def testProcessRss(self):
source = NewsSource(name="name", feed="feed")
source.save()
feedContents = self.testData("readernews.xml")
saveStories(feedContents, source)
print len(WebStory.objects)
def testProcessRss(self):
source = NewsSource(name="name", feed="feed")
source.save()
feedContents = self.testData("readernews.xml")
saveStories(feedContents, source)
print len(WebStory.objects)
def createDB(): print "Creating the initial db" Company.create_table() NewsSource.create_table() News.create_table() Price.create_table() OpinionAPI.create_table() OpinionAPIResponse.create_table()
def testParseEntry(self):
"should turn an entry into a WebStory by fetching"
source = NewsSource()
entries = getEntries(self.testData())
story = processEntry(entries[0], source)
self.assertTrue(hasattr(story, "fullText"))
link = "http://telegraph.feedsportal.com/c/32726/f/564430/s/139f1592/l/0L0Stelegraph0O0Cculture0Ctvandradio0Cbbc0C840A610A70CBBC0Eaxes0EMy0EFamily0Esitcom0Eafter0Emore0Ethan0E10A0A0Eepisodes0Bhtml/story01.htm"
self.assertEqual(link, story.link)
date = datetime.strptime("2011-03-25T10:57:35Z", D_FMT)
self.assertEqual(date, story.date)
title = 'BBC axes My Family sitcom after more than 100 episodes'
self.assertEqual(title, story.title)
def newSource(request):
source = NewsSource()
source.title = request.POST["name"]
source.description = request.POST["description"]
source.url = request.POST["url"]
source.save()
return HttpResponseRedirect("/source/" + str(source.id))
def main():
#Select companies that don't have any articles
companies = Company.raw(
"""
Select *
FROM company
WHERE id not in (
SELECT company_id
from news
)
"""
)
ns = NewsSource.select().where(NewsSource.name=='Reuters').get()
for c in companies:
print "Finding stories about "+c.name
firstURL = baseURL+'/search?blob="'+c.name.replace(' ','+')+'"'
readSearchPage(c,ns,firstURL,1)
print 'DONE!'
def addNewsSources(): print "Adding News Sources" NewsSource.create(name="Reuters", url="http://www.reuters.com")
