html_usage.py 文件源码

def load_names_data():
    fp = os.path.join(tempfile.gettempdir(), ZIP_NAME)
    if not os.path.exists(fp):
        r = requests.get(URL_NAMES)
        with open(fp, 'wb') as f:
            f.write(r.content)

    post = collections.OrderedDict()
    with zipfile.ZipFile(fp) as zf:
        # get ZipInfo instances
        for zi in sorted(zf.infolist(), key=lambda zi: zi.filename):
            fn = zi.filename
            if fn.startswith('yob'):
                year = int(fn[3:7])
                df = pd.read_csv(
                    zf.open(zi),
                    header=None,
                    names=('name', 'gender', 'count'))
                df['year'] = year
                post[year] = df

        df = pd.concat(post.values())
        df.set_index('name', inplace=True, drop=True)
        return df