Fix(Robot): Stop splitting and un-splitting URLs

[bookmarks_db.git] / parse_html / bkmk_ph_html5.py

diff --git a/parse_html/bkmk_ph_html5.py b/parse_html/bkmk_ph_html5.py
deleted file mode 100644 (file)
index 53109be..0000000
--- a/parse_html/bkmk_ph_html5.py
+++ /dev/null
@@ -1,103 +0,0 @@
-"""HTML Parser using html5
-
-This file is a part of Bookmarks database and Internet robot.
-"""
-
-__author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 2010-2013 PhiloSoft Design"
-__license__ = "GNU GPL"
-
-__all__ = ['parse_html']
-
-
-from html5lib import HTMLParser as HTML5Parser
-from .bkmk_ph_util import HTMLParser
-
-
-def parse_html(filename, charset=None, log=None):
-    parser = HTML5Parser()
-    fp = open(filename)
-    parser._parse(fp, encoding=charset, parseMeta=bool(charset))
-    fp.close()
-    html_tree = parser.tree.getDocument()
-
-    for node in html_tree.childNodes:
-        if (node.name == 'html') and (node.type != 3): # Skip DocType element
-            html = node
-            break
-    else:
-        html = None
-
-    if not html:
-        return None
-
-    for node in html.childNodes:
-        if node.name == 'head':
-            head = node
-            break
-    else:
-        head = None
-
-    meta_charset = False
-    title = None
-    refresh = None
-    icon = None
-
-    if head:
-        for node in head.childNodes:
-            if node.name == 'title':
-                if node.childNodes:
-                    title = node.childNodes[0].value
-                    break
-                else:
-                    title = ''
-
-        for node in head.childNodes:
-            if (node.name == 'meta') and \
-                    ('http-equiv' in node.attributes) and \
-                    (node.attributes['http-equiv'] == 'content-type'):
-                meta_content = node.attributes['content']
-                if meta_content:
-                    try:
-                        meta_charset = \
-                            meta_content.lower().split('charset=')[1].split(';')[0]
-                    except IndexError:
-                        meta_charset = False
-                    else:
-                        break
-            elif (node.name == 'meta') and ('charset' in node.attributes):
-                meta_charset = node.attributes['charset'].lower()
-                break
-
-        if not charset:
-            charset = parser.tokenizer.stream.charEncoding[0]
-
-        if title and (charset or meta_charset):
-            title = title.encode(charset or meta_charset)
-
-        for node in head.childNodes:
-            if node.name == 'meta' and \
-                    ('http-equiv' in node.attributes) and \
-                    (node.attributes['http-equiv'] == 'refresh'):
-                refresh = node.attributes['content']
-                break
-
-        for node in head.childNodes:
-            if node.name == 'link' and \
-                    ('rel' in node.attributes) and \
-                    (node.attributes['rel'] in ('icon', 'shortcut icon')):
-                icon = node.attributes['href']
-                break
-
-    else:
-        for node in html.childNodes:
-            if node.name == 'title':
-                if node.childNodes:
-                    title = node.childNodes[0].value
-                    break
-                else:
-                    title = ''
-
-    if (title is None) and (refresh is None) and (icon is None):
-        return None
-    return HTMLParser(charset, meta_charset, title, refresh, icon)