From 3b5cff7850d4a97b441de6476b15c61ea74126d5 Mon Sep 17 00:00:00 2001
From: cdhigh <cdhigh@users.noreply.github.com>
Date: Sat, 27 Apr 2024 08:30:00 -0300
Subject: [PATCH] disable content embedded feature to avoid feedparser bug.

---
 application/lib/calibre/web/feeds/news.py | 2 +-
 application/lib/recipe_helper.py          | 7 ++++++-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/application/lib/calibre/web/feeds/news.py b/application/lib/calibre/web/feeds/news.py
index a6d33f8d..15edaa5d 100644
--- a/application/lib/calibre/web/feeds/news.py
+++ b/application/lib/calibre/web/feeds/news.py
@@ -2232,7 +2232,7 @@ def preprocess_raw_html(self, raw_html, url):
             self.remove_tags_from_rules(soup, rules)
             
         #提取失败，尝试自动提取
-        if len(newBody.get_text(strip=True)) < 100:
+        if len(newBody.get_text(strip=True)) < 50:
             self.log.warning(f'Failed to extract content using content_extract_rules, try readability algorithm: {url}')
             try:
                 raw_html = self.extract_readable_article(raw_html, url)
diff --git a/application/lib/recipe_helper.py b/application/lib/recipe_helper.py
index f5180c26..8af89742 100644
--- a/application/lib/recipe_helper.py
+++ b/application/lib/recipe_helper.py
@@ -13,7 +13,7 @@ def py3_repr(x):
 
 #根据输入的一些信息，自动创建一个recipe的源码
 def GenerateRecipeSource(title, feeds, user, isfulltext=False, language=None, max_articles=30, 
-    cover_url=None, base='AutomaticNewsRecipe'):
+    cover_url=None, base='BasicNewsRecipe'):
     className = f'UserRecipe{int(time.time())}'
     title = py3_repr(str(title).strip() or className)
     indent = ' ' * 8
@@ -30,6 +30,10 @@ def GenerateRecipeSource(title, feeds, user, isfulltext=False, language=None, ma
     desc = 'News from {}'.format(', '.join(feedTitles)) if feedTitles else 'Deliver from KindleEar'
     desc = desc[:100]
     oldest_article = user.book_cfg('oldest_article')
+    #至少到feedparser 6.0.11为止，其提取xml内的内容有bug，经常提取不到，在他修复之前，我们先暂停全文rss功能
+    #全部都当非全文rss使用
+    isfulltext = False
+    auto_cleanup = 'False' if isfulltext else 'True'
     isfulltext = 'True' if isfulltext else 'None'
     language = language or user.book_cfg('language')
     timefmt = user.book_cfg('time_fmt')
@@ -45,6 +49,7 @@ class {className}({base}):
         max_articles_per_feed = {max_articles}
         oldest_article = {oldest_article}
         use_embedded_content  = {isfulltext}
+        auto_cleanup          = {auto_cleanup}
         timefmt               = '{timefmt}'
         cover_url             = {cover_url}
         {feeds}''')