X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=8764acda0592df1c628b0a7d4dceeaa59d2b7394;hb=dbccb6cd84347de647e8ea34da9ed27e4e664a39;hp=0df6ba14104cdefc0761d31a57225c10bb5d3772;hpb=22899cea59bf31fb31efab9c03a92214684f94d6;p=youtube-dl.git diff --git a/youtube-dl b/youtube-dl index 0df6ba141..8764acda0 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1,9 +1,11 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- # Author: Ricardo Garcia Gonzalez +# Author: Danny Colligan # License: Public domain code import htmlentitydefs import httplib +import locale import math import netrc import os @@ -16,8 +18,8 @@ import time import urllib import urllib2 -std_headers = { - 'User-Agent': 'UserAgent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9) Gecko/2008052906 Firefox/3.0', +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', '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', @@ -25,6 +27,31 @@ std_headers = { simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') +class DownloadError(Exception): + """Download Error exception. + + This exception may be thrown by FileDownloader objects if they are not + configured to continue on errors. They will contain the appropriate + error message. + """ + pass + +class SameFileError(Exception): + """Same File exception. + + This exception will be thrown by FileDownloader objects if they detect + multiple files would have to be downloaded to the same file on disk. + """ + pass + +class PostProcessingError(Exception): + """Post Processing exception. + + This exception may be raised by PostProcessor's .run() method to + indicate an error in the postprocessing task. + """ + pass + class FileDownloader(object): """File Downloader class. @@ -38,16 +65,17 @@ 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 - options instead. These options are available through the get_params() - method for the InfoExtractors to use. The FileDownloader also registers - itself as the downloader in charge for the InfoExtractors that are - added to it, so this is a "mutual registration". + options instead. These options are available through the params + attribute for the InfoExtractors to use. The FileDownloader also + registers itself as the downloader in charge for the InfoExtractors + that are added to it, so this is a "mutual registration". Available options: @@ -55,23 +83,34 @@ class FileDownloader(object): password: Password for authentication purposes. usenetrc: Use netrc for authentication instead. quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. simulate: Do not download the video files. format: Video format code. outtmpl: Template for output names. + ignoreerrors: Do not stop on download errors. + ratelimit: Download speed limit, in bytes/sec. + nooverwrites: Prevent overwriting files. """ - _params = None + params = None _ies = [] + _pps = [] + _download_retcode = None def __init__(self, params): + """Create a FileDownloader object with the given options.""" self._ies = [] - self.set_params(params) + self._pps = [] + self._download_retcode = 0 + self.params = params @staticmethod def pmkdir(filename): """Create directory components in filename. Similar to Unix "mkdir -p".""" components = filename.split(os.sep) aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))] + aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator for dir in aggregate: if not os.path.exists(dir): os.mkdir(dir) @@ -108,7 +147,7 @@ class FileDownloader(object): return '--:--' return '%02d:%02d' % (eta_mins, eta_secs) - @staticmethod + @staticmethod def calc_speed(start, now, bytes): dif = now - start if bytes == 0 or dif < 0.001: # One millisecond @@ -128,83 +167,160 @@ class FileDownloader(object): return int(new_min) return int(rate) - def set_params(self, params): - """Sets parameters.""" - if type(params) != dict: - raise ValueError('params: dictionary expected') - self._params = params - - def get_params(self): - """Get parameters.""" - return self._params + @staticmethod + def parse_bytes(bytestr): + """Parse a string indicating a byte quantity into a long integer.""" + matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) + if matchobj is None: + return None + number = float(matchobj.group(1)) + multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) + return long(round(number * multiplier)) def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" self._ies.append(ie) ie.set_downloader(self) + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + def to_stdout(self, message, skip_eol=False): """Print message to stdout if not in quiet mode.""" - if not self._params.get('quiet', False): - sys.stdout.write('%s%s' % (message, ['\n', ''][skip_eol])) + if not self.params.get('quiet', False): + 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.""" - sys.stderr.write('%s\n' % message) + print >>sys.stderr, message def fixed_template(self): """Checks if the output template is fixed.""" - return (re.search(ur'%\(.+?\)s', self._params['outtmpl']) is None) + return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) + + def trouble(self, message=None): + """Determine action to take when a download problem appears. + + 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 message is not None: + self.to_stderr(message) + if not self.params.get('ignoreerrors', False): + raise DownloadError(message) + self._download_retcode = 1 + + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self.params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def report_destination(self, filename): + """Report destination filename.""" + self.to_stdout(u'[download] Destination: %s' % filename) + + def report_progress(self, percent_str, data_len_str, speed_str, eta_str): + """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_finish(self): + """Report download finished.""" + self.to_stdout(u'') + + 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'].encode(locale.getpreferredencoding()) + if self.params.get('forceurl', False): + print info_dict['url'].encode(locale.getpreferredencoding()) + + # Do nothing else if in simulate mode + if self.params.get('simulate', False): + return + + try: + filename = self.params['outtmpl'] % info_dict + self.report_destination(filename) + except (ValueError, KeyError), 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 + try: + self.pmkdir(filename) + except (OSError, IOError), err: + self.trouble('ERROR: unable to create directories: %s' % str(err)) + return + try: + outstream = open(filename, 'wb') + except (OSError, IOError), err: + self.trouble('ERROR: unable to open for writing: %s' % str(err)) + return + try: + self._do_download(outstream, info_dict['url']) + outstream.close() + except (OSError, IOError), err: + self.trouble('ERROR: unable to write video data: %s' % str(err)) + return + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.trouble('ERROR: unable to download video data: %s' % str(err)) + return + try: + self.post_process(filename, info_dict) + except (PostProcessingError), err: + self.trouble('ERROR: postprocessing: %s' % str(err)) + return + + return def download(self, url_list): """Download a given list of URLs.""" if len(url_list) > 1 and self.fixed_template(): - sys.exit('ERROR: fixed output name but more than one file to download') + raise SameFileError(self.params['outtmpl']) for url in url_list: suitable_found = False for ie in self._ies: + # Go to next InfoExtractor if not suitable if not ie.suitable(url): continue + # Suitable InfoExtractor found suitable_found = True - results = [x for x in ie.extract(url) if x is not None] - if len(results) > 1 and self.fixed_template(): - sys.exit('ERROR: fixed output name but more than one file to download') + # Extract information from URL and process it + ie.extract(url) - if self._params.get('simulate', False): - continue - - for result in results: - try: - filename = self._params['outtmpl'] % result - except (ValueError, KeyError), err: - self.to_stderr('ERROR: invalid output template: %s' % str(err)) - continue - try: - self.pmkdir(filename) - except (OSError, IOError), err: - self.to_stderr('ERROR: unable to create directories: %s' % str(err)) - continue - try: - outstream = open(filename, 'wb') - except (OSError, IOError), err: - self.to_stderr('ERROR: unable to open for writing: %s' % str(err)) - continue - try: - self._do_download(outstream, result['url']) - outstream.close() - except (OSError, IOError), err: - self.to_stderr('ERROR: unable to write video data: %s' % str(err)) - continue - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr('ERROR: unable to download video data: %s' % str(err)) - continue + # Suitable InfoExtractor had been found; go to next URL break + if not suitable_found: - self.to_stderr('ERROR: no suitable InfoExtractor: %s' % url) + self.trouble('ERROR: no suitable InfoExtractor: %s' % url) + + return self._download_retcode + + def post_process(self, filename, ie_info): + """Run the postprocessing chain on the given file.""" + info = dict(ie_info) + info['filepath'] = filename + for pp in self._pps: + info = pp.run(info) + if info is None: + break def _do_download(self, stream, url): request = urllib2.Request(url, None, std_headers) @@ -215,12 +331,13 @@ class FileDownloader(object): 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.to_stdout('\r[download] %s of %s at %s ETA %s' % - (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + self.report_progress(percent_str, data_len_str, speed_str, eta_str) + # Download and write before = time.time() data_block = data.read(block_size) after = time.time() @@ -231,7 +348,10 @@ class FileDownloader(object): stream.write(data_block) block_size = self.best_block_size(after - before, data_block_len) - self.to_stdout('') + # 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)) @@ -241,9 +361,10 @@ 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. @@ -270,10 +391,10 @@ class InfoExtractor(object): @staticmethod def suitable(url): """Receives a URL and returns True if suitable for this IE.""" - return True + return False def initialize(self): - """Initializes an instance (login, etc).""" + """Initializes an instance (authentication, etc).""" if not self._ready: self._real_initialize() self._ready = True @@ -287,13 +408,6 @@ class InfoExtractor(object): """Sets the downloader for this IE.""" self._downloader = downloader - def to_stdout(self, message): - if self._downloader is None or not self._downloader.get_params().get('quiet', False): - print message - - def to_stderr(self, message): - sys.stderr.write('%s\n' % message) - def _real_initialize(self): """Real initialization process. Redefine in subclasses.""" pass @@ -305,17 +419,70 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _LOGIN_URL = 'http://www.youtube.com/login?next=/' - _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/' + _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' + _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' + _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' + @staticmethod + def suitable(url): + return (re.match(YoutubeIE._VALID_URL, url) is not None) + + @staticmethod + def htmlentity_transform(matchobj): + """Transforms an HTML entity to a Unicode character.""" + entity = matchobj.group(1) + + # Known non-numeric HTML entity + if entity in htmlentitydefs.name2codepoint: + return unichr(htmlentitydefs.name2codepoint[entity]) + + # Unicode character + mobj = re.match(ur'(?u)#(x?\d+)', entity) + if mobj is not None: + numstr = mobj.group(1) + if numstr.startswith(u'x'): + base = 16 + numstr = u'0%s' % numstr + else: + base = 10 + return unichr(long(numstr, base)) + + # Unknown entity in name, return its literal representation + return (u'&%s;' % entity) + + def report_lang(self): + """Report attempt to set language.""" + self._downloader.to_stdout(u'[youtube] Setting language') + + def report_login(self): + """Report attempt to log in.""" + self._downloader.to_stdout(u'[youtube] Logging in') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_stdout(u'[youtube] Confirming age') + + def report_webpage_download(self, video_id): + """Report attempt to download webpage.""" + self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id) + + def report_information_extraction(self, video_id): + """Report attempt to extract video information.""" + 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._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url)) + def _real_initialize(self): if self._downloader is None: return username = None password = None - downloader_params = self._downloader.get_params() + downloader_params = self._downloader.params # Attempt to use provided username and password or .netrc data if downloader_params.get('username', None) is not None: @@ -330,9 +497,19 @@ class YoutubeIE(InfoExtractor): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError), err: - self.to_stderr('WARNING: parsing .netrc: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) return + # Set language + request = urllib2.Request(self._LANG_URL, None, std_headers) + try: + self.report_lang() + urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) + return + + # No authentication to be performed if username is None: return @@ -346,13 +523,13 @@ class YoutubeIE(InfoExtractor): } request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers) try: - self.to_stdout('[youtube] Logging in') + self.report_login() login_results = urllib2.urlopen(request).read() if re.search(r'(?i)