def generate_event(self, event_num): e = Event() min_date = (date.today() + timedelta(days=-5)).toordinal() max_date = (date.today() + timedelta(days=5)).toordinal() e.start_date = random_day = date.fromordinal(random.randint(min_date, max_date)) e.end_date = e.start_date + timedelta(0, 60 * 60) # duration 60 minutes e.title = 'Event %d' % event_num e.descr = 'Description for event %d' % event_num e.lat = random.randint(24000, 26000)/1000.0 e.lon = random.randint(58000, 62000)/1000.0 ''' e.street_address = models.CharField(max_length=500) e.city = models.CharField(max_length=500) e.country = models.CharField(max_length=100) ''' e.org_name = 'Sample Organizer' e.org_email = '*****@*****.**' e.org_phone = '+358501234567' e.save() return
def extract_events(self, url):
event_urls = []
events = []
handle = urllib2.urlopen(url)
dom = parse(handle)
sanitizer_re = re.compile(r'(style|id|class)="[^"]*"')
items = dom.getElementsByTagName('item')
for item in items:
e = Event()
e.remote_source_name = 'AaltoEvents'
e.remote_url = self.getdata(item, 'link')
if Event.objects.filter(remote_url__iexact=e.remote_url).count() > 0:
print 'Event already exists, continuing.'
continue
e.title = smart_unicode(self.getdata(item, 'title'))
e.descr = smart_unicode(self.getdata(item, 'description'))
e.descr = sanitizer_re.sub('', e.descr) # Strip style, id, class attrs
try:
e.start_date = dateutil.parser.parse(self.getdata(item, 'xcal:dtstart'))
except Exception:
print 'Err'
try:
e.end_date = dateutil.parser.parse(self.getdata(item, 'xcal:dtend'))
except Exception:
print 'Err'
try:
point = self.getdata(item, 'georss:point')
if not point: raise Exception('No georss:point')
point = point.replace(',', '.')
point = point.split(' ')
e.lat = float(point[0])
e.lon = float(point[1])
except Exception as ex:
#print '%s' % ex
e.lat = 0
e.lon = 0
e.org_name = smart_unicode(self.getdata(item, 'author'))
try:
#print e.lat, e.lon
if not (e.lat and e.lat != 0 and e.lon and e.lon != 0):
raise Exception('Missing lat or lon')
res = reverse_geocode(e.lat, e.lon)
#print res
if hasattr(res, 'street_address'):
e.street_address = res.street_address
else:
e.street_address = ''
if hasattr(res, 'city'):
e.city = res.city
else:
e.city = ''
if hasattr(res, 'country'):
e.country = res.country
else:
e.country = 'Finland'
except Exception as ex:
#print 'Error fetching street address: %s' % ex
e.street_address = ''
e.city = ''
e.country = ''
e.org_email = ''
e.org_phone = ''
e.save()
events.append(e)
return events
def handle(self, *args, **options):
print "Scraping AYY event calendar"
datere = re.compile(r"(\d+\.\d+\.\d+), (\d+)\.(\d+)")
baseurl = "http://ayy.fi/kalenteri/"
url = baseurl
fetched_main_pages = 0
while fetched_main_pages < 6 and url:
print "Getting month [current+%d]: %s" % (fetched_main_pages, url)
event_listing = urllib2.urlopen(url)
fetched_main_pages = fetched_main_pages + 1
soup = BeautifulSoup(event_listing.read())
try:
url = baseurl + soup.find(id="content").find_all("a")[1]["href"]
print "Next url: %s" % url
except Exception:
print "No next url found, this will be the last page"
url = None
for row in soup.find_all("tr"):
try:
link = row.a
if not link:
continue # No links found
detail_url = link["href"]
if detail_url == "":
continue # No valid url
print "\tParsing: %s" % (detail_url)
# Get data, parse
detail_data = urllib2.urlopen(detail_url)
dsoup = BeautifulSoup(detail_data.read())
event = Event()
event.remote_source_name = "ayy"
event.remote_url = detail_url
container = dsoup.find(id="content")
if not container:
continue
# Extract title
try:
event.title = container.find("h1", {"class": "main-title"}).string
except Exception as e:
print "\tError extracting title: %s" % e
# print "Title: %s" % (title)
# Extract description
try:
content = container.find("div", {"class": "entry-content"})
for c in content.find_all("script"):
c.extract() # Remove scripts
for c in content.find_all("div", {"class": "pd-rating"}):
c.extract()
event.descr = ""
for c in content.contents:
event.descr += str(c)
except Exception as e:
print "\tError extracting description: %s" % e
# print "Descr: %s" % (contentstr[:100])
# Extract times
try:
metadata = content.next_sibling.next_sibling.next_sibling
start_time = metadata.p
for c in start_time.find_all("b"):
c.extract() # Remove b tags == titles
start_time = start_time.get_text().split("\n") # Split remaining by line
end_time = start_time[1]
start_time = start_time[0]
# Check if dates contain . as time separator, replace with : if so
s = datere.match(start_time)
if s:
start_time = s.expand(r"\1 \2:\3")
s = datere.match(end_time)
if s:
end_time = s.expand(r"\1 \2:\3")
# Parse
event.start_date = parser.parse(start_time, dayfirst=True)
event.end_date = parser.parse(end_time, dayfirst=True)
# print "Start: %s, end: %s" % (event.start_date, event.end_date)
except Exception as e:
print "\tError resolving date: %s" % e
raise e # Fatal, dates are required
# Extract location
try:
info = metadata.contents[7].get_text().split("\n")
event.venue = info[0].split("Paikka: ")[1]
event.street_address = info[1].split("Osoite: ")[1]
event.city = info[2].split("Kaupunki: ")[1]
event.country = "Finland"
query = ""
if event.street_address:
query += "%s, " % self.normalize_street_address(event.street_address)
if event.city:
query += "%s, " % event.city
if event.country:
query += "%s" % event.country
query = smart_unicode(query)
geores = geocoder.geocode(query)
if geores:
event.lat = geores["lat"]
event.lon = geores["lon"]
else:
print "\tUnable to resolve coordinates for query %s" % query
except Exception as e:
print "\tError resolving location: %s" % e
# print 'Loc: %s, addr: %s, city: %s' % (loc, addr, city)
# Extract links
try:
metadata = metadata.next_sibling.next_sibling
info = metadata.contents[3]
links = info.find_all("a")
homepage = links[0]["href"]
facebookev = links[1]["href"]
except Exception as e:
print "\tError resolving links: %s" % e
# print 'Homepage: %s, FB: %s' % (homepage, facebookev)
# Extract contact info
try:
info = metadata.contents[7].get_text().split("\n")
event.org_name = info[0].split(u"Järjestäjä: ")[1]
event.org_email = info[1].split(u"Sähköposti: ")[1]
event.org_phone = info[2].split("Puhelin: ")[1]
except Exception as e:
print "\tError resolving organizer info: %s" % e
# print 'Name: %s, email: %s, phone: %s' % (org_name, org_email, org_phone)
event.save()
except Exception as e:
print "\tFATAL ERROR handling event, discarded"
# print '----------------------------------------'
# break
return