X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=10dd7c7916c990815c4c388211e1c17d709b1dce;hb=1392f3f52cffec6054862c9031cc54e377131014;hp=65781f95983f46c952e3badbe9c2c445686832ad;hpb=71b7300e63780e9495cbb1030061f469a17a66f4;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index 65781f959..10dd7c791 100755 --- a/youtube-dl +++ b/youtube-dl @@ -2,6 +2,7 @@ # -*- coding: utf-8 -*- # Author: Ricardo Garcia Gonzalez # Author: Danny Colligan +# Author: Benjamin Johnson # License: Public domain code import htmlentitydefs import httplib @@ -13,13 +14,20 @@ import os.path import re import socket import string +import subprocess import sys import time import urllib import urllib2 +# parse_qs was moved from the cgi module to the urlparse module recently. +try: + from urlparse import parse_qs +except ImportError: + from cgi import parse_qs + std_headers = { - 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2', + 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5', 'Accept-Language': 'en-us,en;q=0.5', @@ -27,6 +35,75 @@ std_headers = { simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') +def preferredencoding(): + """Get preferred encoding. + + Returns the best encoding scheme for the system, based on + locale.getpreferredencoding() and some further tweaks. + """ + def yield_preferredencoding(): + try: + pref = locale.getpreferredencoding() + u'TEST'.encode(pref) + except: + pref = 'UTF-8' + while True: + yield pref + return yield_preferredencoding().next() + +def htmlentity_transform(matchobj): + """Transforms an HTML entity to a Unicode character. + + This function receives a match object and is intended to be used with + the re.sub() function. + """ + entity = matchobj.group(1) + + # Known non-numeric HTML entity + if entity in htmlentitydefs.name2codepoint: + return unichr(htmlentitydefs.name2codepoint[entity]) + + # Unicode character + mobj = re.match(ur'(?u)#(x?\d+)', entity) + if mobj is not None: + numstr = mobj.group(1) + if numstr.startswith(u'x'): + base = 16 + numstr = u'0%s' % numstr + else: + base = 10 + return unichr(long(numstr, base)) + + # Unknown entity in name, return its literal representation + return (u'&%s;' % entity) + +def sanitize_title(utitle): + """Sanitizes a video title so it could be used as part of a filename.""" + utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) + return utitle.replace(unicode(os.sep), u'%') + +def sanitize_open(filename, open_mode): + """Try to open the given filename, and slightly tweak it if this fails. + + Attempts to open the given filename. If this fails, it tries to change + the filename slightly, step by step, until it's either able to open it + or it fails and raises a final exception, like the standard open() + function. + + It returns the tuple (stream, definitive_file_name). + """ + try: + stream = open(filename, open_mode) + return (stream, filename) + except (IOError, OSError), err: + # In case of error, try to remove win32 forbidden chars + filename = re.sub(ur'[<>:"\|\?\*]', u'#', filename) + + # An exception here should be caught in the caller + stream = open(filename, open_mode) + return (stream, filename) + + class DownloadError(Exception): """Download Error exception. @@ -205,11 +282,13 @@ class FileDownloader(object): @staticmethod def verify_url(url): - """Verify a URL is valid and data could be downloaded.""" + """Verify a URL is valid and data could be downloaded. Return real data URL.""" request = urllib2.Request(url, None, std_headers) data = urllib2.urlopen(request) data.read(1) + url = data.geturl() data.close() + return url def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" @@ -221,15 +300,19 @@ class FileDownloader(object): self._pps.append(pp) pp.set_downloader(self) - def to_stdout(self, message, skip_eol=False): + def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False): """Print message to stdout if not in quiet mode.""" - if not self.params.get('quiet', False): - print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(locale.getpreferredencoding()), + try: + if not self.params.get('quiet', False): + print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()), sys.stdout.flush() + except (UnicodeEncodeError), err: + if not ignore_encoding_errors: + raise def to_stderr(self, message): """Print message to stderr.""" - print >>sys.stderr, message.encode(locale.getpreferredencoding()) + print >>sys.stderr, message.encode(preferredencoding()) def fixed_template(self): """Checks if the output template is fixed.""" @@ -263,7 +346,7 @@ class FileDownloader(object): def report_destination(self, filename): """Report destination filename.""" - self.to_stdout(u'[download] Destination: %s' % filename) + self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) def report_progress(self, percent_str, data_len_str, speed_str, eta_str): """Report download progress.""" @@ -276,7 +359,10 @@ class FileDownloader(object): def report_file_already_downloaded(self, file_name): """Report file has already been fully downloaded.""" - self.to_stdout(u'[download] %s has already been downloaded' % file_name) + try: + self.to_stdout(u'[download] %s has already been downloaded' % file_name) + except (UnicodeEncodeError), err: + self.to_stdout(u'[download] The file has already been downloaded') def report_unable_to_resume(self): """Report it was impossible to resume download.""" @@ -290,16 +376,18 @@ class FileDownloader(object): """Process a single dictionary returned by an InfoExtractor.""" # Do nothing else if in simulate mode if self.params.get('simulate', False): - try: - self.verify_url(info_dict['url']) - except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err: - raise UnavailableFormatError + # Verify URL if it's an HTTP one + if info_dict['url'].startswith('http'): + try: + info_dict['url'] = self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8') + except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err: + raise UnavailableFormatError # Forced printings if self.params.get('forcetitle', False): - print info_dict['title'].encode(locale.getpreferredencoding()) + print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') if self.params.get('forceurl', False): - print info_dict['url'].encode(locale.getpreferredencoding()) + print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') return @@ -309,7 +397,7 @@ class FileDownloader(object): filename = self.params['outtmpl'] % template_dict except (ValueError, KeyError), err: self.trouble('ERROR: invalid output template or system charset: %s' % str(err)) - if self.params['nooverwrites'] and os.path.exists(filename): + if self.params.get('nooverwrites', False) and os.path.exists(filename): self.to_stderr(u'WARNING: file exists: %s; skipping' % filename) return @@ -320,7 +408,7 @@ class FileDownloader(object): return try: - success = self._do_download(filename, info_dict['url']) + success = self._do_download(filename, info_dict['url'].encode('utf-8')) except (OSError, IOError), err: raise UnavailableFormatError except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -372,21 +460,53 @@ class FileDownloader(object): if info is None: break + def _download_with_rtmpdump(self, filename, url): + self.report_destination(filename) + + # Check for rtmpdump first + try: + subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + except (OSError, IOError): + self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') + return False + + # Download using rtmpdump. rtmpdump returns exit code 2 when + # the connection was interrumpted and resuming appears to be + # possible. This is part of rtmpdump's normal usage, AFAIK. + basic_args = ['rtmpdump', '-q', '-r', url, '-o', filename] + retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]) + while retval == 2 or retval == 1: + self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename), skip_eol=True) + time.sleep(2.0) # This seems to be needed + retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) + if retval == 0: + self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename)) + return True + else: + self.trouble('ERROR: rtmpdump exited with code %d' % retval) + return False + def _do_download(self, filename, url): - stream = None - open_mode = 'ab' + # Attempt to download using rtmpdump + if url.startswith('rtmp'): + return self._download_with_rtmpdump(filename, url) + stream = None + open_mode = 'wb' basic_request = urllib2.Request(url, None, std_headers) request = urllib2.Request(url, None, std_headers) - # Attempt to resume download with "continuedl" option + # Establish possible resume length if os.path.isfile(filename): resume_len = os.path.getsize(filename) else: resume_len = 0 - if self.params['continuedl'] and 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' # Establish connection try: @@ -394,12 +514,16 @@ class FileDownloader(object): except (urllib2.HTTPError, ), err: if err.code != 416: # 416 is 'Requested range not satisfiable' raise + # Unable to resume data = urllib2.urlopen(basic_request) content_length = data.info()['Content-Length'] + if content_length is not None and long(content_length) == resume_len: + # Because the file had already been fully downloaded self.report_file_already_downloaded(filename) return True else: + # Because the server didn't let us self.report_unable_to_resume() open_mode = 'wb' @@ -421,7 +545,7 @@ class FileDownloader(object): # Open file just in time if stream is None: try: - stream = open(filename, open_mode) + (stream, filename) = sanitize_open(filename, open_mode) self.report_destination(filename) except (OSError, IOError), err: self.trouble('ERROR: unable to open for writing: %s' % str(err)) @@ -507,46 +631,24 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?[\?#](?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _NETRC_MACHINE = 'youtube' - _available_formats = ['22', '35', '18', '5', '17', '13'] # listed in order of priority for -b flag + _available_formats = ['37', '22', '35', '18', '34', '5', '17', '13', None] # listed in order of priority for -b flag _video_extensions = { '13': '3gp', '17': 'mp4', '18': 'mp4', '22': 'mp4', + '37': 'mp4', } @staticmethod def suitable(url): return (re.match(YoutubeIE._VALID_URL, url) is not None) - @staticmethod - def htmlentity_transform(matchobj): - """Transforms an HTML entity to a Unicode character.""" - entity = matchobj.group(1) - - # Known non-numeric HTML entity - if entity in htmlentitydefs.name2codepoint: - return unichr(htmlentitydefs.name2codepoint[entity]) - - # Unicode character - mobj = re.match(ur'(?u)#(x?\d+)', entity) - if mobj is not None: - numstr = mobj.group(1) - if numstr.startswith(u'x'): - base = 16 - numstr = u'0%s' % numstr - else: - base = 10 - return unichr(long(numstr, base)) - - # Unknown entity in name, return its literal representation - return (u'&%s;' % entity) - def report_lang(self): """Report attempt to set language.""" self._downloader.to_stdout(u'[youtube] Setting language') @@ -567,14 +669,14 @@ class YoutubeIE(InfoExtractor): """Report attempt to extract video information.""" self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id) - def report_video_url(self, video_id, video_real_url): - """Report extracted video URL.""" - self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url)) - def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format)) + def report_rtmp_download(self): + """Indicate the download will use the RTMP protocol.""" + self._downloader.to_stdout(u'[youtube] RTMP download detected') + def _real_initialize(self): if self._downloader is None: return @@ -673,47 +775,47 @@ class YoutubeIE(InfoExtractor): try: self.report_video_info_webpage_download(video_id) video_info_webpage = urllib2.urlopen(request).read() + video_info = parse_qs(video_info_webpage) except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) return self.report_information_extraction(video_id) # "t" param - mobj = re.search(r'(?m)&token=([^&]+)(?:&|$)', video_info_webpage) - if mobj is None: + if 'token' not in video_info: # Attempt to see if YouTube has issued an error message - mobj = re.search(r'(?m)&reason=([^&]+)(?:&|$)', video_info_webpage) - if mobj is None: + if 'reason' not in video_info: self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason') stream = open('reportme-ydl-%s.dat' % time.time(), 'wb') stream.write(video_info_webpage) stream.close() else: - reason = urllib.unquote_plus(mobj.group(1)) + reason = urllib.unquote_plus(video_info['reason'][0]) self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8')) return - token = urllib.unquote(mobj.group(1)) + token = urllib.unquote_plus(video_info['token'][0]) video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token) if format_param is not None: video_real_url = '%s&fmt=%s' % (video_real_url, format_param) - self.report_video_url(video_id, video_real_url) + + # Check possible RTMP download + if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): + self.report_rtmp_download() + video_real_url = video_info['conn'][0] # uploader - mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage) - if mobj is None: + if 'author' not in video_info: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return - video_uploader = urllib.unquote(mobj.group(1)) + video_uploader = urllib.unquote_plus(video_info['author'][0]) # title - mobj = re.search(r'(?m)&title=([^&]+)(?:&|$)', video_info_webpage) - if mobj is None: + if 'title' not in video_info: self._downloader.trouble(u'ERROR: unable to extract video title') return - video_title = urllib.unquote(mobj.group(1)) + video_title = urllib.unquote_plus(video_info['title'][0]) video_title = video_title.decode('utf-8') - video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title) - video_title = video_title.replace(os.sep, u'%') + video_title = sanitize_title(video_title) # simplified title simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) @@ -853,8 +955,9 @@ class MetacafeIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract title') return video_title = mobj.group(1).decode('utf-8') + video_title = sanitize_title(video_title) - mobj = re.search(r'(?ms)
  • .*?Submitter:.*?(.*?)<', webpage) + mobj = re.search(r'(?ms)By:\s*(.+?)<', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return @@ -874,12 +977,266 @@ class MetacafeIE(InfoExtractor): self._downloader.trouble(u'ERROR: format not available for 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=([^\&]+).*' + + 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_stdout(u'[video.google] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_stdout(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) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + video_extension = 'mp4' + + # Retrieve video webpage to extract further information + request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % 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 + + # Extract URL, uploader, and title from webpage + self.report_extraction(video_id) + mobj = re.search(r"download_url:'([^']+)'", webpage) + if mobj is None: + video_extension = 'flv' + mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = urllib.unquote(mobj.group(1)) + mediaURL = mediaURL.replace('\\x3d', '\x3d') + mediaURL = mediaURL.replace('\\x26', '\x26') + + video_url = mediaURL + + 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 = sanitize_title(video_title) + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + + # Google Video doesn't show uploader nicknames? + video_uploader = 'NA' + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + }) + except UnavailableFormatError: + self._downloader.trouble(u'ERROR: format not available for video') + + +class PhotobucketIE(InfoExtractor): + """Information extractor for photobucket.com.""" + + _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + + 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_stdout(u'[photobucket] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_stdout(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) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + video_extension = 'flv' + + # Retrieve video webpage to extract further information + request = urllib2.Request(url) + 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 + + # Extract URL, uploader, and title from webpage + 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 + mediaURL = urllib.unquote(mobj.group(1)) + + video_url = mediaURL + + mobj = re.search(r'(.*) video by (.*) - Photobucket', 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 = sanitize_title(video_title) + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + + video_uploader = mobj.group(2).decode('utf-8') + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader, + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + }) + except UnavailableFormatError: + self._downloader.trouble(u'ERROR: format not available for video') + + +class GenericIE(InfoExtractor): + """Generic last-resort information extractor.""" + + 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_stdout(u'WARNING: Falling back on generic information extractor.') + self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id) + + def _real_initialize(self): + return + + def _real_extract(self, url): + video_id = url.split('/')[-1] + request = urllib2.Request(url) + 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 + except ValueError, err: + # since this is the last-resort InfoExtractor, if + # this error is thrown, it'll be thrown here + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # Start with something easy: JW Player in SWFObject + mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) + if mobj is None: + # Broaden the search a little bit + mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # It's possible that one of the regexes + # matched, but returned an empty group: + if mobj.group(1) is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_url = urllib.unquote(mobj.group(1)) + 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] + + # it's tempting to parse this further, but you would + # have to take into account all the variations like + # Video Title - Site Name + # Site Name | Video Title + # Video Title - Tagline | Site Name + # and so on and so forth; it's just not practical + 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 = sanitize_title(video_title) + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + + # video uploader is domain name + mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_uploader = mobj.group(1).decode('utf-8') + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader, + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension.decode('utf-8'), + }) + except UnavailableFormatError: + self._downloader.trouble(u'ERROR: format not available for video') + + class YoutubeSearchIE(InfoExtractor): """Information Extractor for YouTube search queries.""" _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+' _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en' _VIDEO_INDICATOR = r'href="/watch\?v=.+?"' - _MORE_PAGES_INDICATOR = r'>Next' + _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' _youtube_ie = None _max_youtube_results = 1000 @@ -893,6 +1250,7 @@ class YoutubeSearchIE(InfoExtractor): def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" + query = query.decode(preferredencoding()) self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) def _real_initialize(self): @@ -906,6 +1264,7 @@ class YoutubeSearchIE(InfoExtractor): prefix, query = query.split(':') prefix = prefix[8:] + query = query.encode('utf-8') if prefix == '': self._download_n_results(query, 1) return @@ -956,7 +1315,7 @@ class YoutubeSearchIE(InfoExtractor): self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return - if self._MORE_PAGES_INDICATOR not in page: + if re.search(self._MORE_PAGES_INDICATOR, page) is None: for id in video_ids: self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return @@ -966,7 +1325,7 @@ class YoutubeSearchIE(InfoExtractor): class YoutubePlaylistIE(InfoExtractor): """Information Extractor for YouTube playlists.""" - _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)' + _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:view_play_list|my_playlists)\?.*?p=([^&]+).*' _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s' @@ -1023,6 +1382,61 @@ 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/(.*)' + _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' + _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this. + _youtube_ie = None + + 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): + """Report attempt to download user page.""" + self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username)) + + def _real_initialize(self): + self._youtube_ie.initialize() + + def _real_extract(self, url): + # Extract username + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + # Download user page + username = mobj.group(1) + video_ids = [] + pagenum = 1 + + 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 + + # 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) + + for id in video_ids: + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) + return + class PostProcessor(object): """Post Processor class. @@ -1076,6 +1490,22 @@ if __name__ == '__main__': 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_stdout('Updating to latest stable version...') + latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION' + latest_version = urllib.urlopen(latest_url).read().strip() + prog_url = 'http://bitbucket.org/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_stdout('Updated to version %s' % latest_version) + # General configuration urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor())) @@ -1084,7 +1514,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2009.06.29', + version='2010.02.13', conflict_handler='resolve', ) @@ -1092,6 +1522,8 @@ if __name__ == '__main__': 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', @@ -1144,7 +1576,7 @@ if __name__ == '__main__': parser.add_option_group(filesystem) (opts, args) = parser.parse_args() - + # Batch file verification batchurls = [] if opts.batchfile is not None: @@ -1157,8 +1589,6 @@ if __name__ == '__main__': all_urls = batchurls + args # Conflicting, missing and erroneous options - if len(all_urls) < 1: - parser.error(u'you must provide at least one URL') if opts.usenetrc and (opts.username is not None or opts.password is not None): parser.error(u'using .netrc conflicts with giving username/password') if opts.password is not None and opts.username is None: @@ -1179,7 +1609,11 @@ if __name__ == '__main__': youtube_ie = YoutubeIE() metacafe_ie = MetacafeIE(youtube_ie) youtube_pl_ie = YoutubePlaylistIE(youtube_ie) + youtube_user_ie = YoutubeUserIE(youtube_ie) youtube_search_ie = YoutubeSearchIE(youtube_ie) + google_ie = GoogleIE() + photobucket_ie = PhotobucketIE() + generic_ie = GenericIE() # File downloader fd = FileDownloader({ @@ -1191,7 +1625,7 @@ if __name__ == '__main__': 'forcetitle': opts.gettitle, 'simulate': (opts.simulate or opts.geturl or opts.gettitle), 'format': opts.format, - 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding())) + 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') or u'%(id)s.%(ext)s'), @@ -1202,8 +1636,26 @@ if __name__ == '__main__': }) 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(youtube_ie) + fd.add_info_extractor(google_ie) + fd.add_info_extractor(photobucket_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) sys.exit(retcode)