X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_ph_beautifulsoup4.py;h=b7f60ffd12033f787d6c4e6973324456948dce68;hb=c2ea4e82718b903aa123dd77490f36657383b0ca;hp=10e06a97cd4fc4e25689cd3a92040878a5f2775a;hpb=4ced9933b914c5569cba1c29c9ae21c3de123acc;p=bookmarks_db.git diff --git a/parse_html/bkmk_ph_beautifulsoup4.py b/parse_html/bkmk_ph_beautifulsoup4.py index 10e06a9..b7f60ff 100644 --- a/parse_html/bkmk_ph_beautifulsoup4.py +++ b/parse_html/bkmk_ph_beautifulsoup4.py @@ -5,7 +5,7 @@ This file is a part of Bookmarks database and Internet robot. """ __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2017 PhiloSoft Design" +__copyright__ = "Copyright (C) 2017-2023 PhiloSoft Design" __license__ = "GNU GPL" __all__ = ['parse_html'] @@ -16,7 +16,7 @@ from bs4 import BeautifulSoup from .bkmk_ph_util import HTMLParser universal_charset = "utf-8" -DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic +DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic def _parse_html(html_text, charset): try: @@ -36,7 +36,7 @@ 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): @@ -66,7 +66,7 @@ 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