I want to pull and print dt, temp, weather, humidity and wind speed given the latitude and longitude.
I thought that using data = r.json() would allow me to access the API Response like a dictionary and be able to access/print the elements I want using print(r[" "]), however, I am getting "KeyError: 'dt'"
def get_weather(lat,lon):
import json
import requests
r = requests.post('https://api.openweathermap.org/data/2.5/onecall?lat={}&lon={}&exclude=hourly,daily&appid=92d93ccc6ac5587d35d3ccc4479083a1'.format(lat,lon))
data = r.json()
dt = data["dt"]
temp = data["temp"]
weather = data["weather"]
humidity = data["humidity"]
wind_speed = data["wind_speed"]
print(r["dt"])
print(r["temp"])
print(r["weather"])
print(r["humidity"])
print(r["wind_speed"])
get_weather(33,44)
'dt' is a member of 'current', so you have to access it through 2 keys, you can see this if you print all items in the json like below:
def get_weather(lat,lon):
import json
import requests
r = requests.post('https://api.openweathermap.org/data/2.5/onecall?lat={}&lon={}&exclude=hourly,daily&appid=92d93ccc6ac5587d35d3ccc4479083a1'.format(lat,lon))
data = r.json()
for k,v in data.items():
print(k,v)
current = data['current']
print(current['dt'])
get_weather(33,44)
Related
I'm pulling data from the NHL API for player stats based on individual games. I'm trying to make a loop that calls the data, parses the JSON, creates a dict which I then can create a data frame from for an entire team. The code before my looping looks like this:
API_URL = "https://statsapi.web.nhl.com/api/v1"
response = requests.get(API_URL + "/people/8477956/stats?stats=gameLog", params={"Content-Type": "application/json"})
data = json.loads(response.text)
df_list_dict = []
for game in data['stats'][0]['splits']:
curr_dict = game['stat']
curr_dict['date'] = game['date']
curr_dict['isHome'] = game['isHome']
curr_dict['isWin'] = game['isWin']
curr_dict['isOT'] = game['isOT']
curr_dict['team'] = game['team']['name']
curr_dict['opponent'] = game['opponent']['name']
df_list_dict.append(curr_dict)
df = pd.DataFrame.from_dict(df_list_dict)
print(df)
This gives me a digestible data frame for a single player. (/people/{player}/....
I want to iterate through a list (the list being an NHL team), while adding a column that identifies the player and concatenates the created data frames. My attempt thus far looks like this:
import requests
import json
import pandas as pd
Rangers = ['8478550', '8476459', '8479323', '8476389', '8475184', '8480817', '8480078', '8476624', '8481554', '8482109', '8476918', '8476885', '8479324',
'8482073', '8479328', '8480833', '8478104', '8477846', '8477380', '8477380', '8477433', '8479333', '8479991']
def callapi(player):
response = (requests.get(f'https://statsapi.web.nhl.com/api/v1/people/{player}/stats?stats=gameLog', params={"Content-Type": "application/json"}))
data = json.loads(response.text)
df_list_dict = []
for game in data['stats'][0]['splits']:
curr_dict = game['stat']
curr_dict['date'] = game['date']
curr_dict['isHome'] = game['isHome']
curr_dict['isWin'] = game['isWin']
curr_dict['isOT'] = game['isOT']
curr_dict['team'] = game['team']['name']
curr_dict['opponent'] = game['opponent']['name']
df_list_dict.append(curr_dict)
df = pd.DataFrame.from_dict(df_list_dict)
print(df)
for player in Rangers:
callapi(player)
print(callapi)
When this is printed I can see all the data frames that were created. I cannot use curr_dict[] to add a column based on the list position (the player ID) because must be a slice or integer, not string.
What I'm hoping to do is make this one data frame in which the stats are identified by a player id column.
My python knowledge is very scattered, I feel as if with the progress I've made I should know how to complete this but I've simply hit a wall. Any help would be appreciated.
You can use concurrent.futures to parallelize the requests before concatenating them all together, and json_normalize to parse the json.
import concurrent.futures
import json
import os
import pandas as pd
import requests
class Scrape:
def main(self) -> pd.DataFrame:
rangers = ["8478550", "8476459", "8479323", "8476389", "8475184", "8480817", "8480078",
"8476624", "8481554", "8482109", "8476918", "8476885", "8479324", "8482073",
"8479328", "8480833", "8478104", "8477846", "8477380", "8477380", "8477433",
"8479333", "8479991"]
with concurrent.futures.ProcessPoolExecutor(max_workers=os.cpu_count()) as executor:
return pd.concat(executor.map(self.get_stats, rangers)).reset_index(drop=True).fillna(0)
#staticmethod
def get_stats(player: str) -> pd.DataFrame:
url = f"https://statsapi.web.nhl.com/api/v1/people/{player}/stats?stats=gameLog"
with requests.Session() as request:
response = request.get(url, timeout=30)
if response.status_code != 200:
print(response.raise_for_status())
data = json.loads(response.text)
df = (pd.
json_normalize(data=data, record_path=["stats", "splits"])
.rename(columns={"team.id": "team_id", "team.name": "team_name",
"opponent.id": "opponent_id", "opponent.name": "opponent_name"})
).assign(player_id=player)
df = df[df.columns.drop(list(df.filter(regex="link|gamePk")))]
df.columns = df.columns.str.split(".").str[-1]
if "faceOffPct" not in df.columns:
df["faceOffPct"] = 0
return df
if __name__ == "__main__":
stats = Scrape().main()
print(stats)
I'm trying to set up a loop to pull in weather data for about 500 weather stations for an entire year which I have in my dataframe. The base URL stays the same, and the only part that changes is the weather station ID.
I'd like to create a dataframe with the results. I believe i'd use requests.get to pull in data for all the weather stations in my list, which the IDs to use in the URL are in a column called "API ID" in my dataframe. I am a python beginner - so any help would be appreciated! My code is below but doesn't work and returns an error:
"InvalidSchema: No connection adapters were found for '0 " http://www.ncei.noaa.gov/access/services/data/...\nName: API ID, Length: 497, dtype: object'
.
def callAPI(API_id):
for IDs in range(len(API_id)):
url = ('http://www.ncei.noaa.gov/access/services/data/v1?dataset=daily-summaries&dataTypes=PRCP,SNOW,TMAX,TMIN&stations=' + distances['API ID'] + '&startDate=2020-01-01&endDate=2020-12-31&includeAttributes=0&includeStationName=true&units=standard&format=json')
r = requests.request('GET', url)
d = r.json()
ll = []
for index1,rows1 in distances.iterrows():
station = rows1['Closest Station']
API_id = rows1['API ID']
data = callAPI(API_id)
ll.append([(data)])
I am not sure about your whole code base, but this is the function that will return the data from the API, If you have multiple station id on a single df column then you can use a for loop otherwise no need to do that.
Also, you are not returning the result from the function. Check the return keyword at the end of the function.
Working code:
import requests
def callAPI(API_id):
url = ('http://www.ncei.noaa.gov/access/services/data/v1?dataset=daily-summaries&dataTypes=PRCP,SNOW,TMAX,TMIN&stations=' + API_id + '&startDate=2020-01-01&endDate=2020-12-31&includeAttributes=0&includeStationName=true&units=standard&format=json')
r = requests.request('GET', url)
d = r.json()
return d
print(callAPI('USC00457180'))
So your full code will be something like this,
def callAPI(API_id):
url = ('http://www.ncei.noaa.gov/access/services/data/v1?dataset=daily-summaries&dataTypes=PRCP,SNOW,TMAX,TMIN&stations=' + API_id + '&startDate=2020-01-01&endDate=2020-12-31&includeAttributes=0&includeStationName=true&units=standard&format=json')
r = requests.request('GET', url)
d = r.json()
return d
ll = []
for index1,rows1 in distances.iterrows():
station = rows1['Closest Station']
API_id = rows1['API ID']
data = callAPI(API_id)
ll.append([(data)])
Note: Even better use asynchronous calls to the API to make the process faster. Something like this: https://stackoverflow.com/a/56926297/1138192
I'm trying to get stocks prices from an API using python, but the thing is that when I put it in a while loop, it doesn't update, while the price is updating in the api, other thing, is there anyway to make the loop each 5 minutes? Here's the code:
import urllib.request
import json
urlprices = "https://financialmodelingprep.com/api/v3/quote-short/AMZN?apikey=555555555555555555"
obj = urllib.request.urlopen(urlprices)
data = json.load(obj)
a = 0
while a == 0:
print(float(data[0]['price']))
It is possible but you need to update your data within the while loop:
import urllib.request
import json
import time
a = 0
while a == 0:
urlprices = "https://financialmodelingprep.com/api/v3/quote-short/AMZN?apikey=555555555555555555"
obj = urllib.request.urlopen(urlprices)
data = json.load(obj)
print(float(data[0]['price']))
# here you should add a pause so that the loop will not hit the request limit for the api
time.sleep(300)
I am getting JIRA data using the following python code,
how do I store the response for more than one key (my example shows only one KEY but in general I get lot of data) and print only the values corresponding to total,key, customfield_12830, summary
import requests
import json
import logging
import datetime
import base64
import urllib
serverURL = 'https://jira-stability-tools.company.com/jira'
user = 'username'
password = 'password'
query = 'project = PROJECTNAME AND "Build Info" ~ BUILDNAME AND assignee=ASSIGNEENAME'
jql = '/rest/api/2/search?jql=%s' % urllib.quote(query)
response = requests.get(serverURL + jql,verify=False,auth=(user, password))
print response.json()
response.json() OUTPUT:-
http://pastebin.com/h8R4QMgB
From the the link you pasted to pastebin and from the json that I saw, its a you issues as list containing key, fields(which holds custom fields), self, id, expand.
You can simply iterate through this response and extract values for keys you want. You can go like.
data = response.json()
issues = data.get('issues', list())
x = list()
for issue in issues:
temp = {
'key': issue['key'],
'customfield': issue['fields']['customfield_12830'],
'total': issue['fields']['progress']['total']
}
x.append(temp)
print(x)
x is list of dictionaries containing the data for fields you mentioned. Let me know if I have been unclear somewhere or what I have given is not what you are looking for.
PS: It is always advisable to use dict.get('keyname', None) to get values as you can always put a default value if key is not found. For this solution I didn't do it as I just wanted to provide approach.
Update: In the comments you(OP) mentioned that it gives attributerror.Try this code
data = response.json()
issues = data.get('issues', list())
x = list()
for issue in issues:
temp = dict()
key = issue.get('key', None)
if key:
temp['key'] = key
fields = issue.get('fields', None)
if fields:
customfield = fields.get('customfield_12830', None)
temp['customfield'] = customfield
progress = fields.get('progress', None)
if progress:
total = progress.get('total', None)
temp['total'] = total
x.append(temp)
print(x)
I was trying to grab a list of prices. So far my code for such a thing is:
def steamlibrarypull(steamID, key):
#Pulls out a CSV of Steam appids.
steaminfo = {
'key': key,
'steamid': steamID,
'format':'JSON',
'include_appinfo':'1'
}
r = requests.get('http://api.steampowered.com/IPlayerService/GetOwnedGames/v0001/', params=steaminfo)
d = json.loads(r.content)
I = d['response']['games']
B = {}
for games in I:
B[games['name'].encode('utf8')] = games['appid']
with open('games.csv', 'w') as f:
for key, value in B.items():
f.write("%s,%s\r\n" % (key, value))
return B
But I'd like to be able to do a request.get that'll take this dictionary and ouput out a list of prices. https://wiki.teamfortress.com/wiki/User:RJackson/StorefrontAPI Seems to require the need of a CSV list but is that really necessary?
this is a non formal steam api meaning steam modifies as they see fit. currently it does not support multiple appids as noted here.
to use it to get the price of a game you would go
http://store.steampowered.com/api/appdetails/?appids=237110&cc=us&filters=price_overview
working from the code you have above you will need to know how to iterate through the dictionary and update the store price once you get it back.
def steamlibrarypull(steamID, key):
#Pulls out a CSV of Steam appids.
steaminfo = {
'key': key,
'steamid': steamID,
'format':'JSON',
'include_appinfo':'1'
}
r = requests.get('http://api.steampowered.com/IPlayerService/GetOwnedGames/v0001/', params=steaminfo)
d = json.loads(r.content)
response = d['response']['games']
games = {}
for game in response:
getprice = requests.get('http://store.steampowered.com/api/appdetails/?appids=%d&filters=price_overview&cc=us' % game['appid'])
if getprice.status_code == 200:
rjson = json.loads(getprice.text)
# use the appid to fetch the value and convert to decimal
# appid is numeric, cast to string to lookup the price
try:
price = rjson[str(game['appid'])]['data']['price_overview']['initial'] * .01
except:
price = 0
games[game['name']] = {'price': price, 'appid': game['appid']}
this will return the following dictionary:
{u'Half-Life 2: Episode Two': {'price': 7.99, 'appid': 420}
it would be easier to navigate via appid instead of name but as per your request and original structure this is how it should be done. this then gives you the name, appid and price that you can work with further or write to a file.
note that this does not include a sleep timer, if your list of games is long you should sleep your api calls for 2 seconds before making another one or the api will block you and will not return data which will cause an error in python when you parse the price.