X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/de5b9c36a58e493e6f8c8c3694370e477da74f94..e2d44fac99aa7cfc6e1d379794b5bda76347965d:/youtube-dl?ds=sidebyside diff --git a/youtube-dl b/youtube-dl index a8e3bd3..818a3a7 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1,13 +1,32 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- -# Author: Ricardo Garcia Gonzalez -# Author: Danny Colligan -# Author: Benjamin Johnson -# Author: Vasyl' Vavrychuk -# License: Public domain code + +__authors__ = ( + 'Ricardo Garcia Gonzalez', + 'Danny Colligan', + 'Benjamin Johnson', + 'Vasyl\' Vavrychuk', + 'Witold Baryluk', + 'Paweł Paprota', + 'Gergely Imreh', + 'Rogério Brito', + 'Philipp Hagemeister', + 'Sören Schulze', + 'Kevin Ngo', + 'Ori Avtalion', + 'shizeeg', + ) + +__license__ = 'Public Domain' +__version__ = '2012.01.05' + +UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' + import cookielib import datetime +import gzip import htmlentitydefs +import HTMLParser import httplib import locale import math @@ -22,6 +41,20 @@ import sys import time import urllib import urllib2 +import warnings +import zlib + +if os.name == 'nt': + import ctypes + +try: + import email.utils +except ImportError: # Python 2.4 + import email.Utils +try: + import cStringIO as StringIO +except ImportError: + import StringIO # parse_qs was moved from the cgi module to the urlparse module recently. try: @@ -29,14 +62,136 @@ try: except ImportError: from cgi import parse_qs +try: + import lxml.etree +except ImportError: + pass # Handled below + +try: + import xml.etree.ElementTree +except ImportError: # Python<2.5: Not officially supported, but let it slip + warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.') + std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12', + 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', + 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'en-us,en;q=0.5', } -simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') +try: + import json +except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): + import re + class json(object): + @staticmethod + def loads(s): + s = s.decode('UTF-8') + def raiseError(msg, i): + raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:])) + def skipSpace(i, expectMore=True): + while i < len(s) and s[i] in ' \t\r\n': + i += 1 + if expectMore: + if i >= len(s): + raiseError('Premature end', i) + return i + def decodeEscape(match): + esc = match.group(1) + _STATIC = { + '"': '"', + '\\': '\\', + '/': '/', + 'b': unichr(0x8), + 'f': unichr(0xc), + 'n': '\n', + 'r': '\r', + 't': '\t', + } + if esc in _STATIC: + return _STATIC[esc] + if esc[0] == 'u': + if len(esc) == 1+4: + return unichr(int(esc[1:5], 16)) + if len(esc) == 5+6 and esc[5:7] == '\\u': + hi = int(esc[1:5], 16) + low = int(esc[7:11], 16) + return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000) + raise ValueError('Unknown escape ' + str(esc)) + def parseString(i): + i += 1 + e = i + while True: + e = s.index('"', e) + bslashes = 0 + while s[e-bslashes-1] == '\\': + bslashes += 1 + if bslashes % 2 == 1: + e += 1 + continue + break + rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)') + stri = rexp.sub(decodeEscape, s[i:e]) + return (e+1,stri) + def parseObj(i): + i += 1 + res = {} + i = skipSpace(i) + if s[i] == '}': # Empty dictionary + return (i+1,res) + while True: + if s[i] != '"': + raiseError('Expected a string object key', i) + i,key = parseString(i) + i = skipSpace(i) + if i >= len(s) or s[i] != ':': + raiseError('Expected a colon', i) + i,val = parse(i+1) + res[key] = val + i = skipSpace(i) + if s[i] == '}': + return (i+1, res) + if s[i] != ',': + raiseError('Expected comma or closing curly brace', i) + i = skipSpace(i+1) + def parseArray(i): + res = [] + i = skipSpace(i+1) + if s[i] == ']': # Empty array + return (i+1,res) + while True: + i,val = parse(i) + res.append(val) + i = skipSpace(i) # Raise exception if premature end + if s[i] == ']': + return (i+1, res) + if s[i] != ',': + raiseError('Expected a comma or closing bracket', i) + i = skipSpace(i+1) + def parseDiscrete(i): + for k,v in {'true': True, 'false': False, 'null': None}.items(): + if s.startswith(k, i): + return (i+len(k), v) + raiseError('Not a boolean (or null)', i) + def parseNumber(i): + mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:]) + if mobj is None: + raiseError('Not a number', i) + nums = mobj.group(1) + if '.' in nums or 'e' in nums or 'E' in nums: + return (i+len(nums), float(nums)) + return (i+len(nums), int(nums)) + CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete} + def parse(i): + i = skipSpace(i) + i,res = CHARMAP.get(s[i], parseNumber)(i) + i = skipSpace(i, False) + return (i,res) + i,res = parse(0) + if i < len(s): + raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')') + return res def preferredencoding(): """Get preferred encoding. @@ -54,9 +209,10 @@ def preferredencoding(): 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. """ @@ -80,11 +236,13 @@ def htmlentity_transform(matchobj): # 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. @@ -111,15 +269,46 @@ def sanitize_open(filename, open_mode): stream = open(filename, open_mode) return (stream, filename) + +def timeconvert(timestr): + """Convert RFC 2822 defined time string into system timestamp""" + timestamp = None + timetuple = email.utils.parsedate_tz(timestr) + if timetuple is not None: + timestamp = email.utils.mktime_tz(timetuple) + return timestamp + +def _simplify_title(title): + expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE) + return expr.sub(u'_', title).strip(u'_') + +def _orderedSet(iterable): + """ Remove all duplicates from the input iterable """ + res = [] + for el in iterable: + if el not in res: + res.append(el) + return res + +def _unescapeHTML(s): + """ + @param s a string (of type unicode) + """ + assert type(s) == type(u'') + + htmlParser = HTMLParser.HTMLParser() + return htmlParser.unescape(s) + 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. @@ -128,6 +317,7 @@ class SameFileError(Exception): """ pass + class PostProcessingError(Exception): """Post Processing exception. @@ -136,6 +326,11 @@ class PostProcessingError(Exception): """ pass +class MaxDownloadsReached(Exception): + """ --max-downloads limit has been reached. """ + pass + + class UnavailableVideoError(Exception): """Unavailable Format exception. @@ -144,6 +339,7 @@ class UnavailableVideoError(Exception): """ pass + class ContentTooShortError(Exception): """Content Too Short exception. @@ -159,6 +355,66 @@ class ContentTooShortError(Exception): self.downloaded = downloaded self.expected = expected + +class YoutubeDLHandler(urllib2.HTTPHandler): + """Handler for HTTP requests and responses. + + This class, when installed with an OpenerDirector, automatically adds + the standard headers to every HTTP request and handles gzipped and + deflated responses from web servers. If compression is to be avoided in + a particular request, the original request in the program code only has + to include the HTTP header "Youtubedl-No-Compression", which will be + removed before making the real request. + + Part of this code was copied from: + + http://techknack.net/python-urllib2-handlers/ + + Andrew Rowls, the author of that code, agreed to release it to the + public domain. + """ + + @staticmethod + def deflate(data): + try: + return zlib.decompress(data, -zlib.MAX_WBITS) + except zlib.error: + return zlib.decompress(data) + + @staticmethod + def addinfourl_wrapper(stream, headers, url, code): + if hasattr(urllib2.addinfourl, 'getcode'): + return urllib2.addinfourl(stream, headers, url, code) + ret = urllib2.addinfourl(stream, headers, url) + ret.code = code + return ret + + def http_request(self, req): + for h in std_headers: + if h in req.headers: + del req.headers[h] + req.add_header(h, std_headers[h]) + if 'Youtubedl-no-compression' in req.headers: + if 'Accept-encoding' in req.headers: + del req.headers['Accept-encoding'] + del req.headers['Youtubedl-no-compression'] + return req + + def http_response(self, req, resp): + old_resp = resp + # gzip + if resp.headers.get('Content-encoding', '') == 'gzip': + gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') + resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) + resp.msg = old_resp.msg + # deflate + if resp.headers.get('Content-encoding', '') == 'deflate': + gz = StringIO.StringIO(self.deflate(resp.read())) + resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) + resp.msg = old_resp.msg + return resp + + class FileDownloader(object): """File Downloader class. @@ -194,6 +450,7 @@ class FileDownloader(object): forcetitle: Force printing title. forcethumbnail: Force printing thumbnail URL. forcedescription: Force printing description. + forcefilename: Force printing final filename. simulate: Do not download the video files. format: Video format code. format_limit: Highest quality format to try. @@ -206,7 +463,14 @@ class FileDownloader(object): noprogress: Do not print the progress bar. playliststart: Playlist item to start at. playlistend: Playlist item to end at. + matchtitle: Download only matching titles. + rejecttitle: Reject downloads for matching titles. logtostderr: Log messages to stderr instead of stdout. + consoletitle: Display progress in console window's titlebar. + nopart: Do not use temporary .part files. + updatetime: Use the Last-modified header to set output file timestamps. + writedescription: Write the video description to a .description file + writeinfojson: Write the video description to a .info.json file """ params = None @@ -224,24 +488,7 @@ class FileDownloader(object): self._num_downloads = 0 self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] 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 temp_name(filename): - """Returns a temporary filename for the given filename.""" - if filename == u'-' or (os.path.exists(filename) and not os.path.isfile(filename)): - return filename - return filename + u'.part' - + @staticmethod def format_bytes(bytes): if bytes is None: @@ -253,7 +500,7 @@ class FileDownloader(object): else: exponent = long(math.log(bytes, 1024.0)) suffix = 'bkMGTPEZY'[exponent] - converted = float(bytes) / float(1024**exponent) + converted = float(bytes) / float(1024 ** exponent) return '%.2f%s' % (converted, suffix) @staticmethod @@ -310,12 +557,12 @@ class FileDownloader(object): """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_screen(self, message, skip_eol=False, ignore_encoding_errors=False): """Print message to stdout if not in quiet mode.""" try: @@ -326,11 +573,22 @@ class FileDownloader(object): 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 to_cons_title(self, message): + """Set console/terminal window title to message.""" + if not self.params.get('consoletitle', False): + return + if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): + # c_wchar_p() might not be necessary if `message` is + # already of type unicode() + ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) + elif 'TERM' in os.environ: + sys.stderr.write('\033]0;%s\007' % 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) @@ -360,7 +618,19 @@ class FileDownloader(object): speed = float(byte_counter) / elapsed if speed > rate_limit: time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) - + + def temp_name(self, filename): + """Returns a temporary filename for the given filename.""" + if self.params.get('nopart', False) or filename == u'-' or \ + (os.path.exists(filename) and not os.path.isfile(filename)): + return filename + return filename + u'.part' + + def undo_temp_name(self, filename): + if filename.endswith(u'.part'): + return filename[:-len(u'.part')] + return filename + def try_rename(self, old_filename, new_filename): try: if old_filename == new_filename: @@ -369,98 +639,196 @@ class FileDownloader(object): except (IOError, OSError), err: self.trouble(u'ERROR: unable to rename file') + def try_utime(self, filename, last_modified_hdr): + """Try to set the last-modified time of the given file.""" + if last_modified_hdr is None: + return + if not os.path.isfile(filename): + return + timestr = last_modified_hdr + if timestr is None: + return + filetime = timeconvert(timestr) + if filetime is None: + return filetime + try: + os.utime(filename, (time.time(), filetime)) + except: + pass + return filetime + + def report_writedescription(self, descfn): + """ Report that the description file is being written """ + self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True) + + def report_writeinfojson(self, infofn): + """ Report that the metadata file has been written """ + self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True) + def report_destination(self, filename): """Report destination filename.""" self.to_screen(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_screen(u'\r[download] %s of %s at %s ETA %s' % (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % + (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) def report_resuming_byte(self, resume_len): """Report attempt to resume at given byte.""" self.to_screen(u'[download] Resuming download at byte %s' % resume_len) - + def report_retry(self, count, retries): """Report retry in case of HTTP error 5xx""" self.to_screen(u'[download] Got server HTTP error. 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_screen(u'[download] %s has already been downloaded' % file_name) except (UnicodeEncodeError), err: self.to_screen(u'[download] The file has already been downloaded') - + def report_unable_to_resume(self): """Report it was impossible to resume download.""" self.to_screen(u'[download] Unable to resume') - + def report_finish(self): """Report download finished.""" if self.params.get('noprogress', False): self.to_screen(u'[download] Download completed') else: self.to_screen(u'') - + def increment_downloads(self): """Increment the ordinal that assigns a number to each file.""" self._num_downloads += 1 - 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): - # 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 - + def prepare_filename(self, info_dict): + """Generate the output filename.""" try: template_dict = dict(info_dict) template_dict['epoch'] = unicode(long(time.time())) template_dict['autonumber'] = unicode('%05d' % self._num_downloads) filename = self.params['outtmpl'] % template_dict + return filename except (ValueError, KeyError), err: self.trouble(u'ERROR: invalid system charset or erroneous output template') + return None + + def _match_entry(self, info_dict): + """ Returns None iff the file should be downloaded """ + + title = info_dict['title'] + matchtitle = self.params.get('matchtitle', False) + if matchtitle and not re.search(matchtitle, title, re.IGNORECASE): + return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' + rejecttitle = self.params.get('rejecttitle', False) + if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE): + return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + return None + + def process_info(self, info_dict): + """Process a single dictionary returned by an InfoExtractor.""" + + reason = self._match_entry(info_dict) + if reason is not None: + self.to_screen(u'[download] ' + reason) return - if self.params.get('nooverwrites', False) and os.path.exists(filename): - self.to_stderr(u'WARNING: file exists and will be skipped') + + max_downloads = self.params.get('max_downloads') + if max_downloads is not None: + if self._num_downloads > int(max_downloads): + raise MaxDownloadsReached() + + filename = self.prepare_filename(info_dict) + + # 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') + if self.params.get('forcefilename', False) and filename is not None: + print filename.encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forceformat', False): + print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace') + + # Do nothing else if in simulate mode + if self.params.get('simulate', False): return - try: - self.pmkdir(filename) - except (OSError, IOError), err: - self.trouble(u'ERROR: unable to create directories: %s' % str(err)) + if filename is None: return try: - success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None)) + dn = os.path.dirname(filename) + if dn != '' and not os.path.exists(dn): + os.makedirs(dn) except (OSError, IOError), err: - raise UnavailableVideoError - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.trouble(u'ERROR: unable to download video data: %s' % str(err)) - return - except (ContentTooShortError, ), err: - self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + self.trouble(u'ERROR: unable to create directory ' + unicode(err)) return - if success: + if self.params.get('writedescription', False): + try: + descfn = filename + '.description' + self.report_writedescription(descfn) + descfile = open(descfn, 'wb') + try: + descfile.write(info_dict['description'].encode('utf-8')) + finally: + descfile.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write description file ' + descfn) + return + + if self.params.get('writeinfojson', False): + infofn = filename + '.info.json' + self.report_writeinfojson(infofn) try: - self.post_process(filename, info_dict) - except (PostProcessingError), err: - self.trouble(u'ERROR: postprocessing: %s' % str(err)) + json.dump + except (NameError,AttributeError): + self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') return + try: + infof = open(infofn, 'wb') + try: + json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) + json.dump(json_info_dict, infof) + finally: + infof.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) + return + + if not self.params.get('skip_download', False): + if self.params.get('nooverwrites', False) and os.path.exists(filename): + success = True + else: + try: + success = self._do_download(filename, info_dict) + except (OSError, IOError), err: + raise UnavailableVideoError + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.trouble(u'ERROR: unable to download video data: %s' % str(err)) + return + except (ContentTooShortError, ), err: + self.trouble(u'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(u'ERROR: postprocessing: %s' % str(err)) + return def download(self, url_list): """Download a given list of URLs.""" @@ -496,7 +864,7 @@ class FileDownloader(object): info = pp.run(info) if info is None: break - + def _download_with_rtmpdump(self, filename, url, player_url): self.report_destination(filename) tmpfilename = self.temp_name(filename) @@ -521,6 +889,11 @@ class FileDownloader(object): cursize = os.path.getsize(tmpfilename) if prevsize == cursize and retval == 1: break + # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those + if prevsize == cursize and retval == 2 and cursize > 1024: + self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') + retval = 0 + break if retval == 0: self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename)) self.try_rename(tmpfilename, filename) @@ -529,9 +902,12 @@ class FileDownloader(object): self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) return False - def _do_download(self, filename, url, player_url): + def _do_download(self, filename, info_dict): + url = info_dict['url'] + player_url = info_dict.get('player_url', None) + # Check file already present - if self.params.get('continuedl', False) and os.path.isfile(filename): + if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False): self.report_file_already_downloaded(filename) return True @@ -541,9 +917,11 @@ class FileDownloader(object): tmpfilename = self.temp_name(filename) stream = None - open_mode = 'wb' - basic_request = urllib2.Request(url, None, std_headers) - request = urllib2.Request(url, None, std_headers) + + # Do not include the Accept-Encoding header + headers = {'Youtubedl-no-compression': 'True'} + basic_request = urllib2.Request(url, None, headers) + request = urllib2.Request(url, None, headers) # Establish possible resume length if os.path.isfile(tmpfilename): @@ -551,17 +929,22 @@ class FileDownloader(object): 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' + open_mode = 'wb' + if resume_len != 0: + if self.params.get('continuedl', False): + self.report_resuming_byte(resume_len) + request.add_header('Range','bytes=%d-' % resume_len) + open_mode = 'ab' + else: + resume_len = 0 count = 0 retries = self.params.get('retries', 0) while count <= retries: # Establish connection try: + if count == 0 and 'urlhandle' in info_dict: + data = info_dict['urlhandle'] data = urllib2.urlopen(request) break except (urllib2.HTTPError, ), err: @@ -580,7 +963,7 @@ class FileDownloader(object): else: # Examine the reported length if (content_length is not None and - (resume_len - 100 < long(content_length) < resume_len + 100)): + (resume_len - 100 < long(content_length) < resume_len + 100)): # The file had already been fully downloaded. # Explanation to the above condition: in issue #175 it was revealed that # YouTube sometimes adds or removes a few bytes from the end of the file, @@ -606,8 +989,10 @@ class FileDownloader(object): return False data_len = data.info().get('Content-length', None) + if data_len is not None: + data_len = long(data_len) + resume_len data_len_str = self.format_bytes(data_len) - byte_counter = 0 + byte_counter = 0 + resume_len block_size = 1024 start = time.time() while True: @@ -615,15 +1000,16 @@ class FileDownloader(object): before = time.time() data_block = data.read(block_size) after = time.time() - data_block_len = len(data_block) - if data_block_len == 0: + if len(data_block) == 0: break - byte_counter += data_block_len + byte_counter += len(data_block) # Open file just in time if stream is None: try: (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) + assert stream is not None + filename = self.undo_temp_name(tmpfilename) self.report_destination(filename) except (OSError, IOError), err: self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) @@ -633,24 +1019,36 @@ class FileDownloader(object): except (IOError, OSError), err: self.trouble(u'\nERROR: unable to write data: %s' % str(err)) return False - block_size = self.best_block_size(after - before, data_block_len) + block_size = self.best_block_size(after - before, len(data_block)) # 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) + speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) + if data_len is None: + self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') + else: + percent_str = self.calc_percent(byte_counter, data_len) + eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) + self.report_progress(percent_str, data_len_str, speed_str, eta_str) # Apply rate limit - self.slow_down(start, byte_counter) + self.slow_down(start, byte_counter - resume_len) + if stream is None: + self.trouble(u'\nERROR: Did not get any data blocks') + return False stream.close() self.report_finish() - if data_len is not None and str(byte_counter) != data_len: + if data_len is not None and byte_counter != data_len: raise ContentTooShortError(byte_counter, long(data_len)) self.try_rename(tmpfilename, filename) + + # Update file modification time + if self.params.get('updatetime', True): + info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) + return True + class InfoExtractor(object): """Information Extractor class. @@ -681,9 +1079,8 @@ class InfoExtractor(object): 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. + _real_extract() methods and define a _VALID_URL regexp. + Probably, they should also be added to the list of extractors. """ _ready = False @@ -694,10 +1091,9 @@ class InfoExtractor(object): self._ready = False self.set_downloader(downloader) - @staticmethod - def suitable(url): + def suitable(self, url): """Receives a URL and returns True if suitable for this IE.""" - return False + return re.match(self._VALID_URL, url) is not None def initialize(self): """Initializes an instance (authentication, etc).""" @@ -713,7 +1109,7 @@ class InfoExtractor(object): 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 @@ -722,16 +1118,18 @@ class InfoExtractor(object): """Real extraction process. Redefine in subclasses.""" pass + class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'https://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' # Listed in order of quality - _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13'] + _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] + _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] _video_extensions = { '13': '3gp', '17': 'mp4', @@ -740,12 +1138,25 @@ class YoutubeIE(InfoExtractor): '37': 'mp4', '38': 'video', # You actually don't know if this will be MOV, AVI or whatever '43': 'webm', + '44': 'webm', '45': 'webm', } - - @staticmethod - def suitable(url): - return (re.match(YoutubeIE._VALID_URL, url) is not None) + _video_dimensions = { + '5': '240x400', + '6': '???', + '13': '???', + '17': '144x176', + '18': '360x640', + '22': '720x1280', + '34': '360x640', + '35': '480x854', + '37': '1080x1920', + '38': '3072x4096', + '43': '360x640', + '44': '480x854', + '45': '720x1280', + } + IE_NAME = u'youtube' def report_lang(self): """Report attempt to set language.""" @@ -754,31 +1165,36 @@ class YoutubeIE(InfoExtractor): def report_login(self): """Report attempt to log in.""" self._downloader.to_screen(u'[youtube] Logging in') - + def report_age_confirmation(self): """Report attempt to confirm age.""" self._downloader.to_screen(u'[youtube] Confirming age') - + def report_video_webpage_download(self, video_id): """Report attempt to download video webpage.""" self._downloader.to_screen(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_screen(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_screen(u'[youtube] %s: Extracting video information' % video_id) - + def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" self._downloader.to_screen(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_screen(u'[youtube] RTMP download detected') - + + def _print_formats(self, formats): + print 'Available formats:' + for x in formats: + print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')) + def _real_initialize(self): if self._downloader is None: return @@ -804,7 +1220,7 @@ class YoutubeIE(InfoExtractor): return # Set language - request = urllib2.Request(self._LANG_URL, None, std_headers) + request = urllib2.Request(self._LANG_URL) try: self.report_lang() urllib2.urlopen(request).read() @@ -824,7 +1240,7 @@ class YoutubeIE(InfoExtractor): 'username': username, 'password': password, } - request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers) + request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) try: self.report_login() login_results = urllib2.urlopen(request).read() @@ -834,13 +1250,13 @@ class YoutubeIE(InfoExtractor): except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) return - + # Confirm age age_form = { 'next_url': '/', 'action_confirm': 'Confirm', } - request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers) + request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form)) try: self.report_age_confirmation() age_results = urllib2.urlopen(request).read() @@ -858,7 +1274,7 @@ class YoutubeIE(InfoExtractor): # Get video webpage self.report_video_webpage_download(video_id) - request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id, None, std_headers) + request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) try: video_webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -876,8 +1292,8 @@ class YoutubeIE(InfoExtractor): self.report_video_info_webpage_download(video_id) for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' - % (video_id, el_type)) - request = urllib2.Request(video_info_url, None, std_headers) + % (video_id, el_type)) + request = urllib2.Request(video_info_url) try: video_info_webpage = urllib2.urlopen(request).read() video_info = parse_qs(video_info_webpage) @@ -911,8 +1327,7 @@ class YoutubeIE(InfoExtractor): video_title = sanitize_title(video_title) # simplified title - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) - simple_title = simple_title.strip(ur'_') + simple_title = _simplify_title(video_title) # thumbnail image if 'thumbnail_url' not in video_info: @@ -923,10 +1338,10 @@ class YoutubeIE(InfoExtractor): # upload date upload_date = u'NA' - mobj = re.search(r'id="eow-date".*?>(.*?)', video_webpage, re.DOTALL) + mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL) if mobj is not None: upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) - format_expressions = ['%d %B %Y', '%B %d %Y'] + format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] for expression in format_expressions: try: upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') @@ -934,46 +1349,68 @@ class YoutubeIE(InfoExtractor): pass # description - video_description = 'No description available.' - if self._downloader.params.get('forcedescription', False): - mobj = re.search(r'', video_webpage) - if mobj is not None: - video_description = mobj.group(1) + try: + lxml.etree + except NameError: + video_description = u'No description available.' + if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False): + mobj = re.search(r'', video_webpage) + if mobj is not None: + video_description = mobj.group(1).decode('utf-8') + else: + html_parser = lxml.etree.HTMLParser(encoding='utf-8') + vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser) + video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) + # TODO use another parser # token video_token = urllib.unquote_plus(video_info['token'][0]) # Decide which formats to download req_format = self._downloader.params.get('format', None) - get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token) - if 'fmt_url_map' in video_info: - url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(',')) + if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): + self.report_rtmp_download() + video_url_list = [(None, video_info['conn'][0])] + elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: + url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') + url_data = [parse_qs(uds) for uds in url_data_strs] + url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) + url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data) + format_limit = self._downloader.params.get('format_limit', None) - if format_limit is not None and format_limit in self._available_formats: - format_list = self._available_formats[self._available_formats.index(format_limit):] + available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats + if format_limit is not None and format_limit in available_formats: + format_list = available_formats[available_formats.index(format_limit):] else: - format_list = self._available_formats + format_list = available_formats existing_formats = [x for x in format_list if x in url_map] if len(existing_formats) == 0: self._downloader.trouble(u'ERROR: no known formats available for video') return - if req_format is None: + if self._downloader.params.get('listformats', None): + self._print_formats(existing_formats) + return + if req_format is None or req_format == 'best': video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality - elif req_format == '-1': + elif req_format == 'worst': + video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality + elif req_format in ('-1', 'all'): video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats else: - if req_format in url_map: - video_url_list = [(req_format, url_map[req_format])] # Specific format - else: - video_url_list = [(req_format, get_video_template % req_format)] # Specific format - - elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): - self.report_rtmp_download() - video_url_list = [(None, video_info['conn'][0])] - + # Specific formats. We pick the first in a slash-delimeted sequence. + # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. + req_formats = req_format.split('/') + video_url_list = None + for rf in req_formats: + if rf in url_map: + video_url_list = [(rf, url_map[rf])] + break + if video_url_list is None: + self._downloader.trouble(u'ERROR: requested format not available') + return else: - self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info') + self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') return for format_param, video_real_url in video_url_list: @@ -983,7 +1420,6 @@ class YoutubeIE(InfoExtractor): # Extension video_extension = self._video_extensions.get(format_param, 'flv') - # Find the video URL in fmt_url_map or conn paramters try: # Process video information self._downloader.process_info({ @@ -996,11 +1432,11 @@ class YoutubeIE(InfoExtractor): 'ext': video_extension.decode('utf-8'), 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), 'thumbnail': video_thumbnail.decode('utf-8'), - 'description': video_description.decode('utf-8'), + 'description': video_description, 'player_url': player_url, }) except UnavailableVideoError, err: - self._downloader.trouble(u'ERROR: unable to download video (format may not be available)') + self._downloader.trouble(u'\nERROR: unable to download video') class MetacafeIE(InfoExtractor): @@ -1010,15 +1446,12 @@ class MetacafeIE(InfoExtractor): _DISCLAIMER = 'http://www.metacafe.com/family_filter/' _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' _youtube_ie = None + IE_NAME = u'metacafe' def __init__(self, youtube_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._youtube_ie = youtube_ie - @staticmethod - def suitable(url): - return (re.match(MetacafeIE._VALID_URL, url) is not None) - def report_disclaimer(self): """Report disclaimer retrieval.""" self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') @@ -1026,18 +1459,18 @@ class MetacafeIE(InfoExtractor): def report_age_confirmation(self): """Report attempt to confirm age.""" self._downloader.to_screen(u'[metacafe] Confirming age') - + def report_download_webpage(self, video_id): """Report webpage download.""" self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) - + def report_extraction(self, video_id): """Report information extraction.""" self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) def _real_initialize(self): # Retrieve disclaimer - request = urllib2.Request(self._DISCLAIMER, None, std_headers) + request = urllib2.Request(self._DISCLAIMER) try: self.report_disclaimer() disclaimer = urllib2.urlopen(request).read() @@ -1050,14 +1483,14 @@ class MetacafeIE(InfoExtractor): 'filters': '0', 'submit': "Continue - I'm over 18", } - request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers) + request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form)) try: self.report_age_confirmation() disclaimer = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), 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) @@ -1093,7 +1526,7 @@ class MetacafeIE(InfoExtractor): if mobj is not None: mediaURL = urllib.unquote(mobj.group(1)) video_extension = mediaURL[-3:] - + # Extract gdaKey if available mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) if mobj is None: @@ -1145,32 +1578,26 @@ class MetacafeIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class DailymotionIE(InfoExtractor): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' + IE_NAME = u'dailymotion' def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - @staticmethod - def suitable(url): - return (re.match(DailymotionIE._VALID_URL, url) is not None) - def report_download_webpage(self, video_id): """Report webpage download.""" self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) - + def report_extraction(self, video_id): """Report information extraction.""" self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) - def _real_initialize(self): - return - def _real_extract(self, url): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) @@ -1182,11 +1609,11 @@ class DailymotionIE(InfoExtractor): self._downloader.increment_downloads() video_id = mobj.group(1) - simple_title = mobj.group(2).decode('utf-8') video_extension = 'flv' # Retrieve video webpage to extract further information request = urllib2.Request(url) + request.add_header('Cookie', 'family_filter=off') try: self.report_download_webpage(video_id) webpage = urllib2.urlopen(request).read() @@ -1196,25 +1623,30 @@ class DailymotionIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) - mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage) + mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract media URL') return - mediaURL = urllib.unquote(mobj.group(1)) + sequence = urllib.unquote(mobj.group(1)) + mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '') # if needed add http://www.dailymotion.com/ if relative URL video_url = mediaURL - # '' - mobj = re.search(r'(?im)Dailymotion\s*[\-:]\s*(.+?)', webpage) + mobj = re.search(r'', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract title') return - video_title = mobj.group(1).decode('utf-8') + video_title = _unescapeHTML(mobj.group('title').decode('utf-8')) video_title = sanitize_title(video_title) + simple_title = _simplify_title(video_title) - mobj = re.search(r'(?im)
.*?(.+?)', webpage) + mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return @@ -1234,20 +1666,18 @@ class DailymotionIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') + class GoogleIE(InfoExtractor): """Information extractor for video.google.com.""" _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' + IE_NAME = u'video.google' def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - @staticmethod - def suitable(url): - return (re.match(GoogleIE._VALID_URL, url) is not None) - def report_download_webpage(self, video_id): """Report webpage download.""" self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) @@ -1256,9 +1686,6 @@ class GoogleIE(InfoExtractor): """Report information extraction.""" self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) - def _real_initialize(self): - return - def _real_extract(self, url): # Extract id from URL mobj = re.match(self._VALID_URL, url) @@ -1302,7 +1729,7 @@ class GoogleIE(InfoExtractor): return video_title = mobj.group(1).decode('utf-8') video_title = sanitize_title(video_title) - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = _simplify_title(video_title) # Extract video description mobj = re.search(r'([^<]*)', webpage) @@ -1329,7 +1756,6 @@ class GoogleIE(InfoExtractor): else: # we need something to pass to process_info video_thumbnail = '' - try: # Process video information self._downloader.process_info({ @@ -1344,21 +1770,18 @@ class GoogleIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class PhotobucketIE(InfoExtractor): """Information extractor for photobucket.com.""" _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + IE_NAME = u'photobucket' def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - @staticmethod - def suitable(url): - return (re.match(PhotobucketIE._VALID_URL, url) is not None) - def report_download_webpage(self, video_id): """Report webpage download.""" self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) @@ -1367,9 +1790,6 @@ class PhotobucketIE(InfoExtractor): """Report information extraction.""" self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) - def _real_initialize(self): - return - def _real_extract(self, url): # Extract id from URL mobj = re.match(self._VALID_URL, url) @@ -1408,7 +1828,7 @@ class PhotobucketIE(InfoExtractor): return video_title = mobj.group(1).decode('utf-8') video_title = sanitize_title(video_title) - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = _simplify_title(vide_title) video_uploader = mobj.group(2).decode('utf-8') @@ -1426,7 +1846,7 @@ class PhotobucketIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class YahooIE(InfoExtractor): @@ -1436,14 +1856,11 @@ class YahooIE(InfoExtractor): # _VPAGE_URL matches only the extractable '/watch/' URLs _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' + IE_NAME = u'video.yahoo' def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - @staticmethod - def suitable(url): - return (re.match(YahooIE._VALID_URL, url) is not None) - def report_download_webpage(self, video_id): """Report webpage download.""" self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) @@ -1452,9 +1869,6 @@ class YahooIE(InfoExtractor): """Report information extraction.""" self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) - def _real_initialize(self): - return - def _real_extract(self, url, new_video=True): # Extract ID from URL mobj = re.match(self._VALID_URL, url) @@ -1508,7 +1922,7 @@ class YahooIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract video title') return video_title = mobj.group(1).decode('utf-8') - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = _simplify_title(video_title) mobj = re.search(r'

(.*)

', webpage) if mobj is None: @@ -1529,7 +1943,8 @@ class YahooIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract video description') return video_description = mobj.group(1).decode('utf-8') - if not video_description: video_description = 'No description available.' + if not video_description: + video_description = 'No description available.' # Extract video height and width mobj = re.search(r'', webpage) @@ -1550,8 +1965,8 @@ class YahooIE(InfoExtractor): yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents yv_bitrate = '700' # according to Wikipedia this is hard-coded request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + - '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + - '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') + '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + + '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') try: self.report_download_webpage(video_id) webpage = urllib2.urlopen(request).read() @@ -1580,41 +1995,158 @@ class YahooIE(InfoExtractor): 'thumbnail': video_thumbnail.decode('utf-8'), 'description': video_description, 'thumbnail': video_thumbnail, - 'description': video_description, 'player_url': None, }) except UnavailableVideoError: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') -class GenericIE(InfoExtractor): - """Generic last-resort information extractor.""" +class VimeoIE(InfoExtractor): + """Information extractor for vimeo.com.""" + + # _VALID_URL matches Vimeo URLs + _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)' + IE_NAME = u'vimeo' def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - @staticmethod - def suitable(url): - return True - def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') - self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) + self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) def report_extraction(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) + self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) - def _real_initialize(self): - return + def _real_extract(self, url, new_video=True): + # Extract ID from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return - def _real_extract(self, url): # At this point we have a new video self._downloader.increment_downloads() + video_id = mobj.group(1) - video_id = url.split('/')[-1] - request = urllib2.Request(url) + # Retrieve video webpage to extract further information + request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + # Now we begin extracting as much information as we can from what we + # retrieved. First we extract the information common to all extractors, + # and latter we extract those that are Vimeo specific. + self.report_extraction(video_id) + + # Extract title + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + simple_title = _simplify_title(video_title) + + # Extract uploader + mobj = re.search(r'http://vimeo.com/(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video uploader') + return + video_uploader = mobj.group(1).decode('utf-8') + + # Extract video thumbnail + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + # # Extract video description + # mobj = re.search(r'', webpage) + # if mobj is None: + # self._downloader.trouble(u'ERROR: unable to extract video description') + # return + # video_description = mobj.group(1).decode('utf-8') + # if not video_description: video_description = 'No description available.' + video_description = 'Foo.' + + # Vimeo specific: extract request signature + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract request signature') + return + sig = mobj.group(1).decode('utf-8') + + # Vimeo specific: extract video quality information + mobj = re.search(r'(\d+)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video quality information') + return + quality = mobj.group(1).decode('utf-8') + + if int(quality) == 1: + quality = 'hd' + else: + quality = 'sd' + + # Vimeo specific: Extract request signature expiration + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract request signature expiration') + return + sig_exp = mobj.group(1).decode('utf-8') + + video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality) + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': u'mp4', + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description, + 'thumbnail': video_thumbnail, + 'description': video_description, + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') + + +class GenericIE(InfoExtractor): + """Generic last-resort information extractor.""" + + _VALID_URL = r'.*' + IE_NAME = u'generic' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') + self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # At this point we have a new video + self._downloader.increment_downloads() + + video_id = url.split('/')[-1] + request = urllib2.Request(url) try: self.report_download_webpage(video_id) webpage = urllib2.urlopen(request).read() @@ -1644,11 +2176,11 @@ class GenericIE(InfoExtractor): return video_url = urllib.unquote(mobj.group(1)) - video_id = os.path.basename(video_url) + video_id = os.path.basename(video_url) # here's a fun little line of code for you: video_extension = os.path.splitext(video_id)[1][1:] - video_id = os.path.splitext(video_id)[0] + video_id = os.path.splitext(video_id)[0] # it's tempting to parse this further, but you would # have to take into account all the variations like @@ -1662,7 +2194,7 @@ class GenericIE(InfoExtractor): return video_title = mobj.group(1).decode('utf-8') video_title = sanitize_title(video_title) - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = _simplify_title(video_title) # video uploader is domain name mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) @@ -1685,25 +2217,22 @@ class GenericIE(InfoExtractor): 'player_url': None, }) except UnavailableVideoError, err: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'\nERROR: unable to download video') class YoutubeSearchIE(InfoExtractor): """Information Extractor for YouTube search queries.""" - _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+' + _VALID_URL = 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'(?m)>\s*Next\s*' _youtube_ie = None _max_youtube_results = 1000 + IE_NAME = u'youtube:search' def __init__(self, youtube_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._youtube_ie = youtube_ie - - @staticmethod - def suitable(url): - return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None) def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" @@ -1712,16 +2241,16 @@ class YoutubeSearchIE(InfoExtractor): def _real_initialize(self): self._youtube_ie.initialize() - + def _real_extract(self, query): - mobj = re.match(self._VALID_QUERY, query) + mobj = re.match(self._VALID_URL, query) if mobj is None: self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) return prefix, query = query.split(':') prefix = prefix[8:] - query = query.encode('utf-8') + query = query.encode('utf-8') if prefix == '': self._download_n_results(query, 1) return @@ -1735,7 +2264,7 @@ class YoutubeSearchIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) return elif n > self._max_youtube_results: - self._downloader.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 self._download_n_results(query, n) return @@ -1753,7 +2282,7 @@ class YoutubeSearchIE(InfoExtractor): while True: self.report_download_page(query, pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) - request = urllib2.Request(result_url, None, std_headers) + request = urllib2.Request(result_url) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -1779,22 +2308,20 @@ class YoutubeSearchIE(InfoExtractor): pagenum = pagenum + 1 + class GoogleSearchIE(InfoExtractor): """Information Extractor for Google Video search queries.""" - _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+' + _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&' _MORE_PAGES_INDICATOR = r'Next' _google_ie = None _max_google_results = 1000 + IE_NAME = u'video.google:search' def __init__(self, google_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._google_ie = google_ie - - @staticmethod - def suitable(url): - return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None) def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" @@ -1803,16 +2330,16 @@ class GoogleSearchIE(InfoExtractor): def _real_initialize(self): self._google_ie.initialize() - + def _real_extract(self, query): - mobj = re.match(self._VALID_QUERY, query) + mobj = re.match(self._VALID_URL, query) if mobj is None: self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) return prefix, query = query.split(':') prefix = prefix[8:] - query = query.encode('utf-8') + query = query.encode('utf-8') if prefix == '': self._download_n_results(query, 1) return @@ -1826,7 +2353,7 @@ class GoogleSearchIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) return elif n > self._max_google_results: - self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) + self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) n = self._max_google_results self._download_n_results(query, n) return @@ -1844,7 +2371,7 @@ class GoogleSearchIE(InfoExtractor): while True: self.report_download_page(query, pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) - request = urllib2.Request(result_url, None, std_headers) + request = urllib2.Request(result_url) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -1870,22 +2397,20 @@ class GoogleSearchIE(InfoExtractor): pagenum = pagenum + 1 + class YahooSearchIE(InfoExtractor): """Information Extractor for Yahoo! Video search queries.""" - _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+' + _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' _MORE_PAGES_INDICATOR = r'\s*Next' _yahoo_ie = None _max_yahoo_results = 1000 + IE_NAME = u'video.yahoo:search' def __init__(self, yahoo_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._yahoo_ie = yahoo_ie - - @staticmethod - def suitable(url): - return (re.match(YahooSearchIE._VALID_QUERY, url) is not None) def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" @@ -1894,16 +2419,16 @@ class YahooSearchIE(InfoExtractor): def _real_initialize(self): self._yahoo_ie.initialize() - + def _real_extract(self, query): - mobj = re.match(self._VALID_QUERY, query) + mobj = re.match(self._VALID_URL, query) if mobj is None: self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) return prefix, query = query.split(':') prefix = prefix[8:] - query = query.encode('utf-8') + query = query.encode('utf-8') if prefix == '': self._download_n_results(query, 1) return @@ -1917,7 +2442,7 @@ class YahooSearchIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) return elif n > self._max_yahoo_results: - self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) + self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) n = self._max_yahoo_results self._download_n_results(query, n) return @@ -1935,7 +2460,7 @@ class YahooSearchIE(InfoExtractor): while True: self.report_download_page(query, pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) - request = urllib2.Request(result_url, None, std_headers) + request = urllib2.Request(result_url) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -1961,22 +2486,20 @@ class YahooSearchIE(InfoExtractor): pagenum = pagenum + 1 + class YoutubePlaylistIE(InfoExtractor): """Information Extractor for YouTube playlists.""" - _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*' - _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en' + _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' + _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' _youtube_ie = None + IE_NAME = u'youtube:playlist' def __init__(self, youtube_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._youtube_ie = youtube_ie - - @staticmethod - def suitable(url): - return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None) def report_download_page(self, playlist_id, pagenum): """Report attempt to download playlist page with given number.""" @@ -1984,7 +2507,7 @@ class YoutubePlaylistIE(InfoExtractor): def _real_initialize(self): self._youtube_ie.initialize() - + def _real_extract(self, url): # Extract playlist id mobj = re.match(self._VALID_URL, url) @@ -1992,14 +2515,27 @@ class YoutubePlaylistIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid url: %s' % url) return + # Single video case + if mobj.group(3) is not None: + self._youtube_ie.extract(mobj.group(3)) + return + # Download playlist pages - playlist_id = mobj.group(1) + # prefix is 'p' as default for playlists but there are other types that need extra care + playlist_prefix = mobj.group(1) + if playlist_prefix == 'a': + playlist_access = 'artist' + else: + playlist_prefix = 'p' + playlist_access = 'view_play_list' + playlist_id = mobj.group(2) video_ids = [] pagenum = 1 while True: self.report_download_page(playlist_id, pagenum) - request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers) + url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum) + request = urllib2.Request(url) try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -2025,29 +2561,30 @@ class YoutubePlaylistIE(InfoExtractor): self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return + class YoutubeUserIE(InfoExtractor): """Information Extractor for YouTube users.""" - _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)' + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' - _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this. + _GDATA_PAGE_SIZE = 50 + _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' + _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' _youtube_ie = None + IE_NAME = u'youtube:user' def __init__(self, youtube_ie, downloader=None): InfoExtractor.__init__(self, downloader) self._youtube_ie = youtube_ie - - @staticmethod - def suitable(url): - return (re.match(YoutubeUserIE._VALID_URL, url) is not None) - def report_download_page(self, username): + def report_download_page(self, username, start_index): """Report attempt to download user page.""" - self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username)) + self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % + (username, start_index, start_index + self._GDATA_PAGE_SIZE)) def _real_initialize(self): self._youtube_ie.initialize() - + def _real_extract(self, url): # Extract username mobj = re.match(self._VALID_URL, url) @@ -2055,47 +2592,73 @@ class YoutubeUserIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid url: %s' % url) return - # Download user page username = mobj.group(1) + + # Download video ids using YouTube Data API. Result size per + # query is limited (currently to 50 videos) so we need to query + # page by page until there are no video ids - it means we got + # all of them. + video_ids = [] - pagenum = 1 + pagenum = 0 - self.report_download_page(username) - request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers) - try: - page = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) - return + while True: + start_index = pagenum * self._GDATA_PAGE_SIZE + 1 + self.report_download_page(username, start_index) + + request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) + + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + ids_in_page = [] + + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + + video_ids.extend(ids_in_page) + + # A little optimization - if current page is not + # "full", ie. does not contain PAGE_SIZE video ids then + # we can assume that this page is the last one - there + # are no more ids on further pages - no need to query + # again. - # Extract video identifiers - ids_in_page = [] + if len(ids_in_page) < self._GDATA_PAGE_SIZE: + break - for mobj in re.finditer(self._VIDEO_INDICATOR, page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(mobj.group(1)) - video_ids.extend(ids_in_page) + pagenum += 1 + all_ids_count = len(video_ids) playliststart = self._downloader.params.get('playliststart', 1) - 1 playlistend = self._downloader.params.get('playlistend', -1) - video_ids = video_ids[playliststart:playlistend] - for id in video_ids: - self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) - return + if playlistend == -1: + video_ids = video_ids[playliststart:] + else: + video_ids = video_ids[playliststart:playlistend] + + self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" % + (username, all_ids_count, len(video_ids))) + + for video_id in video_ids: + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id) + class DepositFilesIE(InfoExtractor): """Information extractor for depositfiles.com""" - _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)' + _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' + IE_NAME = u'DepositFiles' def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - @staticmethod - def suitable(url): - return (re.match(DepositFilesIE._VALID_URL, url) is not None) - def report_download_webpage(self, file_id): """Report webpage download.""" self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) @@ -2104,9 +2667,6 @@ class DepositFilesIE(InfoExtractor): """Report information extraction.""" self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) - def _real_initialize(self): - return - def _real_extract(self, url): # At this point we have a new file self._downloader.increment_downloads() @@ -2117,7 +2677,7 @@ class DepositFilesIE(InfoExtractor): # Retrieve file webpage with 'Free download' button pressed free_download_indication = { 'gateway_result' : '1' } - request = urllib2.Request(url, urllib.urlencode(free_download_indication), std_headers) + request = urllib2.Request(url, urllib.urlencode(free_download_indication)) try: self.report_download_webpage(file_id) webpage = urllib2.urlopen(request).read() @@ -2163,316 +2723,1801 @@ class DepositFilesIE(InfoExtractor): except UnavailableVideoError, err: self._downloader.trouble(u'ERROR: unable to download file') -class PostProcessor(object): - """Post Processor class. - PostProcessor objects can be added to downloaders with their - add_post_processor() method. When the downloader has finished a - successful download, it will take its internal chain of PostProcessors - and start calling the run() method on each one of them, first with - an initial argument and then with the returned value of the previous - PostProcessor. +class FacebookIE(InfoExtractor): + """Information Extractor for Facebook""" - The chain will be stopped if one of them ever returns None or the end - of the chain is reached. + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P\d+)(?:.*)' + _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' + _NETRC_MACHINE = 'facebook' + _available_formats = ['video', 'highqual', 'lowqual'] + _video_extensions = { + 'video': 'mp4', + 'highqual': 'mp4', + 'lowqual': 'mp4', + } + IE_NAME = u'facebook' - PostProcessor objects follow a "mutual registration" process similar - to InfoExtractor objects. - """ + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) - _downloader = None + def _reporter(self, message): + """Add header and report message.""" + self._downloader.to_screen(u'[facebook] %s' % message) - def __init__(self, downloader=None): - self._downloader = downloader + def report_login(self): + """Report attempt to log in.""" + self._reporter(u'Logging in') - def set_downloader(self, downloader): - """Sets the downloader for this PP.""" - self._downloader = downloader - - def run(self, information): - """Run the PostProcessor. + def report_video_webpage_download(self, video_id): + """Report attempt to download video webpage.""" + self._reporter(u'%s: Downloading video webpage' % video_id) - The "information" argument is a dictionary like the ones - composed by InfoExtractors. The only difference is that this - one has an extra field called "filepath" that points to the - downloaded file. + def report_information_extraction(self, video_id): + """Report attempt to extract video information.""" + self._reporter(u'%s: Extracting video information' % video_id) + + def _parse_page(self, video_webpage): + """Extract video information from page""" + # General data + data = {'title': r'\("video_title", "(.*?)"\)', + 'description': r'
(.*?)
', + 'owner': r'\("video_owner_name", "(.*?)"\)', + 'thumbnail': r'\("thumb_url", "(?P.*?)"\)', + } + video_info = {} + for piece in data.keys(): + mobj = re.search(data[piece], video_webpage) + if mobj is not None: + video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) - When this method returns None, the postprocessing chain is - stopped. However, this method may return an information - dictionary that will be passed to the next postprocessing - object in the chain. It can be the one it received after - changing some fields. + # Video urls + video_urls = {} + for fmt in self._available_formats: + mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage) + if mobj is not None: + # URL is in a Javascript segment inside an escaped Unicode format within + # the generally utf-8 page + video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) + video_info['video_urls'] = video_urls - In addition, this method may raise a PostProcessingError - exception that will be taken into account by the downloader - it was called from. - """ - return information # by default, do nothing - -### MAIN PROGRAM ### -if __name__ == '__main__': - try: - # Modules needed only when running the main program - import getpass - import optparse - - # Function to update the program file with the latest version from bitbucket.org - def update_self(downloader, filename): - # Note: downloader only used for options - if not os.access (filename, os.W_OK): - sys.exit('ERROR: no write permissions on %s' % filename) - - downloader.to_screen('Updating to latest stable version...') - latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' - latest_version = urllib.urlopen(latest_url).read().strip() - prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version - newcontent = urllib.urlopen(prog_url).read() - stream = open(filename, 'w') - stream.write(newcontent) - stream.close() - downloader.to_screen('Updated to version %s' % latest_version) - - # Parse command line - parser = optparse.OptionParser( - usage='Usage: %prog [options] url...', - version='2010.12.09', - 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', '--update', - action='store_true', dest='update_self', help='update this program to latest stable version') - 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='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') - parser.add_option('-R', '--retries', - dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) - parser.add_option('--playlist-start', - dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) - parser.add_option('--playlist-end', - dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) - - authentication = optparse.OptionGroup(parser, 'Authentication Options') - authentication.add_option('-u', '--username', - dest='username', metavar='USERNAME', help='account username') - authentication.add_option('-p', '--password', - dest='password', metavar='PASSWORD', help='account password') - 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='FORMAT', help='video format code') - video_format.add_option('-m', '--mobile-version', - action='store_const', dest='format', help='alias for -f 17', const='17') - video_format.add_option('--all-formats', - action='store_const', dest='format', help='download all available video formats', const='-1') - video_format.add_option('--max-quality', - action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') - video_format.add_option('-b', '--best-quality', - action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)') - 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) - verbosity.add_option('-s', '--simulate', - action='store_true', dest='simulate', help='do not download video', default=False) - verbosity.add_option('-g', '--get-url', - action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) - verbosity.add_option('-e', '--get-title', - action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) - verbosity.add_option('--get-thumbnail', - action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False) - verbosity.add_option('--get-description', - action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False) - verbosity.add_option('--no-progress', - action='store_true', dest='noprogress', help='do not print progress bar', default=False) - 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('-A', '--auto-number', - action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False) - filesystem.add_option('-o', '--output', - dest='outtmpl', metavar='TEMPLATE', help='output filename template') - filesystem.add_option('-a', '--batch-file', - dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') - 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) - filesystem.add_option('--cookies', - dest='cookiefile', metavar='FILE', help='file to dump cookie jar to') - parser.add_option_group(filesystem) - - (opts, args) = parser.parse_args() - - # Open appropriate CookieJar - if opts.cookiefile is None: - jar = cookielib.CookieJar() - else: - try: - jar = cookielib.MozillaCookieJar(opts.cookiefile) - if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): - jar.load() - except (IOError, OSError), err: - sys.exit(u'ERROR: unable to open cookie file') + return video_info + + def _real_initialize(self): + if self._downloader is None: + return - # General configuration - cookie_processor = urllib2.HTTPCookieProcessor(jar) - urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) - urllib2.install_opener(urllib2.build_opener(cookie_processor)) - socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) + useremail = None + password = None + downloader_params = self._downloader.params - # Batch file verification - batchurls = [] - if opts.batchfile is not None: + # Attempt to use provided username and password or .netrc data + if downloader_params.get('username', None) is not None: + useremail = downloader_params['username'] + password = downloader_params['password'] + elif downloader_params.get('usenetrc', False): try: - if opts.batchfile == '-': - batchfd = sys.stdin + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + useremail = info[0] + password = info[2] else: - batchfd = open(opts.batchfile, 'r') - batchurls = batchfd.readlines() - batchurls = [x.strip() for x in batchurls] - batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] - except IOError: - sys.exit(u'ERROR: batch file could not be read') - all_urls = batchurls + args - - # Conflicting, missing and erroneous options - if opts.bestquality: - print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n' - if opts.usenetrc and (opts.username is not None or opts.password is not None): - parser.error(u'using .netrc conflicts with giving username/password') - if opts.password is not None and opts.username is None: - parser.error(u'account username missing') - if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): - parser.error(u'using output template conflicts with using title, literal title or auto number') - if opts.usetitle and opts.useliteral: - 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: - parser.error(u'invalid rate limit specified') - opts.ratelimit = numeric_limit - if opts.retries is not None: - try: - opts.retries = long(opts.retries) - except (TypeError, ValueError), err: - parser.error(u'invalid retry count specified') + 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 + + if useremail is None: + return + + # Log in + login_form = { + 'email': useremail, + 'pass': password, + 'login': 'Log+In' + } + request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) try: - opts.playliststart = long(opts.playliststart) - if opts.playliststart <= 0: - raise ValueError - except (TypeError, ValueError), err: - parser.error(u'invalid playlist start number specified') + self.report_login() + login_results = urllib2.urlopen(request).read() + if re.search(r'', login_results) is not None: + self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') + return + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) + return + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('ID') + + # Get video webpage + self.report_video_webpage_download(video_id) + request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id) try: - opts.playlistend = long(opts.playlistend) - if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): - raise ValueError - except (TypeError, ValueError), err: - parser.error(u'invalid playlist end number specified') - - # Information extractors - youtube_ie = YoutubeIE() - metacafe_ie = MetacafeIE(youtube_ie) - dailymotion_ie = DailymotionIE() - youtube_pl_ie = YoutubePlaylistIE(youtube_ie) - youtube_user_ie = YoutubeUserIE(youtube_ie) - youtube_search_ie = YoutubeSearchIE(youtube_ie) - google_ie = GoogleIE() - google_search_ie = GoogleSearchIE(google_ie) - photobucket_ie = PhotobucketIE() - yahoo_ie = YahooIE() - yahoo_search_ie = YahooSearchIE(yahoo_ie) - deposit_files_ie = DepositFilesIE() - generic_ie = GenericIE() - - # File downloader - fd = FileDownloader({ - 'usenetrc': opts.usenetrc, - 'username': opts.username, - 'password': opts.password, - 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription), - 'forceurl': opts.geturl, - 'forcetitle': opts.gettitle, - 'forcethumbnail': opts.getthumbnail, - 'forcedescription': opts.getdescription, - 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription), - 'format': opts.format, - 'format_limit': opts.format_limit, - 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) - or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') - or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') - or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') - or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') - or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') - or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') - or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') - or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') - or u'%(id)s.%(ext)s'), - 'ignoreerrors': opts.ignoreerrors, - 'ratelimit': opts.ratelimit, - 'nooverwrites': opts.nooverwrites, - 'retries': opts.retries, - 'continuedl': opts.continue_dl, - 'noprogress': opts.noprogress, - 'playliststart': opts.playliststart, - 'playlistend': opts.playlistend, - 'logtostderr': opts.outtmpl == '-', - }) - fd.add_info_extractor(youtube_search_ie) - fd.add_info_extractor(youtube_pl_ie) - fd.add_info_extractor(youtube_user_ie) - fd.add_info_extractor(metacafe_ie) - fd.add_info_extractor(dailymotion_ie) - fd.add_info_extractor(youtube_ie) - fd.add_info_extractor(google_ie) - fd.add_info_extractor(google_search_ie) - fd.add_info_extractor(photobucket_ie) - fd.add_info_extractor(yahoo_ie) - fd.add_info_extractor(yahoo_search_ie) - fd.add_info_extractor(deposit_files_ie) - - # This must come last since it's the - # fallback if none of the others work - fd.add_info_extractor(generic_ie) - - # Update version - if opts.update_self: - update_self(fd, sys.argv[0]) - - # Maybe do nothing - if len(all_urls) < 1: - if not opts.update_self: - parser.error(u'you must provide at least one URL') - else: - sys.exit() - retcode = fd.download(all_urls) + page = urllib2.urlopen(request) + video_webpage = page.read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return - # Dump cookie jar if requested - if opts.cookiefile is not None: - try: - jar.save() - except (IOError, OSError), err: - sys.exit(u'ERROR: unable to save cookie jar') + # Start extracting information + self.report_information_extraction(video_id) - sys.exit(retcode) + # Extract information + video_info = self._parse_page(video_webpage) - except DownloadError: - sys.exit(1) - except SameFileError: - sys.exit(u'ERROR: fixed output name but more than one file to download') + # uploader + if 'owner' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = video_info['owner'] + + # title + if 'title' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = video_info['title'] + video_title = video_title.decode('utf-8') + video_title = sanitize_title(video_title) + + simple_title = _simplify_title(video_title) + + # thumbnail image + if 'thumbnail' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + video_thumbnail = '' + else: + video_thumbnail = video_info['thumbnail'] + + # upload date + upload_date = u'NA' + if 'upload_date' in video_info: + upload_time = video_info['upload_date'] + timetuple = email.utils.parsedate_tz(upload_time) + if timetuple is not None: + try: + upload_date = time.strftime('%Y%m%d', timetuple[0:9]) + except: + pass + + # description + video_description = video_info.get('description', 'No description available.') + + url_map = video_info['video_urls'] + if len(url_map.keys()) > 0: + # Decide which formats to download + req_format = self._downloader.params.get('format', None) + format_limit = self._downloader.params.get('format_limit', None) + + if format_limit is not None and format_limit in self._available_formats: + format_list = self._available_formats[self._available_formats.index(format_limit):] + else: + format_list = self._available_formats + existing_formats = [x for x in format_list if x in url_map] + if len(existing_formats) == 0: + self._downloader.trouble(u'ERROR: no known formats available for video') + return + if req_format is None: + video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality + elif req_format == 'worst': + video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality + elif req_format == '-1': + video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats + else: + # Specific format + if req_format not in url_map: + self._downloader.trouble(u'ERROR: requested format not available') + return + video_url_list = [(req_format, url_map[req_format])] # Specific format + + for format_param, video_real_url in video_url_list: + + # At this point we have a new video + self._downloader.increment_downloads() + + # Extension + video_extension = self._video_extensions.get(format_param, 'mp4') + + 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'), + 'upload_date': upload_date, + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description.decode('utf-8'), + 'player_url': None, + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + +class BlipTVIE(InfoExtractor): + """Information extractor for blip.tv""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' + _URL_EXT = r'^.*\.([a-z0-9]+)$' + IE_NAME = u'blip.tv' + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + + def report_direct_download(self, title): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if '?' in url: + cchar = '&' + else: + cchar = '?' + json_url = url + cchar + 'skin=json&version=2&no_wrap=1' + request = urllib2.Request(json_url) + self.report_extraction(mobj.group(1)) + info = None + try: + urlh = urllib2.urlopen(request) + if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download + basename = url.split('/')[-1] + title,ext = os.path.splitext(basename) + title = title.decode('UTF-8') + ext = ext.replace('.', '') + self.report_direct_download(title) + info = { + 'id': title, + 'url': url, + 'title': title, + 'stitle': _simplify_title(title), + 'ext': ext, + 'urlhandle': urlh + } + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) + return + if info is None: # Regular URL + try: + json_code = urlh.read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err)) + return + + try: + json_data = json.loads(json_code) + if 'Post' in json_data: + data = json_data['Post'] + else: + data = json_data + + upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') + video_url = data['media']['url'] + umobj = re.match(self._URL_EXT, video_url) + if umobj is None: + raise ValueError('Can not determine filename extension') + ext = umobj.group(1) + + info = { + 'id': data['item_id'], + 'url': video_url, + 'uploader': data['display_name'], + 'upload_date': upload_date, + 'title': data['title'], + 'stitle': _simplify_title(data['title']), + 'ext': ext, + 'format': data['media']['mimeType'], + 'thumbnail': data['thumbnailUrl'], + 'description': data['description'], + 'player_url': data['embedUrl'] + } + except (ValueError,KeyError), err: + self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) + return + + self._downloader.increment_downloads() + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class MyVideoIE(InfoExtractor): + """Information Extractor for myvideo.de.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' + IE_NAME = u'myvideo' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._download.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + # Get video webpage + request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + self.report_extraction(video_id) + mobj = re.search(r'', + webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + video_url = mobj.group(1) + ('/%s.flv' % video_id) + + mobj = re.search('([^<]+)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + + video_title = mobj.group(1) + video_title = sanitize_title(video_title) + + simple_title = _simplify_title(video_title) + + try: + self._downloader.process_info({ + 'id': video_id, + 'url': video_url, + 'uploader': u'NA', + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': u'flv', + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: Unable to download video') + +class ComedyCentralIE(InfoExtractor): + """Information extractor for The Daily Show and Colbert Report """ + + _VALID_URL = r'^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?Pthedailyshow|colbertnation)\.com/full-episodes/(?P.*)$' + IE_NAME = u'comedycentral' + + def report_extraction(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) + + def report_config_download(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) + + def report_index_download(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) + + def report_player_url(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if mobj.group('shortname'): + if mobj.group('shortname') in ('tds', 'thedailyshow'): + url = u'http://www.thedailyshow.com/full-episodes/' + else: + url = u'http://www.colbertnation.com/full-episodes/' + mobj = re.match(self._VALID_URL, url) + assert mobj is not None + + dlNewest = not mobj.group('episode') + if dlNewest: + epTitle = mobj.group('showname') + else: + epTitle = mobj.group('episode') + + req = urllib2.Request(url) + self.report_extraction(epTitle) + try: + htmlHandle = urllib2.urlopen(req) + html = htmlHandle.read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) + return + if dlNewest: + url = htmlHandle.geturl() + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) + return + if mobj.group('episode') == '': + self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url) + return + epTitle = mobj.group('episode') + + mMovieParams = re.findall('(?:[^/]+)/(?P[^/?]+)[/?]?.*$' + IE_NAME = u'escapist' + + def report_extraction(self, showName): + self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) + + def report_config_download(self, showName): + self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + showName = mobj.group('showname') + videoId = mobj.group('episode') + + self.report_extraction(showName) + try: + webPage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) + return + + descMatch = re.search('[0-9]+)/(?P.*)$' + IE_NAME = u'collegehumor' + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('videoid') + + self.report_webpage(video_id) + request = urllib2.Request(url) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + m = re.search(r'id="video:(?P[0-9]+)"', webpage) + if m is None: + self._downloader.trouble(u'ERROR: Cannot extract internal video ID') + return + internal_video_id = m.group('internalvideoid') + + info = { + 'id': video_id, + 'internal_id': internal_video_id, + } + + self.report_extraction(video_id) + xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id + try: + metaXml = urllib2.urlopen(xmlUrl).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err)) + return + + mdoc = xml.etree.ElementTree.fromstring(metaXml) + try: + videoNode = mdoc.findall('./video')[0] + info['description'] = videoNode.findall('./description')[0].text + info['title'] = videoNode.findall('./caption')[0].text + info['stitle'] = _simplify_title(info['title']) + info['url'] = videoNode.findall('./file')[0].text + info['thumbnail'] = videoNode.findall('./thumbnail')[0].text + info['ext'] = info['url'].rpartition('.')[2] + info['format'] = info['ext'] + except IndexError: + self._downloader.trouble(u'\nERROR: Invalid metadata XML file') + return + + self._downloader.increment_downloads() + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class XVideosIE(InfoExtractor): + """Information extractor for xvideos.com""" + + _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + IE_NAME = u'xvideos' + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(1).decode('utf-8') + + self.report_webpage(video_id) + + request = urllib2.Request(r'http://www.xvideos.com/video' + video_id) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + self.report_extraction(video_id) + + + # Extract video URL + mobj = re.search(r'flv_url=(.+?)&', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = urllib2.unquote(mobj.group(1).decode('utf-8')) + + + # Extract title + mobj = re.search(r'(.*?)\s+-\s+XVID', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + + + # Extract video thumbnail + mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + + + self._downloader.increment_downloads() + info = { + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'stitle': _simplify_title(video_title), + 'ext': 'flv', + 'format': 'flv', + 'thumbnail': video_thumbnail, + 'description': None, + 'player_url': None, + } + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download ' + video_id) + + +class SoundcloudIE(InfoExtractor): + """Information extractor for soundcloud.com + To access the media, the uid of the song and a stream token + must be extracted from the page source and the script must make + a request to media.soundcloud.com/crossdomain.xml. Then + the media can be grabbed by requesting from an url composed + of the stream token and uid + """ + + _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' + IE_NAME = u'soundcloud' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + # extract uploader (which is in the url) + uploader = mobj.group(1).decode('utf-8') + # extract simple title (uploader + slug of song title) + slug_title = mobj.group(2).decode('utf-8') + simple_title = uploader + '-' + slug_title + + self.report_webpage('%s/%s' % (uploader, slug_title)) + + request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title)) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + self.report_extraction('%s/%s' % (uploader, slug_title)) + + # extract uid and stream token that soundcloud hands out for access + mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage) + if mobj: + video_id = mobj.group(1) + stream_token = mobj.group(2) + + # extract unsimplified title + mobj = re.search('"title":"(.*?)",', webpage) + if mobj: + title = mobj.group(1) + + # construct media url (with uid/token) + mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s" + mediaURL = mediaURL % (video_id, stream_token) + + # description + description = u'No description available' + mobj = re.search('track-description-value"><p>(.*?)</p>', webpage) + if mobj: + description = mobj.group(1) + + # upload date + upload_date = None + mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage) + if mobj: + try: + upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') + except Exception, e: + print str(e) + + # for soundcloud, a request to a cross domain is required for cookies + request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers) + + try: + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': mediaURL, + 'uploader': uploader.decode('utf-8'), + 'upload_date': upload_date, + 'title': simple_title.decode('utf-8'), + 'stitle': simple_title.decode('utf-8'), + 'ext': u'mp3', + 'format': u'NA', + 'player_url': None, + 'description': description.decode('utf-8') + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: unable to download video') + + +class InfoQIE(InfoExtractor): + """Information extractor for infoq.com""" + + _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' + IE_NAME = u'infoq' + + def report_webpage(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + htmlParser = HTMLParser.HTMLParser() + + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + self.report_webpage(url) + + request = urllib2.Request(url) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + + self.report_extraction(url) + + + # Extract video URL + mobj = re.search(r"jsclassref='([^']*)'", webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64')) + + + # Extract title + mobj = re.search(r'contentTitle = "(.*?)";', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + + # Extract description + video_description = u'No description available.' + mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) + if mobj is not None: + video_description = mobj.group(1).decode('utf-8') + + video_filename = video_url.split('/')[-1] + video_id, extension = video_filename.split('.') + + self._downloader.increment_downloads() + info = { + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'stitle': _simplify_title(video_title), + 'ext': extension, + 'format': extension, # Extension is always(?) mp4, but seems to be flv + 'thumbnail': None, + 'description': video_description, + 'player_url': None, + } + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download ' + video_url) + +class MixcloudIE(InfoExtractor): + """Information extractor for www.mixcloud.com""" + _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' + IE_NAME = u'mixcloud' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_json(self, file_id): + """Report JSON download.""" + self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + + def get_urls(self, jsonData, fmt, bitrate='best'): + """Get urls from 'audio_formats' section in json""" + file_url = None + try: + bitrate_list = jsonData[fmt] + if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: + bitrate = max(bitrate_list) # select highest + + url_list = jsonData[fmt][bitrate] + except TypeError: # we have no bitrate info. + url_list = jsonData[fmt] + + return url_list + + def check_urls(self, url_list): + """Returns 1st active url from list""" + for url in url_list: + try: + urllib2.urlopen(url) + return url + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + url = None + + return None + + def _print_formats(self, formats): + print 'Available formats:' + for fmt in formats.keys(): + for b in formats[fmt]: + try: + ext = formats[fmt][b][0] + print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]) + except TypeError: # we have no bitrate info + ext = formats[fmt][0] + print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]) + break + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + # extract uploader & filename from url + uploader = mobj.group(1).decode('utf-8') + file_id = uploader + "-" + mobj.group(2).decode('utf-8') + + # construct API request + file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' + # retrieve .json file with links to files + request = urllib2.Request(file_url) + try: + self.report_download_json(file_url) + jsonData = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err)) + return + + # parse JSON + json_data = json.loads(jsonData) + player_url = json_data['player_swf_url'] + formats = dict(json_data['audio_formats']) + + req_format = self._downloader.params.get('format', None) + bitrate = None + + if self._downloader.params.get('listformats', None): + self._print_formats(formats) + return + + if req_format is None or req_format == 'best': + for format_param in formats.keys(): + url_list = self.get_urls(formats, format_param) + # check urls + file_url = self.check_urls(url_list) + if file_url is not None: + break # got it! + else: + if req_format not in formats.keys(): + self._downloader.trouble(u'ERROR: format is not available') + return + + url_list = self.get_urls(formats, req_format) + file_url = self.check_urls(url_list) + format_param = req_format + + # We have audio + self._downloader.increment_downloads() + try: + # Process file information + self._downloader.process_info({ + 'id': file_id.decode('utf-8'), + 'url': file_url.decode('utf-8'), + 'uploader': uploader.decode('utf-8'), + 'upload_date': u'NA', + 'title': json_data['name'], + 'stitle': _simplify_title(json_data['name']), + 'ext': file_url.split('.')[-1].decode('utf-8'), + 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), + 'thumbnail': json_data['thumbnail_url'], + 'description': json_data['description'], + 'player_url': player_url.decode('utf-8'), + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'ERROR: unable to download file') + +class StanfordOpenClassroomIE(InfoExtractor): + """Information extractor for Stanford's Open ClassRoom""" + + _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' + IE_NAME = u'stanfordoc' + + def report_download_webpage(self, objid): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if mobj.group('course') and mobj.group('video'): # A specific video + course = mobj.group('course') + video = mobj.group('video') + info = { + 'id': _simplify_title(course + '_' + video), + } + + self.report_extraction(info['id']) + baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' + xmlUrl = baseUrl + video + '.xml' + try: + metaXml = urllib2.urlopen(xmlUrl).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err)) + return + mdoc = xml.etree.ElementTree.fromstring(metaXml) + try: + info['title'] = mdoc.findall('./title')[0].text + info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text + except IndexError: + self._downloader.trouble(u'\nERROR: Invalid metadata XML file') + return + info['stitle'] = _simplify_title(info['title']) + info['ext'] = info['url'].rpartition('.')[2] + info['format'] = info['ext'] + self._downloader.increment_downloads() + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download video') + elif mobj.group('course'): # A course page + unescapeHTML = HTMLParser.HTMLParser().unescape + + course = mobj.group('course') + info = { + 'id': _simplify_title(course), + 'type': 'playlist', + } + + self.report_download_webpage(info['id']) + try: + coursepage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) + return + + m = re.search('<h1>([^<]+)</h1>', coursepage) + if m: + info['title'] = unescapeHTML(m.group(1)) + else: + info['title'] = info['id'] + info['stitle'] = _simplify_title(info['title']) + + m = re.search('<description>([^<]+)</description>', coursepage) + if m: + info['description'] = unescapeHTML(m.group(1)) + + links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) + info['list'] = [ + { + 'type': 'reference', + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), + } + for vpage in links] + + for entry in info['list']: + assert entry['type'] == 'reference' + self.extract(entry['url']) + else: # Root page + unescapeHTML = HTMLParser.HTMLParser().unescape + + info = { + 'id': 'Stanford OpenClassroom', + 'type': 'playlist', + } + + self.report_download_webpage(info['id']) + rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' + try: + rootpage = urllib2.urlopen(rootURL).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) + return + + info['title'] = info['id'] + info['stitle'] = _simplify_title(info['title']) + + links = _orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) + info['list'] = [ + { + 'type': 'reference', + 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), + } + for cpage in links] + + for entry in info['list']: + assert entry['type'] == 'reference' + self.extract(entry['url']) + + +class PostProcessor(object): + """Post Processor class. + + PostProcessor objects can be added to downloaders with their + add_post_processor() method. When the downloader has finished a + successful download, it will take its internal chain of PostProcessors + and start calling the run() method on each one of them, first with + an initial argument and then with the returned value of the previous + PostProcessor. + + The chain will be stopped if one of them ever returns None or the end + of the chain is reached. + + PostProcessor objects follow a "mutual registration" process similar + to InfoExtractor objects. + """ + + _downloader = None + + def __init__(self, downloader=None): + self._downloader = downloader + + def set_downloader(self, downloader): + """Sets the downloader for this PP.""" + self._downloader = downloader + + def run(self, information): + """Run the PostProcessor. + + The "information" argument is a dictionary like the ones + composed by InfoExtractors. The only difference is that this + one has an extra field called "filepath" that points to the + downloaded file. + + When this method returns None, the postprocessing chain is + stopped. However, this method may return an information + dictionary that will be passed to the next postprocessing + object in the chain. It can be the one it received after + changing some fields. + + In addition, this method may raise a PostProcessingError + exception that will be taken into account by the downloader + it was called from. + """ + return information # by default, do nothing + +class AudioConversionError(BaseException): + def __init__(self, message): + self.message = message + +class FFmpegExtractAudioPP(PostProcessor): + + def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False): + PostProcessor.__init__(self, downloader) + if preferredcodec is None: + preferredcodec = 'best' + self._preferredcodec = preferredcodec + self._preferredquality = preferredquality + self._keepvideo = keepvideo + + @staticmethod + def get_audio_codec(path): + try: + cmd = ['ffprobe', '-show_streams', '--', path] + handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE) + output = handle.communicate()[0] + if handle.wait() != 0: + return None + except (IOError, OSError): + return None + audio_codec = None + for line in output.split('\n'): + if line.startswith('codec_name='): + audio_codec = line.split('=')[1].strip() + elif line.strip() == 'codec_type=audio' and audio_codec is not None: + return audio_codec + return None + + @staticmethod + def run_ffmpeg(path, out_path, codec, more_opts): + if codec is None: + acodec_opts = [] + else: + acodec_opts = ['-acodec', codec] + cmd = ['ffmpeg', '-y', '-i', path, '-vn'] + acodec_opts + more_opts + ['--', out_path] + try: + p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + stdout,stderr = p.communicate() + except (IOError, OSError): + e = sys.exc_info()[1] + if isinstance(e, OSError) and e.errno == 2: + raise AudioConversionError('ffmpeg not found. Please install ffmpeg.') + else: + raise e + if p.returncode != 0: + msg = stderr.strip().split('\n')[-1] + raise AudioConversionError(msg) + + def run(self, information): + path = information['filepath'] + + filecodec = self.get_audio_codec(path) + if filecodec is None: + self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe') + return None + + more_opts = [] + if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'): + if self._preferredcodec == 'm4a' and filecodec == 'aac': + # Lossless, but in another container + acodec = 'copy' + extension = self._preferredcodec + more_opts = ['-absf', 'aac_adtstoasc'] + elif filecodec in ['aac', 'mp3', 'vorbis']: + # Lossless if possible + acodec = 'copy' + extension = filecodec + if filecodec == 'aac': + more_opts = ['-f', 'adts'] + if filecodec == 'vorbis': + extension = 'ogg' + else: + # MP3 otherwise. + acodec = 'libmp3lame' + extension = 'mp3' + more_opts = [] + if self._preferredquality is not None: + more_opts += ['-ab', self._preferredquality] + else: + # We convert the audio (lossy) + acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec] + extension = self._preferredcodec + more_opts = [] + if self._preferredquality is not None: + more_opts += ['-ab', self._preferredquality] + if self._preferredcodec == 'aac': + more_opts += ['-f', 'adts'] + if self._preferredcodec == 'm4a': + more_opts += ['-absf', 'aac_adtstoasc'] + if self._preferredcodec == 'vorbis': + extension = 'ogg' + if self._preferredcodec == 'wav': + extension = 'wav' + more_opts += ['-f', 'wav'] + + (prefix, ext) = os.path.splitext(path) + new_path = prefix + '.' + extension + self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path) + try: + self.run_ffmpeg(path, new_path, acodec, more_opts) + except: + etype,e,tb = sys.exc_info() + if isinstance(e, AudioConversionError): + self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message) + else: + self._downloader.to_stderr(u'ERROR: error running ffmpeg') + return None + + # Try to update the date time for extracted audio file. + if information.get('filetime') is not None: + try: + os.utime(new_path, (time.time(), information['filetime'])) + except: + self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file') + + if not self._keepvideo: + try: + os.remove(path) + except (IOError, OSError): + self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file') + return None + + information['filepath'] = new_path + return information + + +def updateSelf(downloader, filename): + ''' Update the program file with the latest version from the repository ''' + # Note: downloader only used for options + if not os.access(filename, os.W_OK): + sys.exit('ERROR: no write permissions on %s' % filename) + + downloader.to_screen('Updating to latest version...') + + try: + try: + urlh = urllib.urlopen(UPDATE_URL) + newcontent = urlh.read() + + vmatch = re.search("__version__ = '([^']+)'", newcontent) + if vmatch is not None and vmatch.group(1) == __version__: + downloader.to_screen('youtube-dl is up-to-date (' + __version__ + ')') + return + finally: + urlh.close() + except (IOError, OSError), err: + sys.exit('ERROR: unable to download latest version') + + try: + outf = open(filename, 'wb') + try: + outf.write(newcontent) + finally: + outf.close() + except (IOError, OSError), err: + sys.exit('ERROR: unable to overwrite current version') + + downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.') + +def parseOpts(): + # Deferred imports + import getpass + import optparse + import shlex + + def _readOptions(filename): + try: + optionf = open(filename) + except IOError: + return [] # silently skip if file is not present + try: + res = [] + for l in optionf: + res += shlex.split(l, comments=True) + finally: + optionf.close() + return res + + def _format_option_string(option): + ''' ('-o', '--option') -> -o, --format METAVAR''' + + opts = [] + + if option._short_opts: opts.append(option._short_opts[0]) + if option._long_opts: opts.append(option._long_opts[0]) + if len(opts) > 1: opts.insert(1, ', ') + + if option.takes_value(): opts.append(' %s' % option.metavar) + + return "".join(opts) + + def _find_term_columns(): + columns = os.environ.get('COLUMNS', None) + if columns: + return int(columns) + + try: + sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out,err = sp.communicate() + return int(out.split()[1]) + except: + pass + return None + + max_width = 80 + max_help_position = 80 + + # No need to wrap help messages if we're on a wide console + columns = _find_term_columns() + if columns: max_width = columns + + fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) + fmt.format_option_strings = _format_option_string + + kw = { + 'version' : __version__, + 'formatter' : fmt, + 'usage' : '%prog [options] url [url...]', + 'conflict_handler' : 'resolve', + } + + parser = optparse.OptionParser(**kw) + + # option groups + general = optparse.OptionGroup(parser, 'General Options') + selection = optparse.OptionGroup(parser, 'Video Selection') + authentication = optparse.OptionGroup(parser, 'Authentication Options') + video_format = optparse.OptionGroup(parser, 'Video Format Options') + postproc = optparse.OptionGroup(parser, 'Post-processing Options') + filesystem = optparse.OptionGroup(parser, 'Filesystem Options') + verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') + + general.add_option('-h', '--help', + action='help', help='print this help text and exit') + general.add_option('-v', '--version', + action='version', help='print program version and exit') + general.add_option('-U', '--update', + action='store_true', dest='update_self', help='update this program to latest version') + general.add_option('-i', '--ignore-errors', + action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) + general.add_option('-r', '--rate-limit', + dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') + general.add_option('-R', '--retries', + dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) + general.add_option('--dump-user-agent', + action='store_true', dest='dump_user_agent', + help='display the current browser identification', default=False) + general.add_option('--list-extractors', + action='store_true', dest='list_extractors', + help='List all supported extractors and the URLs they would handle', default=False) + + selection.add_option('--playlist-start', + dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) + selection.add_option('--playlist-end', + dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) + selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') + selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') + selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None) + + authentication.add_option('-u', '--username', + dest='username', metavar='USERNAME', help='account username') + authentication.add_option('-p', '--password', + dest='password', metavar='PASSWORD', help='account password') + authentication.add_option('-n', '--netrc', + action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) + + + video_format.add_option('-f', '--format', + action='store', dest='format', metavar='FORMAT', help='video format code') + video_format.add_option('--all-formats', + action='store_const', dest='format', help='download all available video formats', const='all') + video_format.add_option('--prefer-free-formats', + action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested') + video_format.add_option('--max-quality', + action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') + video_format.add_option('-F', '--list-formats', + action='store_true', dest='listformats', help='list all available formats (currently youtube only)') + + + verbosity.add_option('-q', '--quiet', + action='store_true', dest='quiet', help='activates quiet mode', default=False) + verbosity.add_option('-s', '--simulate', + action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False) + verbosity.add_option('--skip-download', + action='store_true', dest='skip_download', help='do not download the video', default=False) + verbosity.add_option('-g', '--get-url', + action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) + verbosity.add_option('-e', '--get-title', + action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) + verbosity.add_option('--get-thumbnail', + action='store_true', dest='getthumbnail', + help='simulate, quiet but print thumbnail URL', default=False) + verbosity.add_option('--get-description', + action='store_true', dest='getdescription', + help='simulate, quiet but print video description', default=False) + verbosity.add_option('--get-filename', + action='store_true', dest='getfilename', + help='simulate, quiet but print output filename', default=False) + verbosity.add_option('--get-format', + action='store_true', dest='getformat', + help='simulate, quiet but print output format', default=False) + verbosity.add_option('--no-progress', + action='store_true', dest='noprogress', help='do not print progress bar', default=False) + verbosity.add_option('--console-title', + action='store_true', dest='consoletitle', + help='display progress in console titlebar', default=False) + + + 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('-A', '--auto-number', + action='store_true', dest='autonumber', + help='number downloaded files starting from 00000', default=False) + filesystem.add_option('-o', '--output', + dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.') + filesystem.add_option('-a', '--batch-file', + dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') + 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) + filesystem.add_option('--no-continue', + action='store_false', dest='continue_dl', + help='do not resume partially downloaded files (restart from beginning)') + filesystem.add_option('--cookies', + dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') + filesystem.add_option('--no-part', + action='store_true', dest='nopart', help='do not use .part files', default=False) + filesystem.add_option('--no-mtime', + action='store_false', dest='updatetime', + help='do not use the Last-modified header to set the file modification time', default=True) + filesystem.add_option('--write-description', + action='store_true', dest='writedescription', + help='write video description to a .description file', default=False) + filesystem.add_option('--write-info-json', + action='store_true', dest='writeinfojson', + help='write video metadata to a .info.json file', default=False) + + + postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False, + help='convert video files to audio-only files (requires ffmpeg and ffprobe)') + postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', + help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default') + postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K', + help='ffmpeg audio bitrate specification, 128k by default') + postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False, + help='keeps the video file on disk after the post-processing; the video is erased by default') + + + parser.add_option_group(general) + parser.add_option_group(selection) + parser.add_option_group(filesystem) + parser.add_option_group(verbosity) + parser.add_option_group(video_format) + parser.add_option_group(authentication) + parser.add_option_group(postproc) + + xdg_config_home = os.environ.get('XDG_CONFIG_HOME') + if xdg_config_home: + userConf = os.path.join(xdg_config_home, 'youtube-dl.conf') + else: + userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf') + argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:] + opts, args = parser.parse_args(argv) + + return parser, opts, args + +def gen_extractors(): + """ Return a list of an instance of every supported extractor. + The order does matter; the first extractor matched is the one handling the URL. + """ + youtube_ie = YoutubeIE() + google_ie = GoogleIE() + yahoo_ie = YahooIE() + return [ + YoutubePlaylistIE(youtube_ie), + YoutubeUserIE(youtube_ie), + YoutubeSearchIE(youtube_ie), + youtube_ie, + MetacafeIE(youtube_ie), + DailymotionIE(), + google_ie, + GoogleSearchIE(google_ie), + PhotobucketIE(), + yahoo_ie, + YahooSearchIE(yahoo_ie), + DepositFilesIE(), + FacebookIE(), + BlipTVIE(), + VimeoIE(), + MyVideoIE(), + ComedyCentralIE(), + EscapistIE(), + CollegeHumorIE(), + XVideosIE(), + SoundcloudIE(), + InfoQIE(), + MixcloudIE(), + StanfordOpenClassroomIE(), + + GenericIE() + ] + +def _real_main(): + parser, opts, args = parseOpts() + + # Open appropriate CookieJar + if opts.cookiefile is None: + jar = cookielib.CookieJar() + else: + try: + jar = cookielib.MozillaCookieJar(opts.cookiefile) + if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): + jar.load() + except (IOError, OSError), err: + sys.exit(u'ERROR: unable to open cookie file') + + # Dump user agent + if opts.dump_user_agent: + print std_headers['User-Agent'] + sys.exit(0) + + # Batch file verification + batchurls = [] + if opts.batchfile is not None: + try: + if opts.batchfile == '-': + batchfd = sys.stdin + else: + batchfd = open(opts.batchfile, 'r') + batchurls = batchfd.readlines() + batchurls = [x.strip() for x in batchurls] + batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] + except IOError: + sys.exit(u'ERROR: batch file could not be read') + all_urls = batchurls + args + + # General configuration + cookie_processor = urllib2.HTTPCookieProcessor(jar) + opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()) + urllib2.install_opener(opener) + socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) + + extractors = gen_extractors() + + if opts.list_extractors: + for ie in extractors: + print(ie.IE_NAME) + matchedUrls = filter(lambda url: ie.suitable(url), all_urls) + all_urls = filter(lambda url: url not in matchedUrls, all_urls) + for mu in matchedUrls: + print(u' ' + mu) + sys.exit(0) + + # Conflicting, missing and erroneous options + if opts.usenetrc and (opts.username is not None or opts.password is not None): + parser.error(u'using .netrc conflicts with giving username/password') + if opts.password is not None and opts.username is None: + parser.error(u'account username missing') + if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): + parser.error(u'using output template conflicts with using title, literal title or auto number') + if opts.usetitle and opts.useliteral: + 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: + parser.error(u'invalid rate limit specified') + opts.ratelimit = numeric_limit + if opts.retries is not None: + try: + opts.retries = long(opts.retries) + except (TypeError, ValueError), err: + parser.error(u'invalid retry count specified') + try: + opts.playliststart = int(opts.playliststart) + if opts.playliststart <= 0: + raise ValueError(u'Playlist start must be positive') + except (TypeError, ValueError), err: + parser.error(u'invalid playlist start number specified') + try: + opts.playlistend = int(opts.playlistend) + if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): + raise ValueError(u'Playlist end must be greater than playlist start') + except (TypeError, ValueError), err: + parser.error(u'invalid playlist end number specified') + if opts.extractaudio: + if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']: + parser.error(u'invalid audio format specified') + + # File downloader + fd = FileDownloader({ + 'usenetrc': opts.usenetrc, + 'username': opts.username, + 'password': opts.password, + 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), + 'forceurl': opts.geturl, + 'forcetitle': opts.gettitle, + 'forcethumbnail': opts.getthumbnail, + 'forcedescription': opts.getdescription, + 'forcefilename': opts.getfilename, + 'forceformat': opts.getformat, + 'simulate': opts.simulate, + 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), + 'format': opts.format, + 'format_limit': opts.format_limit, + 'listformats': opts.listformats, + 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) + or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') + or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') + or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') + or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') + or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') + or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') + or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') + or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') + or u'%(id)s.%(ext)s'), + 'ignoreerrors': opts.ignoreerrors, + 'ratelimit': opts.ratelimit, + 'nooverwrites': opts.nooverwrites, + 'retries': opts.retries, + 'continuedl': opts.continue_dl, + 'noprogress': opts.noprogress, + 'playliststart': opts.playliststart, + 'playlistend': opts.playlistend, + 'logtostderr': opts.outtmpl == '-', + 'consoletitle': opts.consoletitle, + 'nopart': opts.nopart, + 'updatetime': opts.updatetime, + 'writedescription': opts.writedescription, + 'writeinfojson': opts.writeinfojson, + 'matchtitle': opts.matchtitle, + 'rejecttitle': opts.rejecttitle, + 'max_downloads': opts.max_downloads, + 'prefer_free_formats': opts.prefer_free_formats, + }) + for extractor in extractors: + fd.add_info_extractor(extractor) + + # PostProcessors + if opts.extractaudio: + fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo)) + + # Update version + if opts.update_self: + updateSelf(fd, sys.argv[0]) + + # Maybe do nothing + if len(all_urls) < 1: + if not opts.update_self: + parser.error(u'you must provide at least one URL') + else: + sys.exit() + + try: + retcode = fd.download(all_urls) + except MaxDownloadsReached: + fd.to_screen(u'--max-download limit reached, aborting.') + retcode = 101 + + # Dump cookie jar if requested + if opts.cookiefile is not None: + try: + jar.save() + except (IOError, OSError), err: + sys.exit(u'ERROR: unable to save cookie jar') + + sys.exit(retcode) + +def main(): + try: + _real_main() + except DownloadError: + sys.exit(1) + except SameFileError: + sys.exit(u'ERROR: fixed output name but more than one file to download') except KeyboardInterrupt: sys.exit(u'\nERROR: Interrupted by user') + +if __name__ == '__main__': + main() + +# vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: