{"blog_title":"u++\u306e\u5099\u5fd8\u9332","height":"190","provider_url":"https://hatena.blog","author_url":"https://blog.hatena.ne.jp/upura/","url":"https://upura.hatenablog.com/entry/2020/04/14/233246","author_name":"upura","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fupura.hatenablog.com%2Fentry%2F2020%2F04%2F14%2F233246\" title=\"\u8a00\u8a9e\u51e6\u7406100\u672c\u30ce\u30c3\u30af 2020\u300c23. \u30bb\u30af\u30b7\u30e7\u30f3\u69cb\u9020\u300d - u++\u306e\u5099\u5fd8\u9332\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","version":"1.0","blog_url":"https://upura.hatenablog.com/","provider_name":"Hatena Blog","categories":["\u81ea\u7136\u8a00\u8a9e\u51e6\u7406","python"],"image_url":null,"width":"100%","description":"\u554f\u984c\u6587 nlp100.github.io \u554f\u984c\u306e\u6982\u8981 \u6b63\u898f\u8868\u73fe\u3092\u7528\u3044\u3066\u3001\u30bb\u30af\u30b7\u30e7\u30f3\u306b\u8a72\u5f53\u3059\u308b\u7b87\u6240\u3092\u53d6\u308a\u51fa\u3057\u307e\u3059\u3002 import re import pandas as pd df = pd.read_json('ch03/jawiki-country.json.gz', lines=True) uk_text = df.query('title==\"\u30a4\u30ae\u30ea\u30b9\"')['text'].values[0] for section in re.findall(r'(=+)([^=]+)\\1\\n', uk_text): print(f'{section[1].strip()}\\t{len(section\u2026","type":"rich","title":"\u8a00\u8a9e\u51e6\u7406100\u672c\u30ce\u30c3\u30af 2020\u300c23. \u30bb\u30af\u30b7\u30e7\u30f3\u69cb\u9020\u300d","published":"2020-04-14 23:32:46"}