Renamed parse_html modules to bkmk_ph_* to avoid name clashes.

[bookmarks_db.git] / parse_html / beautifulsoup.py

diff --git a/parse_html/beautifulsoup.py b/parse_html/beautifulsoup.py
deleted file mode 100644 (file)
index 1b2d3a4..0000000
--- a/parse_html/beautifulsoup.py
+++ /dev/null
@@ -1,144 +0,0 @@
-"""HTML Parser using BeautifulSoup
-
-This file is a part of Bookmarks database and Internet robot.
-"""
-
-__version__ = "$Revision$"[11:-2]
-__revision__ = "$Id$"[5:-2]
-__date__ = "$Date$"[7:-2]
-__author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 2007-2011 PhiloSoft Design"
-__license__ = "GNU GPL"
-
-__all__ = ['parse_html']
-
-
-import re
-from sgmllib import SGMLParser, SGMLParseError
-from BeautifulSoup import BeautifulSoup, CData
-from .util import HTMLParser
-
-
-# http://groups.google.com/group/beautifulsoup/browse_thread/thread/69093cb0d3a3cf63
-class BadDeclParser(BeautifulSoup):
-    def parse_declaration(self, i):
-         """Treat a bogus SGML declaration as raw data. Treat a CDATA
-         declaration as a CData object."""
-         j = None
-         if self.rawdata[i:i+9] == '<![CDATA[':
-              k = self.rawdata.find(']]>', i)
-              if k == -1:
-                  k = len(self.rawdata)
-              data = self.rawdata[i+9:k]
-              j = k+3
-              self._toStringSubclass(data, CData)
-         else:
-             try:
-                 j = SGMLParser.parse_declaration(self, i)
-             except SGMLParseError:
-                 # Could not parse the DOCTYPE declaration
-                 # Try to just skip the actual declaration
-                 match = re.search(r'<!DOCTYPE([^>]*?)>', self.rawdata[i:], re.MULTILINE|re.IGNORECASE)
-                 if match:
-                     toHandle = self.rawdata[i:match.end()]
-                 else:
-                     toHandle = self.rawdata[i:]
-                 self.handle_data(toHandle)
-                 j = i + len(toHandle)
-         return j
-
-
-def _parse_html(filename, charset):
-   infile = open(filename, 'r')
-   try:
-      return BadDeclParser(infile, fromEncoding=charset)
-   except TypeError:
-      return None
-   finally:
-      infile.close()
-
-def parse_html(filename, charset=None, log=None):
-   root = _parse_html(filename, charset)
-   if root is None:
-      return None
-
-   _charset = root.originalEncoding
-   if _charset in ("ISO-8859-2", "windows-1252", "MacCyrillic"): # Replace default
-      _charset = DEFAULT_CHARSET
-      root = _parse_html(filename, _charset)
-      if root is None:
-         return None
-
-   html = root.html
-   if html is None:
-      html = root
-
-   head = html.head
-   if head is None:
-      head = html # Some sites put TITLE in HTML without HEAD
-
-   title = head.title
-   if (title is None) and (html is not head):
-      # Some sites put TITLE in HTML outside of HEAD
-      title = html.title
-
-   if title is None:
-      # Lookup TITLE in the root
-      title = root.title
-
-   if title is None:
-      return None
-
-   if title.string:
-      title = title.string
-   else:
-      parts = []
-      for part in title:
-         if not isinstance(part, basestring):
-            part = unicode(part)
-         parts.append(part.strip())
-      title = ''.join(parts)
-
-   meta = head.find(_find_contenttype, recursive=False)
-   if meta:
-      try:
-         meta_content = meta.get("content")
-         if meta_content:
-             __charset = meta_content.lower().split('charset=')[1].split(';')[0]
-         else:
-             __charset = False
-      except IndexError: # No charset in the META Content-Type
-         meta_charset = False
-      else:
-         meta_charset = _charset == __charset
-   else:
-      meta_charset = False
-
-   if _charset or meta_charset:
-      title = title.encode(_charset or meta_charset)
-
-   meta = head.find(_find_refresh, recursive=False)
-   if meta:
-      refresh = meta.get("content")
-   else:
-      refresh = None
-
-   meta = head.find(_find_icon, recursive=False)
-   if meta:
-      icon = meta.get("href")
-   else:
-      icon = None
-
-   return HTMLParser(_charset, meta_charset, title, refresh, icon)
-
-def _find_contenttype(Tag):
-   return (Tag.name == "meta") and \
-      (Tag.get("http-equiv", '').lower() == "content-type")
-
-def _find_refresh(Tag):
-   return (Tag.name == "meta") and \
-      (Tag.get("http-equiv", '').lower() == "refresh")
-
-def _find_icon(Tag):
-   return (Tag.name == "link") and \
-      (Tag.get("rel", '').lower() in ('icon', 'shortcut icon'))