def get_feeds(old_links, url):
r = requests.get(url)
data = r.text
soup = BeautifulSoup(data)
news_source_list = []
twitter_feed_list = []
for link in soup.find_all('a'):
full_link = link.get('href')
try:
o = urlparse(full_link)
news_source = o.hostname
if news_source is None:
continue
if news_source == 'twitter.com':
locs = [m.start() for m in re.finditer('/', o.path)]
news_source += o.path[:locs[1]]
twitter_feed_list.append(news_source)
else:
news_source_list.append(news_source)
except:
pass
print 'Links Found: ', len(set(news_source_list))
print 'Old Links: ', len(old_links)
news_source_list = list(set(news_source_list) - set(old_links))
print 'New Links: ', len(news_source_list)
twitter_feed_list = list(set(twitter_feed_list))
news_rss_list = []
for index, item in enumerate(news_source_list):
print 'Feed: %d/%d' %(index, len(news_source_list))
try:
# put a timeout as feedfinder can stall indefinitely
signal.signal(signal.SIGALRM, handler)
signal.alarm(10)
rss = feedfinder.feeds(item)
# cancel timeout if feedfinder returned
signal.alarm(0)
if rss is not None and len(rss) > 0:
rss.sort(key = lambda s: len(s))
news_rss_list.append((item, rss[0]))
except Exception, exc:
print exc
pass
def url_to_subscription(subscription_url):
"""Create a subscription object from a url —if possible"""
if not subscription_url.startswith('http://'):
subscription_url = 'http://%s' % subscription_url
feeds = feedfinder.feeds(subscription_url)
if feeds:
subscription = Subscription()
subscription.feed_url = feeds[0]
data = feedparser.parse(subscription.feed_url)
links = data.feed.get('links', [])
if links:
hubs = [link for link in data.feed.links if link['rel']==u'hub']
logging.info(hubs)
if len(hubs) > 0:
subscription.hub = hubs[0]['href']
else:
subscription.hub = ''
subscription.feed_id = data.feed.get('id', 'No ID')
subscription.title = data.feed.get('title', 'No title')
subscription.url = data.feed.get('link', subscription_url)
subscription.etag = data.get('etag', '')
updated_tuple = data.feed.get('date_parsed', None)
if updated_tuple:
subscription.updated = datetime.datetime(*updated_tuple[:6])
else:
subscription.updated = datetime.datetime.today()
else:
subscription = None
return subscription
def add_feed(filename, url, rawdog, config): """Try to add a feed to the config file.""" feeds = feedfinder.feeds(url) if feeds == []: print >>sys.stderr, "Cannot find any feeds in " + url else: feed = feeds[0] if feed in rawdog.feeds: print >>sys.stderr, "Feed " + feed + " is already in the config file" else: print >>sys.stderr, "Adding feed " + feed feedline = "feed %s %s\n" % (config["newfeedperiod"], feed) edit_file(filename, AddFeedEditor(feedline).edit)
def scan_url(url, depth):
if url.strip().endswith('robots.txt'):
# Ignore such URLs as they are fruitless.
print "Skipping {}".format(url)
return
u2 = urlscanner.url_scanner(url.strip(), depth)
for U in u2:
if U.strip().lower().endswith('robots.txt'):
continue
logger.info("searching for feeds in: %s", U)
feeds = feedfinder.feeds(U.strip())
logger.info("found %s feeds", len(feeds))
if feeds:
logger.info(str(feeds))
feedfinder.store_feeds(feeds)
def DoFeed(self, base_uri, cooked):
feedds = []
if feedfinder:
feed_uris = feedfinder.feeds(self.page_uri)
for feed_uri in feed_uris:
feedd = {
"@uf" : "feed",
"@link" : feed_uri,
"@title" : "feed",
"src" : feed_uri,
}
feedds.append(feedd)
self.PutData("feed", feedds)
def parsefeed(url):
"""this just attaches to feedfinder. Let's keep this function as a hook though
to add more functionality down the line: eg, multiple results per feed_find"""
try:
logger.info('using feed finder')
res = feedfinder.feeds(url)
# res = feedfinder_new.feeds(url)
feed_len = len(res)
if res:
logger.info('{0} feeds found: {1}'.format(feed_len, res))
return res, feed_len
else:
logger.warn("no results found...")
return False, 0
except Exception, e:
logger.exception("error!")
return False
def add_feed(request):
account = request.account
unread_feeds = account.get_unread_feeds()
if request.POST and request.POST.has_key('link'):
data = request.POST.copy()
try:
fp = feedparser.parse(data['link'])
if fp.has_key('feed') and fp.feed.has_key('title'):
feeds = [data['link']]
else:
feeds = feedfinder.feeds(data['link'])
if not feeds:
request.session['error'] = "No feeds found."
return HttpResponseRedirect('/feeds/unread/')
elif len(feeds) == 1:
try:
feed = Feed.objects.get(link=feeds[0])
except Feed.DoesNotExist:
# add the feed to the db
fp = feedparser.parse(feeds[0])
feed = Feed(title=fp.feed.title, link=feeds[0], is_active=True)
feed.save()
feed.update()
else:
pass # already added
try:
AccountFeed(account=account, feed=feed, title=feed.title).save()
except:
pass
return HttpResponseRedirect("/feeds/%s/" % (feed.slug,))
else:
if data.has_key('feed'):
form = SelectFeedForm(data, account=account, link=data['link'], feeds=feeds)
if form.is_valid():
feed = form.save()
return HttpResponseRedirect("/feeds/%s/" % (feed.slug,))
else:
initial = {
'link': data['link'],
'feed': feeds[0]
}
form = SelectFeedForm(initial=initial, account=account, link=data['link'], feeds=feeds)
return render_to_response('feeds/select.html', {
'feeds': unread_feeds,
'form': form,
'collapse_sidebar': True
}, context_instance=RequestContext(request))
except UnicodeDecodeError:
request.session['error'] = """
Encoding error.
<a href="http://feedparser.org/">Universal Feed Parser</a>
threw an exception while trying to make sense of the feed.
When this happens it is almost certainly the feed's fault.
""".strip().replace('\n', ' ')
except feedfinder.TimeoutError:
request.session['error'] = "Timeout"
# TODO: handle properly
return HttpResponseRedirect('/feeds/unread/')
def add_feed(request):
account = request.account
unread_feeds = account.get_unread_feeds()
if request.POST and request.POST.has_key('link'):
data = request.POST.copy()
try:
fp = feedparser.parse(data['link'])
if fp.has_key('feed') and fp.feed.has_key('title'):
feeds = [data['link']]
else:
feeds = feedfinder.feeds(data['link'])
if not feeds:
request.session['error'] = "No feeds found."
return HttpResponseRedirect('/feeds/unread/')
elif len(feeds) == 1:
try:
feed = Feed.objects.get(link=feeds[0])
except Feed.DoesNotExist:
# add the feed to the db
fp = feedparser.parse(feeds[0])
feed = Feed(title=fp.feed.title,
link=feeds[0],
is_active=True)
feed.save()
feed.update()
else:
pass # already added
try:
AccountFeed(account=account, feed=feed,
title=feed.title).save()
except:
pass
return HttpResponseRedirect("/feeds/%s/" % (feed.slug, ))
else:
if data.has_key('feed'):
form = SelectFeedForm(data,
account=account,
link=data['link'],
feeds=feeds)
if form.is_valid():
feed = form.save()
return HttpResponseRedirect("/feeds/%s/" %
(feed.slug, ))
else:
initial = {'link': data['link'], 'feed': feeds[0]}
form = SelectFeedForm(initial=initial,
account=account,
link=data['link'],
feeds=feeds)
return render_to_response(
'feeds/select.html', {
'feeds': unread_feeds,
'form': form,
'collapse_sidebar': True
},
context_instance=RequestContext(request))
except UnicodeDecodeError:
request.session['error'] = """
Encoding error.
<a href="http://feedparser.org/">Universal Feed Parser</a>
threw an exception while trying to make sense of the feed.
When this happens it is almost certainly the feed's fault.
""".strip().replace('\n', ' ')
except feedfinder.TimeoutError:
request.session['error'] = "Timeout"
# TODO: handle properly
return HttpResponseRedirect('/feeds/unread/')
def getFeedsFromUrl(url_addr):
''' Checks url_addr for any rss feeds and returns their '''\
'''urls as a json array. '''
feeds = feedfind.feeds(url_addr)
return json.dumps(feeds)
blogs.append(l1)
a=crawl(l1)
except:
pass
#else:
#count=0
for url in urls:
try:
html = requests.get(url)
soup = BeautifulSoup(html.content)
name=soup.title.string
fr=feedfinder.feeds(url)
print (fr)
ill=ill+1
# filname=url.replace('http://' or 'https://','')
# filname=filname.replace('.*www.','')
# filname=filname.replace('.com','')
# filname=filname.replace('.org.*','')
# print filname
blogs=[]
with open('link%i.json'%ill,"w") as outfile:
html = requests.get(url)
def getFeedsFromUrl(url_addr):
''' Checks url_addr for any rss feeds and returns their '''\
'''urls as a json array. '''
feeds = feedfind.feeds(url_addr)
return json.dumps(feeds)
