Merge pull request #144 from NekoAria/2.0

修正对标题的处理逻辑，修正 ` 标签处理` 的逻辑
Quan666 · Jun 23, 2021 · d26ec74 · d26ec74
2 parents 2d0f327 + 8d17281
commit d26ec74
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 7 deletions.
diff --git a/.env b/.env
@@ -1,2 +1,2 @@
 ENVIRONMENT=prod
-VERSION='v2.2.5'
+VERSION='v2.2.6'
diff --git a/src/plugins/ELF_RSS2/RSS/rss_parsing.py b/src/plugins/ELF_RSS2/RSS/rss_parsing.py
@@ -151,6 +151,7 @@ async def start(rss: rss_class.Rss) -> None:
         title = item["title"]
         if not config.blockquote:
             title = re.sub(r" - 转发 .*", "", title)
+        title_msg = await handle_title(title=title)
         if not rss.only_title:
             # 先判断与正文相识度，避免标题正文一样，或者是标题为正文前N字等情况
             try:
@@ -162,16 +163,17 @@ async def start(rss: rss_class.Rss) -> None:
                 )
                 # 标题正文相似度
                 if rss.only_pic or similarity.ratio() <= 0.6:
-                    item_msg += await handle_title(title=title)
+                    item_msg += title_msg
                     if rss.translation:
                         item_msg += await handle_translation(content=title)
                 # 处理正文
                 item_msg += await handle_summary(summary=summary, rss=rss)
             except Exception as e:
                 logger.info(f"{rss.name} 没有正文内容！ E: {e}")
-                item_msg += await handle_title(title=title)
+                if title_msg not in item_msg:
+                    item_msg += title_msg
         else:
-            item_msg += await handle_title(title=title)
+            item_msg += title_msg
             if rss.translation:
                 item_msg += await handle_translation(content=title)
 
@@ -395,8 +397,6 @@ async def handle_title(title: str) -> str:
 
 # 处理正文，图片放后面
 async def handle_summary(summary: str, rss: rss_class.Rss) -> str:
-    # 去掉换行
-    # summary = re.sub('\n', '', summary)
     # 处理 summary 使其 HTML标签统一，方便处理
     try:
         summary_html = Pq(summary)
@@ -725,7 +725,7 @@ async def handle_html_tag(html) -> str:
 
     # <a> 标签处理
     for a in new_html("a").items():
-        a_str = re.search(r"<a.+?</a>", html_unescape(str(a)))[0]
+        a_str = re.search(r"<a.+?</a>", html_unescape(str(a)), flags=re.DOTALL)[0]
         if a.text() and str(a.text()) != a.attr("href"):
             rss_str = rss_str.replace(a_str, f" {a.text()}: {a.attr('href')}\n")
         else: