#!/usr/bin/env python # -*- coding: utf-8 -*- # Author: Ricardo Garcia Gonzalez # Author: Danny Colligan # Author: Benjamin Johnson # License: Public domain code import htmlentitydefs import httplib import locale import math import netrc import os import os.path import re import socket import string import subprocess import sys import time import urllib import urllib2 # parse_qs was moved from the cgi module to the urlparse module recently. try: from urlparse import parse_qs except ImportError: from cgi import parse_qs std_headers = { 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6', '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', } simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') def preferredencoding(): """Get preferred encoding. Returns the best encoding scheme for the system, based on locale.getpreferredencoding() and some further tweaks. """ def yield_preferredencoding(): try: pref = locale.getpreferredencoding() u'TEST'.encode(pref) except: pref = 'UTF-8' while True: yield pref return yield_preferredencoding().next() def htmlentity_transform(matchobj): """Transforms an HTML entity to a Unicode character. This function receives a match object and is intended to be used with the re.sub() function. """ 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 sanitize_title(utitle): """Sanitizes a video title so it could be used as part of a filename.""" utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) return utitle.replace(unicode(os.sep), u'%') def sanitize_open(filename, open_mode): """Try to open the given filename, and slightly tweak it if this fails. Attempts to open the given filename. If this fails, it tries to change the filename slightly, step by step, until it's either able to open it or it fails and raises a final exception, like the standard open() function. It returns the tuple (stream, definitive_file_name). """ try: if filename == u'-': return (sys.stdout, filename) stream = open(filename, open_mode) return (stream, filename) except (IOError, OSError), err: # In case of error, try to remove win32 forbidden chars filename = re.sub(ur'[<>:"\|\?\*]', u'#', filename) # An exception here should be caught in the caller stream = open(filename, open_mode) return (stream, filename) 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 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. File downloader objects are the ones responsible of downloading the actual video file and writing it to disk if the user has requested it, among some other tasks. In most cases there should be one per program. As, given a video URL, the downloader doesn't know how to extract all the needed information, task that InfoExtractors do, it has to pass the URL to one of them. 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 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 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: username: Username for authentication purposes. 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. retries: Number of times to retry for HTTP error 503 continuedl: Try to continue downloads if possible. noprogress: Do not print the progress bar. """ params = None _ies = [] _pps = [] _download_retcode = None _num_downloads = None def __init__(self, params): """Create a FileDownloader object with the given options.""" self._ies = [] self._pps = [] self._download_retcode = 0 self._num_downloads = 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) @staticmethod def format_bytes(bytes): if bytes is None: return 'N/A' if type(bytes) is str: bytes = float(bytes) if bytes == 0.0: exponent = 0 else: exponent = long(math.log(bytes, 1024.0)) suffix = 'bkMGTPEZY'[exponent] converted = float(bytes) / float(1024**exponent) return '%.2f%s' % (converted, suffix) @staticmethod def calc_percent(byte_counter, data_len): if data_len is None: return '---.-%' return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) @staticmethod def calc_eta(start, now, total, current): if total is None: return '--:--' dif = now - start if current == 0 or dif < 0.001: # One millisecond return '--:--' rate = float(current) / dif eta = long((float(total) - float(current)) / rate) (eta_mins, eta_secs) = divmod(eta, 60) if eta_mins > 99: return '--:--' return '%02d:%02d' % (eta_mins, eta_secs) @staticmethod def calc_speed(start, now, bytes): dif = now - start if bytes == 0 or dif < 0.001: # One millisecond return '%10s' % '---b/s' return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) @staticmethod def best_block_size(elapsed_time, bytes): 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 long(new_max) rate = bytes / elapsed_time if rate > new_max: return long(new_max) if rate < new_min: return long(new_min) return long(rate) @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)) @staticmethod def verify_url(url): """Verify a URL is valid and data could be downloaded. Return real data URL.""" request = urllib2.Request(url, None, std_headers) data = urllib2.urlopen(request) data.read(1) url = data.geturl() data.close() return url 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, ignore_encoding_errors=False): """Print message to stdout if not in quiet mode.""" try: if not self.params.get('quiet', False): print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()), sys.stdout.flush() except (UnicodeEncodeError), err: if not ignore_encoding_errors: raise def to_stderr(self, message): """Print message to stderr.""" print >>sys.stderr, message.encode(preferredencoding()) def fixed_template(self): """Checks if the output template is fixed.""" 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, ignore_encoding_errors=True) def report_progress(self, percent_str, data_len_str, speed_str, eta_str): """Report download progress.""" if self.params.get('noprogress', False): return 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_retry(self, count, retries): """Report retry in case of HTTP error 503""" self.to_stdout(u'[download] Got HTTP error 503. Retrying (attempt %d of %d)...' % (count, retries)) def report_file_already_downloaded(self, file_name): """Report file has already been fully downloaded.""" try: self.to_stdout(u'[download] %s has already been downloaded' % file_name) except (UnicodeEncodeError), err: self.to_stdout(u'[download] The file has already been downloaded') 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.""" if self.params.get('noprogress', False): self.to_stdout(u'[download] Download completed') else: self.to_stdout(u'') def process_info(self, info_dict): """Process a single dictionary returned by an InfoExtractor.""" # Do nothing else if in simulate mode if self.params.get('simulate', False): # Verify URL if it's an HTTP one if info_dict['url'].startswith('http'): try: self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8') 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(preferredencoding(), 'xmlcharrefreplace') if self.params.get('forceurl', False): print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') if self.params.get('forcedescription', False) and 'description' in info_dict: print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') return try: template_dict = dict(info_dict) template_dict['epoch'] = unicode(long(time.time())) template_dict['ord'] = unicode('%05d' % self._num_downloads) filename = self.params['outtmpl'] % template_dict except (ValueError, KeyError), err: self.trouble('ERROR: invalid output template or system charset: %s' % str(err)) if self.params.get('nooverwrites', False) and os.path.exists(filename): self.to_stderr(u'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: success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None)) except (OSError, IOError), err: raise UnavailableFormatError except (urllib2.URLError, httplib.HTTPException, socket.error), 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 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.""" if len(url_list) > 1 and self.fixed_template(): 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 # Extract information from URL and process it ie.extract(url) # Suitable InfoExtractor had been found; go to next URL break if not suitable_found: 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 _download_with_rtmpdump(self, filename, url, player_url): self.report_destination(filename) # Check for rtmpdump first try: subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) except (OSError, IOError): self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') return False # Download using rtmpdump. rtmpdump returns exit code 2 when # the connection was interrumpted and resuming appears to be # possible. This is part of rtmpdump's normal usage, AFAIK. basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename] retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]) while retval == 2 or retval == 1: prevsize = os.path.getsize(filename) self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) time.sleep(5.0) # This seems to be needed retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) cursize = os.path.getsize(filename) if prevsize == cursize and retval == 1: break if retval == 0: self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename)) return True else: self.trouble('\nERROR: rtmpdump exited with code %d' % retval) return False def _do_download(self, filename, url, player_url): # Attempt to download using rtmpdump if url.startswith('rtmp'): return self._download_with_rtmpdump(filename, url, player_url) stream = None open_mode = 'wb' basic_request = urllib2.Request(url, None, std_headers) request = urllib2.Request(url, None, std_headers) # Establish possible resume length if os.path.isfile(filename): resume_len = os.path.getsize(filename) else: resume_len = 0 # Request parameters in case of being able to resume if self.params.get('continuedl', False) and resume_len != 0: self.report_resuming_byte(resume_len) request.add_header('Range','bytes=%d-' % resume_len) open_mode = 'ab' count = 0 retries = self.params.get('retries', 0) while True: # Establish connection try: data = urllib2.urlopen(request) break except (urllib2.HTTPError, ), err: if err.code == 503: # Retry in case of HTTP error 503 count += 1 if count <= retries: self.report_retry(count, retries) continue if err.code != 416: # 416 is 'Requested range not satisfiable' raise # Unable to resume data = urllib2.urlopen(basic_request) content_length = data.info()['Content-Length'] if content_length is not None and long(content_length) == resume_len: # Because the file had already been fully downloaded self.report_file_already_downloaded(filename) self._num_downloads += 1 return True else: # Because the server didn't let us 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: # Download and write before = time.time() data_block = data.read(block_size) after = time.time() data_block_len = len(data_block) if data_block_len == 0: break byte_counter += data_block_len # Open file just in time if stream is None: try: (stream, filename) = sanitize_open(filename, open_mode) self.report_destination(filename) self._num_downloads += 1 except (OSError, IOError), err: self.trouble('ERROR: unable to open for writing: %s' % str(err)) return False try: stream.write(data_block) except (IOError, OSError), err: self.trouble('\nERROR: unable to write data: %s' % str(err)) 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 ContentTooShortError(byte_counter, long(data_len)) return True class InfoExtractor(object): """Information Extractor class. 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. 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. url: Final video URL. uploader: Nickname of the video uploader. title: Literal title. stitle: Simplified title. ext: Video filename extension. format: Video format. player_url: SWF Player URL (may be None). The following fields are optional. Their primary purpose is to allow youtube-dl to serve as the backend for a video search function, such as the one in youtube2mp3. They are only used when their respective forced printing functions are called: thumbnail: Full URL to a video thumbnail image. description: One-line video description. Subclasses of this one should re-define the _real_initialize() and _real_extract() methods, as well as the suitable() static method. Probably, they should also be instantiated and added to the main downloader. """ _ready = False _downloader = None def __init__(self, downloader=None): """Constructor. Receives an optional downloader.""" self._ready = False self.set_downloader(downloader) @staticmethod def suitable(url): """Receives a URL and returns True if suitable for this IE.""" return False def initialize(self): """Initializes an instance (authentication, etc).""" if not self._ready: self._real_initialize() self._ready = True def extract(self, url): """Extracts URL information and returns it in list of dicts.""" self.initialize() return self._real_extract(url) def set_downloader(self, downloader): """Sets the downloader for this IE.""" self._downloader = downloader def _real_initialize(self): """Real initialization process. Redefine in subclasses.""" pass def _real_extract(self, url): """Real extraction process. Redefine in subclasses.""" pass class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" _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' _available_formats = ['37', '22', '35', '18', '34', '5', '17', '13', None] # listed in order of priority for -b flag _video_extensions = { '13': '3gp', '17': 'mp4', '18': 'mp4', '22': 'mp4', '37': 'mp4', '43': 'webm', '45': 'webm', } @staticmethod def suitable(url): return (re.match(YoutubeIE._VALID_URL, url) is not None) 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_video_webpage_download(self, video_id): """Report attempt to download video webpage.""" self._downloader.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._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id) 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 report_rtmp_download(self): """Indicate the download will use the RTMP protocol.""" self._downloader.to_stdout(u'[youtube] RTMP download detected') def _real_initialize(self): if self._downloader is None: return username = None password = None downloader_params = self._downloader.params # Attempt to use provided username and password or .netrc data if downloader_params.get('username', None) is not None: username = downloader_params['username'] password = downloader_params['password'] elif downloader_params.get('usenetrc', False): try: info = netrc.netrc().authenticators(self._NETRC_MACHINE) if info is not None: username = info[0] password = info[2] else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError), 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 # Log in login_form = { 'current_form': 'loginForm', 'next': '/', 'action_login': 'Log In', 'username': username, 'password': password, } request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers) try: self.report_login() login_results = urllib2.urlopen(request).read() if re.search(r'(?i)