2 # -*- coding: utf-8 -*-
3 # Author: Ricardo Garcia Gonzalez
4 # Author: Danny Colligan
5 # License: Public domain code
22 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2',
23 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
24 'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
25 'Accept-Language': 'en-us,en;q=0.5',
28 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
30 class DownloadError(Exception):
31 """Download Error exception.
33 This exception may be thrown by FileDownloader objects if they are not
34 configured to continue on errors. They will contain the appropriate
39 class SameFileError(Exception):
40 """Same File exception.
42 This exception will be thrown by FileDownloader objects if they detect
43 multiple files would have to be downloaded to the same file on disk.
47 class PostProcessingError(Exception):
48 """Post Processing exception.
50 This exception may be raised by PostProcessor's .run() method to
51 indicate an error in the postprocessing task.
55 class UnavailableFormatError(Exception):
56 """Unavailable Format exception.
58 This exception will be thrown when a video is requested
59 in a format that is not available for that video.
63 class ContentTooShortError(Exception):
64 """Content Too Short exception.
66 This exception may be raised by FileDownloader objects when a file they
67 download is too small for what the server announced first, indicating
68 the connection was probably interrupted.
74 def __init__(self, downloaded, expected):
75 self.downloaded = downloaded
76 self.expected = expected
78 class FileDownloader(object):
79 """File Downloader class.
81 File downloader objects are the ones responsible of downloading the
82 actual video file and writing it to disk if the user has requested
83 it, among some other tasks. In most cases there should be one per
84 program. As, given a video URL, the downloader doesn't know how to
85 extract all the needed information, task that InfoExtractors do, it
86 has to pass the URL to one of them.
88 For this, file downloader objects have a method that allows
89 InfoExtractors to be registered in a given order. When it is passed
90 a URL, the file downloader handles it to the first InfoExtractor it
91 finds that reports being able to handle it. The InfoExtractor extracts
92 all the information about the video or videos the URL refers to, and
93 asks the FileDownloader to process the video information, possibly
94 downloading the video.
96 File downloaders accept a lot of parameters. In order not to saturate
97 the object constructor with arguments, it receives a dictionary of
98 options instead. These options are available through the params
99 attribute for the InfoExtractors to use. The FileDownloader also
100 registers itself as the downloader in charge for the InfoExtractors
101 that are added to it, so this is a "mutual registration".
105 username: Username for authentication purposes.
106 password: Password for authentication purposes.
107 usenetrc: Use netrc for authentication instead.
108 quiet: Do not print messages to stdout.
109 forceurl: Force printing final URL.
110 forcetitle: Force printing title.
111 simulate: Do not download the video files.
112 format: Video format code.
113 outtmpl: Template for output names.
114 ignoreerrors: Do not stop on download errors.
115 ratelimit: Download speed limit, in bytes/sec.
116 nooverwrites: Prevent overwriting files.
117 continuedl: Try to continue downloads if possible.
123 _download_retcode = None
125 def __init__(self, params):
126 """Create a FileDownloader object with the given options."""
129 self._download_retcode = 0
133 def pmkdir(filename):
134 """Create directory components in filename. Similar to Unix "mkdir -p"."""
135 components = filename.split(os.sep)
136 aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
137 aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
138 for dir in aggregate:
139 if not os.path.exists(dir):
143 def format_bytes(bytes):
146 if type(bytes) is str:
151 exponent = long(math.log(bytes, 1024.0))
152 suffix = 'bkMGTPEZY'[exponent]
153 converted = float(bytes) / float(1024**exponent)
154 return '%.2f%s' % (converted, suffix)
157 def calc_percent(byte_counter, data_len):
160 return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
163 def calc_eta(start, now, total, current):
167 if current == 0 or dif < 0.001: # One millisecond
169 rate = float(current) / dif
170 eta = long((float(total) - float(current)) / rate)
171 (eta_mins, eta_secs) = divmod(eta, 60)
174 return '%02d:%02d' % (eta_mins, eta_secs)
177 def calc_speed(start, now, bytes):
179 if bytes == 0 or dif < 0.001: # One millisecond
180 return '%10s' % '---b/s'
181 return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
184 def best_block_size(elapsed_time, bytes):
185 new_min = max(bytes / 2.0, 1.0)
186 new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
187 if elapsed_time < 0.001:
189 rate = bytes / elapsed_time
197 def parse_bytes(bytestr):
198 """Parse a string indicating a byte quantity into a long integer."""
199 matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
202 number = float(matchobj.group(1))
203 multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
204 return long(round(number * multiplier))
208 """Verify a URL is valid and data could be downloaded."""
209 request = urllib2.Request(url, None, std_headers)
210 data = urllib2.urlopen(request)
214 def add_info_extractor(self, ie):
215 """Add an InfoExtractor object to the end of the list."""
217 ie.set_downloader(self)
219 def add_post_processor(self, pp):
220 """Add a PostProcessor object to the end of the chain."""
222 pp.set_downloader(self)
224 def to_stdout(self, message, skip_eol=False):
225 """Print message to stdout if not in quiet mode."""
226 if not self.params.get('quiet', False):
227 print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(locale.getpreferredencoding()),
230 def to_stderr(self, message):
231 """Print message to stderr."""
232 print >>sys.stderr, message.encode(locale.getpreferredencoding())
234 def fixed_template(self):
235 """Checks if the output template is fixed."""
236 return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
238 def trouble(self, message=None):
239 """Determine action to take when a download problem appears.
241 Depending on if the downloader has been configured to ignore
242 download errors or not, this method may throw an exception or
243 not when errors are found, after printing the message.
245 if message is not None:
246 self.to_stderr(message)
247 if not self.params.get('ignoreerrors', False):
248 raise DownloadError(message)
249 self._download_retcode = 1
251 def slow_down(self, start_time, byte_counter):
252 """Sleep if the download speed is over the rate limit."""
253 rate_limit = self.params.get('ratelimit', None)
254 if rate_limit is None or byte_counter == 0:
257 elapsed = now - start_time
260 speed = float(byte_counter) / elapsed
261 if speed > rate_limit:
262 time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
264 def report_destination(self, filename):
265 """Report destination filename."""
266 self.to_stdout(u'[download] Destination: %s' % filename)
268 def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
269 """Report download progress."""
270 self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
271 (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
273 def report_resuming_byte(self, resume_len):
274 """Report attemtp to resume at given byte."""
275 self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
277 def report_file_already_downloaded(self, file_name):
278 """Report file has already been fully downloaded."""
279 self.to_stdout(u'[download] %s has already been downloaded' % file_name)
281 def report_unable_to_resume(self):
282 """Report it was impossible to resume download."""
283 self.to_stdout(u'[download] Unable to resume')
285 def report_finish(self):
286 """Report download finished."""
289 def process_info(self, info_dict):
290 """Process a single dictionary returned by an InfoExtractor."""
291 # Do nothing else if in simulate mode
292 if self.params.get('simulate', False):
294 self.verify_url(info_dict['url'])
295 except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
296 raise UnavailableFormatError
299 if self.params.get('forcetitle', False):
300 print info_dict['title'].encode(locale.getpreferredencoding())
301 if self.params.get('forceurl', False):
302 print info_dict['url'].encode(locale.getpreferredencoding())
307 template_dict = dict(info_dict)
308 template_dict['epoch'] = unicode(long(time.time()))
309 filename = self.params['outtmpl'] % template_dict
310 except (ValueError, KeyError), err:
311 self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
312 if self.params['nooverwrites'] and os.path.exists(filename):
313 self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
317 self.pmkdir(filename)
318 except (OSError, IOError), err:
319 self.trouble('ERROR: unable to create directories: %s' % str(err))
323 success = self._do_download(filename, info_dict['url'])
324 except (OSError, IOError), err:
325 raise UnavailableFormatError
326 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
327 self.trouble('ERROR: unable to download video data: %s' % str(err))
329 except (ContentTooShortError, ), err:
330 self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
335 self.post_process(filename, info_dict)
336 except (PostProcessingError), err:
337 self.trouble('ERROR: postprocessing: %s' % str(err))
340 def download(self, url_list):
341 """Download a given list of URLs."""
342 if len(url_list) > 1 and self.fixed_template():
343 raise SameFileError(self.params['outtmpl'])
346 suitable_found = False
348 # Go to next InfoExtractor if not suitable
349 if not ie.suitable(url):
352 # Suitable InfoExtractor found
353 suitable_found = True
355 # Extract information from URL and process it
358 # Suitable InfoExtractor had been found; go to next URL
361 if not suitable_found:
362 self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
364 return self._download_retcode
366 def post_process(self, filename, ie_info):
367 """Run the postprocessing chain on the given file."""
369 info['filepath'] = filename
375 def _do_download(self, filename, url):
379 basic_request = urllib2.Request(url, None, std_headers)
380 request = urllib2.Request(url, None, std_headers)
382 # Attempt to resume download with "continuedl" option
383 if os.path.isfile(filename):
384 resume_len = os.path.getsize(filename)
387 if self.params['continuedl'] and resume_len != 0:
388 self.report_resuming_byte(resume_len)
389 request.add_header('Range','bytes=%d-' % resume_len)
391 # Establish connection
393 data = urllib2.urlopen(request)
394 except (urllib2.HTTPError, ), err:
395 if err.code != 416: # 416 is 'Requested range not satisfiable'
397 data = urllib2.urlopen(basic_request)
398 content_length = data.info()['Content-Length']
399 if content_length is not None and long(content_length) == resume_len:
400 self.report_file_already_downloaded(filename)
403 self.report_unable_to_resume()
406 data_len = data.info().get('Content-length', None)
407 data_len_str = self.format_bytes(data_len)
414 data_block = data.read(block_size)
416 data_block_len = len(data_block)
417 if data_block_len == 0:
419 byte_counter += data_block_len
421 # Open file just in time
424 stream = open(filename, open_mode)
425 self.report_destination(filename)
426 except (OSError, IOError), err:
427 self.trouble('ERROR: unable to open for writing: %s' % str(err))
429 stream.write(data_block)
430 block_size = self.best_block_size(after - before, data_block_len)
433 percent_str = self.calc_percent(byte_counter, data_len)
434 eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
435 speed_str = self.calc_speed(start, time.time(), byte_counter)
436 self.report_progress(percent_str, data_len_str, speed_str, eta_str)
439 self.slow_down(start, byte_counter)
442 if data_len is not None and str(byte_counter) != data_len:
443 raise ContentTooShortError(byte_counter, long(data_len))
446 class InfoExtractor(object):
447 """Information Extractor class.
449 Information extractors are the classes that, given a URL, extract
450 information from the video (or videos) the URL refers to. This
451 information includes the real video URL, the video title and simplified
452 title, author and others. The information is stored in a dictionary
453 which is then passed to the FileDownloader. The FileDownloader
454 processes this information possibly downloading the video to the file
455 system, among other possible outcomes. The dictionaries must include
456 the following fields:
458 id: Video identifier.
459 url: Final video URL.
460 uploader: Nickname of the video uploader.
461 title: Literal title.
462 stitle: Simplified title.
463 ext: Video filename extension.
465 Subclasses of this one should re-define the _real_initialize() and
466 _real_extract() methods, as well as the suitable() static method.
467 Probably, they should also be instantiated and added to the main
474 def __init__(self, downloader=None):
475 """Constructor. Receives an optional downloader."""
477 self.set_downloader(downloader)
481 """Receives a URL and returns True if suitable for this IE."""
484 def initialize(self):
485 """Initializes an instance (authentication, etc)."""
487 self._real_initialize()
490 def extract(self, url):
491 """Extracts URL information and returns it in list of dicts."""
493 return self._real_extract(url)
495 def set_downloader(self, downloader):
496 """Sets the downloader for this IE."""
497 self._downloader = downloader
499 def _real_initialize(self):
500 """Real initialization process. Redefine in subclasses."""
503 def _real_extract(self, url):
504 """Real extraction process. Redefine in subclasses."""
507 class YoutubeIE(InfoExtractor):
508 """Information extractor for youtube.com."""
510 _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
511 _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
512 _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
513 _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
514 _NETRC_MACHINE = 'youtube'
515 _available_formats = ['22', '35', '18', '5', '17', '13'] # listed in order of priority for -b flag
516 _video_extensions = {
525 return (re.match(YoutubeIE._VALID_URL, url) is not None)
528 def htmlentity_transform(matchobj):
529 """Transforms an HTML entity to a Unicode character."""
530 entity = matchobj.group(1)
532 # Known non-numeric HTML entity
533 if entity in htmlentitydefs.name2codepoint:
534 return unichr(htmlentitydefs.name2codepoint[entity])
537 mobj = re.match(ur'(?u)#(x?\d+)', entity)
539 numstr = mobj.group(1)
540 if numstr.startswith(u'x'):
542 numstr = u'0%s' % numstr
545 return unichr(long(numstr, base))
547 # Unknown entity in name, return its literal representation
548 return (u'&%s;' % entity)
550 def report_lang(self):
551 """Report attempt to set language."""
552 self._downloader.to_stdout(u'[youtube] Setting language')
554 def report_login(self):
555 """Report attempt to log in."""
556 self._downloader.to_stdout(u'[youtube] Logging in')
558 def report_age_confirmation(self):
559 """Report attempt to confirm age."""
560 self._downloader.to_stdout(u'[youtube] Confirming age')
562 def report_webpage_download(self, video_id):
563 """Report attempt to download webpage."""
564 self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
566 def report_information_extraction(self, video_id):
567 """Report attempt to extract video information."""
568 self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
570 def report_video_url(self, video_id, video_real_url):
571 """Report extracted video URL."""
572 self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
574 def report_unavailable_format(self, video_id, format):
575 """Report extracted video URL."""
576 self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
578 def _real_initialize(self):
579 if self._downloader is None:
584 downloader_params = self._downloader.params
586 # Attempt to use provided username and password or .netrc data
587 if downloader_params.get('username', None) is not None:
588 username = downloader_params['username']
589 password = downloader_params['password']
590 elif downloader_params.get('usenetrc', False):
592 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
597 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
598 except (IOError, netrc.NetrcParseError), err:
599 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
603 request = urllib2.Request(self._LANG_URL, None, std_headers)
606 urllib2.urlopen(request).read()
607 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
608 self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
611 # No authentication to be performed
617 'current_form': 'loginForm',
619 'action_login': 'Log In',
620 'username': username,
621 'password': password,
623 request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
626 login_results = urllib2.urlopen(request).read()
627 if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
628 self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
630 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
631 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
637 'action_confirm': 'Confirm',
639 request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
641 self.report_age_confirmation()
642 age_results = urllib2.urlopen(request).read()
643 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
644 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
647 def _real_extract(self, url):
648 # Extract video id from URL
649 mobj = re.match(self._VALID_URL, url)
651 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
653 video_id = mobj.group(2)
655 # Downloader parameters
659 if self._downloader is not None:
660 params = self._downloader.params
661 format_param = params.get('format', None)
662 if format_param == '0':
663 format_param = self._available_formats[quality_index]
668 video_extension = self._video_extensions.get(format_param, 'flv')
670 # Normalize URL, including format
671 normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
672 if format_param is not None:
673 normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
674 request = urllib2.Request(normalized_url, None, std_headers)
676 self.report_webpage_download(video_id)
677 video_webpage = urllib2.urlopen(request).read()
678 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
679 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
681 self.report_information_extraction(video_id)
684 mobj = re.search(r', "t": "([^"]+)"', video_webpage)
686 self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
688 video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
689 if format_param is not None:
690 video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
691 self.report_video_url(video_id, video_real_url)
694 mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
696 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
698 video_uploader = mobj.group(1)
701 mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
703 self._downloader.trouble(u'ERROR: unable to extract video title')
705 video_title = mobj.group(1).decode('utf-8')
706 video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
707 video_title = video_title.replace(os.sep, u'%')
710 simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
711 simple_title = simple_title.strip(ur'_')
714 # Process video information
715 self._downloader.process_info({
716 'id': video_id.decode('utf-8'),
717 'url': video_real_url.decode('utf-8'),
718 'uploader': video_uploader.decode('utf-8'),
719 'title': video_title,
720 'stitle': simple_title,
721 'ext': video_extension.decode('utf-8'),
726 except UnavailableFormatError, err:
728 if quality_index == len(self._available_formats) - 1:
729 # I don't ever expect this to happen
730 self._downloader.trouble(u'ERROR: no known formats available for video')
733 self.report_unavailable_format(video_id, format_param)
735 format_param = self._available_formats[quality_index]
738 self._downloader.trouble('ERROR: format not available for video')
742 class MetacafeIE(InfoExtractor):
743 """Information Extractor for metacafe.com."""
745 _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
746 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
747 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
750 def __init__(self, youtube_ie, downloader=None):
751 InfoExtractor.__init__(self, downloader)
752 self._youtube_ie = youtube_ie
756 return (re.match(MetacafeIE._VALID_URL, url) is not None)
758 def report_disclaimer(self):
759 """Report disclaimer retrieval."""
760 self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
762 def report_age_confirmation(self):
763 """Report attempt to confirm age."""
764 self._downloader.to_stdout(u'[metacafe] Confirming age')
766 def report_download_webpage(self, video_id):
767 """Report webpage download."""
768 self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
770 def report_extraction(self, video_id):
771 """Report information extraction."""
772 self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
774 def _real_initialize(self):
775 # Retrieve disclaimer
776 request = urllib2.Request(self._DISCLAIMER, None, std_headers)
778 self.report_disclaimer()
779 disclaimer = urllib2.urlopen(request).read()
780 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
781 self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
787 'submit': "Continue - I'm over 18",
789 request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
791 self.report_age_confirmation()
792 disclaimer = urllib2.urlopen(request).read()
793 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
794 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
797 def _real_extract(self, url):
798 # Extract id and simplified title from URL
799 mobj = re.match(self._VALID_URL, url)
801 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
804 video_id = mobj.group(1)
806 # Check if video comes from YouTube
807 mobj2 = re.match(r'^yt-(.*)$', video_id)
808 if mobj2 is not None:
809 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
812 simple_title = mobj.group(2).decode('utf-8')
813 video_extension = 'flv'
815 # Retrieve video webpage to extract further information
816 request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
818 self.report_download_webpage(video_id)
819 webpage = urllib2.urlopen(request).read()
820 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
821 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
824 # Extract URL, uploader and title from webpage
825 self.report_extraction(video_id)
826 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
828 self._downloader.trouble(u'ERROR: unable to extract media URL')
830 mediaURL = urllib.unquote(mobj.group(1))
832 #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
834 # self._downloader.trouble(u'ERROR: unable to extract gdaKey')
836 #gdaKey = mobj.group(1)
838 #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
842 mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
844 self._downloader.trouble(u'ERROR: unable to extract title')
846 video_title = mobj.group(1).decode('utf-8')
848 mobj = re.search(r'(?ms)<li id="ChnlUsr">.*?Submitter:.*?<a .*?>(.*?)<', webpage)
850 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
852 video_uploader = mobj.group(1)
855 # Process video information
856 self._downloader.process_info({
857 'id': video_id.decode('utf-8'),
858 'url': video_url.decode('utf-8'),
859 'uploader': video_uploader.decode('utf-8'),
860 'title': video_title,
861 'stitle': simple_title,
862 'ext': video_extension.decode('utf-8'),
864 except UnavailableFormatError:
865 self._downloader.trouble(u'ERROR: format not available for video')
868 class YoutubeSearchIE(InfoExtractor):
869 """Information Extractor for YouTube search queries."""
870 _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
871 _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
872 _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
873 _MORE_PAGES_INDICATOR = r'>Next</a>'
875 _max_youtube_results = 1000
877 def __init__(self, youtube_ie, downloader=None):
878 InfoExtractor.__init__(self, downloader)
879 self._youtube_ie = youtube_ie
883 return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
885 def report_download_page(self, query, pagenum):
886 """Report attempt to download playlist page with given number."""
887 self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
889 def _real_initialize(self):
890 self._youtube_ie.initialize()
892 def _real_extract(self, query):
893 mobj = re.match(self._VALID_QUERY, query)
895 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
898 prefix, query = query.split(':')
901 self._download_n_results(query, 1)
903 elif prefix == 'all':
904 self._download_n_results(query, self._max_youtube_results)
910 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
912 elif n > self._max_youtube_results:
913 self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
914 n = self._max_youtube_results
915 self._download_n_results(query, n)
917 except ValueError: # parsing prefix as integer fails
918 self._download_n_results(query, 1)
921 def _download_n_results(self, query, n):
922 """Downloads a specified number of results for a query"""
929 self.report_download_page(query, pagenum)
930 result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
931 request = urllib2.Request(result_url, None, std_headers)
933 page = urllib2.urlopen(request).read()
934 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
935 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
938 # Extract video identifiers
939 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
940 video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
941 if video_id not in already_seen:
942 video_ids.append(video_id)
943 already_seen.add(video_id)
944 if len(video_ids) == n:
945 # Specified n videos reached
947 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
950 if self._MORE_PAGES_INDICATOR not in page:
952 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
955 pagenum = pagenum + 1
957 class YoutubePlaylistIE(InfoExtractor):
958 """Information Extractor for YouTube playlists."""
960 _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
961 _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
962 _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
963 _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
966 def __init__(self, youtube_ie, downloader=None):
967 InfoExtractor.__init__(self, downloader)
968 self._youtube_ie = youtube_ie
972 return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
974 def report_download_page(self, playlist_id, pagenum):
975 """Report attempt to download playlist page with given number."""
976 self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
978 def _real_initialize(self):
979 self._youtube_ie.initialize()
981 def _real_extract(self, url):
982 # Extract playlist id
983 mobj = re.match(self._VALID_URL, url)
985 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
988 # Download playlist pages
989 playlist_id = mobj.group(1)
994 self.report_download_page(playlist_id, pagenum)
995 request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
997 page = urllib2.urlopen(request).read()
998 except (urllib2.URLError, httplib.HTTPException, socket.error), err:
999 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
1002 # Extract video identifiers
1004 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1005 if mobj.group(1) not in ids_in_page:
1006 ids_in_page.append(mobj.group(1))
1007 video_ids.extend(ids_in_page)
1009 if (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page:
1011 pagenum = pagenum + 1
1013 for id in video_ids:
1014 self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
1017 class PostProcessor(object):
1018 """Post Processor class.
1020 PostProcessor objects can be added to downloaders with their
1021 add_post_processor() method. When the downloader has finished a
1022 successful download, it will take its internal chain of PostProcessors
1023 and start calling the run() method on each one of them, first with
1024 an initial argument and then with the returned value of the previous
1027 The chain will be stopped if one of them ever returns None or the end
1028 of the chain is reached.
1030 PostProcessor objects follow a "mutual registration" process similar
1031 to InfoExtractor objects.
1036 def __init__(self, downloader=None):
1037 self._downloader = downloader
1039 def set_downloader(self, downloader):
1040 """Sets the downloader for this PP."""
1041 self._downloader = downloader
1043 def run(self, information):
1044 """Run the PostProcessor.
1046 The "information" argument is a dictionary like the ones
1047 composed by InfoExtractors. The only difference is that this
1048 one has an extra field called "filepath" that points to the
1051 When this method returns None, the postprocessing chain is
1052 stopped. However, this method may return an information
1053 dictionary that will be passed to the next postprocessing
1054 object in the chain. It can be the one it received after
1055 changing some fields.
1057 In addition, this method may raise a PostProcessingError
1058 exception that will be taken into account by the downloader
1061 return information # by default, do nothing
1063 ### MAIN PROGRAM ###
1064 if __name__ == '__main__':
1066 # Modules needed only when running the main program
1070 # General configuration
1071 urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
1072 urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
1073 socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
1075 # Parse command line
1076 parser = optparse.OptionParser(
1077 usage='Usage: %prog [options] url...',
1078 version='2009.06.29',
1079 conflict_handler='resolve',
1082 parser.add_option('-h', '--help',
1083 action='help', help='print this help text and exit')
1084 parser.add_option('-v', '--version',
1085 action='version', help='print program version and exit')
1086 parser.add_option('-i', '--ignore-errors',
1087 action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
1088 parser.add_option('-r', '--rate-limit',
1089 dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
1091 authentication = optparse.OptionGroup(parser, 'Authentication Options')
1092 authentication.add_option('-u', '--username',
1093 dest='username', metavar='UN', help='account username')
1094 authentication.add_option('-p', '--password',
1095 dest='password', metavar='PW', help='account password')
1096 authentication.add_option('-n', '--netrc',
1097 action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
1098 parser.add_option_group(authentication)
1100 video_format = optparse.OptionGroup(parser, 'Video Format Options')
1101 video_format.add_option('-f', '--format',
1102 action='store', dest='format', metavar='FMT', help='video format code')
1103 video_format.add_option('-b', '--best-quality',
1104 action='store_const', dest='format', help='download the best quality video possible', const='0')
1105 video_format.add_option('-m', '--mobile-version',
1106 action='store_const', dest='format', help='alias for -f 17', const='17')
1107 video_format.add_option('-d', '--high-def',
1108 action='store_const', dest='format', help='alias for -f 22', const='22')
1109 parser.add_option_group(video_format)
1111 verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
1112 verbosity.add_option('-q', '--quiet',
1113 action='store_true', dest='quiet', help='activates quiet mode', default=False)
1114 verbosity.add_option('-s', '--simulate',
1115 action='store_true', dest='simulate', help='do not download video', default=False)
1116 verbosity.add_option('-g', '--get-url',
1117 action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
1118 verbosity.add_option('-e', '--get-title',
1119 action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
1120 parser.add_option_group(verbosity)
1122 filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
1123 filesystem.add_option('-t', '--title',
1124 action='store_true', dest='usetitle', help='use title in file name', default=False)
1125 filesystem.add_option('-l', '--literal',
1126 action='store_true', dest='useliteral', help='use literal title in file name', default=False)
1127 filesystem.add_option('-o', '--output',
1128 dest='outtmpl', metavar='TPL', help='output filename template')
1129 filesystem.add_option('-a', '--batch-file',
1130 dest='batchfile', metavar='F', help='file containing URLs to download')
1131 filesystem.add_option('-w', '--no-overwrites',
1132 action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
1133 filesystem.add_option('-c', '--continue',
1134 action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
1135 parser.add_option_group(filesystem)
1137 (opts, args) = parser.parse_args()
1139 # Batch file verification
1141 if opts.batchfile is not None:
1143 batchurls = open(opts.batchfile, 'r').readlines()
1144 batchurls = [x.strip() for x in batchurls]
1145 batchurls = [x for x in batchurls if len(x) > 0]
1147 sys.exit(u'ERROR: batch file could not be read')
1148 all_urls = batchurls + args
1150 # Conflicting, missing and erroneous options
1151 if len(all_urls) < 1:
1152 parser.error(u'you must provide at least one URL')
1153 if opts.usenetrc and (opts.username is not None or opts.password is not None):
1154 parser.error(u'using .netrc conflicts with giving username/password')
1155 if opts.password is not None and opts.username is None:
1156 parser.error(u'account username missing')
1157 if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
1158 parser.error(u'using output template conflicts with using title or literal title')
1159 if opts.usetitle and opts.useliteral:
1160 parser.error(u'using title conflicts with using literal title')
1161 if opts.username is not None and opts.password is None:
1162 opts.password = getpass.getpass(u'Type account password and press return:')
1163 if opts.ratelimit is not None:
1164 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
1165 if numeric_limit is None:
1166 parser.error(u'invalid rate limit specified')
1167 opts.ratelimit = numeric_limit
1169 # Information extractors
1170 youtube_ie = YoutubeIE()
1171 metacafe_ie = MetacafeIE(youtube_ie)
1172 youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
1173 youtube_search_ie = YoutubeSearchIE(youtube_ie)
1176 fd = FileDownloader({
1177 'usenetrc': opts.usenetrc,
1178 'username': opts.username,
1179 'password': opts.password,
1180 'quiet': (opts.quiet or opts.geturl or opts.gettitle),
1181 'forceurl': opts.geturl,
1182 'forcetitle': opts.gettitle,
1183 'simulate': (opts.simulate or opts.geturl or opts.gettitle),
1184 'format': opts.format,
1185 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding()))
1186 or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
1187 or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
1188 or u'%(id)s.%(ext)s'),
1189 'ignoreerrors': opts.ignoreerrors,
1190 'ratelimit': opts.ratelimit,
1191 'nooverwrites': opts.nooverwrites,
1192 'continuedl': opts.continue_dl,
1194 fd.add_info_extractor(youtube_search_ie)
1195 fd.add_info_extractor(youtube_pl_ie)
1196 fd.add_info_extractor(metacafe_ie)
1197 fd.add_info_extractor(youtube_ie)
1198 retcode = fd.download(all_urls)
1201 except DownloadError:
1203 except SameFileError:
1204 sys.exit(u'ERROR: fixed output name but more than one file to download')
1205 except KeyboardInterrupt:
1206 sys.exit(u'\nERROR: Interrupted by user')