X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=becf1d25de31ccbdbaaef76b517bb23490a9c001;hb=2a04438c7c6de2dc9ef2a0bbaaa8ebc1dc654f44;hp=bc7e3b5fe9c6dffc68f6ca78f1d4a5faf382a0b3;hpb=2f4d18a9f78f9d18635c6047e56b33c689b8d026;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index bc7e3b5fe..becf1d25d 100755 --- a/youtube-dl +++ b/youtube-dl @@ -19,7 +19,7 @@ import urllib import urllib2 std_headers = { - 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8', + 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5', 'Accept-Language': 'en-us,en;q=0.5', @@ -52,6 +52,29 @@ class PostProcessingError(Exception): """ pass +class UnavailableFormatError(Exception): + """Unavailable Format exception. + + This exception will be thrown when a video is requested + in a format that is not available for that video. + """ + pass + +class ContentTooShortError(Exception): + """Content Too Short exception. + + This exception may be raised by FileDownloader objects when a file they + download is too small for what the server announced first, indicating + the connection was probably interrupted. + """ + # Both in bytes + downloaded = None + expected = None + + def __init__(self, downloaded, expected): + self.downloaded = downloaded + self.expected = expected + class FileDownloader(object): """File Downloader class. @@ -65,9 +88,10 @@ class FileDownloader(object): For this, file downloader objects have a method that allows InfoExtractors to be registered in a given order. When it is passed a URL, the file downloader handles it to the first InfoExtractor it - finds that reports being able to handle it. The InfoExtractor returns - all the information to the FileDownloader and the latter downloads the - file or does whatever it's instructed to do. + finds that reports being able to handle it. The InfoExtractor extracts + all the information about the video or videos the URL refers to, and + asks the FileDownloader to process the video information, possibly + downloading the video. File downloaders accept a lot of parameters. In order not to saturate the object constructor with arguments, it receives a dictionary of @@ -90,16 +114,19 @@ class FileDownloader(object): ignoreerrors: Do not stop on download errors. ratelimit: Download speed limit, in bytes/sec. nooverwrites: Prevent overwriting files. + continuedl: Try to continue downloads if possible. """ params = None _ies = [] _pps = [] + _download_retcode = None def __init__(self, params): """Create a FileDownloader object with the given options.""" self._ies = [] self._pps = [] + self._download_retcode = 0 self.params = params @staticmethod @@ -116,10 +143,12 @@ class FileDownloader(object): def format_bytes(bytes): if bytes is None: return 'N/A' - if bytes == 0: + if type(bytes) is str: + bytes = float(bytes) + if bytes == 0.0: exponent = 0 else: - exponent = long(math.log(float(bytes), 1024.0)) + exponent = long(math.log(bytes, 1024.0)) suffix = 'bkMGTPEZY'[exponent] converted = float(bytes) / float(1024**exponent) return '%.2f%s' % (converted, suffix) @@ -156,13 +185,13 @@ class FileDownloader(object): new_min = max(bytes / 2.0, 1.0) new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB if elapsed_time < 0.001: - return int(new_max) + return long(new_max) rate = bytes / elapsed_time if rate > new_max: - return int(new_max) + return long(new_max) if rate < new_min: - return int(new_min) - return int(rate) + return long(new_min) + return long(rate) @staticmethod def parse_bytes(bytestr): @@ -174,6 +203,14 @@ class FileDownloader(object): multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) return long(round(number * multiplier)) + @staticmethod + def verify_url(url): + """Verify a URL is valid and data could be downloaded.""" + request = urllib2.Request(url, None, std_headers) + data = urllib2.urlopen(request) + data.read(1) + data.close() + def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" self._ies.append(ie) @@ -187,12 +224,12 @@ class FileDownloader(object): def to_stdout(self, message, skip_eol=False): """Print message to stdout if not in quiet mode.""" if not self.params.get('quiet', False): - print u'%s%s' % (message, [u'\n', u''][skip_eol]), + print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(locale.getpreferredencoding()), sys.stdout.flush() def to_stderr(self, message): """Print message to stderr.""" - print >>sys.stderr, message + print >>sys.stderr, message.encode(locale.getpreferredencoding()) def fixed_template(self): """Checks if the output template is fixed.""" @@ -203,15 +240,13 @@ class FileDownloader(object): Depending on if the downloader has been configured to ignore download errors or not, this method may throw an exception or - not when errors are found, after printing the message. If it - doesn't raise, it returns an error code suitable to be returned - later as a program exit code to indicate error. + not when errors are found, after printing the message. """ if message is not None: self.to_stderr(message) if not self.params.get('ignoreerrors', False): raise DownloadError(message) - return 1 + self._download_retcode = 1 def slow_down(self, start_time, byte_counter): """Sleep if the download speed is over the rate limit.""" @@ -234,6 +269,18 @@ class FileDownloader(object): """Report download progress.""" self.to_stdout(u'\r[download] %s of %s at %s ETA %s' % (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + + def report_resuming_byte(self, resume_len): + """Report attemtp to resume at given byte.""" + self.to_stdout(u'[download] Resuming download at byte %s' % resume_len) + + def report_file_already_downloaded(self, file_name): + """Report file has already been fully downloaded.""" + self.to_stdout(u'[download] %s has already been downloaded' % file_name) + + def report_unable_to_resume(self): + """Report it was impossible to resume download.""" + self.to_stdout(u'[download] Unable to resume') def report_finish(self): """Report download finished.""" @@ -241,49 +288,57 @@ class FileDownloader(object): def process_info(self, info_dict): """Process a single dictionary returned by an InfoExtractor.""" - # Forced printings - if self.params.get('forcetitle', False): - print info_dict['title'] - if self.params.get('forceurl', False): - print info_dict['url'] - # Do nothing else if in simulate mode if self.params.get('simulate', False): - return 0 + try: + self.verify_url(info_dict['url']) + except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err: + raise UnavailableFormatError + # Forced printings + if self.params.get('forcetitle', False): + print info_dict['title'].encode(locale.getpreferredencoding()) + if self.params.get('forceurl', False): + print info_dict['url'].encode(locale.getpreferredencoding()) + + return + try: - filename = self.params['outtmpl'] % info_dict - self.report_destination(filename) + template_dict = dict(info_dict) + template_dict['epoch'] = unicode(long(time.time())) + filename = self.params['outtmpl'] % template_dict except (ValueError, KeyError), err: - return self.trouble('ERROR: invalid output template or system charset: %s' % str(err)) + self.trouble('ERROR: invalid output template or system charset: %s' % str(err)) if self.params['nooverwrites'] and os.path.exists(filename): - self.to_stderr('WARNING: file exists: %s; skipping' % filename) - return 0 + self.to_stderr(u'WARNING: file exists: %s; skipping' % filename) + return + try: self.pmkdir(filename) except (OSError, IOError), err: - return self.trouble('ERROR: unable to create directories: %s' % str(err)) - try: - outstream = open(filename, 'wb') - except (OSError, IOError), err: - return self.trouble('ERROR: unable to open for writing: %s' % str(err)) + self.trouble('ERROR: unable to create directories: %s' % str(err)) + return + try: - self._do_download(outstream, info_dict['url']) - outstream.close() + success = self._do_download(filename, info_dict['url']) except (OSError, IOError), err: - return self.trouble('ERROR: unable to write video data: %s' % str(err)) + raise UnavailableFormatError except (urllib2.URLError, httplib.HTTPException, socket.error), err: - return self.trouble('ERROR: unable to download video data: %s' % str(err)) - try: - self.post_process(filename, info_dict) - except (PostProcessingError), err: - return self.trouble('ERROR: postprocessing: %s' % str(err)) + self.trouble('ERROR: unable to download video data: %s' % str(err)) + return + except (ContentTooShortError, ), err: + self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + return - return 0 + if success: + try: + self.post_process(filename, info_dict) + except (PostProcessingError), err: + self.trouble('ERROR: postprocessing: %s' % str(err)) + return def download(self, url_list): """Download a given list of URLs.""" - retcode = 0 if len(url_list) > 1 and self.fixed_template(): raise SameFileError(self.params['outtmpl']) @@ -297,33 +352,16 @@ class FileDownloader(object): # Suitable InfoExtractor found suitable_found = True - # Extract information from URL - all_results = ie.extract(url) - results = [x for x in all_results if x is not None] - - # See if there were problems extracting any information - if len(results) != len(all_results): - retcode = self.trouble() - - # Two results could go to the same file - if len(results) > 1 and self.fixed_template(): - raise SameFileError(self.params['outtmpl']) - - # Process each result - for result in results: - result = self.process_info(result) - - # Do not overwrite an error code with a success code - if result != 0: - retcode = result + # Extract information from URL and process it + ie.extract(url) # Suitable InfoExtractor had been found; go to next URL break if not suitable_found: - retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url) + self.trouble('ERROR: no suitable InfoExtractor: %s' % url) - return retcode + return self._download_retcode def post_process(self, filename, ie_info): """Run the postprocessing chain on the given file.""" @@ -334,21 +372,43 @@ class FileDownloader(object): if info is None: break - def _do_download(self, stream, url): + def _do_download(self, filename, url): + stream = None + open_mode = 'ab' + + basic_request = urllib2.Request(url, None, std_headers) request = urllib2.Request(url, None, std_headers) - data = urllib2.urlopen(request) + + # Attempt to resume download with "continuedl" option + if os.path.isfile(filename): + resume_len = os.path.getsize(filename) + else: + resume_len = 0 + if self.params['continuedl'] and resume_len != 0: + self.report_resuming_byte(resume_len) + request.add_header('Range','bytes=%d-' % resume_len) + + # Establish connection + try: + data = urllib2.urlopen(request) + except (urllib2.HTTPError, ), err: + if err.code != 416: # 416 is 'Requested range not satisfiable' + raise + data = urllib2.urlopen(basic_request) + content_length = data.info()['Content-Length'] + if content_length is not None and long(content_length) == resume_len: + self.report_file_already_downloaded(filename) + return True + else: + self.report_unable_to_resume() + open_mode = 'wb' + data_len = data.info().get('Content-length', None) data_len_str = self.format_bytes(data_len) byte_counter = 0 block_size = 1024 start = time.time() while True: - # Progress message - percent_str = self.calc_percent(byte_counter, data_len) - eta_str = self.calc_eta(start, time.time(), data_len, byte_counter) - speed_str = self.calc_speed(start, time.time(), byte_counter) - self.report_progress(percent_str, data_len_str, speed_str, eta_str) - # Download and write before = time.time() data_block = data.read(block_size) @@ -357,15 +417,31 @@ class FileDownloader(object): if data_block_len == 0: break byte_counter += data_block_len + + # Open file just in time + if stream is None: + try: + stream = open(filename, open_mode) + self.report_destination(filename) + except (OSError, IOError), err: + self.trouble('ERROR: unable to open for writing: %s' % str(err)) + return False stream.write(data_block) block_size = self.best_block_size(after - before, data_block_len) + # Progress message + percent_str = self.calc_percent(byte_counter, data_len) + eta_str = self.calc_eta(start, time.time(), data_len, byte_counter) + speed_str = self.calc_speed(start, time.time(), byte_counter) + self.report_progress(percent_str, data_len_str, speed_str, eta_str) + # Apply rate limit self.slow_down(start, byte_counter) self.report_finish() if data_len is not None and str(byte_counter) != data_len: - raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len)) + raise ContentTooShortError(byte_counter, long(data_len)) + return True class InfoExtractor(object): """Information Extractor class. @@ -373,9 +449,10 @@ class InfoExtractor(object): Information extractors are the classes that, given a URL, extract information from the video (or videos) the URL refers to. This information includes the real video URL, the video title and simplified - title, author and others. It is returned in a list of dictionaries when - calling its extract() method. It is a list because a URL can refer to - more than one video (think of playlists). The dictionaries must include + title, author and others. The information is stored in a dictionary + which is then passed to the FileDownloader. The FileDownloader + processes this information possibly downloading the video to the file + system, among other possible outcomes. The dictionaries must include the following fields: id: Video identifier. @@ -419,15 +496,6 @@ class InfoExtractor(object): """Sets the downloader for this IE.""" self._downloader = downloader - def to_stdout(self, message): - """Print message to stdout if downloader is not in quiet mode.""" - if self._downloader is None or not self._downloader.params.get('quiet', False): - print message - - def to_stderr(self, message): - """Print message to stderr.""" - print >>sys.stderr, message - def _real_initialize(self): """Real initialization process. Redefine in subclasses.""" pass @@ -444,6 +512,13 @@ class YoutubeIE(InfoExtractor): _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _NETRC_MACHINE = 'youtube' + _available_formats = ['22', '35', '18', '5', '17', '13', None] # listed in order of priority for -b flag + _video_extensions = { + '13': '3gp', + '17': 'mp4', + '18': 'mp4', + '22': 'mp4', + } @staticmethod def suitable(url): @@ -474,27 +549,31 @@ class YoutubeIE(InfoExtractor): def report_lang(self): """Report attempt to set language.""" - self.to_stdout(u'[youtube] Setting language') + self._downloader.to_stdout(u'[youtube] Setting language') def report_login(self): """Report attempt to log in.""" - self.to_stdout(u'[youtube] Logging in') + self._downloader.to_stdout(u'[youtube] Logging in') def report_age_confirmation(self): """Report attempt to confirm age.""" - self.to_stdout(u'[youtube] Confirming age') + self._downloader.to_stdout(u'[youtube] Confirming age') - def report_webpage_download(self, video_id): - """Report attempt to download webpage.""" - self.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id) + def report_video_info_webpage_download(self, video_id): + """Report attempt to download video info webpage.""" + self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id) def report_information_extraction(self, video_id): """Report attempt to extract video information.""" - self.to_stdout(u'[youtube] %s: Extracting video information' % video_id) + self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id) def report_video_url(self, video_id, video_real_url): """Report extracted video URL.""" - self.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url)) + self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url)) + + def report_unavailable_format(self, video_id, format): + """Report extracted video URL.""" + self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format)) def _real_initialize(self): if self._downloader is None: @@ -517,7 +596,7 @@ class YoutubeIE(InfoExtractor): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError), err: - self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) return # Set language @@ -526,7 +605,7 @@ class YoutubeIE(InfoExtractor): self.report_lang() urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'WARNING: unable to set language: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) return # No authentication to be performed @@ -546,10 +625,10 @@ class YoutubeIE(InfoExtractor): self.report_login() login_results = urllib2.urlopen(request).read() if re.search(r'(?i)]* name="loginForm"', login_results) is not None: - self.to_stderr(u'WARNING: unable to log in: bad username or password') + self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') return except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'WARNING: unable to log in: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) return # Confirm age @@ -562,90 +641,119 @@ class YoutubeIE(InfoExtractor): self.report_age_confirmation() age_results = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) return def _real_extract(self, url): # Extract video id from URL mobj = re.match(self._VALID_URL, url) if mobj is None: - self.to_stderr(u'ERROR: invalid URL: %s' % url) - return [None] + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return video_id = mobj.group(2) # Downloader parameters + best_quality = False format_param = None + quality_index = 0 if self._downloader is not None: params = self._downloader.params format_param = params.get('format', None) - if format_param is None: - format_param = '34' - - # Extension - video_extension = { - '17': '3gp', - '18': 'mp4', - '22': 'mp4', - }.get(format_param, 'flv') - - # Normalize URL, including format - normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id - if format_param is not None: - normalized_url = '%s&fmt=%s' % (normalized_url, format_param) - request = urllib2.Request(normalized_url, None, std_headers) - try: - self.report_webpage_download(video_id) - video_webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'ERROR: unable to download video webpage: %s' % str(err)) - return [None] - self.report_information_extraction(video_id) - - # "t" param - mobj = re.search(r', "t": "([^"]+)"', video_webpage) - if mobj is None: - self.to_stderr(u'ERROR: unable to extract "t" parameter') - return [None] - video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1)) - if format_param is not None: - video_real_url = '%s&fmt=%s' % (video_real_url, format_param) - self.report_video_url(video_id, video_real_url) - - # uploader - mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage) - if mobj is None: - self.to_stderr(u'ERROR: unable to extract uploader nickname') - return [None] - video_uploader = mobj.group(1) + if format_param == '0': + format_param = self._available_formats[quality_index] + best_quality = True + + while True: + # Extension + video_extension = self._video_extensions.get(format_param, 'flv') + + # Get video info + video_info_url = 'http://www.youtube.com/get_video_info?&video_id=%s&el=detailpage&ps=default&eurl=&gl=US&hl=en' % video_id + request = urllib2.Request(video_info_url, None, std_headers) + try: + self.report_video_info_webpage_download(video_id) + video_info_webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) + return + self.report_information_extraction(video_id) + + # "t" param + mobj = re.search(r'(?m)&token=([^&]+)(?:&|$)', video_info_webpage) + if mobj is None: + # Attempt to see if YouTube has issued an error message + mobj = re.search(r'(?m)&reason=([^&]+)(?:&|$)', video_info_webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason') + stream = open('reportme-ydl-%s.dat' % time.time(), 'wb') + stream.write(video_info_webpage) + stream.close() + else: + reason = urllib.unquote_plus(mobj.group(1)) + self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8')) + return + token = urllib.unquote(mobj.group(1)) + video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token) + if format_param is not None: + video_real_url = '%s&fmt=%s' % (video_real_url, format_param) + self.report_video_url(video_id, video_real_url) + + # uploader + mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = urllib.unquote(mobj.group(1)) + + # title + mobj = re.search(r'(?m)&title=([^&]+)(?:&|$)', video_info_webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = urllib.unquote(mobj.group(1)) + video_title = video_title.decode('utf-8') + video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title) + video_title = video_title.replace(os.sep, u'%') + + # simplified title + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = simple_title.strip(ur'_') + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_real_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + }) + + return + + except UnavailableFormatError, err: + if best_quality: + if quality_index == len(self._available_formats) - 1: + # I don't ever expect this to happen + self._downloader.trouble(u'ERROR: no known formats available for video') + return + else: + self.report_unavailable_format(video_id, format_param) + quality_index += 1 + format_param = self._available_formats[quality_index] + continue + else: + self._downloader.trouble('ERROR: format not available for video') + return - # title - mobj = re.search(r'(?im)YouTube - ([^<]*)', video_webpage) - if mobj is None: - self.to_stderr(u'ERROR: unable to extract video title') - return [None] - video_title = mobj.group(1).decode('utf-8') - video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title) - video_title = video_title.replace(os.sep, u'%') - - # simplified title - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) - simple_title = simple_title.strip(ur'_') - - # Return information - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_real_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'title': video_title, - 'stitle': simple_title, - 'ext': video_extension.decode('utf-8'), - }] class MetacafeIE(InfoExtractor): """Information Extractor for metacafe.com.""" _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' _DISCLAIMER = 'http://www.metacafe.com/family_filter/' + _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' _youtube_ie = None def __init__(self, youtube_ie, downloader=None): @@ -658,19 +766,19 @@ class MetacafeIE(InfoExtractor): def report_disclaimer(self): """Report disclaimer retrieval.""" - self.to_stdout(u'[metacafe] Retrieving disclaimer') + self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer') def report_age_confirmation(self): """Report attempt to confirm age.""" - self.to_stdout(u'[metacafe] Confirming age') + self._downloader.to_stdout(u'[metacafe] Confirming age') def report_download_webpage(self, video_id): """Report webpage download.""" - self.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id) + self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id) def report_extraction(self, video_id): """Report information extraction.""" - self.to_stdout(u'[metacafe] %s: Extracting information' % video_id) + self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id) def _real_initialize(self): # Retrieve disclaimer @@ -679,7 +787,7 @@ class MetacafeIE(InfoExtractor): self.report_disclaimer() disclaimer = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) return # Confirm age @@ -687,27 +795,28 @@ class MetacafeIE(InfoExtractor): 'filters': '0', 'submit': "Continue - I'm over 18", } - request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers) + request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers) try: self.report_age_confirmation() disclaimer = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) return def _real_extract(self, url): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) if mobj is None: - self.to_stderr(u'ERROR: invalid URL: %s' % url) - return [None] + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return video_id = mobj.group(1) # Check if video comes from YouTube mobj2 = re.match(r'^yt-(.*)$', video_id) if mobj2 is not None: - return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) + return simple_title = mobj.group(2).decode('utf-8') video_extension = 'flv' @@ -718,46 +827,51 @@ class MetacafeIE(InfoExtractor): self.report_download_webpage(video_id) webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'ERROR: unable retrieve video webpage: %s' % str(err)) - return [None] + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) + return # Extract URL, uploader and title from webpage self.report_extraction(video_id) - mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage) + mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) if mobj is None: - self.to_stderr(u'ERROR: unable to extract media URL') - return [None] - mediaURL = mobj.group(1).replace('\\', '') + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = urllib.unquote(mobj.group(1)) - mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage) - if mobj is None: - self.to_stderr(u'ERROR: unable to extract gdaKey') - return [None] - gdaKey = mobj.group(1) + #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) + #if mobj is None: + # self._downloader.trouble(u'ERROR: unable to extract gdaKey') + # return + #gdaKey = mobj.group(1) + # + #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) + video_url = mediaURL mobj = re.search(r'(?im)(.*) - Video', webpage) if mobj is None: - self.to_stderr(u'ERROR: unable to extract title') - return [None] + self._downloader.trouble(u'ERROR: unable to extract title') + return video_title = mobj.group(1).decode('utf-8') - mobj = re.search(r'(?m)
  • .*?Submitter:
    (.*?)
  • ', webpage) + mobj = re.search(r'(?ms)
  • .*?Submitter:.*?(.*?)<', webpage) if mobj is None: - self.to_stderr(u'ERROR: unable to extract uploader nickname') - return [None] - video_uploader = re.sub(r'<.*?>', '', mobj.group(1)) + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = mobj.group(1) - # Return information - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'title': video_title, - 'stitle': simple_title, - 'ext': video_extension.decode('utf-8'), - }] + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + }) + except UnavailableFormatError: + self._downloader.trouble(u'ERROR: format not available for video') class YoutubeSearchIE(InfoExtractor): @@ -765,7 +879,7 @@ class YoutubeSearchIE(InfoExtractor): _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+' _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en' _VIDEO_INDICATOR = r'href="/watch\?v=.+?"' - _MORE_PAGES_INDICATOR = r'>Next' + _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' _youtube_ie = None _max_youtube_results = 1000 @@ -779,7 +893,7 @@ class YoutubeSearchIE(InfoExtractor): def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" - self.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) + self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) def _real_initialize(self): self._youtube_ie.initialize() @@ -787,27 +901,31 @@ class YoutubeSearchIE(InfoExtractor): def _real_extract(self, query): mobj = re.match(self._VALID_QUERY, query) if mobj is None: - self.to_stderr(u'ERROR: invalid search query "%s"' % query) - return [None] + self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) + return prefix, query = query.split(':') prefix = prefix[8:] if prefix == '': - return self._download_n_results(query, 1) + self._download_n_results(query, 1) + return elif prefix == 'all': - return self._download_n_results(query, self._max_youtube_results) + self._download_n_results(query, self._max_youtube_results) + return else: try: - n = int(prefix) + n = long(prefix) if n <= 0: - self.to_stderr(u'ERROR: invalid download number %s for query "%s"' % (n, query)) - return [None] + self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) + return elif n > self._max_youtube_results: - self.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) + self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) n = self._max_youtube_results - return self._download_n_results(query, n) - except ValueError: # parsing prefix as int fails - return self._download_n_results(query, 1) + self._download_n_results(query, n) + return + except ValueError: # parsing prefix as integer fails + self._download_n_results(query, 1) + return def _download_n_results(self, query, n): """Downloads a specified number of results for a query""" @@ -823,8 +941,8 @@ class YoutubeSearchIE(InfoExtractor): try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err)) - return [None] + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return # Extract video identifiers for mobj in re.finditer(self._VIDEO_INDICATOR, page): @@ -834,26 +952,24 @@ class YoutubeSearchIE(InfoExtractor): already_seen.add(video_id) if len(video_ids) == n: # Specified n videos reached - information = [] for id in video_ids: - information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) - return information + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) + return - if self._MORE_PAGES_INDICATOR not in page: - information = [] + if re.search(self._MORE_PAGES_INDICATOR, page) is None: for id in video_ids: - information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) - return information + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) + return pagenum = pagenum + 1 class YoutubePlaylistIE(InfoExtractor): """Information Extractor for YouTube playlists.""" - _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)' + _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:view_play_list|my_playlists)\?.*?p=([^&]+).*' _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' - _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s' + _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s' _youtube_ie = None def __init__(self, youtube_ie, downloader=None): @@ -866,7 +982,7 @@ class YoutubePlaylistIE(InfoExtractor): def report_download_page(self, playlist_id, pagenum): """Report attempt to download playlist page with given number.""" - self.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) + self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) def _real_initialize(self): self._youtube_ie.initialize() @@ -875,8 +991,8 @@ class YoutubePlaylistIE(InfoExtractor): # Extract playlist id mobj = re.match(self._VALID_URL, url) if mobj is None: - self.to_stderr(u'ERROR: invalid url: %s' % url) - return [None] + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return # Download playlist pages playlist_id = mobj.group(1) @@ -889,8 +1005,8 @@ class YoutubePlaylistIE(InfoExtractor): try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err)) - return [None] + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return # Extract video identifiers ids_in_page = [] @@ -899,14 +1015,13 @@ class YoutubePlaylistIE(InfoExtractor): ids_in_page.append(mobj.group(1)) video_ids.extend(ids_in_page) - if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page: + if (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page: break pagenum = pagenum + 1 - information = [] for id in video_ids: - information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) - return information + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) + return class PostProcessor(object): """Post Processor class. @@ -930,15 +1045,6 @@ class PostProcessor(object): def __init__(self, downloader=None): self._downloader = downloader - def to_stdout(self, message): - """Print message to stdout if downloader is not in quiet mode.""" - if self._downloader is None or not self._downloader.params.get('quiet', False): - print message - - def to_stderr(self, message): - """Print message to stderr.""" - print >>sys.stderr, message - def set_downloader(self, downloader): """Sets the downloader for this PP.""" self._downloader = downloader @@ -947,7 +1053,7 @@ class PostProcessor(object): """Run the PostProcessor. The "information" argument is a dictionary like the ones - returned by InfoExtractors. The only difference is that this + composed by InfoExtractors. The only difference is that this one has an extra field called "filepath" that points to the downloaded file. @@ -977,76 +1083,96 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( - usage='Usage: %prog [options] url...', - version='INTERNAL', - conflict_handler='resolve', - ) + usage='Usage: %prog [options] url...', + version='INTERNAL', + conflict_handler='resolve', + ) + parser.add_option('-h', '--help', action='help', help='print this help text and exit') parser.add_option('-v', '--version', action='version', help='print program version and exit') - parser.add_option('-u', '--username', + parser.add_option('-i', '--ignore-errors', + action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) + parser.add_option('-r', '--rate-limit', + dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)') + + authentication = optparse.OptionGroup(parser, 'Authentication Options') + authentication.add_option('-u', '--username', dest='username', metavar='UN', help='account username') - parser.add_option('-p', '--password', + authentication.add_option('-p', '--password', dest='password', metavar='PW', help='account password') - parser.add_option('-o', '--output', - dest='outtmpl', metavar='TPL', help='output filename template') - parser.add_option('-q', '--quiet', + authentication.add_option('-n', '--netrc', + action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) + parser.add_option_group(authentication) + + video_format = optparse.OptionGroup(parser, 'Video Format Options') + video_format.add_option('-f', '--format', + action='store', dest='format', metavar='FMT', help='video format code') + video_format.add_option('-b', '--best-quality', + action='store_const', dest='format', help='download the best quality video possible', const='0') + video_format.add_option('-m', '--mobile-version', + action='store_const', dest='format', help='alias for -f 17', const='17') + video_format.add_option('-d', '--high-def', + action='store_const', dest='format', help='alias for -f 22', const='22') + parser.add_option_group(video_format) + + verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') + verbosity.add_option('-q', '--quiet', action='store_true', dest='quiet', help='activates quiet mode', default=False) - parser.add_option('-s', '--simulate', + verbosity.add_option('-s', '--simulate', action='store_true', dest='simulate', help='do not download video', default=False) - parser.add_option('-t', '--title', - action='store_true', dest='usetitle', help='use title in file name', default=False) - parser.add_option('-l', '--literal', - action='store_true', dest='useliteral', help='use literal title in file name', default=False) - parser.add_option('-n', '--netrc', - action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) - parser.add_option('-g', '--get-url', + verbosity.add_option('-g', '--get-url', action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) - parser.add_option('-e', '--get-title', + verbosity.add_option('-e', '--get-title', action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) - parser.add_option('-f', '--format', - dest='format', metavar='FMT', help='video format code') - parser.add_option('-m', '--mobile-version', - action='store_const', dest='format', help='alias for -f 17', const='17') - parser.add_option('-d', '--high-def', - action='store_const', dest='format', help='alias for -f 22', const='22') - parser.add_option('-i', '--ignore-errors', - action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) - parser.add_option('-r', '--rate-limit', - dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)') - parser.add_option('-a', '--batch-file', + parser.add_option_group(verbosity) + + filesystem = optparse.OptionGroup(parser, 'Filesystem Options') + filesystem.add_option('-t', '--title', + action='store_true', dest='usetitle', help='use title in file name', default=False) + filesystem.add_option('-l', '--literal', + action='store_true', dest='useliteral', help='use literal title in file name', default=False) + filesystem.add_option('-o', '--output', + dest='outtmpl', metavar='TPL', help='output filename template') + filesystem.add_option('-a', '--batch-file', dest='batchfile', metavar='F', help='file containing URLs to download') - parser.add_option('-w', '--no-overwrites', + filesystem.add_option('-w', '--no-overwrites', action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) + filesystem.add_option('-c', '--continue', + action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False) + parser.add_option_group(filesystem) + (opts, args) = parser.parse_args() # Batch file verification batchurls = [] if opts.batchfile is not None: try: - batchurls = [line.strip() for line in open(opts.batchfile, 'r')] + batchurls = open(opts.batchfile, 'r').readlines() + batchurls = [x.strip() for x in batchurls] + batchurls = [x for x in batchurls if len(x) > 0] except IOError: sys.exit(u'ERROR: batch file could not be read') all_urls = batchurls + args # Conflicting, missing and erroneous options if len(all_urls) < 1: - sys.exit(u'ERROR: you must provide at least one URL') + parser.error(u'you must provide at least one URL') if opts.usenetrc and (opts.username is not None or opts.password is not None): - sys.exit(u'ERROR: using .netrc conflicts with giving username/password') + parser.error(u'using .netrc conflicts with giving username/password') if opts.password is not None and opts.username is None: - sys.exit(u'ERROR: account username missing') + parser.error(u'account username missing') if opts.outtmpl is not None and (opts.useliteral or opts.usetitle): - sys.exit(u'ERROR: using output template conflicts with using title or literal title') + parser.error(u'using output template conflicts with using title or literal title') if opts.usetitle and opts.useliteral: - sys.exit(u'ERROR: using title conflicts with using literal title') + parser.error(u'using title conflicts with using literal title') if opts.username is not None and opts.password is None: opts.password = getpass.getpass(u'Type account password and press return:') if opts.ratelimit is not None: numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) if numeric_limit is None: - sys.exit(u'ERROR: invalid rate limit specified') + parser.error(u'invalid rate limit specified') opts.ratelimit = numeric_limit # Information extractors @@ -1056,9 +1182,6 @@ if __name__ == '__main__': youtube_search_ie = YoutubeSearchIE(youtube_ie) # File downloader - charset = locale.getpreferredencoding() - if charset is None: - charset = 'ascii' fd = FileDownloader({ 'usenetrc': opts.usenetrc, 'username': opts.username, @@ -1068,13 +1191,14 @@ if __name__ == '__main__': 'forcetitle': opts.gettitle, 'simulate': (opts.simulate or opts.geturl or opts.gettitle), 'format': opts.format, - 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset)) + 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding())) or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') or u'%(id)s.%(ext)s'), 'ignoreerrors': opts.ignoreerrors, 'ratelimit': opts.ratelimit, 'nooverwrites': opts.nooverwrites, + 'continuedl': opts.continue_dl, }) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie)