X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_ph_htmlparser.py;h=05ad6584d47ec37f67ae5883181fdc6de5328880;hb=9faa13f6f8199790cf01533e857c593520559649;hp=45e89f5119817787b0b926c7f43627a7dc22e7dd;hpb=c88cb7a75e7caf1d67466cfa107981d95115fa0c;p=bookmarks_db.git diff --git a/parse_html/bkmk_ph_htmlparser.py b/parse_html/bkmk_ph_htmlparser.py index 45e89f5..05ad658 100644 --- a/parse_html/bkmk_ph_htmlparser.py +++ b/parse_html/bkmk_ph_htmlparser.py @@ -5,7 +5,7 @@ This file is a part of Bookmarks database and Internet robot. """ __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 1997-2017 PhiloSoft Design" +__copyright__ = "Copyright (C) 1997-2023 PhiloSoft Design" __license__ = "GNU GPL" __all__ = ['parse_html'] @@ -49,8 +49,9 @@ class HTMLParser(_HTMLParser): try: # extract charset from "text/html; foo; charset=UTF-8, bar; baz;" self.charset = content.lower().split('charset=')[1].split(';')[0].split(',')[0] - self.meta_charset = 1 # Remember that the charset was retrieved from - # META tag, not from the Content-Type header + # Remember that the charset was retrieved from + # META tag, not from the Content-Type header + self.meta_charset = 1 except IndexError: pass @@ -61,7 +62,7 @@ class HTMLParser(_HTMLParser): self.accumulator = '' def end_title(self): - if not self.title: # use only the first title + if not self.title: # use only the first title self.title = self.accumulator def do_link(self, attrs):