def feed_update():
feed_updated_list = []
article_updated_list = []
feeds = Feed.objects.all()
for feed in feeds:
try:
feed_update = feedparser.parse(feed.url, etag=feed.etag)
except:
print feed.title, "Does not have an etag!!!!!!!!!!!!!!!!!!"
title_list = []
if feed_update.status != 304:
article_inner = []
feed_updated_list.append(feed.title)
feeds = Article.objects.all()
for i in feeds:
title_list.append(i.title)
for entry in feed_update.entries:
if entry.title not in title_list:
article_inner.append(entry.title)
article = Article()
article.title = entry.title
article.url = entry.link
c = 'https?://(.*?)/'
try:
article.domain = re.findall(c, entry.link)[0]
except:
article.domain = entry.link
if feed.author:
article.author = feed.author
else:
article.author = entry.author
article.authorSlug = slugify(article.author)
#description script
try:
remove = re.findall('<p>(The post.*?)</p>',
entry.description)[0]
article.description = entry.description.replace(
remove, '')
except:
try:
remove = re.findall('<p>(The post.*?)</p>',
entry.description)[0]
except:
article.description = entry.description
#end descripton script
d = datetime.datetime(*(entry.published_parsed[0:6]))
dateString = d.strftime('%Y-%m-%d')
article.publication_date = dateString
article.feed = feed
article.practiceArea = feed.practiceArea
article.practiceAreaSlug = feed.practiceArea.replace(
" ", "_").lower()
article.save()
article_updated_list.append(article_inner)
try:
feed.etag = feed_update.etag
except:
pass
feed.save()
return feed_updated_list, article_updated_list
