def new_from_wikipedia(klass, url):
# if we have a page for a given url already we can return it
wikipedia_pages = WikipediaPage.objects.filter(url=url)
if wikipedia_pages.count() > 0:
return wikipedia_pages[0], False
title_escaped = wikipedia.url_to_title(url)
info = wikipedia.info(title_escaped)
wikipedia_page = WikipediaPage.objects.create(title=info['title'],
url=url, last_modified=rfc3339_parse(info['touched']))
for cat in wikipedia.categories(wikipedia_page.title):
title = cat['title'][9:]
if not title:
continue
category, created = WikipediaCategory.objects.get_or_create(title=title)
wikipedia_page.categories.add(category)
wikipedia_page.save()
return wikipedia_page, True
def new_from_wikipedia(klass, url):
# if we have a page for a given url already we can return it
wikipedia_pages = WikipediaPage.objects.filter(url=url)
if wikipedia_pages.count() > 0:
return wikipedia_pages[0], False
title_escaped = wikipedia.url_to_title(url)
info = wikipedia.info(title_escaped)
wikipedia_page = WikipediaPage.objects.create(
title=info['title'],
url=url,
last_modified=rfc3339_parse(info['touched']))
for cat in wikipedia.categories(wikipedia_page.title):
title = cat['title'][9:]
if not title:
continue
category, created = WikipediaCategory.objects.get_or_create(
title=title)
wikipedia_page.categories.add(category)
wikipedia_page.save()
return wikipedia_page, True
def test_categories(self):
info = wikipedia.categories('Skull_and_Bones')
self.assertTrue(len(info) > 1)
def test_categories(self):
info = wikipedia.categories('Skull_and_Bones')
self.assertTrue(len(info) > 1)
