X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_ph_beautifulsoup.py;h=1479f034255c4c5b4e53b872ea5b0c157b4a74c6;hb=c2ea4e82718b903aa123dd77490f36657383b0ca;hp=99cff4f68f0ceebbe3ba0a18c3f035eb80f4c15f;hpb=4ced9933b914c5569cba1c29c9ae21c3de123acc;p=bookmarks_db.git diff --git a/parse_html/bkmk_ph_beautifulsoup.py b/parse_html/bkmk_ph_beautifulsoup.py index 99cff4f..1479f03 100644 --- a/parse_html/bkmk_ph_beautifulsoup.py +++ b/parse_html/bkmk_ph_beautifulsoup.py @@ -16,7 +16,7 @@ from sgmllib import SGMLParser, SGMLParseError from BeautifulSoup import BeautifulSoup, CData from .bkmk_ph_util import HTMLParser -DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic +DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic # http://groups.google.com/group/beautifulsoup/browse_thread/thread/69093cb0d3a3cf63 class BadDeclParser(BeautifulSoup): @@ -62,7 +62,7 @@ def parse_html(html_text, charset=None, log=None): return None _charset = root.originalEncoding - if _charset in ("ISO-8859-2", "windows-1252", "MacCyrillic"): # Replace default + if _charset in ("ISO-8859-2", "windows-1252", "MacCyrillic"): # Replace default _charset = DEFAULT_CHARSET root = _parse_html(html_text, _charset) if root is None: @@ -74,7 +74,7 @@ def parse_html(html_text, charset=None, log=None): head = html.head if head is None: - head = html # Some sites put TITLE in HTML without HEAD + head = html # Some sites put TITLE in HTML without HEAD title = head.title if (title is None) and (html is not head): @@ -104,7 +104,7 @@ def parse_html(html_text, charset=None, log=None): __charset = meta_content.lower().split('charset=')[1].split(';')[0] else: __charset = False - except IndexError: # No charset in the META Content-Type + except IndexError: # No charset in the META Content-Type meta_charset = False else: meta_charset = _charset == __charset