Python urllib.urlcleanup函数代码示例

 def getfiles(self, *files):
     """Download Rebase files."""
     for file in self.update(*files):
         print('copying %s' % file)
         fn = os.path.basename(file)
         # filename = os.path.join(Rebase, fn)
         filename = os.path.join(os.getcwd(), fn)
         print('to %s' % filename)
         try:
             self.retrieve(file, filename)
             # The following line is a workaround for an urllib bug in
             # Python 2.7.11 - 2.7.xx (?). It does not seem to work on
             # Python 3.xx. Try to remove the line in new Python versions.
             urlcleanup()
         except IOError as e:
             print(e)
             print('This error is probably due to a non-solved ftp bug in '
                   'recent Python versions. Please download the emboss '
                   'files manually from http://rebase.neb.com/rebase/'
                   'rebase.f37.html and then run ranacompiler.py. Find '
                   'more details in the Restriction manual.')
             self.close()
             return
     self.close()
     return

def mainProcess(linkList=[]):
    print 'Process {0} is starting to work!'.format(os.getpid())
    st=time.time()
    p=PAIRSeg()
    p._PAIRSeg__ResetSQLVariables()
    log=LogProcessor.LogProcess()
    fNum=os.path.basename(linkList[0]).split('.')[0]
    lNum=os.path.basename(linkList[len(linkList)-1]).split('.')[0]
    numRange=fNum+'-'+lNum
    for link in linkList:
        fileName=os.path.basename(link)
        filePath=p.dirPath+'/'+fileName
        try:
            urllib.urlretrieve(link,filePath)
            #print '[Downloaded .zip File: [{0}]'.format(fileName)
            urllib.urlcleanup()
            zipOrNot=zipfile.is_zipfile(filePath)
            if(zipOrNot==True):
                p.ExtractTSV(filePath)
                os.remove(filePath) # save space on sofus
            elif(zipOrNot==False):
                os.remove(filePath)
            log.write(log.logPath_PAIR,fileName+'\t'+link+'\t'+'PAIR\tProcessed')
        except:
            print 'ERROR: time out. {fileName}'.format(fileName)
            log.write(log.logPath_PAIR_Error,fileName+'\t'+link+'\t'+'PAIR\tProcessed')
    p.writeCSV(numRange)
    print 'Processed range:{range}'.format(range=numRange)
    print '[Process {0} is finished. Populated {1} links. Time:{2}]'.format(os.getpid(),len(linkList),time.time()-st)

def image_analyzer(url, string, depth, k):
    
    try:
        example_image = download_image(url)
    except (HTTPError,IOError), e:
        urllib.urlcleanup()    
        sys.exit('Unable to download %s.\n' % url + 'Error: %s.\n' % e)

def aursearch(keywords, totalnum):
	search = "http://aur.archlinux.org/packages.php?O=0&L=0&C=0&K=" + keywords.replace(" ", "+") + "&SeB=nd&SB=n&SO=a&PP=25&do_Search=Go"
	urllib.urlretrieve(search, "aur.tmp")
	block = ""
	num = 0
	sect = 0
	packages = ""
	aur = open("aur.tmp")
	for aurl in aur:
		if num <= totalnum:
			if aurl[:20] == "  <td class='data1'>" or aurl[:20] == "  <td class='data2'>": print "aursearch", aurl
			
			if aurl[:20] == "  <td class='data1'>" and not block == "data1":
				sect = 0
				block = "data1"
			elif aurl[:20] == "  <td class='data2'>" and not block == "data2":
				sect = 0
				block = "data2"
			elif aurl[:20] == "  <td class='data1'>" or aurl[:20] == "  <td class='data2'>":
				print aurl
				sect += 1
				if sect == 2:
					pacname = aurl.split("<span class='black'>")
					pacname = pacname[1].split("</span>")
					pacname = pacname[0]
					packages = packages + pacname
				elif sect == 4:
					pacdesc = aurl.split("<span class='blue'>")
					pacdesc = pacdesc[1].split("</span>")
					pacdesc = pacdesc[0]
					packages = packages + " - " + pacdesc + "\n"
					num += 1
	aur.close()
	urllib.urlcleanup()
	return packages

def download_file(url, destfile):
    """
     download_file: function for download from url to save as destfile
        @url the source file to download.
        @destfile the destination save file for local.
    """
    file_url = url

    try:
        print("--> Downloading file: %s" % file_url)
        filename, msg = urllib.urlretrieve(
                #'http://code.jquery.com/jquery-2.1.1.js',
                file_url,
                reporthook = reporthook)

        print ""
        #print "File:", filename
        print "Header:"
        print msg
        if os.path.exists(filename):
            if os.path.exists(destfile):
                now = currenttime()
                tmpfile = "%s.%s" % (destfile, now)
                shutil.move(destfile, tmpfile)
            shutil.move(filename, destfile)

        #print 'File exists before cleanup:', os.path.exists(filename)
    finally:
        urllib.urlcleanup()

def downloadImage( imageURL, subID ) :
    """Download images"""

    # image url
    image_url = 'http://bbs.sjtu.edu.cn' + imageURL

    # create the directory to store images
    # if not os.path.exists( './download' ) :
    try :
        os.makedirs( './download/' + subID )
    except OSError :
        pass
        #print "Failed to create directories"

     
    # get filename of image
    filename = 'download/' + subID + '/' + imageURL.split( '/' )[-1]

    # clear the cache that may have been built up
    # by previous calls to urlretrieve()
    urllib.urlcleanup()
     
    # retrieve the image
    try :
        urllib.urlretrieve( image_url, filename )
    except ContentTooShortError :
        print "The data available was less than that of expected"
        print "Downloading file %s was interrupted" \
                        % os.path.basename( filename )
    else :
        # get the size of file
        size = os.path.getsize( filename ) / 1024
        print ">>>File %s (%s Kb) was done..." % ( filename, size )

    def get_wallpgig(self):
        if not self.check_connection():
            return "No internet connection!"

        tags_from_file = self.filemanage.file_get_tags()
        query_from_file = self.filemanage.file_get_query()
        if (set(tags_from_file) == set(self.tags)) & (query_from_file == self.query):
            self.status.set_label("Loading urls...")
            urls = self.filemanage.file_get_urls()
            self.status.set_label("Urls loaded.")
        else:
            self.status.set_label("Downloading urls...")
            urls = self.download_urls()
            self.status.set_label("Urls downloaded.")

        random.shuffle(urls)

        try:
            url = urls[0]
            urllib.urlretrieve(url, tfile)
            urllib.urlcleanup()

            check = 1
        except IndexError:
            check = "No photos for this tags!"
        except urllib2.URLError:
            check = "No internet connection!"

        return check

 def run(self):
     try:
         urllib._urlopener = SmartFancyURLopener()
         urllib.urlretrieve(self.url, self.tmpfile, reporthook=self._hook)
         urllib.urlcleanup()
     except Abort: print 'Download Aborted'
     except:

	def populate_sidebar(self, branch = 'master', count = 50):
		self.commits = self.repo.commits(branch, max_count = count)
		for commit in self.commits:
			commit_time = time.strftime("%c", commit.authored_date)
			parts = commit.message.split('\n')
			if len(parts) > 1:
				text = "<b>%s ...</b>" % parts[0]
			else:
				text = "<b>%s</b>" % commit.message

			text += "\n<small>by %s on %s</small>" % (commit.author,
														commit_time)
			
			hashed = hashlib.md5(commit.author.email).hexdigest()
			image_path = "%s/grav_cache/%s.jpg" % (installdir, hashed)
			
			if not os.path.exists(image_path):
				gravatar_url = "http://www.gravatar.com/avatar.php?"			
				gravatar_url += urllib.urlencode({'gravatar_id':hashed, 
													'size':str(30)})
				urllib.urlretrieve(gravatar_url, image_path)
				urllib.urlcleanup()
				
			image = gtk.gdk.pixbuf_new_from_file(image_path)

			self.sidebar.add_item(None,	[text, image])

def download_version(version):

  chromium_file = 'chromium-%s.tar.xz' % version
  path = '%s%s' % (chromium_url, chromium_file)

  if (args.clean):
    remove_file_if_exists(chromium_file)

  # Let's make sure we haven't already downloaded it.
  if os.path.isfile("./%s" % chromium_file):
    print "%s already exists!" % chromium_file
  else:
    print "Downloading %s" % path
    # Perhaps look at using python-progressbar at some point?
    urllib.urlretrieve(path, chromium_file, reporthook=dlProgress)
    urllib.urlcleanup()
    print ""

  if (args.tests):
    chromium_testdata_file = 'chromium-%s-testdata.tar.xz' % version
    path = '%s%s' % (chromium_url, chromium_testdata_file)

    if (args.clean):
      remove_file_if_exists(chromium_testdata_file)

    # Let's make sure we haven't already downloaded it.
    if os.path.isfile("./%s" % chromium_testdata_file):
      print "%s already exists!" % chromium_testdata_file
    else:
      # Perhaps look at using python-progressbar at some point?
      print "Downloading %s" % path
      urllib.urlretrieve(path, chromium_testdata_file, reporthook=dlProgress)
      urllib.urlcleanup()
      print ""

 def oai_listIdentifiers(self, src="www.astros-test.bodleian.ox.ac.uk/sandbox", resumptionToken=None):
     self.ids_data_file = '/tmp/%s_ids_data_file'%unicode(uuid.uuid4())
     src_url = None
     if resumptionToken:
         src_url = "%s?verb=ListIdentifiers&resumptionToken=%s"%(src, resumptionToken)
     else:
         src_url = "%s?verb=ListIdentifiers&metadataPrefix=oai_dc"%src_
         for arg, val in self.args.iteritems():
             if val:
                 src_url = "%s&%s=%s"%(src_url, arg, val)
         if 'args' in src:
             src_url = "%s&%s"%(src_url,src['args'])
     tries = 1
     while tries < 11:
         urlretrieve(src_url, self.ids_data_file)
         if os.path.isfile(self.ids_data_file):
             self.logger.info("Downloaded identifiers for %s - %s"%(src, src_url))
             break
         self.logger.warn("Error retreiving identifiers for %s - %s (try # %d)"%(src, src_url, tries))
         tries += 1
     urlcleanup()
     tree = ET.ElementTree(file=self.ids_data_file)
     rt = tree.getroot()
     ids = rt.findall("%(ns)sListIdentifiers/%(ns)sheader/%(ns)sidentifier"%{'ns':self.oai_ns})
     for ID in ids:
         if resumptionToken and 'deletion' in resumptionToken:
             self.delete_identifiers.append(ID.text)
         else:
             self.identifiers.append(ID.text)
     rtoken = rt.findall("%(ns)sListIdentifiers/%(ns)sresumptionToken"%{'ns':self.oai_ns})
     os.remove(self.ids_data_file)
     if rtoken:
         self.oai_listIdentifiers(src, resumptionToken=rtoken[0].text)

 def iq_register(self, iq):
     """
     Register to a new VMCast.
     @type iq: xmpp.Protocol.Iq
     @param iq: the sender request IQ
     @rtype: xmpp.Protocol.Iq
     @return: a ready-to-send IQ containing the results
     """
     reply = iq.buildReply("result")
     url = iq.getTag("query").getTag("archipel").getAttr("url")
     try:
         if not url or url == "":
             raise Exception("IncorrectStanza", "Stanza must have url: %s" % str(iq))
         try:
             urllib.urlcleanup()
             f = urllib.urlopen(url)
         except:
             raise Exception("The given url doesn't exist. Can't register.")
         try:
             self.getFeed(f.read())
         except:
             raise Exception("The given url doesn't contains a valid VMCast feed. Can't register.")
         self.cursor.execute("INSERT INTO vmcastsources (url) VALUES ('%s')" % url)
         self.database_connection.commit()
         self.parseRSS()
         self.entity.push_change("vmcasting", "register")
         self.entity.shout("vmcast", "I'm now registred to vmcast %s as asked by %s" % (url, iq.getFrom()))
     except Exception as ex:
         reply = build_error_iq(self, ex, iq, ARCHIPEL_ERROR_CODE_VMCASTS_REGISTER)
     return reply

	def showInfo(self):
		if self.check == "true" and self.menulist:
			m_title = self["menulist"].getCurrent()[0][0]
			m_url = self["menulist"].getCurrent()[0][1]
			if m_url:
				#m_url = re.findall('(.*?)\.', m_url)
				#extra_imdb_convert = "._V1_SX320.jpg"
				#m_url = "http://ia.media-imdb.com/images/%s%s" % (m_url[0], extra_imdb_convert)
				print "EMC iMDB: Download Poster - %s" % m_url
				urllib._urlopener = AppURLopener()
				urllib.urlretrieve(m_url, self.path)
				urllib.urlcleanup()
				if os.path.exists(self.path):
					self.poster_resize(self.path, m_title)

					#ptr = LoadPixmap(self.path)
					#if ptr is None:
					#        ptr = LoadPixmap("/usr/lib/enigma2/python/Plugins/Extensions/EnhancedMovieCenter/img/no_poster.png")
					#        print "EMC iMDB: Load default NO Poster."
					#if ptr is not None:
					#        self["poster"].instance.setPixmap(ptr)
					#        print "EMC iMDB: Load Poster - %s" % m_title
				else:
					print "EMC iMDB: No url found for - %s" % m_title
			else:
				print "EMC iMDB: No url found for - %s" % m_title

def song_download():
       

        song = user_input('Enter the name of song: ')  
        
        try:
            query_string = encode({"search_query" : song})
            content = urlopen("http://www.youtube.com/results?" + query_string)
            
            if version == 3:
                ##I hate RE

                search_results = re.findall(r'href=\"\/watch\?v=(.{11})', content.read().decode())
                
            else:
                ##ok!! if its not going work! I'm gonna kill you!!!
                search_results = re.findall(r'href=\"\/watch\?v=(.{11})', content.read())
                ##finally(Thanks to git)
                
        except:
            print('Something happened!!')
            exit(1)

        # youtube2mp3 API
        downloadLinkOnly = 'http://www.youtubeinmp3.com/fetch/?video=' + 'http://www.youtube.com/watch?v=' + search_results[0]
        try:
            print('Downloading %s' % song)
            urllib.urlretrieve(downloadLinkOnly, filename='%s.mp3' % song)
            urllib.urlcleanup()  
        except:
            print('Error  %s' % song)
            exit(1)

 def fetch_preferred_team_overview(self):
   if not self.is_offday_for_preferred_team():
     urllib.urlcleanup()
     game = self.games[self.game_index_for_preferred_team()]
     game_overview = mlbgame.overview(game.game_id)
     debug.log("Preferred Team's Game Status: {}, {} {}".format(game_overview.status, game_overview.inning_state, game_overview.inning))
     return game_overview