2020-07-23 23:53:30

BookerTrans/__init__.py

@@ -10,7 +10,7 @@ from . import config
 __author__ = "ApacheCN"
 __email__ = "apachecn@163.com"
 __license__ = "SATA"
-__version__ = "2020.07.22"
+__version__ = "2020.07.23"
 
 RE_CODE = r'<(pre|code)[^>]*?>[\s\S]*?</\1>'
 RE_TAG = r'<[^>]*?>'
@@ -96,6 +96,9 @@ def trans_one(html):
     return html
 
 def trans_html(html):
+    # 预处理
+    html = re.sub(r'<\?xml[^>]*\?>', '', html)
+    html = re.sub(r'xmlns=".+?"', '', html)
     html = process_code(html)
     root = pq(html)
     

history.md

 # 历史记录
 
+v2020.7.23
+
++   解决 XHTML 的解析问题
+
 v2020.7.22
 
 +   将 BS4 改为 PyQuery 修复列表翻译问题

update.sh

+git add -A
+git commit -am "$(date "+%Y-%m-%d %H:%M:%S")"
+git push
\ No newline at end of file