Python pinyin.get方法代码示例

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def process_item(self, item, spider):
        if spider.name not in ['meituan']:
            return item
        if self.filter_dic.get(item['restaurant_name']) == item['address']:
            print(item['restaurant_name'])
            print(item['address'])
            raise DropItem("Duplicate item found: %s" % item)
        else:
            self.filter_dic[item['restaurant_name']] = item['address']
            try:
                item['lng'], item['lat'] = gaode_to_baidu(float(item['lng']), float(item['lat']))
                item['province_code'] = pinyin.get(item['province'])
                item['city_code'] = pinyin.get(item['city'])
                item['region_code'] = pinyin.get(item['region'])
                item['area_code'] = pinyin.get(item['area'])
            except BaseException as e:
                print(e)
            return item 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def segment_lyric_convert_pinyin_mir1k():
    openCC = OpenCC('tw2s')
    folder_lyrics_mir1k = os.path.join(mir1k_root, 'Lyrics')
    filenames_lyrics_mir1k = list(set(get_filenames_in_folder(folder_lyrics_mir1k)))
    for fn in filenames_lyrics_mir1k:
        fn_txt = os.path.join(folder_lyrics_mir1k, fn+'.txt')
        try:
            list_line = read_mir1k_lyrics(fn_txt)
            line_simplified = openCC.convert(list_line[0])
            line_pinyin = pinyin.get(line_simplified, format='strip', delimiter=' ')
            line_char = ' '.join(fool.cut(line_simplified)[0])
            write_lyrics_one_line(filename=os.path.join(mir1k_root, 'annotation', fn + '_phrase_char.txt'),
                                  line=line_char)
            write_lyrics_one_line(filename=os.path.join(mir1k_root, 'annotation', fn + '_phrase_pinyin.txt'),
                                  line=line_pinyin)
        except UnicodeDecodeError:
            print(fn) 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def pinyin(value):
    import pinyin
    result = pinyin.get(value, delimiter=' ')

    patterns_replacements = (
        (r'\{.*( ).*\}', ''),
        (r' +', ' ',),
        (r'\( ', '(',),
        (r' \) ', ')'),
        (r'\[ ', '[',),
        (r' \] ', ']'),
    )
    for pattern, replacement in patterns_replacements:
        result = re.sub(pattern, replacement, result)

    return result 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def request(cls, url: str, data: Dict[str, Any], method: str = "POST") -> Dict[str, Any]:

        results = {}
        status = requests.codes.ok
        text = ""

        try:
            if method == "GET":
                resp = cls.session.get(url, params=data, timeout=20)
            else:
                resp = cls.session.post(url, data=data, timeout=20)
            results = resp.json()
            text = resp.text
            status = resp.status_code
        except Exception as e:
            results = {}
            logger.debug(e)

        if status != requests.codes.ok or not text:
            results = {}

        return results 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def test(model, step_num, loss):
    model.eval()

    text = "相对论直接和间接的催生了量子力学的诞生 也为研究微观世界的高速运动确立了全新的数学模型"
    text = pinyin.get(text, format="numerical", delimiter=" ")
    sequence = np.array(text_to_sequence(text))[None, :]
    sequence = torch.autograd.Variable(torch.from_numpy(sequence)).cuda().long()
    with torch.no_grad():
        mel_outputs, mel_outputs_postnet, _, alignments = model.inference(sequence)
    plot_data((mel_outputs.float().data.cpu().numpy()[0],
               mel_outputs_postnet.float().data.cpu().numpy()[0],
               alignments.float().data.cpu().numpy()[0].T))
    title = 'step={0}, loss={1:.5f}'.format(step_num, loss)
    plt.title(title)
    filename = 'images/temp.jpg'
    plt.savefig(filename)
    img = cv.imread(filename)
    img = cv.cvtColor(img, cv.COLOR_BGR2RGB)
    img = img / 255.
    return img 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def parse_start_url(self, response):
        js = response.xpath('//script[@type="commment"]').extract()[0]
        data = re.search('\{[\s\S]*\}', js).group(0)
        data = json.loads(data)
        region_list = data['BizAreaList']
        category_list = data['CateList'][0]['subCategories']

        for category in category_list:
            if category['name'] == u'全部':
                continue
            for region in region_list:
                if region['name'] == u'全城':
                    continue
                for area in region['subareas']:
                    if area['name'] == u'全部':
                        continue
                    item = MeituanItem()
                    item['province'], item['city'] = [s.split('=')[1] for s in response.xpath('//meta[@name="location"]/@content').extract()[0].split(';')]
                    item['region'] = region['name'].strip()
                    item['area'] = area['name'].strip()
                    item['category'] = category['name'].strip()
                    url = 'http://i.meituan.com/%s?cid=%d&bid=%d&cateType=poi&stid=_b1'%(pinyin.get(item['city']), category['id'], area['id'])

                    yield Request(url,
                            method='GET',
                            meta={'item': item, 'url': url},
                            headers=headers,
                            cookies=None,
                            body=None,
                            priority=0,
                            errback=None,
                            encoding=response.encoding,
                            callback=self.parse_category_area) 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def prepare_corpus(input_files):
	sentences = []
	cnt = 0
	for input_file in input_files:
		with tf.gfile.GFile(input_file, "r") as reader:
			while True:
				line = reader.readline()
				
				if not line:
					break
				line = line.strip().split()
				line_pinyin = []
				
				for word in line:
					char_cn = ch_pattern.findall(word)
					if len(char_cn) >= 1:
						line_pinyin.extend(pinyin.get(item, format="strip", delimiter=" "))
					else:
						if len(word) >= 1:
							line_pinyin.extend(word.split())
				if cnt <= 10:
					print(line, line_pinyin)
				cnt += 1

				# Empty lines are used as document delimiters
				if not line:
					# all_documents.append([])
					continue
				sentences.append(line_pinyin)
	return sentences 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def pinyin():
    parser = argparse.ArgumentParser()
    parser.add_argument("chars", help="Input chinese words")
    args = parser.parse_args()

    if not args.chars:
        parser.print_help()
        return

    print(get(u(args.chars))) 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def BLOBParser_human(blob):
    # http://mac-alias.readthedocs.io/en/latest/bookmark_fmt.html
    try:
        b = Bookmark.from_bytes(blob)
        return "/" + u"/".join(b.get(0x1004, default=None))
    except Exception as e:
        print(e)


# for 10.13 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def convert2Pinyin(filename):
    # convert "你好" to " ni hao "
    def c2p(matchObj):
        return " " + pinyin.get(matchObj.group(), format="strip", delimiter=" ") + " "
    # replace chinese character with pinyin
    return re.sub(ur'[\u4e00-\u9fff]+', c2p, filename) 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def segmentation_conversion_helper(fn, list_line, sub_folder, phrase_syllable="phrase"):
    list_line_char = [[line[0], line[1], ' '.join(fool.cut(line[2])[0])] for line in list_line if
                      len(line[2].replace(" ", "")) > 0]
    list_line_pinyin = [[line[0], line[1], pinyin.get(line[2], format='strip', delimiter=' ')] for line in list_line if
                        len(line[2].replace(" ", "")) > 0]
    write_line(filename=os.path.join(mandarin_kugou_root, sub_folder, fn + '_' + phrase_syllable + '_char.txt'),
               list_line=list_line_char)
    write_line(filename=os.path.join(mandarin_kugou_root, sub_folder, fn + '_' + phrase_syllable + '_pinyin.txt'),
               list_line=list_line_pinyin) 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def pinyinfy(name: str) -> str:
    """
    Returns the pinyin of the input name.

    Args:
        name (str): Input name string

    Returns:
        str: Pinyin or english of the input name

    """
    return pinyin.get(name, delimiter='', format='strip').lower() 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def get_lyric(idx) -> str:
    row_data = {"csrf_token": "", "id": idx, "lv": -1, "tv": -1}
    data = NeteaseRequest.encrypted_request(row_data)
    return NeteaseRequest.request(url="https://music.163.com/weapi/song/lyric", method="POST", data=data).get("lrc", {}).get("lyric", "") 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def save_checkpoint(epoch, epochs_since_improvement, model, optimizer, loss, is_best):
    state = {'epoch': epoch,
             'epochs_since_improvement': epochs_since_improvement,
             'loss': loss,
             'model': model,
             'optimizer': optimizer}

    filename = 'checkpoint.tar'
    torch.save(state, filename)
    # If this checkpoint is the best so far, store a copy so it doesn't get overwritten by a worse checkpoint
    if is_best:
        torch.save(state, 'BEST_checkpoint.tar') 

# 需要导入模块: import pinyin [as 别名]
# 或者: from pinyin import get [as 别名]
def parse_start_url(self, response):
        city_cnt = 0
        big_city_list = response.xpath('//ul[@id="divArea"]/li[1]/div/a/strong/text()').extract()
        big_city_code_list = response.xpath('//ul[@id="divArea"]/li[1]/div/a/@href').extract()
        for index, city in enumerate(big_city_list):
            item = DazhongdianpingItem()
            item['province'] = ''
            item['province_code'] = ''
            item['city_code'] = big_city_code_list[index]
            item['city'] = city
            url = 'http://www.dianping.com/' + item['city_code'].strip('/') + '/food'

            city_cnt += 1
            print('大城市数量:\t'+str(city_cnt))
            yield Request(url,
                    method='GET',
                    meta={'item': item},
                    headers=headers,
                    cookies=None,
                    body=None,
                    priority=0,
                    errback=None,
                    encoding=response.encoding,
                    callback=self.parse_city)

        city_cnt = 0
        province_list = response.xpath('//li[@class="root"]//dl[@class="terms"]').extract()
        for province in province_list:
            province = Selector(text=province)
            city_list = province.xpath('//strong/text()').extract()
            city_code_list = province.xpath('//a/@href').extract()
            for index, city in enumerate(city_list):
                item = DazhongdianpingItem()
                item['province'] = province.xpath('//dt/text()').extract()[0]
                item['province_code'] = pinyin.get(item['province']).strip()
                item['city'] = city.strip()
                item['city_code'] = city_code_list[index].strip('\r\n\t/ ')
                url = 'http://www.dianping.com/' + item['city_code'].strip('/') + '/food'

                city_cnt += 1
                print('小城市数量:\t'+str(city_cnt))
                yield Request(url,
                        method='GET',
                        meta={'item': item},
                        headers=headers,
                        cookies=None,
                        body=None,
                        priority=0,
                        errback=None,
                        encoding=response.encoding,
                        callback=self.parse_city)