From: Oleg Broytman <phd@phdru.name>
Date: Fri, 13 Aug 2010 13:38:06 +0000 (+0000)
Subject: Moved lxml-based parser after BeautifulSoup - it doesn't accept charset.
X-Git-Tag: v4.5.3~95
X-Git-Url: https://git.phdru.name/?a=commitdiff_plain;h=8bc6571d6eaba3a72ecb543c0fe9b95dbea31634;p=bookmarks_db.git

Moved lxml-based parser after BeautifulSoup - it doesn't accept charset.


git-svn-id: file:///home/phd/archive/SVN/bookmarks_db/trunk@281 fdd5c36f-1aea-0310-aeeb-c58d7e2b6c23
---

diff --git a/Robots/parse_html.py b/Robots/parse_html.py
index 5e8061c..228a3ce 100755
--- a/Robots/parse_html.py
+++ b/Robots/parse_html.py
@@ -13,19 +13,19 @@ DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic
 parsers = []
 
 try:
-   from parse_html_lxml import parse_html
+   import parse_html_beautifulsoup
+   parse_html_beautifulsoup.DEFAULT_CHARSET = DEFAULT_CHARSET
 except ImportError:
    pass
 else:
-    parsers.append(parse_html)
+   parsers.append(parse_html_beautifulsoup.parse_html)
 
 try:
-   import parse_html_beautifulsoup
-   parse_html_beautifulsoup.DEFAULT_CHARSET = DEFAULT_CHARSET
+   from parse_html_lxml import parse_html
 except ImportError:
    pass
 else:
-   parsers.append(parse_html_beautifulsoup.parse_html)
+    parsers.append(parse_html)
 
 try:
    from parse_html_htmlparser import parse_html