def update(status): try: get("http://starfury.eu5.org/alter.php?name=" + envars["Name"] + "&gamemode=" + envars["Gamemode"] + "&map=" + envars["Map"] + "&players=" + str(len(users)) + "/" + envars["Player Limit"] + "&status=" + status + "&ip=" + envars["IPv4"] + "&port=" + envars["Port"]) except: pass
def cari_link(page): import urllib as link from bs4 import BeautifulSoup import re print (page) html_page = link.urlopen("https://www.mainbasket.com/c/4/berita/abl?page="+str(page)).read() soup = BeautifulSoup(html_page, "html.parser") for a in soup.findAll('div', 'post-title'): #print a for link in a.findAll('a', attrs={'href': re.compile("^https://")}): print link.get('href') kumpulan_link.append(link.get('href'))
def download(self, follow_par_dir = False, verbose = True, ext = ''): if verbose: print "[*] Starting WebScraper" for url in self.urls: self.__br.open(url) fol = self.__folder_encode(url) if not os.path.exists(self.__folder_encode(url)): os.mkdir(self.__folder_encode(url)) if verbose: print "[*] Scraping: ", self.__br.title() for link in self.__br.links(): url_ = link.absolute_url try: if not self.__is_dir(url_) and link.url[0:3] != '?C=' and url_.split('.')[-1] in ext: if verbose: print "[!] Downloading: ", self.__file_encode(url_.split('/')[-1]) get(url_, fol+self.__file_encode(url_.split('/')[-1])) else: if url_ not in self.urls and follow_par_dir and link.url[0:3] != '?C=' and self.__is_dir(url_): if verbose: print "[*] Adding parent directory ",url_," to the URL Queue" self.urls.append(url_) elif url_ not in self.urls and not follow_par_dir and url_ == '/'.join(link.base_url.split('/')[0:-2])+'/': continue except Exception, err: print "[!!] ", err pass
def cari_link(page): import urllib as link from bs4 import BeautifulSoup import re print(page) html_page = link.urlopen( "http://surabaya.tribunnews.com/topic/berita-gresik?&page=" + str(page)).read() soup = BeautifulSoup(html_page, "lxml") for a in soup.findAll('h3', 'f20 ln24 fbo'): for link in a.findAll('a', attrs={'href': re.compile("^http://")}): #print link.get('href') kumpulan_link.append(link.get('href'))
def find_emails(url): print("Finding Emails on: {}".format(url)) try: html_body = get(url) parsed = BeautifulSoup(html_body, 'html.parser') except Exception as e: print(e) return None title = parsed.title.string if parsed.title else url emails = re.findall(ReEmailAddress, parsed.getText()) return (title, emails)
def getActualFollow(): global viewers,CHAN,PASS,fetching fetching = True try: headers = {'Accept': 'application/vnd.twitchtv.v3+json'} r = urllib.get('https://api.twitch.tv/kraken/streams/'+CHAN[1:]+'?oauth_token='+PASS[6:], headers=headers) jsonData = r.json() ac.console('json {}'.format(jsonData)) if jsonData['stream'] != None: viewers = str(jsonData['stream']['viewers']) else: viewers = 'offline' except: pass fetching = False
API_params = {'token': 'c5213a1102b8422c80378944e1246d10', 'qc': 'all', 'complete': '1', 'network': '1,2', 'status': 'active', 'recent': '360'} # inciweb_url = 'http://inciweb.nwcg.gov/feeds/rss/incidents/' # inciweb = feedparser.parse(inciweb_url) fire_lat = [] fire_lon = [] file_in = 'C:\\FireWeatherNow\\storage\\fire_data\\active_fires.json' with open(file_in, 'r') as file1: json.load(file1) print(file1) nearest_stids = [] for k in range(len(fire_lat)): #put polygon path here r = urllib.get(baseURL+API_params + '&radius=' + str(fire_lat[k]) + ',' + str(fire_lon[k])+',50') nearest_stids.append(r.json()) all_stations = [] stid_dict = {} for l in range(len(nearest_stids)): all_stations = nearest_stids[l]['STATION'] stid_dict[fire_title[l]] = [] for m in range(len(all_stations)): stid_dict[fire_title[l]].append(all_stations[m]['STID']) ''' # API query gets latest 12 hours of data from RAWS and AWOS/ASOS/FAA stations API_request = requests.get(baseURL + 'timeseries?' + token + parameters) API_data = API_request.json()
# get an elevation profile from a bunch of trail points import json from urllib import urlretrieve as get from math import ceil with open("sample-route.json") as infile: route = json.load(infile)["route"] route = json.loads(route) print route[0] locs_per_query = 500 route_length = len(route) if route_length > locs_per_query: num_queries = ceil(route_length / locs_per_query) for i in range(int(num_queries)): start = i * locs_per_query end = (i + 1) * locs_per_query locations = "|".join(",".join(str(c) for c in coords) for coords in route[start:end]) print locations url = "http://maps.googleapis.com/maps/api/elevation/json?sensor=false&path=%s" % locations get(url, filename="elevation-profile%d.json" % i) print i, start, end else: locations = "|".join(",".join(str(c) for c in coords) for coords in route) url = "http://maps.googleapis.com/maps/api/elevation/json?sensor=false&path=%s" % locations #get(url, filename="elevation-profile.json") #print "got elevation profile"
url = "http://maps.googleapis.com/maps/api/distancematrix/json?units=imperial&sensor=false&key=" + keys.google + "&%s" params = {"origins": [], "destinations": []} # test: params["origins"] = [ "+".join("16th and mission st san francisco ca".split(" ")) ] with open("data/locations.csv") as infile: parks = [] for row in csv.DictReader(infile): if row["type"] in ["Park", "Trailhead"]: location = ",".join([row["Y"], row["X"]]) params["destinations"].append(location) # params["destinations"] = params["destinations"][:-1] # so it's 100 exactly # print len(params["destinations"]) # import sys # sys.exit() # construct the query origins = "origins=" + "|".join(params["origins"]) destinations = "destinations=" + "|".join(params["destinations"]) query = "&".join([origins, destinations]) distances = url % query # test: get(distances, filename="json/test-more.json") with open("json/test-destinations-more.json", "w") as outfile: outfile.write(json.dumps(params["destinations"]))
def update(status): try: get("http://starfury.eu5.org/alter.php?name="+envars["Name"]+"&gamemode="+envars["Gamemode"]+"&map="+envars["Map"]+"&players="+str(len(users))+"/"+envars["Player Limit"]+"&status="+status+"&ip="+envars["IPv4"]+"&port="+envars["Port"]) except: pass
import urllib from tqdm import tqdm class DownloadProgressBar(tqdm): def update_tp url = "https://s3.amazonaws.com/nyc-tlc/trip+data/green_tripdata_2018-01.csv" r = urllib.get(url) f = open(local_filename,'w') f.close()
import keys url = "http://maps.googleapis.com/maps/api/distancematrix/json?units=imperial&sensor=false&key=" + keys.google + "&%s" params = {"origins": [], "destinations":[]} # test: params["origins"] = ["+".join("16th and mission st san francisco ca".split(" "))] with open("data/locations.csv") as infile: parks = [] for row in csv.DictReader(infile): if row["type"] in ["Park", "Trailhead"]: location = ",".join([row["Y"], row["X"]]) params["destinations"].append(location) # params["destinations"] = params["destinations"][:-1] # so it's 100 exactly # print len(params["destinations"]) # import sys # sys.exit() # construct the query origins = "origins=" + "|".join(params["origins"]) destinations = "destinations=" + "|".join(params["destinations"]) query = "&".join([origins, destinations]) distances = url % query # test: get(distances, filename="json/test-more.json") with open("json/test-destinations-more.json","w") as outfile: outfile.write(json.dumps(params["destinations"]))