Esempio n. 1
0
def dump_text(url, out, fmt='%05d.txt', max_size=None, fid=1, max_fid=2500):
    utils.mkdir(out)
    fn = utils.join(out, fmt)

    if max_size is None:
        max_size = 4 * 1024 * 1024

    zm = ZhhanzMan()
    zc = ZhCalc()

    fout = utils.openfile(fn % fid, 'w')
    records = []

    for text in extract_text(url):
        prop = zc.calc(text)
        if zc.calc(text) > 1e-2:
            records.append(prop)
            fout.write(zm.s2t(text))

        ft = fout.tell()
        progress = (ft / max(ft, max_size)) * 100
        print(end=f'FID: {fid}/{max_fid}, File Size: {progress:5.2f}%\r')

        if fout.tell() >= max_size:
            fout.close()
            fid += 1
            if fid > max_fid:
                break
            fout = utils.openfile(fn % fid, 'w')

    fout.close()

    with open('statistic.pkl', 'wb') as pkl:
        import pickle as pk
        pk.dump(records, pkl)
Esempio n. 2
0
 def __init__(self, filename, hash_key, key_persist, value_persist,
              block_size):
     self.hash_key = hash_key
     self.value_file = openfile(filename + '.dictionary')
     self.key_file = openfile(filename + '.posting')
     self.key_persist = key_persist
     self.value_persist = value_persist
     self.block_size = block_size
     self.index_cache = {}
     self.insert_index_cache = {}
Esempio n. 3
0
    def __init__(self, order, filename, persist):
        self.order = order
        self.persist = persist

        self.file = openfile(filename)
        self.file.seek(0, 2)
        self.filesize = self.file.tell()
Esempio n. 4
0
def radiosobterurlstream(name,url):
    #GA("None","Radio - " + name)
    mensagemprogresso.create('TV Portuguesa','A carregar...')
    mensagemprogresso.update(0)
    if re.search('www.radios.pt',url):
        link=abrir_url(url)
        try:
            endereco=re.compile('<param name="url" value="(.+?)"').findall(link)[0]
        except:
            xbmc.executebuiltin("XBMC.Notification(Fightnight Music,Não é possível ouvir esta rádio.,'500000',)")
            return
        idradio=url.replace('http://www.radios.pt/portalradio/Sintonizador/?radio_id=','').replace('&scope=0','')
        thumbnail='http://www.radio.com.pt/APR.ROLI.WEB/Images/Logos/'+ idradio +'.gif'
    else:
        urlfinal='http://www.radioonline.com.pt/ajax/player.php?clear_s_name=' + url
        link= clean(abrir_url(urlfinal))
        try: player=re.compile('soundManager.createSound\({(.+?)autoLoad').findall(link)[0]
        except: player=False
        try:
            endereco=re.compile('url: "(.+?)"').findall(player)[0].replace(';','')
            if re.search('serverURL',player):
                rtmp=re.compile('serverURL: "(.+?)"').findall(player)[0]
                #rtmp=rtmp.replace('rtmp://195.23.102.206','rtmp://195.23.102.209') #tempfix
                rtmp=rtmp.replace(':1936','') #tempfix
                endereco=rtmp + ' playPath=' + endereco

        except:endereco=False
        if not endereco:
            try:endereco=re.compile('<param name="URL" value="(.+?)"').findall(link)[0]
            except:
                try: endereco=re.compile('<object data="(.+?)"').findall(link)[0]
                except: endereco=False

        if not endereco:
            xbmc.executebuiltin("XBMC.Notification(TV Portuguesa,Não é possível ouvir esta rádio.,'500000',)")
            mensagemprogresso.close()
            return

        try:thumbnail=re.compile('<img id="station-logo-player" src="(.+?)"').findall(link)[0]
        except: thumbnail=''
        if re.search('.asx',endereco):
            nomeasx='stream.asx'
            path = xbmc.translatePath(os.path.join(pastaperfil))
            lib=os.path.join(path, nomeasx)
            downloader(endereco,lib)
            texto= openfile(nomeasx)
            endereco = xbmc.PlayList(1)
            endereco.clear()
            streams=re.compile('<ref.+?"(.+?)"/>').findall(texto)
            for musica in streams:
                listitem = xbmcgui.ListItem(name, iconImage="DefaultVideo.png", thumbnailImage=thumbnail)
                listitem.setInfo("music", {"Title":name})
                endereco.add(musica,listitem)
        else: pass
    mensagemprogresso.close()
    listitem = xbmcgui.ListItem(name, iconImage="DefaultVideo.png", thumbnailImage=thumbnail)
    listitem.setInfo("music", {"Title":name})
    xbmc.Player().play(endereco,listitem)
 def updateChannelList(self):
     idx=-1
     listControl = self.getControl(6000)
     listControl.reset()
     canaison=openfile('canaison')
     canaison=canaison.replace('[','')
     lista=re.compile('B](.+?)/B]').findall(canaison)
     for nomecanal in lista:
         idx=int(idx+1)
         if idx==0: idxaux=' '
         else:
             idxaux='%4s.' % (idx)
             item = xbmcgui.ListItem(idxaux + ' %s' % (nomecanal), iconImage = '')
             item.setProperty('idx', str(idx))
             item.setProperty('chname', '[B]' + nomecanal + '[/B]')
             listControl.addItem(item)
Esempio n. 6
0
 def updateChannelList(self):
     idx = -1
     listControl = self.getControl(6000)
     listControl.reset()
     canaison = openfile('canaison')
     canaison = canaison.replace('[', '')
     lista = re.compile('B](.+?)/B]').findall(canaison)
     for nomecanal in lista:
         idx = int(idx + 1)
         if idx == 0: idxaux = ' '
         else:
             idxaux = '%4s.' % (idx)
             item = xbmcgui.ListItem(idxaux + ' %s' % (nomecanal),
                                     iconImage='')
             item.setProperty('idx', str(idx))
             item.setProperty('chname', '[B]' + nomecanal + '[/B]')
             listControl.addItem(item)
Esempio n. 7
0
entryMap = {}
for line in user_entries:
    entry = Entry(line, defaults)
    debug(1, entry)
    entryMap.setdefault(entry.pdbid, []).append(entry)
pdbids = entryMap.keys()
pdbids.sort()

for pdbid in pdbids:
    debug(1, pdbid)
    pdbfilename = goodpdbfilename(pdbid)
    if not pdbfilename:
        warning('Could not find PDB file for', pdbid)
        continue
    debug(2, pdbfilename)
    entries = entryMap[pdbid]

    infh = openfile(pdbfilename)
    for line in infh:
        rectype = line[:6].strip()
        if rectype in ['ENDMDL']:
            break
        if rectype not in ['ATOM', 'HETATM']:
            continue
        atom = PDBAtom(line)

        for entry in entries:
            if entry.accept(atom):
                OutputAtom(pdbid, atom)
Esempio n. 8
0
 def __init__(self, filename, persist):
     self.file = openfile(filename)
     self.persist = persist
Esempio n. 9
0
def radiosobterurlstream(name, url):
    #GA("None","Radio - " + name)
    mensagemprogresso.create('TV Portuguesa', 'A carregar...')
    mensagemprogresso.update(0)
    if re.search('www.radios.pt', url):
        link = abrir_url(url)
        try:
            endereco = re.compile('<param name="url" value="(.+?)"').findall(
                link)[0]
        except:
            xbmc.executebuiltin(
                "XBMC.Notification(Fightnight Music,Não é possível ouvir esta rádio.,'500000',)"
            )
            return
        idradio = url.replace(
            'http://www.radios.pt/portalradio/Sintonizador/?radio_id=',
            '').replace('&scope=0', '')
        thumbnail = 'http://www.radio.com.pt/APR.ROLI.WEB/Images/Logos/' + idradio + '.gif'
    else:
        urlfinal = 'http://www.radioonline.com.pt/ajax/player.php?clear_s_name=' + url
        link = clean(abrir_url(urlfinal))
        try:
            player = re.compile(
                'soundManager.createSound\({(.+?)autoLoad').findall(link)[0]
        except:
            player = False
        try:
            endereco = re.compile('url: "(.+?)"').findall(player)[0].replace(
                ';', '')
            if re.search('serverURL', player):
                rtmp = re.compile('serverURL: "(.+?)"').findall(player)[0]
                #rtmp=rtmp.replace('rtmp://195.23.102.206','rtmp://195.23.102.209') #tempfix
                rtmp = rtmp.replace(':1936', '')  #tempfix
                endereco = rtmp + ' playPath=' + endereco

        except:
            endereco = False
        if not endereco:
            try:
                endereco = re.compile(
                    '<param name="URL" value="(.+?)"').findall(link)[0]
            except:
                try:
                    endereco = re.compile('<object data="(.+?)"').findall(
                        link)[0]
                except:
                    endereco = False

        if not endereco:
            xbmc.executebuiltin(
                "XBMC.Notification(TV Portuguesa,Não é possível ouvir esta rádio.,'500000',)"
            )
            mensagemprogresso.close()
            return

        try:
            thumbnail = re.compile(
                '<img id="station-logo-player" src="(.+?)"').findall(link)[0]
        except:
            thumbnail = ''
        if re.search('.asx', endereco):
            nomeasx = 'stream.asx'
            path = xbmc.translatePath(os.path.join(pastaperfil))
            lib = os.path.join(path, nomeasx)
            downloader(endereco, lib)
            texto = openfile(nomeasx)
            endereco = xbmc.PlayList(1)
            endereco.clear()
            streams = re.compile('<ref.+?"(.+?)"/>').findall(texto)
            for musica in streams:
                listitem = xbmcgui.ListItem(name,
                                            iconImage="DefaultVideo.png",
                                            thumbnailImage=thumbnail)
                listitem.setInfo("music", {"Title": name})
                endereco.add(musica, listitem)
        else:
            pass
    mensagemprogresso.close()
    listitem = xbmcgui.ListItem(name,
                                iconImage="DefaultVideo.png",
                                thumbnailImage=thumbnail)
    listitem.setInfo("music", {"Title": name})
    xbmc.Player().play(endereco, listitem)
Esempio n. 10
0
 def _open(self):
     openfile(self._path)
     self._close()
Esempio n. 11
0
 def _open(self):
     openfile(self._path)
     self._close()