def fetch_wordpress_default_rss(source, markup, url, add_rpc, got_result):
link = url + "/?feed=rss"
# print "Trying", link
def callback(feed_markup):
if feed_markup:
def _got_result(res):
if res:
res.method = 'wordpress_default_rss'
got_result(res)
rss_fetch(source, feed_markup, link, add_rpc, _got_result)
add_rpc(url_fetch_async(link, callback))
def fetch_hardcoded_rss_url(source, markup, url, add_rpc, got_result):
lookup = {
'news.ycombinator.com': 'http://hnrss.org/newest?points=25',
'newyorker.com': 'http://www.newyorker.com/feed/everything',
'longform.org': 'http://longform.org/feed.rss'
}
rss_url = lookup.get(strip_url_prefix(url))
if rss_url:
def callback(feed_markup):
def _got_result(res):
if res:
res.method = 'hardcoded_rss'
got_result(res)
rss_fetch(source, feed_markup, rss_url, add_rpc, _got_result)
add_rpc(url_fetch_async(rss_url, callback))
def fetch_linked_rss(source, markup, url, add_rpc, got_result):
soup = BeautifulSoup(markup, 'lxml')
link = soup.find('link', attrs={'rel': 'alternate', 'type': ['application/rss+xml', 'application/atom+xml']})
if link and type(link) == bs4.element.Tag and link['href']:
feed_url = urljoin(url, link['href'])
print 'Found rss URL: ', feed_url
def callback(feed_markup):
if feed_markup:
def _got_result(result):
if result:
result.method = 'linked_rss'
return got_result(result)
else:
print 'failed to parse markup'
return rss_fetch(source, feed_markup, feed_url, add_rpc, _got_result)
else:
print "Error fetching linked rss {0}".format(feed_url)
add_rpc(url_fetch_async(feed_url, callback))
return None
