From c8cff9a3dd088cec58b4df16503e10e7198ddb25 Mon Sep 17 00:00:00 2001
From: miteruzo <miteruzo@naver.com>
Date: Sat, 7 Sep 2024 06:51:57 +0900
Subject: [PATCH] =?UTF-8?q?=E3=83=AA=E3=83=B3=E3=82=AF=E3=83=BB=E3=82=AB?=
 =?UTF-8?q?=E3=83=BC=E3=83=89=E3=81=A1=E3=82=87=E3=81=A3=E3=81=A8=E4=BF=AE?=
 =?UTF-8?q?=E6=AD=A3?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main.py | 38 +++++++++++++++++++++++++++++++++++---
 1 file changed, 35 insertions(+), 3 deletions(-)

diff --git a/main.py b/main.py
index d45a2af..04566e5 100644
--- a/main.py
+++ b/main.py
@@ -4,6 +4,7 @@ import time
 import sys
 
 from atproto import Client, models
+from bs4 import BeautifulSoup
 import requests
 
 from ai.talk import Talk
@@ -91,11 +92,14 @@ def main (
                         if e['contentId'] not in watched_videos]:
             watched_videos += [datum['contentId']]
 
+            uri = f"https://www.nicovideo.jp/watch/{ datum['contentId'] }"
+            (title, description, thumb) = get_embed_info (uri)
             embed_external = models.AppBskyEmbedExternal.Main (
                     external = models.AppBskyEmbedExternal.External (
-                        title       = datum['title'],
-                        description = datum['description'],
-                        uri         = f"https://www.nicovideo.jp/watch/{ datum['contentId'] }"))
+                        title       = title,
+                        description = description,
+                        thumb       = thumb,
+                        uri         = uri))
             client.post (Talk.main (f"""
 ニコニコに『{ datum['title'] }』という動画がアップされました。
 つけられたタグは「{ '」、「'.join (datum['tags']) }」です。
@@ -175,5 +179,33 @@ def get_nico_deerjika ():
     return data
 
 
+def get_embed_info (
+        url:    str
+) -> (str, str, str):
+    try:
+        res = requests.get (url, timeout = 60)
+    except Exception:
+        return ('', '', '')
+
+    if res.status_code != 200:
+        return ('', '', '')
+
+    soup = BeautifulSoup (res.text, 'html.parser')
+
+    tmp = soup.find ('title')
+    if tmp is not None:
+        title = tmp.text
+
+    tmp = soup.find ('meta', attrs = { 'name': 'description' })
+    if tmp is not None:
+        description = tmp.get ('content')
+
+    tmp = soup.find ('meta', attrs = { 'name': 'thumbnail' })
+    if tmp is not None:
+        thumbnail = tmp.get (' content')
+
+    return (title, description, thumbnail)
+
+
 if __name__ == '__main__':
     main (*sys.argv[1:])