ubuntuusers.de

string = '<a href="/test/foo123.html">foo</a>foo fooo <img src="/foo.gif"/>'
string_neu = re.sub('(?!<a href[A-Za-z0-9[:punct:]]*)foo(?![A-Za-z0-9[:punct:]]*</a>)', 'bar', string)

<a href="/test/bar123.html">bar</a>bar baro <img src="/bar.gif"/>

>>> from BeautifulSoup import BeautifulSoup
>>> string = '<a href="/test/foo123.html">foo</a>foo fooo <img src="/foo.gif"/>'
>>> soup = BeautifulSoup(string)
>>> print soup(text=True)
[u'foo', u'foo fooo ']
>>> link = '<a href="/murks/bla.html">foo</a> fooo '
>>> soup(text=True)[1].replaceWith(link)
>>> print soup
<a href="/test/foo123.html">foo</a><a href="/murks/bla.html">foo</a> fooo <img src="/foo.gif" />

def replace_splitted(soup, n, repl):
    '''replace_splitted(soup, n, repl)

    Split the soup using space chars as seperator, replace the nth element and 
    return the new soup.
    '''
    split = soup.split(' ')
    split[n] = repl
    return soup.replaceWith(' '.join(split))

>>> import souptools
>>> from BeautifulSoup import BeautifulSoup
>>> string = '<a href="/test/foo123.html">foo</a>foo fooo <img src="/foo.gif"/>'
>>> soup = BeautifulSoup(string)
>>> link = '<a href="/murks/bla.html">foo</a>'
>>> souptools.replace_splitted(soup(text=True)[1], 0, link)
>>> soup
<a href="/test/foo123.html">foo</a><a href="/murks/bla.html">foo</a> fooo <img src="/foo.gif" />

tagliste = ['link1', 'link2']

from BeautifulSoup import BeautifulSoup
string = '<p><a href="link1.html">link1</a><a href=/bar/bar.html>bar</a>link2 <a href=/bar/bar.html>bar</a></p>'
soup = BeautifulSoup(string)
for tag in tagliste:
	soup = BeautifulSoup(string)
	if find(string, tag) > -1:
		i = 0
		link_soup = soup.findAll('a')
		for item in soup.findAll('a'):
			soup.find('a').replaceWith('[[[LINK]]]')
			i = i+1
		i_2 = 0
		for item in soup(text=True):
			text = replace(item, tag, '<a href=/bar/bar.html>bar</a>')
			soup(text=True)[i_2].replaceWith(text)
			i_2 = i_2+1
		#print link_soup
		i_3 = 0
		soup = str(soup)
		for item in link_soup:
				soup = replace(soup, '[[[LINK]]]', str(item), 1)
				i_3 = i_3+1
		string = soup	
	else :
		print 'nicht gefunden'
print str(soup)

>>> import testding

Traceback (most recent call last):
  File "<pyshell#0>", line 1, in <module>
    import testding
  File "C:\Python25\testding.py", line 8, in <module>
    if find(string, tag) > -1:
NameError: name 'find' is not defined

from string import find, replace

tagliste = ['link1', 'foo']

from BeautifulSoup import BeautifulSoup
string = '<p><a href="link1.html">link1</a><a href=/bar/bar.html>bar</a>foo <a href=/bar/foo.html>bar</a></p>'
soup = BeautifulSoup(string)
for tag in tagliste:
	soup = BeautifulSoup(string)
	if find(string, tag) > -1:
		i = 0
		link_soup = soup.findAll('a')
		for item in soup.findAll('a'):
			soup.find('a').replaceWith('[[[LINK]]]')
			i = i+1
		i_2 = 0
		for item in soup(text=True):
			text = replace(item, tag, '<a href=/bar/bar.html>bar</a>')
			soup(text=True)[i_2].replaceWith(text)
			i_2 = i_2+1
		#print link_soup
		i_3 = 0
		soup = str(soup)
		for item in link_soup:
				soup = replace(soup, '[[[LINK]]]', str(item), 1)
				i_3 = i_3+1
		string = soup	
print str(soup)

if string.find(tag) > -1:

def set_anchor(head, taglist):
    for elem in head.contents:
        if not str(elem).startswith(('<a', '<img')):
            split = str(elem).split(' ')
            i = 0
            for word in split:
                for entry in taglist:
                    if word == entry:
                        split[i] = '<a href=/bar/bar.html>bar</a>'
                i += 1
            elem.replaceWith(' '.join(split))
    return head

>>> from BeautifulSoup import BeautifulSoup
>>> import testding
>>> tagliste = ['link1', 'foo']
>>> tagliste = ['link1', 'foo', 'katze']
>>> string = '<p><a href="link1.html">link1</a><a href=/bar/bar.html>bar</a>foo <a href=/bar/foo.html>bar</a>die katze faucht</p>'
>>> soup = BeautifulSoup(string)
>>> head = soup.p
>>> testding.set_anchor(head, tagliste)
<p><a href="link1.html">link1</a><a href="/bar/bar.html">bar</a><a href=/bar/bar.html>bar</a> <a href="/bar/foo.html">bar</a>die <a href=/bar/bar.html>bar</a> faucht</p>

import string


def set_anchors(soup, termlist):
    '''set_anchors(soup, termlist)
    
    Inspect all elements of a BeautifulSoup instance whether they are not 
    included by an a- or img-tag. In that case compare each word of the element 
    with the entries in termlist. Change each matching word to an anchor where 
    URL is /description/%s.html (%s = word). 
    '''
    for elem in soup.contents:
        if not str(elem).startswith(('<a', '<img')):
            elem.replaceWith(_anchors(elem, termlist))
    return soup


def _anchors(elem, termlist):
    split = str(elem).split(' ')
    i = 0
    for word in split:
        adj_word = _adjust(word)
        for entry in termlist:
            if adj_word == entry.lower():
                split[i] = '<a href="/description/%s.html">%s</a>' % (adj_word, 
                                                                      word)
        i += 1
    return ' '.join(split)


def _adjust(word):
    chars = [char for char in word.lower()]
    for char in chars:
        if char in string.punctuation:
            chars.remove(char)
    return ''.join(chars)

>>> import bla
>>> from BeautifulSoup import BeautifulSoup
>>> string = '<p><a href="link1.html">link1</a><a href=/bar/bar.html>bar</a>foo <a href=/bar/foo.html>bar</a>die Katze, die im Garten ist, faucht</p>'
>>> soup = BeautifulSoup(string)
>>> termlist = ['foo', 'bar', 'Katze', 'garten']
>>> bla.set_anchors(soup, termlist)
<p><a href="link1.html">link1</a><a href="/bar/bar.html">bar</a><a href="/description/foo.html">foo</a> <a href="/bar/foo.html">bar</a>die <a href="/description/katze.html">Katze,</a> die im <a href="/description/garten.html">Garten</a> ist, faucht</p>