def parse_stores(self, response):
location = re.findall(r"[;?]ll=[^(&)]+", response.body_as_unicode())
addr_full = response.xpath('//div[@class="cq-shop-info"]/p[1]/text()|//div[@id="cq-shop-info"]/p[1]/text()|//div[@id="cq-full-width"]/div[@class="cq-content"]/div/p[@class="shop-address"]/text()').extract()
if len(addr_full)>2:
city = addr_full[1]
postcode = addr_full[2]
else:
city = addr_full[1].split(',')[0]
postcode = addr_full[1].split(',')[1]
if(len(location)>0):
lat = float( location[0][4:].split(",")[0])
lon = float( location[0][4:].split(",")[1])
else:
lat =''
lon=''
properties = {
'addr_full': addr_full[0],
'phone': response.xpath('normalize-space(//div[@id="cq-shop-info"]/p[@class="impinfo"]/text())').extract_first(),
'city':city,
'state': '',
'postcode': postcode,
'ref': response.url,
'website': response.url,
'lat': lat,
'lon': lon,
}
# hours = self.parse_hours(response.xpath('//ul[@class="cleanList srHours srSection"]/li'))
# if hours:
# properties['opening_hours'] = hours
yield inputoutput(**properties)
def parse(self, response):
data = json.loads(response.body_as_unicode())
for key, value in data.items():
if 'AddressLine' in value:
addr_full = value['AddressLine'].split(',')
address = ", ".join(addr_full[:len(addr_full) - 1])
city = addr_full[len(addr_full) - 1]
else:
address = ""
city = ""
if 'postcode' in value:
postcode = value['postcode']
else:
postcode = ""
properties = {
'ref': key,
'name': value['branch_name'],
'addr_full': address,
'city': city,
'country': 'United Kingdom',
'postcode': postcode,
'lat': value['Latitude'],
'lon': value['Longitude'],
'phone': value['telephone'],
}
opening_hours = self.store_hours(value)
if opening_hours:
properties['opening_hours'] = opening_hours
yield inputoutput(**properties)
def parse_store(self, response):
json_data = response.xpath(
'//head/script[@type="application/ld+json"]/text()')[1].extract()
json_data = json_data.replace(
'// if the location file does not have the hours separated into open/close for each day, remove the below section',
'')
data = json.loads(json_data)
properties = {
'phone':
data['telephone'],
'website':
response.xpath('//head/link[@rel="canonical"]/@href')[0].extract(),
'ref':
data['@id'],
'opening_hours':
self.store_hours(data['openingHoursSpecification']),
'lon':
float(data['geo']['longitude']),
'lat':
float(data['geo']['latitude']),
}
address = self.address(data['address'])
if address:
properties.update(address)
yield inputoutput(**properties)
def parse(self, response):
stores = json.loads(response.body_as_unicode())
for store in stores:
props = {}
store_info = store.get('store_info', '')
props['ref'] = store_info['corporate_id']
props['lat'] = store_info['latitude']
props['lon'] = store_info['longitude']
props['state'] = store_info['region']
props['city'] = store_info['locality']
props['opening_hours'] = self.parse_hours(
store_info.get('store_hours', ''))
props['addr_full'] = ', '.join([
store_info['address'],
store_info.get('address_extended', '')
])
sieve_out = ['website', 'phone', 'postcode', 'country']
props.update({key: store_info[key] for key in sieve_out})
yield inputoutput(**props)
def parse(self, response):
results = json.loads(response.body_as_unicode())
for data in results['results']:
ref = data['id_suc']
name = "Coto " + data['desc_suc']
street = data['direccion']
phone = data['telefono']
lat = data['latitud']
lon = data['longitud']
mon_thu = "Mo-Th " + data['hor_lu_a_ju']
fri = "Fr " + data['hor_vi']
sat = "Sa " + data['hor_sa']
sun = "Su " + data['hor_do'] if data['hor_do'] != "Cerrado" else "Su off"
opening_hours = "{}; {}; {}; {}".format(
mon_thu, fri, sat, sun).replace(' a ', '-')
yield inputoutput(
ref=ref,
lat=lat,
lon=lon,
name=name,
street=street,
country="Argentina",
phone=phone,
addr_full=street,
opening_hours=opening_hours
)
def parse(self, response):
data = response.xpath('.//div[@class="location-listing-item row"]')
for store in data:
ref = self.parse_Ref(store)
properties = {
'ref':
ref,
'addr_full':
store.xpath("//span[@class='address']//text()").extract_first(
).strip(),
'city':
store.xpath(
"//span[@class='city']//text()").extract_first().strip(),
'state':
store.xpath(
"//span[@class='state']//text()").extract_first().strip(),
'postcode':
store.xpath(
"//span[@class='zip']//text()").extract_first().strip(),
'phone':
store.xpath(
"//span[@class='phone']//text()").extract_first().strip(),
'name':
store.xpath(".//strong//text()").extract_first().strip(),
'lon':
store.xpath("@data-lon").extract_first(),
'lat':
store.xpath("@data-lat").extract_first()
}
yield inputoutput(**properties)
def parse(self, response):
data = json.loads(response.body_as_unicode())
for store in data.get('features', []):
store_info = store['properties']
properties = {
"ref": store_info['id'],
'addr_full': store_info['addressLine1'],
'city': store_info['addressLine3'],
'state': store_info['subDivision'],
'country': store_info['addressLine4'],
'postcode': store_info['postcode'],
'phone': store_info.get('telephone'),
'lon': store['geometry']['coordinates'][0],
'lat': store['geometry']['coordinates'][1],
}
hours = store_info.get('restauranthours')
try:
hours = self.store_hours(hours)
if hours:
properties['opening_hours'] = hours
except:
self.logger.exception("Couldn't process opening hours: %s",
hours)
yield inputoutput(**properties)
def parse_detail_product(self, response):
product = response.meta.get('product')
open_dates = response.xpath('//table[@id="hours-table"]//tr')
product['opening_hours'] = self.store_hours(
open_dates) if len(open_dates) > 0 else u'24/7'
yield inputoutput(**product)
def parse_us(self, response):
results = json.loads(response.body_as_unicode())
stores = results['stores']
for store_key in stores:
store_data = stores[store_key]
properties = {
'phone': store_data['phone'],
'addr_full': store_data['address1'].title(),
'city': store_data['city'].title(),
'state': store_data['stateCode'],
'postcode': store_data['postalCode'],
'lon': float(store_data['longitude']),
'lat': float(store_data['latitude']),
'ref': store_key,
}
hours = (store_data['storeHours']
if 'storeHours' in store_data else None)
opening_hours = None
if hours and ("Please call" not in hours):
opening_hours = self.store_hours(hours)
if opening_hours:
properties['opening_hours'] = opening_hours
yield inputoutput(**properties)
def parse_store(self, response):
# There are newlines in the opening hours, which is bad JSON. We turn
# off strict mode so Python's JSON library will parse it.
json_content = response.xpath('//script[@type="application/ld+json"]/text()').extract_first()
data = json.loads(json_content, strict=False)
store_data = data[0]
properties = {
'website': store_data['url'],
'name': store_data['name'],
'phone': store_data['address']['telephone'],
'ref': store_data['url'],
'addr_full': store_data['address']['streetAddress'],
'postcode': store_data['address']['postalCode'],
'state': store_data['address']['addressRegion'],
'city': store_data['address']['addressLocality'],
'lon': float(store_data['geo']['longitude']),
'lat': float(store_data['geo']['latitude']),
}
opening_hours = self.store_hours(store_data['openingHours'])
if opening_hours:
raw = store_data['openingHours']
formatted = opening_hours
yield inputoutput(raw, formatted)
def process_store(self, store):
opening_hours, phone = ('', '')
data = store.xpath(
'//div[@class="col-lg-4"]/div/*[not(self::h2 or self::strong)]//text()'
).extract()
normalize_data = [
val for val in [info.strip() for info in data] if val
]
final_data = [clean for clean in normalize_data if clean not in SIEVE]
city, state_zip = final_data[2].split(',')
state, pcode = state_zip.strip().split()
if 'Phone Number' in final_data:
phone = final_data[final_data.index('Phone Number') + 1]
if 'Store Hours' in final_data:
opening_hours = self.parse_hours(
final_data[final_data.index('Store Hours') + 1:][0])
props = {
'addr_full': final_data[1],
'ref': store.url,
'city': city,
'postcode': pcode,
'state': state,
'website': store.url,
'opening_hours': opening_hours,
'phone': phone,
}
yield inputoutput(**props)
def parse_links(self, response):
hours = response.xpath(
'//form[@id="directions-form"]/input[@name="hours"]/@value'
).extract_first()
website = response.xpath(
'//head/link[@rel="canonical"]/@href').extract_first()
link_id = website.split("/")[-2]
# properties = {
# "addr_full": response.xpath('//form[@id="directions-form"]/input[@name="address"]/@value').extract_first(),
# "city": response.xpath('//form[@id="directions-form"]/input[@name="city"]/@value').extract_first(),
# "state": response.xpath('//form[@id="directions-form"]/input[@name="state"]/@value').extract_first(),
# "postcode": response.xpath('//form[@id="directions-form"]/input[@name="zip"]/@value').extract_first(),
# "phone": response.xpath('//form[@id="directions-form"]/input[@name="phone"]/@value').extract_first(),
# "website": website,
# "ref": link_id,
# "opening_hours": self.process_hours(hours[0]),
# "lat": float(response.xpath('//form[@id="directions-form"]/input[@name="lat"]/@value').extract_first()),
# "lon": float(response.xpath('//form[@id="directions-form"]/input[@name="long"]/@value').extract_first()),
# }
# yield inputoutput(**properties)
raw = hours[0]
formatted = self.process_hours(hours[0])
yield inputoutput(raw, formatted)
def parse(self, response):
data = json.loads(response.body_as_unicode())
for store in data:
# properties = {
# "ref": store.get('id'),
# "name": store.get('name'),
# "addr_full": store.get('address'),
# "city": store.get('city'),
# "state": store.get('state'),
# "postcode": store.get('zip'),
# "phone": store.get('telephone'),
# }
# if store.get('url'):
# properties['website'] = 'https://www.whitecastle.com' + store.get('url')
# if store.get('latitude'): properties['lat'] = float(store.get('latitude'))
# if store.get('longitude'): properties['lon'] = float(store.get('longitude'))
if store.get('timetable'):
raw = store.get('timetable')
formatted = self.store_hours(store.get('timetable'))
yield inputoutput(raw,formatted)
def parse_page(self, response):
row = response.xpath('//tr')
for i in row:
storeid = i.xpath('./td[1]/text()').extract_first()
name = i.xpath('./td[2]/text()').extract_first()
street = i.xpath('./td[3]/text()').extract_first()
city = i.xpath('./td[4]/text()').extract_first()
state = i.xpath('./td[5]/text()').extract_first()
postcode = i.xpath('./td[6]/text()').extract_first()
phone = i.xpath('./td[7]/text()').extract_first()
lat = i.xpath('./td[8]/text()').extract_first()
lon = i.xpath('./td[9]/text()').extract_first()
addr_full = "{} {}, {} {}".format(street, city, state, postcode)
yield inputoutput(
ref=storeid,
name=name,
street=street,
city=city,
state=state,
postcode=postcode,
addr_full=addr_full,
phone=phone,
lat=lat,
lon=lon,
)
def parse(self, response):
results = json.loads(response.body_as_unicode())
if results:
for i in results:
# ref = i['storeid']
# name = i['restaurantname']
# street = i['address1']
# city = i['city']
# state = i['statecode']
# postcode = i['zipcode']
# phone = i['phone']
# lon = i['longitude']
# lat = i['latitude']
hours = self.convert_hours(i['businesshours'])
# addr_full = "{} {}, {} {}".format(street, city, state, postcode)
# yield inputoutput(
# ref=ref,
# name=name,
# street=street,
# city=city,
# state=state,
# postcode=postcode,
# addr_full=addr_full,
# phone=phone,
# lon=lon,
# lat=lat,
# opening_hours=hours
# )
raw = i['businesshours']
formatted = hours
yield inputoutput(raw, formatted)
def parse(self, response):
for match in response.xpath(
"//h2[contains(@class,'font-weight-700 text-uppercase')]/parent::div/parent::div"
):
# cityState = match.xpath(".//div[contains(@class,'heading-text el-text')]/div/p/text()").extract_first();
# cityString = cityState.split(",")[0].strip()
# stateString = cityState.split(",")[1].strip()
# addressString = match.xpath(".//div[contains(@class,'uncode_text_column')]/p[contains(@style,'text-align: center;')][not(.//strong)]/text()").extract_first().strip()
# postcodeString = addressString.split(stateString)[1].strip()
# addressString = addressString.split(stateString)[0].replace(',','').strip().strip(cityString).strip()
# if(match.xpath(".//div[contains(@class,'uncode_text_column')]/p[contains(@style,'text-align: center;')][not (.//strong)]/br/following-sibling::text()").extract_first() is None):
# phoneString = ""
# else:
# phoneString = match.xpath(".//div[contains(@class,'uncode_text_column')]/p[contains(@style,'text-align: center;')][not (.//strong)]/br/following-sibling::text()").extract_first()
# phoneString = phoneString.replace(' ','').strip()
hoursString = ""
unfmthours = ''
for hoursMatch in match.xpath(
".//p[contains(@style,'text-align: center;')]/strong//following-sibling::text()"
):
unfmthours = unfmthours + ' ' + hoursMatch.extract().replace(
'\n', '')
hoursString = hoursString + ' ' + self.store_hours(
hoursMatch.extract().replace('\n', ''))
raw = unfmthours
formatted = hoursString
yield inputoutput(raw, formatted)
def parse(self, response):
data = json.loads(response.body_as_unicode())
for store in data['results']:
# properties = {
# "ref": store['id'],
# "name": store['name'],
# "opening_hours": store['hours']['operating'],
# "addr_full": store['address'],
# "city": store['city'],
# "state": store['state'],
# "postcode": store['zip'],
# "country": store['country'],
# "lon": float(store['lon']),
# "lat": float(store['lat']),
# "phone": store['phone'],
# }
# "opening_hours": store['hours']['operating'],
raw = store['hours']['operating']
formatted = store['hours']['operating']
yield inputoutput(raw,formatted)
next_url = data['next']
if next_url is not None:
next_url = response.urljoin(next_url)
yield scrapy.Request(url=next_url, headers=HEADERS, callback=self.parse)
def parse_store(self, response):
json_data = response.xpath('//script[@type="text/javascript"]/text()'
).extract_first().replace('\n', '').replace(
'\t', '').split('.push(')[1].rstrip(')')
data = json.loads(json_data)
geojson_data = response.xpath(
'//script[@class="js-store-finder-initial-state"][@type="application/json"]/text()'
).extract_first()
geodata = json.loads(geojson_data)
# properties = {
# 'name': data['seoData']['name'],
# 'ref': data['seoData']['name'],
# 'addr_full': data['seoData']['address']['streetAddress'],
# 'city': data['seoData']['address']['addressLocality'],
# 'postcode': data['seoData']['address']['postalCode'],
# 'country': data['seoData']['address']['addressCountry'],
# 'website': response.request.url,
# 'opening_hours': str(data['seoData']['openingHours']).replace('[','').replace(']','').replace("'",''),
# 'lat': float(geodata['store']['latlng']['lat']),
# 'lon': float(geodata['store']['latlng']['lng']),
# }
raw = str(data['seoData']['openingHours'])
formatted = str(data['seoData']['openingHours']).replace(
'[', '').replace(']', '').replace("'", '')
yield inputoutput(raw, formatted)
def parse(self, response):
data = json.loads(response.body_as_unicode())
stores = data.get('Stores', None)
props = {}
for store in stores:
props['lat'] = store.pop('Latitude', None)
props['lon'] = store.pop('Longitude', None)
props['ref'] = store.pop('StoreID', None)
props['website'] = URL
for new_key, old_keys in NORMALIZE_KEYS:
props[new_key] = ", ".join([
store.pop(key, '').strip() for key in old_keys
if store[key]
])
opening_hours = normalize_time(store.pop('Hours', ''))
if opening_hours:
props['opening_hours'] = opening_hours
props.pop('Hours', None)
yield inputoutput(**props)
def parse_location(self, response):
unp = {} # Unprocessed properties
properties = {}
unp['phone'] = response.xpath(
'//span[@itemprop="telephone"]/a/text()').extract_first()
unp['name'] = response.xpath(
'//span[@itemprop="name"]/h2[@class="loc_d_title"]/text()'
).extract_first()
unp['ref'] = response.url
unp['website'] = response.url
addressdiv = response.xpath('//div[@itemprop="address"]')[0]
unp['addr_full'] = addressdiv.xpath(
'.//span[@itemprop="streetAddress"]/text()').extract_first()
unp['city'] = addressdiv.xpath(
'.//span[@itemprop="addressLocality"]/text()').extract_first()
unp['state'] = addressdiv.xpath(
'.//span[@itemprop="addressRegion"]/text()').extract_first()
unp['postcode'] = addressdiv.xpath(
'.//span[@itemprop="postalCode"]/text()').extract_first()
hours = response.xpath(
'//ul[@class="loc_d_times row"]/li/text()').extract()
raw = hours
opening_hours = None
if hours:
opening_hours = self.store_hours(','.join(hours))
if opening_hours:
formatted = opening_hours
yield inputoutput(raw, formatted)
for key in unp:
if unp[key]:
properties[key] = unp[key].strip()
def parse(self, response):
# retrieve JSON data from REST endpoint
# items = response.xpath('//text()').extract()
# convert data variable from unicode to string
# items = str(items)
# convert type string representation of list to type list
# data = [items]
# load list into json object for parsing
jsondata = json.loads(response.body_as_unicode())
# iterate items
for item in jsondata['d']['results']:
# print str(item['Address1'])
yield inputoutput(
ref=item['EntityID'],
lat=float(item['Latitude']),
lon=float(item['Longitude']),
addr_full=self.parseAddr(item['Address1'], item['Address2']),
city=item['Locality'],
state=item['AdminDistrict'],
postcode=item['PostalCode'],
name=item['MallName'],
phone=item['Phone'],
opening_hours=item['StoreHours'],
)
def parse_location(self, response):
ref = response.xpath('//a[@class="btn set-as-location"]/@data-loc-id').extract_first() \
or response.request.url
properties = {
"phone":
response.xpath(
'//div[@class="module"]/p/a/text()').extract_first(),
"ref":
ref,
"name":
response.xpath(
'//div[@class="location-details"]/h1/text()').extract_first(),
"opening_hours":
self.store_hours(response.xpath('//dl[@class="hours"]')[0]),
"lon":
float(
response.xpath('//span[@id="currentlocdistanceid"]/@data-long'
).extract_first()),
"lat":
float(
response.xpath('//span[@id="currentlocdistanceid"]/@data-lat').
extract_first()),
}
properties.update(self.address(response))
yield inputoutput(**properties)
def parse_stores(self, response):
ref = response.meta['id']
json_data = json.loads(response.body_as_unicode())
if 'address1' not in json_data:
return
properties = {
'addr_full': json_data['address1'],
'phone': json_data['phoneNumber'],
'city': json_data['city'],
'state': json_data['stateCode'],
'postcode': json_data['postalCode'],
'ref': ref,
'website':
"http://www.acehardware.com/mystore/index.jsp?store=" + ref,
'lat': float(json_data['latitude']),
'lon': float(json_data['longitude']),
}
hours = self.parse_hours(json_data['hours'])
raw = json_data['hours']
if hours:
properties['opening_hours'] = hours
formatted = hours
yield inputoutput(raw, formatted)
def parse(self, response):
json_str = response.body_as_unicode()
data = json.loads(json_str)['locations']
for store in data:
store_details = store['bing']
(num, street) = store_details['AddressLine'].split(' ', 1)
properties = {
"phone": store_details['Phone'],
"ref": store_details['EntityID'],
"name": store['post']['post_title'],
"opening_hours": self.store_hours(store_details),
"lat": store_details['Latitude'],
"lon": store_details['Longitude'],
"addr_full": store_details['AddressLine'],
"housenumber": num,
"street": street,
"city": store_details['Locality'],
"state": store_details['AdminDistrict'],
"postcode": store_details['PostalCode'],
"country": store_details['CountryRegion'],
"website": store['url'],
}
yield inputoutput(**properties)
def parse_store(self, response):
contacts = response.xpath(
'//ul[@class="contact"]/li/span/text()').extract()
properties = {
'addr_full': contacts[0],
'city': contacts[1],
'state': contacts[2],
'postcode': contacts[3],
'phone': contacts[4],
'ref': response.url,
'website': response.url,
}
day_groups = response.xpath(
'//ul[@class="hours"]/li[@class="storehours"]/text()').extract()
opening_hours = []
for day_group in day_groups:
match = re.match(r'(.*): (\d+)-(\d+)', day_group)
days, f_hr, t_hr = match.groups()
f_hr = int(f_hr)
t_hr = int(t_hr) + 12
opening_hours.append('{} {:02d}:00-{:02d}:00'.format(
days, f_hr, t_hr))
if opening_hours:
properties['opening_hours'] = '; '.join(opening_hours)
yield inputoutput(**properties)
def parse_store(self, response):
properties = {
'website':
response.xpath(
'//head/link[@rel="canonical"]/@href').extract_first(),
'ref':
str(
response.xpath('/html/body/div[1]/div[1]/header/h1/text()').
extract()).strip("['']"),
'opening_hours':
re.sub(
'\s+', ' ',
response.css('#secondary').extract()[0].split('<h5>Hours</h5>')
[1].replace('<br>', '').replace('</aside>', '').replace(
'\t', ' ').replace('\n', '').replace('\r', ' ')).strip(),
# 'lon': float(data['geo']['longitude']), # not lon on page
# 'lat': float(data['geo']['latitude']), # not lat on page
}
address = self.address(
response.xpath(
'/html/body/div[1]/div[1]/aside/address/text()').extract())
if address:
properties.update(address)
yield inputoutput(**properties)
def parse(self, response):
phoneregex = re.compile('^<a.+>([0-9\-]+)<\/a>$')
stores = json.loads(response.body_as_unicode())
for key, value in stores.items():
all_address = value['address'].split(',')
len_address = len(all_address)
state_zipcode = all_address[len_address - 1]
zipcode = re.findall(r"(\d{5})", state_zipcode)
addr_full = re.findall(r"^[^(,|.)]+", value['address'])[0]
if (len(zipcode) > 0):
zipcode = zipcode[0]
else:
zipcode = ''
state = re.findall(r"([A-Z]{2})", state_zipcode)
if (len(state) > 0):
state = state[0]
else:
state = ''
properties = {
'ref': value['ID'],
'name': value['title'],
'addr_full': addr_full,
'city': value['title'],
'state': state,
'postcode': zipcode,
'lat': value['location']['lat'],
'lon': value['location']['lng'],
}
if value['phone']:
properties['phone'] = value['phone']
yield inputoutput(**properties)
def parse_store(self, response):
address = response.xpath(
'//div[@class="street"]//text()').extract_first().strip()
postalCode, city = self.parse_city(
response.xpath(
'//div[@class="postal-code-city"]//text()').extract_first())
phone = response.xpath(
'//div[@class="field--phone"]//text()').extract_first()
if phone:
phone = phone.strip()
else:
phone = ""
properties = {
'addr_full': address,
'city': city,
'name': "McDonald's",
'postcode': postalCode,
'phone': phone,
'ref': response.meta['ref'],
'lon': response.meta['lon'],
'lat': response.meta['lat']
}
data = re.finditer(r'<span class=\"label\">.*</span>(.*)</li>',
response.body_as_unicode())
opening_hours = self.store_hours(data)
if opening_hours:
properties['opening_hours'] = opening_hours
yield inputoutput(**properties)
def parse(self, response):
jsonresponse = json.loads(response.body_as_unicode())
for store in jsonresponse:
addr_full = store['address'] + ", " + store['city'] + " " + store[
'state'] + " " + store['zip']
datestring = store['hours']
hour_match = re.findall(r"(\d{1,2}:\d{1,2})", datestring)
for hour in hour_match:
if hour == "9:00":
pass
else:
raise DifferentHours(
"Store added with different hours than 09:00-21:00")
properties = {
'name': store['store'],
'addr_full': addr_full,
'street': store['address'],
'city': store['city'],
'state': store['state'],
'postcode': store['zip'],
'country': store['country'],
'phone': store['phone'],
'website': store['permalink'],
'opening_hours': '09:00-21:00',
'ref': store['id'] + " " + store['store'],
'lat': float(store['lat']),
'lon': float(store['lng']),
}
yield inputoutput(**properties)
def parse(self, response):
# testing
response.selector.remove_namespaces()
for store_elem in response.xpath('//LocationFinderStore'):
city = store_elem.xpath('./City/text()').extract_first()
lat = store_elem.xpath('./Latitude/text()').extract_first()
lon = store_elem.xpath('./Longitude/text()').extract_first()
ref = store_elem.xpath('./StoreNumber/text()').extract_first()
addr_full = store_elem.xpath(
'./StreetAddress/text()').extract_first()
zipcode = store_elem.xpath('./ZipCode/text()').extract_first()
state = store_elem.xpath('./State/text()').extract_first()
name = store_elem.xpath('./Name/text()').extract_first()
properties = {
'name': name,
'addr_full': addr_full,
'city': city,
'state': state,
'postcode': zipcode,
'ref': ref,
'website': 'http://locations.in-n-out.com/' + ref,
'lon': float(lon),
'lat': float(lat),
}
yield inputoutput(**properties)