def extract_urls(self, text):
block_parser = TextBlockParser()
soup = BeautifulSoup(text)
urls = set()
for user_url in soup.findAll(text=re.compile(URL_RE)):
if not self.inside_a(user_url):
urls |= block_parser.extract_urls(unicode(user_url))
return urls
def extract_urls(self, text):
block_parser = TextBlockParser()
soup = BeautifulSoup(text)
urls = set()
url_list = []
for user_url in soup.findAll(text=re.compile(URL_RE)):
if not self.inside_a(user_url):
block_urls = block_parser.extract_urls(unicode(user_url))
for url in block_urls:
if url not in urls:
url_list.append(url)
urls.add(url)
return url_list
def parse_data(self, text, maxwidth, maxheight, template_dir, context,
urlize_all_links):
block_parser = TextBlockParser()
original_template_dir = template_dir
soup = BeautifulSoup(text)
for user_url in soup.findAll(text=re.compile(URL_RE)):
if not self.inside_a(user_url):
if self.is_standalone(user_url):
template_dir = original_template_dir
else:
template_dir = 'inline'
replacement = block_parser.parse(str(user_url), maxwidth,
maxheight, template_dir,
context, urlize_all_links)
user_url.replaceWith(BeautifulSoup(replacement))
return unicode(soup)
def setUp(self):
self.parser = TextBlockParser()
super(TextBlockParserTestCase, self).setUp()
