Enclosed an example that i use to highlight words in a text string which might also contain HTML tags and entities.
Maybe you can use it in your Web2py applications? # -*- coding: utf-8 -*- import re from BeautifulSoup import BeautifulStoneSoup # see http://effbot.org/zone/python-list.htm # http://effbot.org/librarybook/htmlentitydefs.htm def remove_tags(in_text): # convert in_text to a mutable object (e.g. list) altreplacechars =['^','~','|','`','%','#','@','!','+','%'] # verify first that one of this alternative replace characters do not appear in search tekst altchar = ' ' for altchar in altreplacechars: if not altchar in in_text: break s_list = list(in_text) i = 0 while i < len(s_list): # find the < if s_list[i] == '<': while s_list[i] != '>': # remove everything between the < and the > s_list.pop(i) s_list.insert(i,altchar) i=i+1 # make sure we get rid of the > to s_list.pop(i) s_list.insert(i,altchar) else: i=i+1 join_char='' return join_char.join(s_list) def insert_highlight_tags(text, searchstring, start_tag_highlight='<span style="background-color:%s" id="found- %s">', \ end_tag_highlight='</span>', color='yellow', case_sensitive=False): converted_text = str(BeautifulStoneSoup(text, convertEntities=BeautifulStoneSoup.HTML_ENTITIES)) clean_text = remove_tags(converted_text) #print clean_text # no_tags_text = list(clean_text) text = ''.join(text) text = list(converted_text) if not case_sensitive: clean_text=clean_text.upper() searchstring =searchstring.upper() idx = [match.start() for match in re.finditer(re.escape (searchstring), clean_text)] offset=0 diff = 0 iprev = 0 tagcounter=0 for i in idx: tagcounter += 1 diff = i - iprev offset = offset + diff #no_tags_text.insert(offset, start_tag_highlight %tagcounter) text.insert(offset, start_tag_highlight %(color, tagcounter)) offset = offset + len(searchstring) + 1 # positioning after search word #no_tags_text.insert(offset, end_tag_highlight) text.insert(offset, end_tag_highlight) offset = offset - len(searchstring) + 1 # positioning after end tag iprev = i # no_tags_text = ''.join(no_tags_text) text = ''.join(text) return text if __name__ == '__main__': import sys text = u'''<html><body><h1>This ~is my ^’ text to test;<h1><a href="http://localhost";>& O yeh, This is the hyperlink to my »local machine».</a><p>This is my paragraph< /p></ body></html>''' searchstring='~' #search string start_tag_highlight='<a style="background-color:red" id="found- %s">' # start highlight-tag end_tag_highlight='</a>' # end highlight-tag print insert_highlight_tags(text, searchstring, color='green', case_sensitive=True) -- You received this message because you are subscribed to the Google Groups "web2py-users" group. To post to this group, send email to web...@googlegroups.com. To unsubscribe from this group, send email to web2py+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/web2py?hl=en.
