
121 class SameFileError(Exception):
122 """Same File exception.
124 This exception will be thrown by FileDownloader objects if they detect
125 multiple files would have to be downloaded to the same file on disk.
129 class PostProcessingError(Exception):
130 """Post Processing exception.
132 This exception may be raised by PostProcessor's .run() method to
133 indicate an error in the postprocessing task.
137 class UnavailableVideoError(Exception):
138 """Unavailable Format exception.
140 This exception will be thrown when a video is requested
141 in a format that is not available for that video.
145 class ContentTooShortError(Exception):
146 """Content Too Short exception.
148 This exception may be raised by FileDownloader objects when a file they
149 download is too small for what the server announced first, indicating
150 the connection was probably interrupted.
156 def __init__(self, downloaded, expected):
157 self.downloaded = downloaded
158 self.expected = expected
160 class FileDownloader(object):
161 """File Downloader class.
163 File downloader objects are the ones responsible of downloading the
164 actual video file and writing it to disk if the user has requested
165 it, among some other tasks. In most cases there should be one per
166 program. As, given a video URL, the downloader doesn't know how to
167 extract all the needed information, task that InfoExtractors do, it
168 has to pass the URL to one of them.
170 For this, file downloader objects have a method that allows
171 InfoExtractors to be registered in a given order. When it is passed
172 a URL, the file downloader handles it to the first InfoExtractor it
173 finds that reports being able to handle it. The InfoExtractor extracts
174 all the information about the video or videos the URL refers to, and
175 asks the FileDownloader to process the video information, possibly
176 downloading the video.
178 File downloaders accept a lot of parameters. In order not to saturate
179 the object constructor with arguments, it receives a dictionary of
180 options instead. These options are available through the params
181 attribute for the InfoExtractors to use. The FileDownloader also
182 registers itself as the downloader in charge for the InfoExtractors
183 that are added to it, so this is a "mutual registration".
187 username: Username for authentication purposes.
188 password: Password for authentication purposes.
189 usenetrc: Use netrc for authentication instead.
190 quiet: Do not print messages to stdout.
191 forceurl: Force printing final URL.
192 forcetitle: Force printing title.
193 simulate: Do not download the video files.
194 format: Video format code.
195 format_limit: Highest quality format to try.
196 outtmpl: Template for output names.
197 ignoreerrors: Do not stop on download errors.
198 ratelimit: Download speed limit, in bytes/sec.
199 nooverwrites: Prevent overwriting files.
200 retries: Number of times to retry for HTTP error 5xx
201 continuedl: Try to continue downloads if possible.
202 noprogress: Do not print the progress bar.
208 _download_retcode = None
209 _num_downloads = None
211 def __init__(self, params):
212 """Create a FileDownloader object with the given options."""
215 self._download_retcode = 0
216 self._num_downloads = 0
220 def pmkdir(filename):
221 """Create directory components in filename. Similar to Unix "mkdir -p"."""
222 components = filename.split(os.sep)
223 aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
224 aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
225 for dir in aggregate:
226 if not os.path.exists(dir):
230 def format_bytes(bytes):
233 if type(bytes) is str:
238 exponent = long(math.log(bytes, 1024.0))
239 suffix = 'bkMGTPEZY'[exponent]
240 converted = float(bytes) / float(1024**exponent)
241 return '%.2f%s' % (converted, suffix)
244 def calc_percent(byte_counter, data_len):
247 return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
250 def calc_eta(start, now, total, current):
254 if current == 0 or dif < 0.001: # One millisecond
256 rate = float(current) / dif
257 eta = long((float(total) - float(current)) / rate)
258 (eta_mins, eta_secs) = divmod(eta, 60)
261 return '%02d:%02d' % (eta_mins, eta_secs)
264 def calc_speed(start, now, bytes):
266 if bytes == 0 or dif < 0.001: # One millisecond
267 return '%10s' % '---b/s'
268 return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
271 def best_block_size(elapsed_time, bytes):
272 new_min = max(bytes / 2.0, 1.0)
273 new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
274 if elapsed_time < 0.001:
276 rate = bytes / elapsed_time
284 def parse_bytes(bytestr):
285 """Parse a string indicating a byte quantity into a long integer."""
286 matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
289 number = float(matchobj.group(1))
290 multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
291 return long(round(number * multiplier))
293 def add_info_extractor(self, ie):
294 """Add an InfoExtractor object to the end of the list."""
296 ie.set_downloader(self)
298 def add_post_processor(self, pp):
299 """Add a PostProcessor object to the end of the chain."""
301 pp.set_downloader(self)
303 def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
304 """Print message to stdout if not in quiet mode."""
306 if not self.params.get('quiet', False):
307 print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
309 except (UnicodeEncodeError), err:
310 if not ignore_encoding_errors:
313 def to_stderr(self, message):
314 """Print message to stderr."""
315 print >>sys.stderr, message.encode(preferredencoding())
317 def fixed_template(self):
318 """Checks if the output template is fixed."""
319 return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
321 def trouble(self, message=None):
322 """Determine action to take when a download problem appears.
324 Depending on if the downloader has been configured to ignore
325 download errors or not, this method may throw an exception or
326 not when errors are found, after printing the message.
328 if message is not None:
329 self.to_stderr(message)
330 if not self.params.get('ignoreerrors', False):
331 raise DownloadError(message)
332 self._download_retcode = 1
334 def slow_down(self, start_time, byte_counter):
335 """Sleep if the download speed is over the rate limit."""
336 rate_limit = self.params.get('ratelimit', None)
337 if rate_limit is None or byte_counter == 0:
340 elapsed = now - start_time
343 speed = float(byte_counter) / elapsed
344 if speed > rate_limit:
345 time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
347 def report_destination(self, filename):
348 """Report destination filename."""
349 self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
351 def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
352 """Report download progress."""
353 if self.params.get('noprogress', False):
355 self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
356 (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
358 def report_resuming_byte(self, resume_len):
359 """Report attempt to resume at given byte."""
360 self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
362 def report_retry(self, count, retries):
363 """Report retry in case of HTTP error 5xx"""
364 self.to_stdout(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
366 def report_file_already_downloaded(self, file_name):
367 """Report file has already been fully downloaded."""
369 self.to_stdout(u'[download] %s has already been downloaded' % file_name)
370 except (UnicodeEncodeError), err:
371 self.to_stdout(u'[download] The file has already been downloaded')
373 def report_unable_to_resume(self):
374 """Report it was impossible to resume download."""
375 self.to_stdout(u'[download] Unable to resume')
377 def report_finish(self):
378 """Report download finished."""
379 if self.params.get('noprogress', False):
380 self.to_stdout(u'[download] Download completed')
384 def increment_downloads(self):
385 """Increment the ordinal that assigns a number to each file."""
386 self._num_downloads += 1
388 def process_info(self, info_dict):
389 """Process a single dictionary returned by an InfoExtractor."""
390 # Do nothing else if in simulate mode
391 if self.params.get('simulate', False):
393 if self.params.get('forcetitle', False):
394 print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
395 if self.params.get('forceurl', False):
396 print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
397 if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
398 print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
399 if self.params.get('forcedescription', False) and 'description' in info_dict:
400 print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
405 template_dict = dict(info_dict)
406 template_dict['epoch'] = unicode(long(time.time()))
407 template_dict['ord'] = unicode('%05d' % self._num_downloads)
408 filename = self.params['outtmpl'] % template_dict
409 except (ValueError, KeyError), err:
410 self.trouble(u'ERROR: invalid system charset or erroneous output template')
412 if self.params.get('nooverwrites', False) and os.path.exists(filename):
413 self.to_stderr(u'WARNING: file exists and will be skipped')
417 self.pmkdir(filename)
418 except (OSError, IOError), err:
419 self.trouble(u'ERROR: unable to create directories: %s' % str(err))
423 success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
424 except (OSError, IOError), err:
425 raise UnavailableVideoError
426 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
427 self.trouble(u'ERROR: unable to download video data: %s' % str(err))
429 except (ContentTooShortError, ), err:
430 self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
435 self.post_process(filename, info_dict)
436 except (PostProcessingError), err:
437 self.trouble(u'ERROR: postprocessing: %s' % str(err))
440 def download(self, url_list):
441 """Download a given list of URLs."""
442 if len(url_list) > 1 and self.fixed_template():
443 raise SameFileError(self.params['outtmpl'])
446 suitable_found = False
448 # Go to next InfoExtractor if not suitable
449 if not ie.suitable(url):
452 # Suitable InfoExtractor found
453 suitable_found = True
455 # Extract information from URL and process it
458 # Suitable InfoExtractor had been found; go to next URL
461 if not suitable_found:
462 self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
464 return self._download_retcode
466 def post_process(self, filename, ie_info):
467 """Run the postprocessing chain on the given file."""
469 info['filepath'] = filename
475 def _download_with_rtmpdump(self, filename, url, player_url):
476 self.report_destination(filename)
478 # Check for rtmpdump first
480 subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
481 except (OSError, IOError):
482 self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
485 # Download using rtmpdump. rtmpdump returns exit code 2 when
486 # the connection was interrumpted and resuming appears to be
487 # possible. This is part of rtmpdump's normal usage, AFAIK.
488 basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename]
489 retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
490 while retval == 2 or retval == 1:
491 prevsize = os.path.getsize(filename)
492 self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
493 time.sleep(5.0) # This seems to be needed
494 retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
495 cursize = os.path.getsize(filename)
496 if prevsize == cursize and retval == 1:
499 self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
502 self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
505 def _do_download(self, filename, url, player_url):
506 # Attempt to download using rtmpdump
507 if url.startswith('rtmp'):
508 return self._download_with_rtmpdump(filename, url, player_url)
512 basic_request = urllib2.Request(url, None, std_headers)
513 request = urllib2.Request(url, None, std_headers)
515 # Establish possible resume length
516 if os.path.isfile(filename):
517 resume_len = os.path.getsize(filename)
521 # Request parameters in case of being able to resume
522 if self.params.get('continuedl', False) and resume_len != 0:
523 self.report_resuming_byte(resume_len)
524 request.add_header('Range','bytes=%d-' % resume_len)
528 retries = self.params.get('retries', 0)
529 while count <= retries:
530 # Establish connection
532 data = urllib2.urlopen(request)
534 except (urllib2.HTTPError, ), err:
535 if (err.code < 500 or err.code >= 600) and err.code != 416:
536 # Unexpected HTTP error
538 elif err.code == 416:
539 # Unable to resume (requested range not satisfiable)
541 # Open the connection again without the range header
542 data = urllib2.urlopen(basic_request)
543 content_length = data.info()['Content-Length']
544 except (urllib2.HTTPError, ), err:
545 if err.code < 500 or err.code >= 600:
548 # Examine the reported length
549 if (content_length is not None and
550 (resume_len - 100 < long(content_length) < resume_len + 100)):
551 # The file had already been fully downloaded.
552 # Explanation to the above condition: in issue #175 it was revealed that
553 # YouTube sometimes adds or removes a few bytes from the end of the file,
554 # changing the file size slightly and causing problems for some users. So
555 # I decided to implement a suggested change and consider the file
556 # completely downloaded if the file size differs less than 100 bytes from
557 # the one in the hard drive.
558 self.report_file_already_downloaded(filename)
561 # The length does not match, we start the download over
562 self.report_unable_to_resume()
568 self.report_retry(count, retries)
571 self.trouble(u'ERROR: giving up after %s retries' % retries)
574 data_len = data.info().get('Content-length', None)
575 data_len_str = self.format_bytes(data_len)
582 data_block = data.read(block_size)
584 data_block_len = len(data_block)
585 if data_block_len == 0:
587 byte_counter += data_block_len
589 # Open file just in time
592 (stream, filename) = sanitize_open(filename, open_mode)
593 self.report_destination(filename)
594 except (OSError, IOError), err:
595 self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
598 stream.write(data_block)
599 except (IOError, OSError), err:
600 self.trouble(u'\nERROR: unable to write data: %s' % str(err))
602 block_size = self.best_block_size(after - before, data_block_len)
605 percent_str = self.calc_percent(byte_counter, data_len)
606 eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
607 speed_str = self.calc_speed(start, time.time(), byte_counter)
608 self.report_progress(percent_str, data_len_str, speed_str, eta_str)
611 self.slow_down(start, byte_counter)
614 if data_len is not None and str(byte_counter) != data_len:
615 raise ContentTooShortError(byte_counter, long(data_len))
618 class InfoExtractor(object):
619 """Information Extractor class.
621 Information extractors are the classes that, given a URL, extract
622 information from the video (or videos) the URL refers to. This
623 information includes the real video URL, the video title and simplified
624 title, author and others. The information is stored in a dictionary
625 which is then passed to the FileDownloader. The FileDownloader
626 processes this information possibly downloading the video to the file
627 system, among other possible outcomes. The dictionaries must include
628 the following fields:
630 id: Video identifier.
631 url: Final video URL.
632 uploader: Nickname of the video uploader.
633 title: Literal title.
634 stitle: Simplified title.
635 ext: Video filename extension.
636 format: Video format.
637 player_url: SWF Player URL (may be None).
639 The following fields are optional. Their primary purpose is to allow
640 youtube-dl to serve as the backend for a video search function, such
641 as the one in youtube2mp3. They are only used when their respective
642 forced printing functions are called:
644 thumbnail: Full URL to a video thumbnail image.
645 description: One-line video description.
647 Subclasses of this one should re-define the _real_initialize() and
648 _real_extract() methods, as well as the suitable() static method.
649 Probably, they should also be instantiated and added to the main
656 def __init__(self, downloader=None):
657 """Constructor. Receives an optional downloader."""
659 self.set_downloader(downloader)
663 """Receives a URL and returns True if suitable for this IE."""
666 def initialize(self):
667 """Initializes an instance (authentication, etc)."""
669 self._real_initialize()
672 def extract(self, url):
673 """Extracts URL information and returns it in list of dicts."""
675 return self._real_extract(url)
677 def set_downloader(self, downloader):
678 """Sets the downloader for this IE."""
679 self._downloader = downloader
681 def _real_initialize(self):
682 """Real initialization process. Redefine in subclasses."""
685 def _real_extract(self, url):
686 """Real extraction process. Redefine in subclasses."""
689 class YoutubeIE(InfoExtractor):
690 """Information extractor for youtube.com."""
692 _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
693 _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
694 _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
695 _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
696 _NETRC_MACHINE = 'youtube'
697 # Listed in order of quality
698 _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
699 _video_extensions = {
705 '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
712 return (re.match(YoutubeIE._VALID_URL, url) is not None)
714 def report_lang(self):
715 """Report attempt to set language."""
716 self._downloader.to_stdout(u'[youtube] Setting language')
718 def report_login(self):
719 """Report attempt to log in."""
720 self._downloader.to_stdout(u'[youtube] Logging in')
722 def report_age_confirmation(self):
723 """Report attempt to confirm age."""
724 self._downloader.to_stdout(u'[youtube] Confirming age')
726 def report_video_webpage_download(self, video_id):
727 """Report attempt to download video webpage."""
728 self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
730 def report_video_info_webpage_download(self, video_id):
731 """Report attempt to download video info webpage."""
732 self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
734 def report_information_extraction(self, video_id):
735 """Report attempt to extract video information."""
736 self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
738 def report_unavailable_format(self, video_id, format):
739 """Report extracted video URL."""
740 self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
742 def report_rtmp_download(self):
743 """Indicate the download will use the RTMP protocol."""
744 self._downloader.to_stdout(u'[youtube] RTMP download detected')
746 def _real_initialize(self):
747 if self._downloader is None:
752 downloader_params = self._downloader.params
754 # Attempt to use provided username and password or .netrc data
755 if downloader_params.get('username', None) is not None:
756 username = downloader_params['username']
757 password = downloader_params['password']
758 elif downloader_params.get('usenetrc', False):
760 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
765 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
766 except (IOError, netrc.NetrcParseError), err:
767 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
771 request = urllib2.Request(self._LANG_URL, None, std_headers)
774 urllib2.urlopen(request).read()
775 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
776 self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
779 # No authentication to be performed
785 'current_form': 'loginForm',
787 'action_login': 'Log In',
788 'username': username,
789 'password': password,
791 request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
794 login_results = urllib2.urlopen(request).read()
795 if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
796 self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
798 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
799 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
805 'action_confirm': 'Confirm',
807 request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
809 self.report_age_confirmation()
810 age_results = urllib2.urlopen(request).read()
811 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
812 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
815 def _real_extract(self, url):
816 # Extract video id from URL
817 mobj = re.match(self._VALID_URL, url)
819 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
821 video_id = mobj.group(2)
824 self.report_video_webpage_download(video_id)
825 request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
827 video_webpage = urllib2.urlopen(request).read()
828 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
829 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
832 # Attempt to extract SWF player URL
833 mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage)
835 player_url = mobj.group(1)
840 self.report_video_info_webpage_download(video_id)
841 for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
842 video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
843 % (video_id, el_type))
844 request = urllib2.Request(video_info_url, None, std_headers)
846 video_info_webpage = urllib2.urlopen(request).read()
847 video_info = parse_qs(video_info_webpage)
848 if 'token' in video_info:
850 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
851 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
853 if 'token' not in video_info:
854 if 'reason' in video_info:
855 self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
857 self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
860 # Start extracting information
861 self.report_information_extraction(video_id)
864 if 'author' not in video_info:
865 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
867 video_uploader = urllib.unquote_plus(video_info['author'][0])
870 if 'title' not in video_info:
871 self._downloader.trouble(u'ERROR: unable to extract video title')
873 video_title = urllib.unquote_plus(video_info['title'][0])
874 video_title = video_title.decode('utf-8')
875 video_title = sanitize_title(video_title)
878 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
879 simple_title = simple_title.strip(ur'_')
882 if 'thumbnail_url' not in video_info:
883 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
885 else: # don't panic if we can't find it
886 video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
889 video_description = 'No description available.'
890 if self._downloader.params.get('forcedescription', False):
891 mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
893 video_description = mobj.group(1)
896 video_token = urllib.unquote_plus(video_info['token'][0])
898 # Decide which formats to download
899 requested_format = self._downloader.params.get('format', None)
900 get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token)
902 if 'fmt_url_map' in video_info:
903 url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
904 format_limit = self._downloader.params.get('format_limit', None)
905 if format_limit is not None and format_limit in self._available_formats:
906 format_list = self._available_formats[self._available_formats.index(format_limit):]
908 format_list = self._available_formats
909 existing_formats = [x for x in format_list if x in url_map]
910 if len(existing_formats) == 0:
911 self._downloader.trouble(u'ERROR: no known formats available for video')
913 if requested_format is None:
914 video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality
915 elif requested_format == '-1':
916 video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats
918 video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format
920 elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
921 self.report_rtmp_download()
922 video_url_list = [(None, video_info['conn'][0])]
925 self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
928 for format_param, video_real_url in video_url_list:
929 # At this point we have a new video
930 self._downloader.increment_downloads()
933 video_extension = self._video_extensions.get(format_param, 'flv')
935 # Find the video URL in fmt_url_map or conn paramters
937 # Process video information
938 self._downloader.process_info({
939 'id': video_id.decode('utf-8'),
940 'url': video_real_url.decode('utf-8'),
941 'uploader': video_uploader.decode('utf-8'),
942 'title': video_title,
943 'stitle': simple_title,
944 'ext': video_extension.decode('utf-8'),
945 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
946 'thumbnail': video_thumbnail.decode('utf-8'),
947 'description': video_description.decode('utf-8'),
948 'player_url': player_url,
950 except UnavailableVideoError, err:
951 self._downloader.trouble(u'ERROR: unable to download video (format may not be available)')
954 class MetacafeIE(InfoExtractor):
955 """Information Extractor for metacafe.com."""
957 _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
958 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
959 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
962 def __init__(self, youtube_ie, downloader=None):
963 InfoExtractor.__init__(self, downloader)
964 self._youtube_ie = youtube_ie
968 return (re.match(MetacafeIE._VALID_URL, url) is not None)
970 def report_disclaimer(self):
971 """Report disclaimer retrieval."""
972 self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
974 def report_age_confirmation(self):
975 """Report attempt to confirm age."""
976 self._downloader.to_stdout(u'[metacafe] Confirming age')
978 def report_download_webpage(self, video_id):
979 """Report webpage download."""
980 self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
982 def report_extraction(self, video_id):
983 """Report information extraction."""
984 self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
986 def _real_initialize(self):
987 # Retrieve disclaimer
988 request = urllib2.Request(self._DISCLAIMER, None, std_headers)
990 self.report_disclaimer()
991 disclaimer = urllib2.urlopen(request).read()
992 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
993 self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
999 'submit': "Continue - I'm over 18",
1001 request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
1003 self.report_age_confirmation()
1004 disclaimer = urllib2.urlopen(request).read()
1005 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1006 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
1009 def _real_extract(self, url):
1010 # Extract id and simplified title from URL
1011 mobj = re.match(self._VALID_URL, url)
1013 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1016 video_id = mobj.group(1)
1018 # Check if video comes from YouTube
1019 mobj2 = re.match(r'^yt-(.*)$', video_id)
1020 if mobj2 is not None:
1021 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
1024 # At this point we have a new video
1025 self._downloader.increment_downloads()
1027 simple_title = mobj.group(2).decode('utf-8')
1029 # Retrieve video webpage to extract further information
1030 request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
1032 self.report_download_webpage(video_id)
1033 webpage = urllib2.urlopen(request).read()
1034 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1035 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
1038 # Extract URL, uploader and title from webpage
1039 self.report_extraction(video_id)
1040 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
1041 if mobj is not None:
1042 mediaURL = urllib.unquote(mobj.group(1))
1043 video_extension = mediaURL[-3:]
1045 # Extract gdaKey if available
1046 mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
1048 video_url = mediaURL
1050 gdaKey = mobj.group(1)
1051 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
1053 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
1055 self._downloader.trouble(u'ERROR: unable to extract media URL')
1057 vardict = parse_qs(mobj.group(1))
1058 if 'mediaData' not in vardict:
1059 self._downloader.trouble(u'ERROR: unable to extract media URL')
1061 mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
1063 self._downloader.trouble(u'ERROR: unable to extract media URL')
1065 mediaURL = mobj.group(1).replace('\\/', '/')
1066 video_extension = mediaURL[-3:]
1067 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
1069 mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
1071 self._downloader.trouble(u'ERROR: unable to extract title')
1073 video_title = mobj.group(1).decode('utf-8')
1074 video_title = sanitize_title(video_title)
1076 mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
1078 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1080 video_uploader = mobj.group(1)
1083 # Process video information
1084 self._downloader.process_info({
1085 'id': video_id.decode('utf-8'),
1086 'url': video_url.decode('utf-8'),
1087 'uploader': video_uploader.decode('utf-8'),
1088 'title': video_title,
1089 'stitle': simple_title,
1090 'ext': video_extension.decode('utf-8'),
1094 except UnavailableVideoError:
1095 self._downloader.trouble(u'ERROR: unable to download video')
1098 class DailymotionIE(InfoExtractor):
1099 """Information Extractor for Dailymotion"""
1101 _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
1103 def __init__(self, downloader=None):
1104 InfoExtractor.__init__(self, downloader)
1108 return (re.match(DailymotionIE._VALID_URL, url) is not None)
1110 def report_download_webpage(self, video_id):
1111 """Report webpage download."""
1112 self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id)
1114 def report_extraction(self, video_id):
1115 """Report information extraction."""
1116 self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id)
1118 def _real_initialize(self):
1121 def _real_extract(self, url):
1122 # Extract id and simplified title from URL
1123 mobj = re.match(self._VALID_URL, url)
1125 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
1128 # At this point we have a new video
1129 self._downloader.increment_downloads()
1130 video_id = mobj.group(1)
1132 simple_title = mobj.group(2).decode('utf-8')
1133 video_extension = 'flv'
1135 # Retrieve video webpage to extract further information
1136 request = urllib2.Request(url)
1138 self.report_download_webpage(video_id)
1139 webpage = urllib2.urlopen(request).read()
1140 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1141 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
1144 # Extract URL, uploader and title from webpage
1145 self.report_extraction(video_id)
1146 mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
1148 self._downloader.trouble(u'ERROR: unable to extract media URL')
1150 mediaURL = urllib.unquote(mobj.group(1))
1152 # if needed add http://www.dailymotion.com/ if relative URL
1154 video_url = mediaURL
1156 # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
1157 mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
1159 self._downloader.trouble(u'ERROR: unable to extract title')
1161 video_title = mobj.group(1).decode('utf-8')
1162 video_title = sanitize_title(video_title)
1164 mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage)
1166 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
1168 video_uploader = mobj.group(1)
1171 # Process video information
1172 self._downloader.process_info({
1173 'id': video_id.decode('utf-8'),
1174 'url': video_url.decode('utf-8'),
1175 'uploader': video_uploader.decode('utf-8'),
1176 'title': video_title,
1177 'stitle': simple_title,
1178 'ext': video_extension.decode('utf-8'),
1182 except UnavailableVideoError:
1183 self._downloader.trouble(u'ERROR: unable to download video')
1185 class GoogleIE(InfoExtractor):
1186 """Information extractor for video.google.com."""
1188 _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
1190 def __init__(self, downloader=None):
1191 InfoExtractor.__init__(self, downloader)
1195 return (re.match(GoogleIE._VALID_URL, url) is not None)
1197 def report_download_webpage(self, video_id):
1198 """Report webpage download."""
1199 self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
1201 def report_extraction(self, video_id):
1202 """Report information extraction."""
1203 self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
1205 def _real_initialize(self):
1208 def _real_extract(self, url):
1209 # Extract id from URL
1210 mobj = re.match(self._VALID_URL, url)
1212 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1215 # At this point we have a new video
1216 self._downloader.increment_downloads()
1217 video_id = mobj.group(1)
1219 video_extension = 'mp4'
1221 # Retrieve video webpage to extract further information
1222 request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
1224 self.report_download_webpage(video_id)
1225 webpage = urllib2.urlopen(request).read()
1226 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1227 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1230 # Extract URL, uploader, and title from webpage
1231 self.report_extraction(video_id)
1232 mobj = re.search(r"download_url:'([^']+)'", webpage)
1234 video_extension = 'flv'
1235 mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
1237 self._downloader.trouble(u'ERROR: unable to extract media URL')
1239 mediaURL = urllib.unquote(mobj.group(1))
1240 mediaURL = mediaURL.replace('\\x3d', '\x3d')
1241 mediaURL = mediaURL.replace('\\x26', '\x26')
1243 video_url = mediaURL
1245 mobj = re.search(r'<title>(.*)</title>', webpage)
1247 self._downloader.trouble(u'ERROR: unable to extract title')
1249 video_title = mobj.group(1).decode('utf-8')
1250 video_title = sanitize_title(video_title)
1251 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1253 # Extract video description
1254 mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
1256 self._downloader.trouble(u'ERROR: unable to extract video description')
1258 video_description = mobj.group(1).decode('utf-8')
1259 if not video_description:
1260 video_description = 'No description available.'
1262 # Extract video thumbnail
1263 if self._downloader.params.get('forcethumbnail', False):
1264 request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
1266 webpage = urllib2.urlopen(request).read()
1267 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1268 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1270 mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
1272 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1274 video_thumbnail = mobj.group(1)
1275 else: # we need something to pass to process_info
1276 video_thumbnail = ''
1280 # Process video information
1281 self._downloader.process_info({
1282 'id': video_id.decode('utf-8'),
1283 'url': video_url.decode('utf-8'),
1285 'title': video_title,
1286 'stitle': simple_title,
1287 'ext': video_extension.decode('utf-8'),
1291 except UnavailableVideoError:
1292 self._downloader.trouble(u'ERROR: unable to download video')
1295 class PhotobucketIE(InfoExtractor):
1296 """Information extractor for photobucket.com."""
1298 _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
1300 def __init__(self, downloader=None):
1301 InfoExtractor.__init__(self, downloader)
1305 return (re.match(PhotobucketIE._VALID_URL, url) is not None)
1307 def report_download_webpage(self, video_id):
1308 """Report webpage download."""
1309 self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
1311 def report_extraction(self, video_id):
1312 """Report information extraction."""
1313 self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
1315 def _real_initialize(self):
1318 def _real_extract(self, url):
1319 # Extract id from URL
1320 mobj = re.match(self._VALID_URL, url)
1322 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1325 # At this point we have a new video
1326 self._downloader.increment_downloads()
1327 video_id = mobj.group(1)
1329 video_extension = 'flv'
1331 # Retrieve video webpage to extract further information
1332 request = urllib2.Request(url)
1334 self.report_download_webpage(video_id)
1335 webpage = urllib2.urlopen(request).read()
1336 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1337 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1340 # Extract URL, uploader, and title from webpage
1341 self.report_extraction(video_id)
1342 mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
1344 self._downloader.trouble(u'ERROR: unable to extract media URL')
1346 mediaURL = urllib.unquote(mobj.group(1))
1348 video_url = mediaURL
1350 mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
1352 self._downloader.trouble(u'ERROR: unable to extract title')
1354 video_title = mobj.group(1).decode('utf-8')
1355 video_title = sanitize_title(video_title)
1356 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1358 video_uploader = mobj.group(2).decode('utf-8')
1361 # Process video information
1362 self._downloader.process_info({
1363 'id': video_id.decode('utf-8'),
1364 'url': video_url.decode('utf-8'),
1365 'uploader': video_uploader,
1366 'title': video_title,
1367 'stitle': simple_title,
1368 'ext': video_extension.decode('utf-8'),
1372 except UnavailableVideoError:
1373 self._downloader.trouble(u'ERROR: unable to download video')
1376 class YahooIE(InfoExtractor):
1377 """Information extractor for video.yahoo.com."""
1379 # _VALID_URL matches all Yahoo! Video URLs
1380 # _VPAGE_URL matches only the extractable '/watch/' URLs
1381 _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
1382 _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
1384 def __init__(self, downloader=None):
1385 InfoExtractor.__init__(self, downloader)
1389 return (re.match(YahooIE._VALID_URL, url) is not None)
1391 def report_download_webpage(self, video_id):
1392 """Report webpage download."""
1393 self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
1395 def report_extraction(self, video_id):
1396 """Report information extraction."""
1397 self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
1399 def _real_initialize(self):
1402 def _real_extract(self, url, new_video=True):
1403 # Extract ID from URL
1404 mobj = re.match(self._VALID_URL, url)
1406 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1409 # At this point we have a new video
1410 self._downloader.increment_downloads()
1411 video_id = mobj.group(2)
1412 video_extension = 'flv'
1414 # Rewrite valid but non-extractable URLs as
1415 # extractable English language /watch/ URLs
1416 if re.match(self._VPAGE_URL, url) is None:
1417 request = urllib2.Request(url)
1419 webpage = urllib2.urlopen(request).read()
1420 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1421 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1424 mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
1426 self._downloader.trouble(u'ERROR: Unable to extract id field')
1428 yahoo_id = mobj.group(1)
1430 mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
1432 self._downloader.trouble(u'ERROR: Unable to extract vid field')
1434 yahoo_vid = mobj.group(1)
1436 url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
1437 return self._real_extract(url, new_video=False)
1439 # Retrieve video webpage to extract further information
1440 request = urllib2.Request(url)
1442 self.report_download_webpage(video_id)
1443 webpage = urllib2.urlopen(request).read()
1444 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1445 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1448 # Extract uploader and title from webpage
1449 self.report_extraction(video_id)
1450 mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
1452 self._downloader.trouble(u'ERROR: unable to extract video title')
1454 video_title = mobj.group(1).decode('utf-8')
1455 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1457 mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
1459 self._downloader.trouble(u'ERROR: unable to extract video uploader')
1461 video_uploader = mobj.group(1).decode('utf-8')
1463 # Extract video thumbnail
1464 mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
1466 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
1468 video_thumbnail = mobj.group(1).decode('utf-8')
1470 # Extract video description
1471 mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
1473 self._downloader.trouble(u'ERROR: unable to extract video description')
1475 video_description = mobj.group(1).decode('utf-8')
1476 if not video_description: video_description = 'No description available.'
1478 # Extract video height and width
1479 mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
1481 self._downloader.trouble(u'ERROR: unable to extract video height')
1483 yv_video_height = mobj.group(1)
1485 mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
1487 self._downloader.trouble(u'ERROR: unable to extract video width')
1489 yv_video_width = mobj.group(1)
1491 # Retrieve video playlist to extract media URL
1492 # I'm not completely sure what all these options are, but we
1493 # seem to need most of them, otherwise the server sends a 401.
1494 yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
1495 yv_bitrate = '700' # according to Wikipedia this is hard-coded
1496 request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
1497 '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
1498 '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
1500 self.report_download_webpage(video_id)
1501 webpage = urllib2.urlopen(request).read()
1502 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1503 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1506 # Extract media URL from playlist XML
1507 mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
1509 self._downloader.trouble(u'ERROR: Unable to extract media URL')
1511 video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
1512 video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
1515 # Process video information
1516 self._downloader.process_info({
1517 'id': video_id.decode('utf-8'),
1519 'uploader': video_uploader,
1520 'title': video_title,
1521 'stitle': simple_title,
1522 'ext': video_extension.decode('utf-8'),
1523 'thumbnail': video_thumbnail.decode('utf-8'),
1524 'description': video_description,
1525 'thumbnail': video_thumbnail,
1526 'description': video_description,
1529 except UnavailableVideoError:
1530 self._downloader.trouble(u'ERROR: unable to download video')
1533 class GenericIE(InfoExtractor):
1534 """Generic last-resort information extractor."""
1536 def __init__(self, downloader=None):
1537 InfoExtractor.__init__(self, downloader)
1543 def report_download_webpage(self, video_id):
1544 """Report webpage download."""
1545 self._downloader.to_stdout(u'WARNING: Falling back on generic information extractor.')
1546 self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id)
1548 def report_extraction(self, video_id):
1549 """Report information extraction."""
1550 self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id)
1552 def _real_initialize(self):
1555 def _real_extract(self, url):
1556 # At this point we have a new video
1557 self._downloader.increment_downloads()
1559 video_id = url.split('/')[-1]
1560 request = urllib2.Request(url)
1562 self.report_download_webpage(video_id)
1563 webpage = urllib2.urlopen(request).read()
1564 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1565 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
1567 except ValueError, err:
1568 # since this is the last-resort InfoExtractor, if
1569 # this error is thrown, it'll be thrown here
1570 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1573 # Start with something easy: JW Player in SWFObject
1574 mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
1576 # Broaden the search a little bit
1577 mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
1579 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1582 # It's possible that one of the regexes
1583 # matched, but returned an empty group:
1584 if mobj.group(1) is None:
1585 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1588 video_url = urllib.unquote(mobj.group(1))
1589 video_id = os.path.basename(video_url)
1591 # here's a fun little line of code for you:
1592 video_extension = os.path.splitext(video_id)[1][1:]
1593 video_id = os.path.splitext(video_id)[0]
1595 # it's tempting to parse this further, but you would
1596 # have to take into account all the variations like
1597 # Video Title - Site Name
1598 # Site Name | Video Title
1599 # Video Title - Tagline | Site Name
1600 # and so on and so forth; it's just not practical
1601 mobj = re.search(r'<title>(.*)</title>', webpage)
1603 self._downloader.trouble(u'ERROR: unable to extract title')
1605 video_title = mobj.group(1).decode('utf-8')
1606 video_title = sanitize_title(video_title)
1607 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
1609 # video uploader is domain name
1610 mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
1612 self._downloader.trouble(u'ERROR: unable to extract title')
1614 video_uploader = mobj.group(1).decode('utf-8')
1617 # Process video information
1618 self._downloader.process_info({
1619 'id': video_id.decode('utf-8'),
1620 'url': video_url.decode('utf-8'),
1621 'uploader': video_uploader,
1622 'title': video_title,
1623 'stitle': simple_title,
1624 'ext': video_extension.decode('utf-8'),
1628 except UnavailableVideoError, err:
1629 self._downloader.trouble(u'ERROR: unable to download video')
1632 class YoutubeSearchIE(InfoExtractor):
1633 """Information Extractor for YouTube search queries."""
1634 _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
1635 _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
1636 _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
1637 _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
1639 _max_youtube_results = 1000
1641 def __init__(self, youtube_ie, downloader=None):
1642 InfoExtractor.__init__(self, downloader)
1643 self._youtube_ie = youtube_ie
1647 return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
1649 def report_download_page(self, query, pagenum):
1650 """Report attempt to download playlist page with given number."""
1651 query = query.decode(preferredencoding())
1652 self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
1654 def _real_initialize(self):
1655 self._youtube_ie.initialize()
1657 def _real_extract(self, query):
1658 mobj = re.match(self._VALID_QUERY, query)
1660 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1663 prefix, query = query.split(':')
1665 query = query.encode('utf-8')
1667 self._download_n_results(query, 1)
1669 elif prefix == 'all':
1670 self._download_n_results(query, self._max_youtube_results)
1676 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1678 elif n > self._max_youtube_results:
1679 self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
1680 n = self._max_youtube_results
1681 self._download_n_results(query, n)
1683 except ValueError: # parsing prefix as integer fails
1684 self._download_n_results(query, 1)
1687 def _download_n_results(self, query, n):
1688 """Downloads a specified number of results for a query"""
1691 already_seen = set()
1695 self.report_download_page(query, pagenum)
1696 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
1697 request = urllib2.Request(result_url, None, std_headers)
1699 page = urllib2.urlopen(request).read()
1700 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1701 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
1704 # Extract video identifiers
1705 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1706 video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
1707 if video_id not in already_seen:
1708 video_ids.append(video_id)
1709 already_seen.add(video_id)
1710 if len(video_ids) == n:
1711 # Specified n videos reached
1712 for id in video_ids:
1713 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
1716 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1717 for id in video_ids:
1718 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
1721 pagenum = pagenum + 1
1723 class GoogleSearchIE(InfoExtractor):
1724 """Information Extractor for Google Video search queries."""
1725 _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
1726 _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
1727 _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
1728 _MORE_PAGES_INDICATOR = r'<span>Next</span>'
1730 _max_google_results = 1000
1732 def __init__(self, google_ie, downloader=None):
1733 InfoExtractor.__init__(self, downloader)
1734 self._google_ie = google_ie
1738 return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
1740 def report_download_page(self, query, pagenum):
1741 """Report attempt to download playlist page with given number."""
1742 query = query.decode(preferredencoding())
1743 self._downloader.to_stdout(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
1745 def _real_initialize(self):
1746 self._google_ie.initialize()
1748 def _real_extract(self, query):
1749 mobj = re.match(self._VALID_QUERY, query)
1751 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1754 prefix, query = query.split(':')
1756 query = query.encode('utf-8')
1758 self._download_n_results(query, 1)
1760 elif prefix == 'all':
1761 self._download_n_results(query, self._max_google_results)
1767 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1769 elif n > self._max_google_results:
1770 self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
1771 n = self._max_google_results
1772 self._download_n_results(query, n)
1774 except ValueError: # parsing prefix as integer fails
1775 self._download_n_results(query, 1)
1778 def _download_n_results(self, query, n):
1779 """Downloads a specified number of results for a query"""
1782 already_seen = set()
1786 self.report_download_page(query, pagenum)
1787 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
1788 request = urllib2.Request(result_url, None, std_headers)
1790 page = urllib2.urlopen(request).read()
1791 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1792 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
1795 # Extract video identifiers
1796 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1797 video_id = mobj.group(1)
1798 if video_id not in already_seen:
1799 video_ids.append(video_id)
1800 already_seen.add(video_id)
1801 if len(video_ids) == n:
1802 # Specified n videos reached
1803 for id in video_ids:
1804 self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
1807 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1808 for id in video_ids:
1809 self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
1812 pagenum = pagenum + 1
1814 class YahooSearchIE(InfoExtractor):
1815 """Information Extractor for Yahoo! Video search queries."""
1816 _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
1817 _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
1818 _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
1819 _MORE_PAGES_INDICATOR = r'\s*Next'
1821 _max_yahoo_results = 1000
1823 def __init__(self, yahoo_ie, downloader=None):
1824 InfoExtractor.__init__(self, downloader)
1825 self._yahoo_ie = yahoo_ie
1829 return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
1831 def report_download_page(self, query, pagenum):
1832 """Report attempt to download playlist page with given number."""
1833 query = query.decode(preferredencoding())
1834 self._downloader.to_stdout(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
1836 def _real_initialize(self):
1837 self._yahoo_ie.initialize()
1839 def _real_extract(self, query):
1840 mobj = re.match(self._VALID_QUERY, query)
1842 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1845 prefix, query = query.split(':')
1847 query = query.encode('utf-8')
1849 self._download_n_results(query, 1)
1851 elif prefix == 'all':
1852 self._download_n_results(query, self._max_yahoo_results)
1858 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1860 elif n > self._max_yahoo_results:
1861 self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
1862 n = self._max_yahoo_results
1863 self._download_n_results(query, n)
1865 except ValueError: # parsing prefix as integer fails
1866 self._download_n_results(query, 1)
1869 def _download_n_results(self, query, n):
1870 """Downloads a specified number of results for a query"""
1873 already_seen = set()
1877 self.report_download_page(query, pagenum)
1878 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
1879 request = urllib2.Request(result_url, None, std_headers)
1881 page = urllib2.urlopen(request).read()
1882 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1883 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
1886 # Extract video identifiers
1887 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1888 video_id = mobj.group(1)
1889 if video_id not in already_seen:
1890 video_ids.append(video_id)
1891 already_seen.add(video_id)
1892 if len(video_ids) == n:
1893 # Specified n videos reached
1894 for id in video_ids:
1895 self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
1898 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1899 for id in video_ids:
1900 self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
1903 pagenum = pagenum + 1
1905 class YoutubePlaylistIE(InfoExtractor):
1906 """Information Extractor for YouTube playlists."""
1908 _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*'
1909 _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
1910 _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
1911 _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
1914 def __init__(self, youtube_ie, downloader=None):
1915 InfoExtractor.__init__(self, downloader)
1916 self._youtube_ie = youtube_ie
1920 return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
1922 def report_download_page(self, playlist_id, pagenum):
1923 """Report attempt to download playlist page with given number."""
1924 self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
1926 def _real_initialize(self):
1927 self._youtube_ie.initialize()
1929 def _real_extract(self, url):
1930 # Extract playlist id
1931 mobj = re.match(self._VALID_URL, url)
1933 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1936 # Download playlist pages
1937 playlist_id = mobj.group(1)
1942 self.report_download_page(playlist_id, pagenum)
1943 request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
1945 page = urllib2.urlopen(request).read()
1946 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
1947 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
1950 # Extract video identifiers
1952 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1953 if mobj.group(1) not in ids_in_page:
1954 ids_in_page.append(mobj.group(1))
1955 video_ids.extend(ids_in_page)
1957 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1959 pagenum = pagenum + 1
1961 playliststart = self._downloader.params.get('playliststart', 1)
1962 playliststart -= 1 #our arrays are zero-based but the playlist is 1-based
1963 if playliststart > 0:
1964 video_ids = video_ids[playliststart:]
1966 for id in video_ids:
1967 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
1970 class YoutubeUserIE(InfoExtractor):
1971 """Information Extractor for YouTube users."""
1973 _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
1974 _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
1975 _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
1978 def __init__(self, youtube_ie, downloader=None):
1979 InfoExtractor.__init__(self, downloader)
1980 self._youtube_ie = youtube_ie
1984 return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
1986 def report_download_page(self, username):
1987 """Report attempt to download user page."""
1988 self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username))
1990 def _real_initialize(self):
1991 self._youtube_ie.initialize()
1993 def _real_extract(self, url):
1995 mobj = re.match(self._VALID_URL, url)
1997 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
2000 # Download user page
2001 username = mobj.group(1)
2005 self.report_download_page(username)
2006 request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers)
2008 page = urllib2.urlopen(request).read()
2009 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
2010 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
2013 # Extract video identifiers
2016 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
2017 if mobj.group(1) not in ids_in_page:
2018 ids_in_page.append(mobj.group(1))
2019 video_ids.extend(ids_in_page)
2021 playliststart = self._downloader.params.get('playliststart', 1)
2022 playliststart = playliststart-1 #our arrays are zero-based but the playlist is 1-based
2023 if playliststart > 0:
2024 video_ids = video_ids[playliststart:]
2026 for id in video_ids:
2027 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
2030 class PostProcessor(object):
2031 """Post Processor class.
2033 PostProcessor objects can be added to downloaders with their
2034 add_post_processor() method. When the downloader has finished a
2035 successful download, it will take its internal chain of PostProcessors
2036 and start calling the run() method on each one of them, first with
2037 an initial argument and then with the returned value of the previous
2040 The chain will be stopped if one of them ever returns None or the end
2041 of the chain is reached.
2043 PostProcessor objects follow a "mutual registration" process similar
2044 to InfoExtractor objects.
2049 def __init__(self, downloader=None):
2050 self._downloader = downloader
2052 def set_downloader(self, downloader):
2053 """Sets the downloader for this PP."""
2054 self._downloader = downloader
2056 def run(self, information):
2057 """Run the PostProcessor.
2059 The "information" argument is a dictionary like the ones
2060 composed by InfoExtractors. The only difference is that this
2061 one has an extra field called "filepath" that points to the
2064 When this method returns None, the postprocessing chain is
2065 stopped. However, this method may return an information
2066 dictionary that will be passed to the next postprocessing
2067 object in the chain. It can be the one it received after
2068 changing some fields.
2070 In addition, this method may raise a PostProcessingError
2071 exception that will be taken into account by the downloader
2074 return information # by default, do nothing
2076 ### MAIN PROGRAM ###
2077 if __name__ == '__main__':
2079 # Modules needed only when running the main program
2083 # Function to update the program file with the latest version from bitbucket.org
2084 def update_self(downloader, filename):
2085 # Note: downloader only used for options
2086 if not os.access (filename, os.W_OK):
2087 sys.exit('ERROR: no write permissions on %s' % filename)
2089 downloader.to_stdout('Updating to latest stable version...')
2090 latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
2091 latest_version = urllib.urlopen(latest_url).read().strip()
2092 prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
2093 newcontent = urllib.urlopen(prog_url).read()
2094 stream = open(filename, 'w')
2095 stream.write(newcontent)
2097 downloader.to_stdout('Updated to version %s' % latest_version)
2099 # General configuration
2100 urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
2101 urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
2102 socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
2104 # Parse command line
2105 parser = optparse.OptionParser(
2106 usage='Usage: %prog [options] url...',
2107 version='2010.10.03',
2108 conflict_handler='resolve',
2111 parser.add_option('-h', '--help',
2112 action='help', help='print this help text and exit')
2113 parser.add_option('-v', '--version',
2114 action='version', help='print program version and exit')
2115 parser.add_option('-U', '--update',
2116 action='store_true', dest='update_self', help='update this program to latest stable version')
2117 parser.add_option('-i', '--ignore-errors',
2118 action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
2119 parser.add_option('-r', '--rate-limit',
2120 dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
2121 parser.add_option('-R', '--retries',
2122 dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
2123 parser.add_option('--playlist-start',
2124 dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
2126 authentication = optparse.OptionGroup(parser, 'Authentication Options')
2127 authentication.add_option('-u', '--username',
2128 dest='username', metavar='USERNAME', help='account username')
2129 authentication.add_option('-p', '--password',
2130 dest='password', metavar='PASSWORD', help='account password')
2131 authentication.add_option('-n', '--netrc',
2132 action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
2133 parser.add_option_group(authentication)
2135 video_format = optparse.OptionGroup(parser, 'Video Format Options')
2136 video_format.add_option('-f', '--format',
2137 action='store', dest='format', metavar='FORMAT', help='video format code')
2138 video_format.add_option('-m', '--mobile-version',
2139 action='store_const', dest='format', help='alias for -f 17', const='17')
2140 video_format.add_option('--all-formats',
2141 action='store_const', dest='format', help='download all available video formats', const='-1')
2142 video_format.add_option('--max-quality',
2143 action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
2144 video_format.add_option('-b', '--best-quality',
2145 action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)')
2146 parser.add_option_group(video_format)
2148 verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
2149 verbosity.add_option('-q', '--quiet',
2150 action='store_true', dest='quiet', help='activates quiet mode', default=False)
2151 verbosity.add_option('-s', '--simulate',
2152 action='store_true', dest='simulate', help='do not download video', default=False)
2153 verbosity.add_option('-g', '--get-url',
2154 action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
2155 verbosity.add_option('-e', '--get-title',
2156 action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
2157 verbosity.add_option('--get-thumbnail',
2158 action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False)
2159 verbosity.add_option('--get-description',
2160 action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False)
2161 verbosity.add_option('--no-progress',
2162 action='store_true', dest='noprogress', help='do not print progress bar', default=False)
2163 parser.add_option_group(verbosity)
2165 filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
2166 filesystem.add_option('-t', '--title',
2167 action='store_true', dest='usetitle', help='use title in file name', default=False)
2168 filesystem.add_option('-l', '--literal',
2169 action='store_true', dest='useliteral', help='use literal title in file name', default=False)
2170 filesystem.add_option('-o', '--output',
2171 dest='outtmpl', metavar='TEMPLATE', help='output filename template')
2172 filesystem.add_option('-a', '--batch-file',
2173 dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
2174 filesystem.add_option('-w', '--no-overwrites',
2175 action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
2176 filesystem.add_option('-c', '--continue',
2177 action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
2178 parser.add_option_group(filesystem)
2180 (opts, args) = parser.parse_args()
2182 # Batch file verification
2184 if opts.batchfile is not None:
2186 if opts.batchfile == '-':
2189 batchfd = open(opts.batchfile, 'r')
2190 batchurls = batchfd.readlines()
2191 batchurls = [x.strip() for x in batchurls]
2192 batchurls = [x for x in batchurls if len(x) > 0]
2194 sys.exit(u'ERROR: batch file could not be read')
2195 all_urls = batchurls + args
2197 # Conflicting, missing and erroneous options
2198 if opts.bestquality:
2199 print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n'
2200 if opts.usenetrc and (opts.username is not None or opts.password is not None):
2201 parser.error(u'using .netrc conflicts with giving username/password')
2202 if opts.password is not None and opts.username is None:
2203 parser.error(u'account username missing')
2204 if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
2205 parser.error(u'using output template conflicts with using title or literal title')
2206 if opts.usetitle and opts.useliteral:
2207 parser.error(u'using title conflicts with using literal title')
2208 if opts.username is not None and opts.password is None:
2209 opts.password = getpass.getpass(u'Type account password and press return:')
2210 if opts.ratelimit is not None:
2211 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
2212 if numeric_limit is None:
2213 parser.error(u'invalid rate limit specified')
2214 opts.ratelimit = numeric_limit
2215 if opts.retries is not None:
2217 opts.retries = long(opts.retries)
2218 except (TypeError, ValueError), err:
2219 parser.error(u'invalid retry count specified')
2220 if opts.playliststart is not None:
2222 opts.playliststart = long(opts.playliststart)
2223 except (TypeError, ValueError), err:
2224 parser.error(u'invalid playlist page specified')
2226 # Information extractors
2227 youtube_ie = YoutubeIE()
2228 metacafe_ie = MetacafeIE(youtube_ie)
2229 dailymotion_ie = DailymotionIE()
2230 youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
2231 youtube_user_ie = YoutubeUserIE(youtube_ie)
2232 youtube_search_ie = YoutubeSearchIE(youtube_ie)
2233 google_ie = GoogleIE()
2234 google_search_ie = GoogleSearchIE(google_ie)
2235 photobucket_ie = PhotobucketIE()
2236 yahoo_ie = YahooIE()
2237 yahoo_search_ie = YahooSearchIE(yahoo_ie)
2238 generic_ie = GenericIE()
2241 fd = FileDownloader({
2242 'usenetrc': opts.usenetrc,
2243 'username': opts.username,
2244 'password': opts.password,
2245 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
2246 'forceurl': opts.geturl,
2247 'forcetitle': opts.gettitle,
2248 'forcethumbnail': opts.getthumbnail,
2249 'forcedescription': opts.getdescription,
2250 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
2251 'format': opts.format,
2252 'format_limit': opts.format_limit,
2253 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
2254 or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
2255 or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
2256 or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
2257 or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
2258 or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
2259 or u'%(id)s.%(ext)s'),
2260 'ignoreerrors': opts.ignoreerrors,
2261 'ratelimit': opts.ratelimit,
2262 'nooverwrites': opts.nooverwrites,
2263 'retries': opts.retries,
2264 'continuedl': opts.continue_dl,
2265 'noprogress': opts.noprogress,
2266 'playliststart': opts.playliststart,
2268 fd.add_info_extractor(youtube_search_ie)
2269 fd.add_info_extractor(youtube_pl_ie)
2270 fd.add_info_extractor(youtube_user_ie)
2271 fd.add_info_extractor(metacafe_ie)
2272 fd.add_info_extractor(dailymotion_ie)
2273 fd.add_info_extractor(youtube_ie)
2274 fd.add_info_extractor(google_ie)
2275 fd.add_info_extractor(google_search_ie)
2276 fd.add_info_extractor(photobucket_ie)
2277 fd.add_info_extractor(yahoo_ie)
2278 fd.add_info_extractor(yahoo_search_ie)
2280 # This must come last since it's the
2281 # fallback if none of the others work
2282 fd.add_info_extractor(generic_ie)
2285 if opts.update_self:
2286 update_self(fd, sys.argv[0])
2289 if len(all_urls) < 1:
2290 if not opts.update_self:
2291 parser.error(u'you must provide at least one URL')
2294 retcode = fd.download(all_urls)
2297 except DownloadError:
2299 except SameFileError:
2300 sys.exit(u'ERROR: fixed output name but more than one file to download')
2301 except KeyboardInterrupt:
2302 sys.exit(u'\nERROR: Interrupted by user')