def get_nearby_places_for_site(national_site):
coordinates = get_site_coordinates(national_site)
if coordinates[0] == 0:
print(">>> UNABLE TO RETRIEVE NEARBY PLACES")
return None
latitude = str(coordinates[0])
longitude = str(coordinates[1])
location = latitude + "," + longitude
site = "GOOGLE"
national_site = national_site
topic = "nearby " + national_site
cache = Cache(cache_file)
base2 = "https://maps.googleapis.com/maps/api/place/nearbysearch/json?"
params_d2 = {}
params_d2["key"] = google_places_key
params_d2["location"] = location
params_d2["radius"] = 10000
UID = create_id(site, topic)
nearby_response = cache.get(UID)
if nearby_response == None:
nearby_response = requests.get(base2, params_d2).text
testurl = requests.get(base2, params_d2).url
#print(testurl)
#response = nearby_response.json()
cache.set(UID, nearby_response)
responses = json.loads(nearby_response)
responses = responses["results"]
NearbyList = []
for i in responses:
name = i["name"]
latitude = i["geometry"]["location"]["lat"]
longitude = i["geometry"]["location"]["lng"]
place = NearbyPlace(name, latitude, longitude)
NearbyList.append(place)
return NearbyList
def get_nearby_places_for_site(national_site):
cache_file = "part2_nearbysearch.json"
cache = Cache(cache_file)
base = "https://maps.googleapis.com/maps/api/place/nearbysearch/json?"
params_diction = {}
params_diction["key"] = google_places_key
params_diction["location"] = get_location_for_site(national_site)
params_diction["radius"] = 10000
identifier = base + params_diction["key"] + params_diction[
"location"] + str(params_diction["radius"])
response = cache.get(identifier)
while response is None:
response = json.loads(requests.get(base, params_diction).text)
cache.set(identifier, response, 10)
nearby_result_list = response["results"]
nearby_list = []
for nearby in nearby_result_list:
name = nearby["name"]
lat = nearby["geometry"]["location"]["lat"]
lng = nearby["geometry"]["location"]["lng"]
nearby_list.append(NearbyPlace(name, lat, lng))
return nearby_list
def get_site_coordinates(national_site):
site = "GOOGLE"
topic = national_site
cache = Cache(cache_file)
base1 = "https://maps.googleapis.com/maps/api/place/findplacefromtext/json?"
params_d = {}
params_d["key"] = google_places_key
params_d["input"] = national_site
params_d["inputtype"] = "textquery"
params_d['fields'] = 'geometry,formatted_address'
# params_d["locationbias"] = "point:lat,lng"
UID = create_id(site, topic)
get_data = cache.get(UID)
if get_data == None:
get_data = requests.get(base1, params_d).text
#testurl = requests.get(base1, params_d).url
#print(testurl)
cache.set(UID, get_data)
lat = 0
long = 0
site_data = json.loads(get_data)
try:
place = site_data['candidates'][0]
latitude = place['geometry']['location']['lat']
longitude = place['geometry']['location']['lng']
site_coordinates = latitude, longitude
except:
site_coordinates = lat, long
print(
"Sorry! There was an error retrieving coordinates for {}. We will not be able to list its nearby places or map it."
.format(national_site))
return site_coordinates
def website_scraping_and_cache(url):
cache = Cache("national_sites.json")
result = cache.get(url)
if not result:
result = requests.get(url).text
cache.set(url, result, 30)
return BeautifulSoup(result, 'html.parser')
def get_sites_for_state(state_abbr):
cache_file = "part1.json"
url_to_scrape = "https://www.nps.gov/state/{}/index.htm".format(state_abbr)
cache = Cache(cache_file)
while cache.get(url_to_scrape) is None:
html_text = requests.get(url_to_scrape).text
cache.set(url_to_scrape, html_text, 10)
soup = BeautifulSoup(cache.get(url_to_scrape), features='html.parser')
parks = soup.find(id="list_parks").find_all(class_='clearfix')
### Information you should get for each National Site will include the site name, site type, and the physical (or mailing) address.
national_park_list = []
for park in parks:
site_name = park.find('h3').text
site_type = park.find('h2').text
site_desc = park.find('p').text
address_url = park.find_all('a')[2].get('href')
cache_file = "part1_address.json"
url_to_scrape = address_url
cache = Cache(cache_file)
while cache.get(url_to_scrape) is None:
html_text = requests.get(url_to_scrape).text
cache.set(url_to_scrape, html_text, 10)
soup_add = BeautifulSoup(cache.get(url_to_scrape),
features='html.parser')
address_street = soup_add.find(itemprop='streetAddress').text
address_city = soup_add.find(itemprop='addressLocality').text
address_state = soup_add.find(itemprop='addressRegion').text
address_zip = soup_add.find(itemprop='postalCode').text
national_park_list.append(
NationalSite(site_type, site_name, site_desc, address_street,
address_city, address_state, address_zip))
return national_park_list
def get_sites_for_state(state_abbr):
state = state_abbr
topic = state
cache = Cache(cache_file)
base = project_dictionary[state]
UID = create_id(site, topic)
state_response = cache.get(UID)
if state_response == None:
state_response = requests.get(base).text
cache.set(UID, state_response)
NationalSiteList = state_process(state_response)
return NationalSiteList
def get_nearby_places_for_site(national_site):
nearby_places_list = [] # the result list that stores the nearby places
lng, lat = get_geolocation_info(national_site)
national_site.lat = lat
national_site.lng = lng
if lng == None and lat == None:
print("There is no geolocation info for " + str(national_site) + ".")
else:
params_dic = {
"key": google_places_key,
"location": str(lat) + "," + str(lng),
"radius": 10000
}
unique_identifier = params_unique_combination(nearbysearch_base_url,
params_dic)
cache = Cache("nearby_places.json")
places_json = cache.get(unique_identifier)
if not places_json:
result = requests.get(nearbysearch_base_url, params=params_dic)
places_json = json.loads(result.text)
cache.set(unique_identifier, places_json, 30)
try:
places = places_json["results"]
for place in places:
place_class = NearbyPlace(place['name'])
try:
place_class.lat = place['geometry']['location']['lat']
place_class.lng = place['geometry']['location']['lng']
except:
pass
nearby_places_list.append(place_class)
except:
pass
return nearby_places_list
def get_location_for_site(national_site):
cache_file = "part2_textsearch.json"
cache = Cache(cache_file)
base = "https://maps.googleapis.com/maps/api/place/textsearch/json?"
params_diction = {}
params_diction["query"] = "{},{}".format(national_site.name,
national_site.type)
params_diction["key"] = google_places_key
identifier = base + params_diction["query"] + params_diction["key"]
response = cache.get(identifier)
while response is None:
response = json.loads(requests.get(base, params_diction).text)
cache.set(identifier, response, 10)
try:
lat = str((response["results"][0]["geometry"]["location"]["lat"]))
lng = str((response["results"][0]["geometry"]["location"]["lng"]))
return lat + ',' + lng
except:
return None
def get_geolocation_info(national_site):
params_dic = {
"key": google_places_key,
"address": national_site.name + " " + national_site.type
}
unique_identifier = params_unique_combination(geolocation_base_url,
params_dic)
cache = Cache("geolocation_info.json")
geolocation_json = cache.get(unique_identifier)
if not geolocation_json:
result = requests.get(geolocation_base_url, params=params_dic)
geolocation_json = json.loads(result.text)
cache.set(unique_identifier, geolocation_json, 30)
try:
geolocation = geolocation_json["results"][0]['geometry']['location']
lng = geolocation['lng']
lat = geolocation['lat']
except:
lng = None
lat = None
return lng, lat
import requests
from datetime import datetime
import json
import plotly
import plotly.plotly as py
import plotly.graph_objs as go
#################################
# PART 1: SCRAPING DATA FROM TA #
#################################
CACHE_FNAME = "top_destination.json"
url_to_scrape = "https://www.tripadvisor.com/TravelersChoice-Destinations"
cache_html = Cache(CACHE_FNAME)
while cache_html.get(url_to_scrape) is None:
data = requests.get(url_to_scrape)
html_text = data.text
cache_html.set(url_to_scrape, html_text, 10)
print("DATA NOT IN CACHE, SCRAPING FROM URL NOW")
soup = BeautifulSoup(cache_html.get(url_to_scrape), features="html.parser")
mainnames = soup.find_all("div", class_="mainName")
destination_name_lst = []
for mainname in mainnames:
name = mainname.find("a").text
destination_name_lst.append(name)
city_name_lst = []
for items in destination_name_lst:
city_name = items.split(",")[0]
city_name_lst.append(city_name)
project_dictionary[t.attrs['href']
[7:9]] = "https://www.nps.gov" + t.attrs["href"]
return project_dictionary
#################################
# CONFIG & RUN LIST SCRAPE #
#################################
cache_file = "NPS.json"
site = "NPS"
topic = "states"
cache = Cache(cache_file)
base = "https://www.nps.gov/index.htm"
UID = create_id(site, topic)
response = cache.get(UID)
if response == None:
response = requests.get(base).text
cache.set(UID, response)
process(response)
#####################################
## NATIONAL SITE CLASS
#####################################
class NationalSite():
def __init__(self, type, name, desc, address, url=None):
self.type = type
def process(response):
name_lst = []
url_lst = []
site_lst = []
soup = BeautifulSoup(response, 'html.parser')
national_site_container = soup.find_all(
'div', class_='col-md-9 col-sm-9 col-xs-12 table-cell list_left')
for container in national_site_container:
# Name
name = container.h3.text
name_lst.append(name)
# print(name)
# Type
type = container.h2.text
# print(type)
# Description
process.desc = container.p.text
# print(desc)
# URL
process.url = "https://www.nps.gov" + container.h3.a.get(
'href') + "index.htm"
url_lst.append(process.url)
# print(url)
# Look at each URL and scrape that page
for urls in url_lst:
cache_file = "nps_address.json"
cache_address = Cache(cache_file)
UID = create_id_sites(urls)
response2 = cache_address.get(UID)
if response2 == None:
response2 = requests.get(urls).text
cache_address.set(UID, response2, 100)
soup2 = BeautifulSoup(response2, "html.parser")
try:
## Address Street
address_street_fndr = soup2.find(
attrs={"itemprop": "streetAddress"})
process.address_street = address_street_fndr.text
process.address_street = process.address_street.replace(
'\n', '')
# print(process.address_street)
## Address City
address_city_fndr = soup2.find(
attrs={"itemprop": "addressLocality"})
process.address_city = address_city_fndr.text
# print(process.address_city)
## Address State
address_state_fndr = soup2.find(
attrs={"itemprop": "addressRegion"})
process.address_state = address_state_fndr.text
# print(process.address_state)
## Address ZIP
address_zip_fndr = soup2.find(attrs={"itemprop": "postalCode"})
process.address_zip = address_zip_fndr.text
process.address_zip = process.address_zip.strip()
# print(process.address_zip)
except: # If address is not found
# print("No address found for {}".format(urls))
process.address_street = "Not found"
process.address_city = "Not found"
process.address_state = "Not found"
process.address_zip = "Not found"
national_sites = NationalSite(
type, name) # Create a new NationalSite instance
site_lst.append(national_sites
) # Append each NationalSite instance to site_lst list
return site_lst