def collect_with_feedzilla():
news = Feedzilla.collect()
for n in news:
cluster = Cluster()
cluster.display_name = n["title"]
cluster.relevancy = 1.0 / n["search_place"] * 100
cluster.topic = Topic.objects.get(short_name=str(n["topic"]))
cluster.date = format_date(n["publish_date"])
cluster.save()
if (n["check_url"]):
try:
cluster_content = extractFromURL(n["url"])
cluster_countries = Placemaker.get_countries_from_string(
cluster_content)
for country in cluster_countries:
try:
l = Location.objects.get(name=country)
except Location.DoesNotExist:
l = Location()
l.name = country
l.save()
cluster.location.add(l)
cluster_continents = Placemaker.get_continents_from_countries(
cluster_countries)
for continent in cluster_continents:
try:
c = Continent.objects.get(name=continent)
except Continent.DoesNotExist:
c = Continent()
c.name = continent
c.save()
cluster.continent_location.add(c)
except TypeError:
print "webarticle2text Error"
a = Article()
a.title = n["title"]
a.url = n["url"]
a.publisher = n["source"]
a.content = n["summary"][:999]
a.published_date = format_date(n["publish_date"])
a.cluster = cluster
a.save()
def collect_with_feedzilla():
news = Feedzilla.collect()
for n in news:
cluster = Cluster()
cluster.display_name = n["title"]
cluster.relevancy = 1.0 / n["search_place"] * 100
cluster.topic = Topic.objects.get(short_name=str(n["topic"]))
cluster.date = format_date(n["publish_date"])
cluster.save()
if n["check_url"]:
try:
cluster_content = extractFromURL(n["url"])
cluster_countries = Placemaker.get_countries_from_string(cluster_content)
for country in cluster_countries:
try:
l = Location.objects.get(name=country)
except Location.DoesNotExist:
l = Location()
l.name = country
l.save()
cluster.location.add(l)
cluster_continents = Placemaker.get_continents_from_countries(cluster_countries)
for continent in cluster_continents:
try:
c = Continent.objects.get(name=continent)
except Continent.DoesNotExist:
c = Continent()
c.name = continent
c.save()
cluster.continent_location.add(c)
except TypeError:
print "webarticle2text Error"
a = Article()
a.title = n["title"]
a.url = n["url"]
a.publisher = n["source"]
a.content = n["summary"][:999]
a.published_date = format_date(n["publish_date"])
a.cluster = cluster
a.save()
def collect_with_google():
google_news = GoogleNews.collect()
for google_article in google_news:
if(is_today(google_article["publishedDate"])):
cluster_content = ""
cluster = Cluster()
if("image" in google_article):
cluster.image = google_article["image"]["url"]
else:
cluster.image = "http://panhandletickets.com/images/not_available.jpg"
if("relatedStories" in google_article):
cluster.relevancy = (len(google_article["relatedStories"]) + 1)*100/google_article["page"]
else:
cluster.relevancy = 100/google_article["page"]
cluster.topic = Topic.objects.get(name=google_article["topic"])
cluster.is_local = False
cluster.date = format_date(google_article["publishedDate"])
cluster.save()
article = Article()
article.title = google_article["titleNoFormatting"]
article.url = google_article["unescapedUrl"]
article.location = google_article["location"]
article.publisher = google_article["publisher"]
cluster_content += google_article["titleNoFormatting"] + " "
if "content" in google_article:
article.content = google_article["content"]
cluster_content += google_article["content"]+ " "
else:
article.content = ""
article.published_date = format_date(google_article["publishedDate"])
article.cluster = cluster
article.save()
if("relatedStories" in google_article):
article_related_stories = google_article["relatedStories"]
for related in article_related_stories:
article = Article()
article.title = related["titleNoFormatting"]
article.url = related["unescapedUrl"]
article.location = related["location"]
article.publisher = related["publisher"]
if "content" in related:
article.content = related["content"]
cluster_content += related["content"]+ " "
else:
article.content = ""
article.published_date = format_date(related["publishedDate"])
article.cluster = cluster
article.save()
cluster.save()
cluster_countries = Placemaker.get_countries_from_string(cluster_content)
for country in cluster_countries:
try:
l = Location.objects.get(name=country)
except Location.DoesNotExist:
l = Location()
l.name = country
l.save()
cluster.location.add(l)
cluster_continents = Placemaker.get_continents_from_countries(cluster_countries)
for continent in cluster_continents:
try:
c = Continent.objects.get(name=continent)
except Continent.DoesNotExist:
c = Continent()
c.name = continent
c.save()
cluster.continent_location.add(c)
cluster.save()
