Merge branch 'main' into arknights

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nonebot-hk-reporter"
-version = "0.2.1"
+version = "0.2.2"
 description = "Subscribe message from social medias"
 authors = ["felinae98 <felinae225@qq.com>"]
 license = "MIT"

src/plugins/hk_reporter/platform/bilibili.py

@@ -66,6 +66,7 @@ class Bilibili(Platform):
     async def parse(self, raw_post: RawPost) -> Post:
         card_content = json.loads(raw_post['card'])
         post_type = self.get_category(raw_post)
+        target_name = raw_post['desc']['user_profile']['info']['uname']
         if post_type == 1:
             # 一般动态
             text = card_content['item']['description']
@@ -88,5 +89,5 @@ class Bilibili(Platform):
             pic = []
         else:
             raise CategoryNotSupport(post_type)
-        return Post('bilibili', text, url, pic)
+        return Post('bilibili', text=text, url=url, pics=pic, target_name=target_name)
 

src/plugins/hk_reporter/platform/rss.py

@@ -38,4 +38,4 @@ class Rss(Platform):
         soup = bs(raw_post.description, 'html.parser')
         text = soup.text
         pics = list(map(lambda x: x.attrs['src'], soup('img')))
-        return Post('rss', text, raw_post.link, pics)
+        return Post('rss', text=text, url=raw_post.link, pics=pics)

src/plugins/hk_reporter/platform/weibo.py

@@ -1,6 +1,7 @@
 from collections import defaultdict
 from datetime import datetime
 import json
+import re
 import time
 from typing import Any, Optional
 
@@ -64,11 +65,20 @@ class Weibo(Platform):
             return Category(2)
         else:
             return Category(3)
- 
+
+    def _get_text(self, raw_text: str) -> str:
+        text = raw_text.replace('<br />', '\n')
+        return bs(text).text
+
     async def parse(self, raw_post: RawPost) -> Post:
         info = raw_post['mblog']
-        parsed_text = bs(info['text'], 'html.parser').text
+        if info['isLongText'] or info['pic_num'] > 9:
+            async with httpx.AsyncClient() as client:
+                res = await client.get('https://m.weibo.cn/detail/{}'.format(info['mid']))
+            full_json_text = re.search(r'"status": ([\s\S]+),\s+"hotScheme"', res.text).group(1)
+            info = json.loads(full_json_text)
+        parsed_text = self._get_text(info['text'])
         pic_urls = [img['large']['url'] for img in info.get('pics', [])]
         detail_url = 'https://weibo.com/{}/{}'.format(info['user']['id'], info['bid'])
         # return parsed_text, detail_url, pic_urls
-        return Post('weibo', parsed_text, detail_url, pic_urls)
+        return Post('weibo', text=parsed_text, url=detail_url, pics=pic_urls, target_name=info['user']['screen_name'])

src/plugins/hk_reporter/post.py

@@ -1,4 +1,5 @@
 from dataclasses import dataclass, field
+from typing import Optional
 from .plugin_config import plugin_config
 from .utils import parse_text
 
@@ -8,23 +9,33 @@ class Post:
     target_type: str
     text: str
     url: str
+    target_name: Optional[str] = None
+    show_text: bool = True
     pics: list[str] = field(default_factory=list)
 
     async def generate_messages(self):
-        if plugin_config.hk_reporter_use_pic:
-            text_msg = '来源: {}\n{}'.format(self.target_type, self.text)
-            if self.target_type == 'rss':
-                res = [await parse_text(text_msg)]
-            elif self.target_type == 'arknights':
-                res = []
+        msgs = []
+        if self.show_text:
+            text = '来源: {}'.format(self.target_type)
+            if self.target_name:
+                text += '\n{}'.format(self.target_name)
+            if self.text:
+                text += '\n{}'.format(self.text)
+            if plugin_config.hk_reporter_use_pic:
+                msgs.append(await parse_text(text))
+                if not self.target_type == 'rss':
+                    msgs.append(self.url)
             else:
-                res = [await parse_text(text_msg), self.url]
-        else:
-            first_msg = '来源: {}\n{}\n详情：{}'.format(self.target_type, self.text, self.url)
-            res = [first_msg]
+                text += '详情: {}'.format(self.url)
+                msgs.append(text)
         for pic in self.pics:
-            res.append("[CQ:image,file={url}]".format(url=pic))
-        return res
+            msgs.append("[CQ:image,file={url}]".format(url=pic))
+        return msgs
 
     def __str__(self):
-        return 'type: {}\ntext: {}\nurl: {}\npic: {}'.format(self.target_type, self.text[:50], self.url, ','.join(map(lambda x: 'b64img' if x.startswith('base64') else x, self.pics)))
+        return 'type: {}\ntext: {}\nurl: {}\npic: {}'.format(
+                self.target_type,
+                self.text,
+                self.url,
+                ', '.join(map(lambda x: 'b64img' if x.startswith('base64') else x, self.pics))
+            )