# ライブラリをimport from readability.readability import Document import urllib.request import html2text # 実行 url = "https://flatclub.jp/shinobiwriting/" html = urllib.request.urlopen(url).read() # 本文っぽい部分を抽出 article = Document(html).summary() # htmlからmarkdown形式に変換 text = html2text.html2text(article) # とりあえずコマンドラインに出力 print(text)
![Readabilityで本文っぽい文章を抽出 - Qiita](https://cdn-ak-scissors.b.st-hatena.com/image/square/f3033db632b77ab7ef8c4c1ba08f039921291a75/height=288;version=1;width=512/https%3A%2F%2Fqiita-user-contents.imgix.net%2Fhttps%253A%252F%252Fcdn.qiita.com%252Fassets%252Fpublic%252Farticle-ogp-background-412672c5f0600ab9a64263b751f1bc81.png%3Fixlib%3Drb-4.0.0%26w%3D1200%26mark64%3DaHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjAuMCZ3PTk3MiZoPTM3OCZ0eHQ9UmVhZGFiaWxpdHklRTMlODElQTclRTYlOUMlQUMlRTYlOTYlODclRTMlODElQTMlRTMlODElQkQlRTMlODElODQlRTYlOTYlODclRTclQUIlQTAlRTMlODIlOTIlRTYlOEElQkQlRTUlODclQkEmdHh0LWFsaWduPWxlZnQlMkN0b3AmdHh0LWNvbG9yPSUyMzIxMjEyMSZ0eHQtZm9udD1IaXJhZ2lubyUyMFNhbnMlMjBXNiZ0eHQtc2l6ZT01NiZzPTdkMjk0NmM1NTljNGZlMTFjZmQ1ODY2MGIxYTA5ZGQx%26mark-x%3D142%26mark-y%3D57%26blend64%3DaHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjAuMCZoPTc2Jnc9NzcwJnR4dD0lNDBzaGlubzAwJnR4dC1jb2xvcj0lMjMyMTIxMjEmdHh0LWZvbnQ9SGlyYWdpbm8lMjBTYW5zJTIwVzYmdHh0LXNpemU9MzYmdHh0LWFsaWduPWxlZnQlMkN0b3Amcz1iNWVkNTg1YTE3MTZiYWViYzI0MGYyZTMwMjdmNDc2MA%26blend-x%3D142%26blend-y%3D486%26blend-mode%3Dnormal%26s%3Dac8a002f035a5381b751577477c415ec)