X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_ph_beautifulsoup4.py;h=e1662ed9e84b9866fceef5f72c0744b35b870111;hb=22d567ee3a7eac29b4c83eb1344f7bae4ef0bdb1;hp=b7f60ffd12033f787d6c4e6973324456948dce68;hpb=c2ea4e82718b903aa123dd77490f36657383b0ca;p=bookmarks_db.git diff --git a/parse_html/bkmk_ph_beautifulsoup4.py b/parse_html/bkmk_ph_beautifulsoup4.py index b7f60ff..e1662ed 100644 --- a/parse_html/bkmk_ph_beautifulsoup4.py +++ b/parse_html/bkmk_ph_beautifulsoup4.py @@ -11,19 +11,20 @@ __license__ = "GNU GPL" __all__ = ['parse_html'] -import re from bs4 import BeautifulSoup from .bkmk_ph_util import HTMLParser universal_charset = "utf-8" DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic + def _parse_html(html_text, charset): try: return BeautifulSoup(html_text, from_encoding=charset) except TypeError: return None + def parse_html(html_text, charset=None, log=None): root = _parse_html(html_text, charset) if root is None: @@ -63,7 +64,8 @@ def parse_html(html_text, charset=None, log=None): try: meta_content = meta.get("content") if meta_content: - __charset = meta_content.lower().split('charset=')[1].split(';')[0] + __charset = meta_content.lower().split('charset=')[1].\ + split(';')[0] else: __charset = False except IndexError: # No charset in the META Content-Type @@ -103,17 +105,22 @@ def parse_html(html_text, charset=None, log=None): return None return HTMLParser(_charset, meta_charset, title, refresh, icon) + def _find_contenttype(Tag): return (Tag.name == "meta") and \ (Tag.get_attribute_list("http-equiv", '')[0].lower() == "content-type") + def _find_charset(Tag): return (Tag.name == "meta") and Tag.get("charset", '') + def _find_refresh(Tag): return (Tag.name == "meta") and \ (Tag.get_attribute_list("http-equiv", '')[0].lower() == "refresh") + def _find_icon(Tag): return (Tag.name == "link") and \ - (Tag.get_attribute_list("rel", '')[0].lower() in ('icon', 'shortcut icon')) + (Tag.get_attribute_list("rel", '')[0].lower() + in ('icon', 'shortcut icon'))