Scrape values from json python requests - python

So I am building a scraper for sizes on a site and I am confused how to extract the "EUR" and "pieces" from this json.... I want to print later all sizes like "EU 41 = Pieces 6". probably I need a for loop
Here ist the output of the json : "{'translations': {'en': {'lang': 'en', 'title': 'Nike Dunk Low Retro Premium', 'subtitle': 'Black / Pure Platinum-Anthracite', 'slug': 'nike-dunk-low-retro-premium', 'description': 'DH7913-001'}}, 'id': 'vpEW0nkBHBhvh4GFDXSb', 'prices': {'EUR': {'currency': 'EUR', 'value': 119}}, 'sizeSets': {'Men': {'name': 'Men', 'sizes': [{'id': '685d200c-c470-11eb-b5ee-a66da43170c1', 'us': '8', 'eur': '41', 'uk': '7', 'cm': '26', 'ean': '194955875308', 'pieces': 6}, {'id': '685d21c4-c470-11eb-9f9f-a66da43170c1', 'us': '8.5', 'eur': '42', 'uk': '7.5', 'cm': '26.5', 'ean': '194955875315', 'pieces': 18}, {'id': '685d232c-c470-11eb-8bda-a66da43170c1', 'us': '9', 'eur': '42.5', 'uk': '8', 'cm': '27', 'ean': '194955875322', 'pieces': 10}, {'id': '685d248a-c470-11eb-bf78-a66da43170c1', 'us': '9.5', 'eur': '43', 'uk': '8.5', 'cm': '27.5', 'ean': '194955875339', 'pieces': 17}, {'id': '685d25de-c470-11eb-8741-a66da43170c1', 'us': '10', 'eur': '44', 'uk': '9', 'cm': '28', 'ean': '194955875346', 'pieces': 15}, {'id': '685d2732-c470-11eb-bfb5-a66da43170c1', 'us': '10.5', 'eur': '44.5', 'uk': '9.5', 'cm': '28.5', 'ean': '194955875353', 'pieces': 5}, {'id': '685d2886-c470-11eb-ac68-a66da43170c1', 'us': '11', 'eur': '45', 'uk': '10', 'cm': '29', 'ean': '194955875360', 'pieces': 1}, {'id': '685d29e4-c470-11eb-8578-a66da43170c1', 'us': '11.5', 'eur': '45.5', 'uk': '10.5', 'cm': '29.5', 'ean': '194955875377', 'pieces': 2}, {'id': '685d2b38-c470-11eb-a729-a66da43170c1', 'us': '12', 'eur': '46', 'uk': '11', 'cm': '30', 'ean': '194955875384', 'pieces': 3}]}, 'Unisex': {'name': 'Unisex', 'sizes': []}, 'Women': {'name': 'Women', 'sizes': []}, 'Kids': {'name': 'Kids', 'sizes': []}}, 'images': ['0/08/083/0837c383a3212d52f2e4455e0d876f47.jpeg', 'c/ca/ca0/ca01c2ca1dfb35013a06723b60c062cc.jpeg', '8/8e/8e9/8e9d04f6d1e8712da6d85c3db98ff989.jpeg', '3/37/376/3769e3f56186e46b91c725d09dff3252.jpeg', 'a/aa/aa5/aa5a8934a05be2badfe9cff5e07f122c.jpeg', '7/7b/7b0/7b088912b94bb0b2e41d527d573d568d.jpeg', 'b/b8/b8b/b8b214b6e1a33d56880e412b7ef8fe01.jpeg', '5/56/562/562809e497cc98b69cf8789e3238e482.jpeg'], 'imagesPortrait': ['a/ab/abc/abc1eac4bcdf74bd899f8e2f7827f30c.jpeg'], 'createdAt': '2021-06-03T13:34:22+00:00', 'publishAt': '2021-06-10T10:00:00+00:00', 'openRegistrationAt': '2021-06-10T10:00:00+00:00', 'closeRegistrationAt': '2021-06-18T23:00:00+00:00', 'finished': True, 'headliner': False, 'code': 'DH7913-001', 'footshopLink': 'https://www.footshop.eu/en/723-limited-edition/orderby-activated_at/orderway-desc', 'soldout': False, 'deleted': False, 'limitedShipping': True, 'delayedExport': False, 'productIdentifier': '115147', 'status': 'Closed',
'resultAt': '2021-06-19T03:00:00+00:00'}"
from os import error
import requests
from bs4 import BeautifulSoup
from discord_webhook import DiscordWebhook,DiscordEmbed
import time
import json
URL= "https://releases.footshop.com/api/raffles/vpEW0nkBHBhvh4GFDXSb"
headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36"}
page = requests.get(URL,headers=headers)
soup = BeautifulSoup(page.content, 'html.parser')
site_info= page.json()
print(site_info)

For the Json, I would recommend you first put it in a Json viewer/reader you can find online to see how is the data is more clearly and where is the information you want to get.
Here something like that should get you the information you want :
for s in site_info['sizeSets']['Men']['sizes']:
print(s['eur']+' '+ str(s['pieces']))

Related

How can I import a nested json object into a pandas dataframe?

I have a json object like this:
[{'currency_pair': 'UOS_USDT',
'orders': [{'account': 'spot',
'amount': '1282.84',
'create_time': '1655394430',
'create_time_ms': 1655394430129,
'currency_pair': 'UOS_USDT',
'fee': '0',
'fee_currency': 'UOS',
'fill_price': '0',
'filled_total': '0',
'gt_discount': False,
'gt_fee': '0',
'iceberg': '0',
'id': '169208865523',
'left': '1282.84',
'point_fee': '0',
'price': '0.1949',
'rebated_fee': '0',
'rebated_fee_currency': 'USDT',
'side': 'buy',
'status': 'open',
'text': 'apiv4',
'time_in_force': 'gtc',
'type': 'limit',
'update_time': '1655394430',
'update_time_ms': 1655394430129}],
'total': 1},
{'currency_pair': 'RMRK_USDT',
'orders': [{'account': 'spot',
'amount': '79.365',
'create_time': '1655394431',
'create_time_ms': 1655394431249,
'currency_pair': 'RMRK_USDT',
'fee': '0',
'fee_currency': 'RMRK',
'fill_price': '0',
'filled_total': '0',
'gt_discount': False,
'gt_fee': '0',
'iceberg': '0',
'id': '169208877018',
'left': '79.365',
'point_fee': '0',
'price': '2.52',
'rebated_fee': '0',
'rebated_fee_currency': 'USDT',
'side': 'buy',
'status': 'open',
'text': 'apiv4',
'time_in_force': 'gtc',
'type': 'limit',
'update_time': '1655394431',
'update_time_ms': 1655394431249}],
'total': 1}]
I want to convert it to a dataframe.
The data comes from an api call to a crypto exchange. I converted this to json, using the .json() method. So it's proper json. I have tried:
df = pd.DataFrame(data)
df = pd.DataFrame(data["orders")
df = pd.DataFrame(data["currency_pair"]["orders"])
and every other imaginable path.
I want a df which has as columns ["currency_pair", "amount", "create_time", "price", "side"]
I some times get an error TypeError: list indices must be integers or slices, not str or the df works but the orders object is not unpacked. All help gratefully received. Thank you.
import pandas as pd
data = [{'currency_pair': 'UOS_USDT',
'orders': [{'account': 'spot',
'amount': '1282.84',
'create_time': '1655394430',
'create_time_ms': 1655394430129,
'currency_pair': 'UOS_USDT',
'fee': '0',
'fee_currency': 'UOS',
'fill_price': '0',
'filled_total': '0',
'gt_discount': False,
'gt_fee': '0',
'iceberg': '0',
'id': '169208865523',
'left': '1282.84',
'point_fee': '0',
'price': '0.1949',
'rebated_fee': '0',
'rebated_fee_currency': 'USDT',
'side': 'buy',
'status': 'open',
'text': 'apiv4',
'time_in_force': 'gtc',
'type': 'limit',
'update_time': '1655394430',
'update_time_ms': 1655394430129}],
'total': 1},
{'currency_pair': 'RMRK_USDT',
'orders': [{'account': 'spot',
'amount': '79.365',
'create_time': '1655394431',
'create_time_ms': 1655394431249,
'currency_pair': 'RMRK_USDT',
'fee': '0',
'fee_currency': 'RMRK',
'fill_price': '0',
'filled_total': '0',
'gt_discount': False,
'gt_fee': '0',
'iceberg': '0',
'id': '169208877018',
'left': '79.365',
'point_fee': '0',
'price': '2.52',
'rebated_fee': '0',
'rebated_fee_currency': 'USDT',
'side': 'buy',
'status': 'open',
'text': 'apiv4',
'time_in_force': 'gtc',
'type': 'limit',
'update_time': '1655394431',
'update_time_ms': 1655394431249}],
'total': 1}]
Use:
df = pd.json_normalize(data, record_path=['orders'])
And keep the columns you need.
It's only one line and it should cover your case since 'currency_pair' that you want is already in the 'orders' dictionary and from what I understand from your data it will always be the same as the 'currency_pair' value outside 'orders. As you said you don't need 'total' too.
Use:
df = pd.json_normalize(data, record_path=['orders'], meta=['currency_pair', 'total'], record_prefix='orders_')
If you want them all
import pandas as pd
data = [{'currency_pair': 'UOS_USDT',
'orders': [{'account': 'spot',
'amount': '1282.84',
'create_time': '1655394430',
'create_time_ms': 1655394430129,
'currency_pair': 'UOS_USDT',
'fee': '0',
'fee_currency': 'UOS',
'fill_price': '0',
'filled_total': '0',
'gt_discount': False,
'gt_fee': '0',
'iceberg': '0',
'id': '169208865523',
'left': '1282.84',
'point_fee': '0',
'price': '0.1949',
'rebated_fee': '0',
'rebated_fee_currency': 'USDT',
'side': 'buy',
'status': 'open',
'text': 'apiv4',
'time_in_force': 'gtc',
'type': 'limit',
'update_time': '1655394430',
'update_time_ms': 1655394430129}],
'total': 1},
{'currency_pair': 'RMRK_USDT',
'orders': [{'account': 'spot',
'amount': '79.365',
'create_time': '1655394431',
'create_time_ms': 1655394431249,
'currency_pair': 'RMRK_USDT',
'fee': '0',
'fee_currency': 'RMRK',
'fill_price': '0',
'filled_total': '0',
'gt_discount': False,
'gt_fee': '0',
'iceberg': '0',
'id': '169208877018',
'left': '79.365',
'point_fee': '0',
'price': '2.52',
'rebated_fee': '0',
'rebated_fee_currency': 'USDT',
'side': 'buy',
'status': 'open',
'text': 'apiv4',
'time_in_force': 'gtc',
'type': 'limit',
'update_time': '1655394431',
'update_time_ms': 1655394431249}],
'total': 1}]
df = pd.DataFrame(data)
df['amount'] = df.apply( lambda row: row.orders[0]['amount'] , axis=1)
df['create_time'] = df.apply( lambda row: row.orders[0]['create_time'] , axis=1)
df['price'] = df.apply( lambda row: row.orders[0]['price'] , axis=1)
df['side'] = df.apply( lambda row: row.orders[0]['side'] , axis=1)
required_df = df[['currency_pair', 'amount', 'create_time', 'price', 'side']]
required_df
Result:
currency_pair amount create_time price side
0 UOS_USDT 1282.84 1655394430 0.1949 buy
1 RMRK_USDT 79.365 1655394431 2.52 buy
HI, hope this process can help you
#Import pandas library
import pandas as pd
#Your data
data = [{'currency_pair': 'UOS_USDT',
'orders': [{'account': 'spot',
'amount': '1282.84',
'create_time': '1655394430',
'create_time_ms': 1655394430129,
'currency_pair': 'UOS_USDT',
'fee': '0',
'fee_currency': 'UOS',
'fill_price': '0',
'filled_total': '0',
'gt_discount': False,
'gt_fee': '0',
'iceberg': '0',
'id': '169208865523',
'left': '1282.84',
'point_fee': '0',
'price': '0.1949',
'rebated_fee': '0',
'rebated_fee_currency': 'USDT',
'side': 'buy',
'status': 'open',
'text': 'apiv4',
'time_in_force': 'gtc',
'type': 'limit',
'update_time': '1655394430',
'update_time_ms': 1655394430129}],
'total': 1},
{'currency_pair': 'RMRK_USDT',
'orders': [{'account': 'spot',
'amount': '79.365',
'create_time': '1655394431',
'create_time_ms': 1655394431249,
'currency_pair': 'RMRK_USDT',
'fee': '0',
'fee_currency': 'RMRK',
'fill_price': '0',
'filled_total': '0',
'gt_discount': False,
'gt_fee': '0',
'iceberg': '0',
'id': '169208877018',
'left': '79.365',
'point_fee': '0',
'price': '2.52',
'rebated_fee': '0',
'rebated_fee_currency': 'USDT',
'side': 'buy',
'status': 'open',
'text': 'apiv4',
'time_in_force': 'gtc',
'type': 'limit',
'update_time': '1655394431',
'update_time_ms': 1655394431249}],
'total': 1}]
#Accessing nested values
#you cloud transform the specific column
#into a DataFrame and access it values with indices
#then parse the value to the type you need
#i.e
float(pd.DataFrame(data[0]['orders'])['amount'].values[0])
int(pd.DataFrame(data[0]['orders'])['create_time'].values[0])
float(pd.DataFrame(data[0]['orders'])['price'].values[0])
pd.DataFrame(data[0]['orders'])['side'].values[0]
#Create a dictionary with your chosen structure
#["currency_pair", "amount", "create_time", "price", "side"]
# then insert the corresponding columns
custom_dictionary = {
'currency_pair': [data[0]['currency_pair'], data[1]['currency_pair']],
'amount': [float(pd.DataFrame(data[0]['orders'])['amount'].values[0]),
float(pd.DataFrame(data[1]['orders'])['amount'].values[0])],
'create_time': [int(pd.DataFrame(data[0]['orders'])['create_time'].values[0]),
int(pd.DataFrame(data[1]['orders'])['create_time'].values[0])],
'price': [float(pd.DataFrame(data[0]['orders'])['price'].values[0]),
float(pd.DataFrame(data[1]['orders'])['price'].values[0])],
'side': [pd.DataFrame(data[0]['orders'])['side'].values[0],
pd.DataFrame(data[1]['orders'])['side'].values[0]]}
#Create a DataFrame with your custom dictionary and voila
df = pd.DataFrame(custom_dictionary)
df
the dataframe (df) could look like:
custom DataFrame

Extract value in Python

My Code:
import requests
import json
web_page = requests.get("http://api.bart.gov/api/etd.aspx?cmd=etd&orig=mont&key=MW9S-E7SL-26DU-VV8V&json=y")
response = web_page.text
parsed_json = json.loads(response)
#print(parsed_json)
print(parsed_json['root']['date'])
print(parsed_json['root']['time'])
print(parsed_json['root']['station']['name'])
How to extract value of destination and minutes from below in Python.
[{'name': 'Montgomery St.', 'abbr': 'MONT', 'etd': [{'destination': 'Daly City', 'abbreviation': 'DALY', 'limited': '0', 'estimate': [{'minutes': '39', 'platform': '1', 'direction': 'South', 'length': '10', 'color': 'WHITE', 'hexcolor': '#ffffff', 'bikeflag': '1', 'delay': '220'}]}, {'destination': 'SF Airport', 'abbreviation': 'SFIA', 'limited': '0', 'estimate': [{'minutes': '16', 'platform': '1', 'direction': 'South', 'length': '10', 'color': 'YELLOW', 'hexcolor': '#ffff33', 'bikeflag': '1', 'delay': '132'}, {'minutes': '26', 'platform': '1', 'direction': 'South', 'length': '10', 'color': 'BLUE', 'hexcolor': '#0099cc', 'bikeflag': '1', 'delay': '69'}]}]}]
Try this:
json_obj = {'name': 'Montgomery St.', 'abbr': 'MONT', 'etd': [{'destination': 'Antioch', 'abbreviation': 'ANTC', 'limited': '0', 'estimate': [{'minutes': '1', 'platform': '2', 'direction': 'North', 'length': '10', 'color': 'YELLOW', 'hexcolor': '#ffff33', 'bikeflag': '1', 'delay': '254'}]},
{'destination': 'Daly City', 'abbreviation': 'DALY', 'limited': '0', 'estimate': [{'minutes': '39', 'platform': '1', 'direction': 'South', 'length': '0', 'color': 'BLUE', 'hexcolor': '#0099cc', 'bikeflag': '1', 'delay': '0'}]},
{'destination': 'SF Airport', 'abbreviation': 'SFIA', 'limited': '0', 'estimate': [{'minutes': '38', 'platform': '1', 'direction': 'South', 'length': '10', 'color': 'YELLOW', 'hexcolor': '#ffff33', 'bikeflag': '1', 'delay': '0'}]}]}
for item in json_obj['etd']:
dest = item['destination']
minute = item['estimate'][0]['minutes']
print(dest, minute)
Output:
Antioch 1
Daly City 39
SF Airport 38
The problem is in parsed_json['root']['station']['name']. parsed_json['root']['station'] is a list, not a dict, so it doesn't have name key. You need to use index 0 or iterate over it
for station in parsed_json['root']['station']:
for etd in station['etd']:
for estimate in etd['estimate']:
print(etd['destination'], estimate['minutes'])
Output
Daly City 35
SF Airport 16
SF Airport 26
Try this to get json data:
import json
# some JSON:
json_data= {'destination': 'Daly City', 'abbreviation': 'DALY', 'limited': '0', 'estimate': [{'minutes': '39', 'platform': '1', 'direction': 'South', 'length': '0', 'color': 'BLUE', 'hexcolor': '#0099cc', 'bikeflag': '1', 'delay': '0'}]}
# parse json_data:
data = json.dumps(json_data)
extract_json = json.loads(data)
print("Destination: "+extract_json["destination"])
print("Minutes: "+extract_json["estimate"][0]["minutes"])
Output:
Destination: Daly City
Minutes: 39
Assuming the data is in d_MONT:
d_MONT = {'name': 'Montgomery St.', 'abbr': 'MONT', 'etd': [{'destination': 'Antioch', 'abbreviation': 'ANTC', 'limited': '0', 'estimate': [{'minutes': '1', 'platform': '2', 'direction': 'North', 'length': '10', 'color': 'YELLOW', 'hexcolor': '#ffff33', 'bikeflag': '1', 'delay': '254'}]},
{'destination': 'Daly City', 'abbreviation': 'DALY', 'limited': '0', 'estimate': [{'minutes': '39', 'platform': '1', 'direction': 'South', 'length': '0', 'color': 'BLUE', 'hexcolor': '#0099cc', 'bikeflag': '1', 'delay': '0'}]},
{'destination': 'SF Airport', 'abbreviation': 'SFIA', 'limited': '0', 'estimate': [{'minutes': '38', 'platform': '1', 'direction': 'South', 'length': '10', 'color': 'YELLOW', 'hexcolor': '#ffff33', 'bikeflag': '1', 'delay': '0'}]}]}
This will find the next train to destinationRequired:
destinationList = d_MONT['etd']
destinationRequired = 'Daly City'
for destinationDict in destinationList:
if destinationDict['destination'] == destinationRequired:
earliest = None
for estimate in destinationDict['estimate']:
if earliest is None or estimate['minutes'] < eariest:
earliest = estimate['minutes']
print("Next train to {0}: {1} minutes".format(destinationRequired, earliest))
break
else:
print("No trains to {0}".format(destinationRequired))
Note there are more Pythonic ways to do this, and the code example above does not follow PEP8, but I think it is important you understand the basic logic of how to do what you want rather than a complex Python one-liner.
You do not document the JSON object format, so I don't think it is safe to assume the list of trains to destination will be in order, therefore the safest is to step through each one and find the earliest. It isn't even clear if more than one train will ever be returned in the list, in which case a simple [0] would be sufficient rather than stepping through each one.

How to make dictionary data in json format in python

I am new in python and tried to understand the working with dictionaries operations but stuck in between.
I have data like below:
[{'mesure':'10', 'name': 'mumbai', 'age': '15', 'class':'kg1'}, {'mesure':'20', 'name': 'hyd', 'age': '20', 'class':'kg2'},{'mesure':'11', 'name': 'mumbai', 'age': '145', 'class':'kg6'}, {'mesure':'21', 'name': 'hyd', 'age': '20', 'class':'kg2'}, {'mesure':'40', 'name': 'pune', 'age': '30', 'class':'kg4'}, {'mesure':'30', 'name': 'chennai', 'age': '25', 'class':'kg3'}, {'mesure':'41', 'name': 'pune', 'age': '30', 'class':'kg7'}, {'mesure':'22', 'name': 'hyd', 'age': '20', 'class':'kg2'}{'mesure':'12', 'name': 'mumbai', 'age': '40', 'class':'kg7'}, {'mesure':'46', 'name': 'pune', 'age': '30', 'class':'kg8'}]
I want to convert it in format like:
[{"Name": "mumbai",
"data": [{'mesure':'10', 'name': 'mumbai', 'age': '15', 'class':'kg1'},
{'mesure':'11', 'name': 'mumbai', 'age': '145', 'class':'kg6'},
{'mesure':'12', 'name': 'mumbai', 'age': '40', 'class':'kg7'}]}
{"Name": "hyd",
"data":[{'mesure':'20', 'name': 'hyd', 'age': '20', 'class':'kg2'},
{'mesure':'21', 'name': 'hyd', 'age': '20', 'class':'kg2'},
{'mesure':'22', 'name': 'hyd', 'age': '20', 'class':'kg2'}]}
{"Name": "pune",
"data":[{'mesure':'40', 'name': 'pune', 'age': '30', 'class':'kg4'},
{'mesure':'41', 'name': 'pune', 'age': '30', 'class':'kg7'},
{'mesure':'46', 'name': 'pune', 'age': '30', 'class':'kg8'}]}]
I Tried:
def dir_data(data):
main_list = []
main_dir = []
for i in data:
names = i["name"]
main_dir.append({"name": names, "data": i})
print(main_dir)
if __name__== "__main__":
data = [{'mesure':'10', 'name': 'mumbai', 'age': '15', 'class':'kg1'}, {'mesure':'20', 'name': 'hyd', 'age': '20', 'class':'kg2'},{'mesure':'11', 'name': 'mumbai', 'age': '145', 'class':'kg6'}, {'mesure':'21', 'name': 'hyd', 'age': '20', 'class':'kg2'}, {'mesure':'40', 'name': 'pune', 'age': '30', 'class':'kg4'}, {'mesure':'30', 'name': 'chennai', 'age': '25', 'class':'kg3'}, {'mesure':'41', 'name': 'pune', 'age': '30', 'class':'kg7'}, {'mesure':'22', 'name': 'hyd', 'age': '20', 'class':'kg2'}{'mesure':'12', 'name': 'mumbai', 'age': '40', 'class':'kg7'}, {'mesure':'46', 'name': 'pune', 'age': '30', 'class':'kg8'}]
dir_data(data)
I tried above code but couldn't get exact output so please guide me to get it....
Thank you
def dir_data(data):
items = []
names = []
for i in data:
if i['name'] not in names:
items.append({"Name": i['name'], "data": [i]})
names.append(i['name'])
else:
iname = names.index(i['name'])
items[iname]['data'].append(i)
return items
data = [{'mesure':'10', 'name': 'mumbai', 'age': '15', 'class':'kg1'},
{'mesure':'20', 'name': 'hyd', 'age': '20', 'class':'kg2'},
{'mesure':'11', 'name': 'mumbai', 'age': '145', 'class':'kg6'},
{'mesure':'21', 'name': 'hyd', 'age': '20', 'class':'kg2'},
{'mesure':'40', 'name': 'pune', 'age': '30', 'class':'kg4'},
{'mesure':'30', 'name': 'chennai', 'age': '25', 'class':'kg3'},
{'mesure':'41', 'name': 'pune', 'age': '30', 'class':'kg7'},
{'mesure':'22', 'name': 'hyd', 'age': '20', 'class':'kg2'},
{'mesure':'12', 'name': 'mumbai', 'age': '40', 'class':'kg7'},
{'mesure':'46', 'name': 'pune', 'age': '30', 'class':'kg8'}
]
print(dir_data(data))
Try that one.
I can see the code you have written seems to be working but, you haven't returning the function, comma missing in data and also there is some mistakes in the way of call the function.
Just call the function like this,
def dir_data(data):
main_list = []
main_dir = []
for i in data:
names = i["name"]
main_dir.append({"name": names, "data": i})
return(main_dir)
data = [{'mesure':'10', 'name': 'mumbai', 'age': '15', 'class':'kg1'}, {'mesure':'20', 'name': 'hyd', 'age': '20', 'class':'kg2'},{'mesure':'11', 'name': 'mumbai', 'age': '145', 'class':'kg6'}, {'mesure':'21', 'name': 'hyd', 'age': '20', 'class':'kg2'}, {'mesure':'40', 'name': 'pune', 'age': '30', 'class':'kg4'}, {'mesure':'30', 'name': 'chennai', 'age': '25', 'class':'kg3'}, {'mesure':'41', 'name': 'pune', 'age': '30', 'class':'kg7'}, {'mesure':'22', 'name': 'hyd', 'age': '20', 'class':'kg2'},{'mesure':'12', 'name': 'mumbai', 'age': '40', 'class':'kg7'}, {'mesure':'46', 'name': 'pune', 'age': '30', 'class':'kg8'}]
dir_data(data)
You can get desired solution by using below code
test_data = [{'mesure': '10', 'name': 'mumbai', 'age': '15', 'class': 'kg1'}, {'mesure': '20', 'name': 'hyd', 'age': '20', 'class': 'kg2'}, {'mesure': '11', 'name': 'mumbai', 'age': '145', 'class': 'kg6'}, {'mesure': '21', 'name': 'hyd', 'age': '20', 'class': 'kg2'}, {'mesure': '40', 'name': 'pune', 'age': '30', 'class': 'kg4'}, {'mesure': '30', 'name': 'chennai', 'age': '25', 'class': 'kg3'}, {'mesure': '41', 'name': 'pune', 'age': '30', 'class': 'kg7'}, {'mesure': '22', 'name': 'hyd', 'age': '20', 'class': 'kg2'}, {'mesure': '12', 'name': 'mumbai', 'age': '40', 'class': 'kg7'}, {'mesure': '46', 'name': 'pune', 'age': '30', 'class': 'kg8'}]
dic = dict()
for i in test_data:
dic.setdefault(i['name'].title(),[]).append(i)
result = [{"name":k ,"data":v} for k,v in dic.items()]
Output
[{'data': [{'class': 'kg4', 'age': '30', 'name': 'pune', 'mesure': '40'},
{'class': 'kg7', 'age': '30', 'name': 'pune', 'mesure': '41'},
{'class': 'kg8', 'age': '30', 'name': 'pune', 'mesure': '46'}], 'name': 'Pune'},
{'data': [{'class': 'kg3', 'age': '25', 'name': 'chennai', 'mesure': '30'}], 'name': 'Chennai'},
{ 'data': [{'class': 'kg2', 'age': '20', 'name': 'hyd', 'mesure': '20'},
{'class': 'kg2', 'age': '20', 'name': 'hyd', 'mesure': '21'},
{'class': 'kg2', 'age': '20', 'name': 'hyd', 'mesure': '22'}], 'name': 'Hyd'},
{
'data': [{'class': 'kg1', 'age': '15', 'name': 'mumbai', 'mesure': '10'},
{'class': 'kg6', 'age': '145', 'name': 'mumbai', 'mesure': '11'},
{'class': 'kg7', 'age': '40', 'name': 'mumbai', 'mesure': '12'}], 'name': 'Mumbai'}]
Try this:
import json
data = [{'mesure':'10', 'name': 'mumbai', 'age': '15', 'class':'kg1'}, {'mesure':'20', 'name': 'hyd', 'age': '20', 'class':'kg2'},{'mesure':'11', 'name': 'mumbai', 'age': '145', 'class':'kg6'}, {'mesure':'21', 'name': 'hyd', 'age': '20', 'class':'kg2'}, {'mesure':'40', 'name': 'pune', 'age': '30', 'class':'kg4'}, {'mesure':'30', 'name': 'chennai', 'age': '25', 'class':'kg3'}, {'mesure':'41', 'name': 'pune', 'age': '30', 'class':'kg7'}, {'mesure':'22', 'name': 'hyd', 'age': '20', 'class':'kg2'},{'mesure':'12', 'name': 'mumbai', 'age': '40', 'class':'kg7'}, {'mesure':'46', 'name': 'pune', 'age': '30', 'class':'kg8'}]
def dir_data(data):
# set guarantees the uniqueness of each name
names = set([item['name'] for item in data])
main_dir = []
# collect the data for each name
for name in names:
name_data = [d for d in data if d['name']==name]
main_dir.append({"Name":name,"data":name_data})
return json.dumps(main_dir)
Below is the solution which will give you the exact result as described by you:
def checkKey(dict, key):
if key in dict:
return True
else:
return False
def dir_data(data):
for item in test:
if checkKey(tem_dict, item['name']):
tem_dict[item['name']].append(item)
else:
tem_dict[item['name']] = []
tem_dict[item['name']].append(item)
res_dict = {}
res = []
for item in tem_dict:
print item
res_dict['Name'] = item
res_dict['data'] = tem_dict[item]
res.append(res_dict)
res_dict = {}
return res
let me know if this works for you or not.

Web scraping using Beautifulsoup to collect dropdown values

I am new to Python, trying to get a list of all the drop down values from the following website "https://www.sfma.org.sg/member/category" but failing to do so.
The below code is producing an empty list
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import re
import pandas as pd
page = "https://www.sfma.org.sg/member/category"
information = requests.get(page)
soup = BeautifulSoup(information.content, 'html.parser')
categories = soup.find_all('select', attrs={'class' :'w3-select w3-border'})
The desired output is the below list :-
['Alcoholic Beverage','Beer','Bottled
Beverage',..........,'Trader','Wholesaler']
Thanks !!
The options are loaded through Javascript, but the data is on the page. With some crude regexes you can extract it:
import re
import json
import requests
url = 'https://www.sfma.org.sg/member/category/'
text = requests.get(url).text
d = re.findall(r'var\s*cObject\s*=\s*(.*)\s*;', text)[0]
d = re.sub(r'(\w+)(?=:)', r'"\1"', d)
d = json.loads(d.replace("'", '"'))
from pprint import pprint
pprint(d, width=200)
Prints:
{'category': [{'cat_type': '1', 'id': '1', 'name': 'Alcoholic Beverage', 'permalink': 'alcoholic-beverage', 'status': '2'},
{'cat_type': '1', 'id': '2', 'name': 'Beer', 'permalink': 'beer', 'status': '2'},
{'cat_type': '1', 'id': '3', 'name': 'Bottled Beverage', 'permalink': 'bottled-beverage', 'status': '2'},
{'cat_type': '1', 'id': '4', 'name': 'Canned Beverage', 'permalink': 'canned-beverage', 'status': '2'},
{'cat_type': '1', 'id': '5', 'name': 'Carbonated Beverage', 'permalink': 'carbonated-beverage', 'status': '2'},
{'cat_type': '1', 'id': '6', 'name': 'Cereal / Grain Beverage', 'permalink': 'cereal-grain-beverage', 'status': '2'},
{'cat_type': '1', 'id': '7', 'name': 'Cider', 'permalink': 'cider', 'status': '2'},
{'cat_type': '1', 'id': '8', 'name': 'Coffee', 'permalink': 'coffee', 'status': '2'},
{'cat_type': '1', 'id': '9', 'name': 'Distilled Water', 'permalink': 'distilled-water', 'status': '2'},
{'cat_type': '1', 'id': '10', 'name': 'Fruit / Vegetable Juice', 'permalink': 'fruit-vegetable-juice', 'status': '2'},
{'cat_type': '1', 'id': '11', 'name': 'Herbal Beverage', 'permalink': 'herbal-beverage', 'status': '2'},
{'cat_type': '1', 'id': '12', 'name': 'Instant Beverage', 'permalink': 'instant-beverage', 'status': '2'},
{'cat_type': '1', 'id': '13', 'name': 'Milk', 'permalink': 'milk', 'status': '2'},
{'cat_type': '1', 'id': '14', 'name': 'Mineral Water', 'permalink': 'mineral-water', 'status': '2'},
...and so on.
EDIT: To print just names of categories, you can do this:
for c in d['category']:
print(c['name'])
Prints:
Alcoholic Beverage
Beer
Bottled Beverage
Canned Beverage
Carbonated Beverage
Cereal / Grain Beverage
Cider
...
Manufacturer
Restaurant
Retail Outlet
Supplier
Trader
Wholesaler
This is not really a proper question but still.
categories = soup.find("select", attrs={"name": "ctype"}).find_all('option')
result = [cat.get_text() for cat in categories]

Convert Pandas Dataframe to_dict() with unique column values as keys

How can I convert a pandas dataframe to a dict using unique column values as the keys for the dictionary? In this case I want to use unique username's as the key.
Here is my progress so far based on information found on here and online.
My test dataframe:
import pandas
import pprint
df = pandas.DataFrame({
'username': ['Kevin', 'John', 'Kevin', 'John', 'Leslie', 'John'],
'sport': ['Soccer', 'Football', 'Racing', 'Tennis', 'Baseball', 'Bowling'],
'age': ['51','32','20','19','34','27'],
'team': ['Cowboyws', 'Packers', 'Sonics', 'Raiders', 'Wolves', 'Lakers']
})
I can create a dictionary by doing this:
dct = df.to_dict(orient='records')
pprint.pprint(dct, indent=4)
>>>>[{'age': '51', 'sport': 'Soccer', 'team': 'Cowboyws', 'username': 'Kevin'},
{'age': '32', 'sport': 'Football', 'team': 'Packers', 'username': 'John'},
{'age': '20', 'sport': 'Racing', 'team': 'Sonics', 'username': 'Kevin'},
{'age': '19', 'sport': 'Tennis', 'team': 'Raiders', 'username': 'John'},
{'age': '34', 'sport': 'Baseball', 'team': 'Wolves', 'username': 'Leslie'},
{'age': '27', 'sport': 'Bowling', 'team': 'Lakers', 'username': 'John'}]
I tried using the groupby and apply method which got me closer but it converts all the values to lists. I want them to remain as dictionaries so i can retain the each value's key:
result = df.groupby('username').apply(lambda x: x.values.tolist()).to_dict()
pprint.pprint(result, indent=4)
{ 'John': [ ['32', 'Football', 'Packers', 'John'],
['19', 'Tennis', 'Raiders', 'John'],
['27', 'Bowling', 'Lakers', 'John']],
'Kevin': [ ['51', 'Soccer', 'Cowboyws', 'Kevin'],
['20', 'Racing', 'Sonics', 'Kevin']],
'Leslie': [['34', 'Baseball', 'Wolves', 'Leslie']]}
This is the desired result I want:
{
'John': [{'age': '32', 'sport': 'Football', 'team': 'Packers', 'username': 'John'},
{'age': '19', 'sport': 'Tennis', 'team': 'Raiders', 'username': 'John'},
{'age': '27', 'sport': 'Bowling', 'team': 'Lakers', 'username': 'John'}],
'Kevin': [{'age': '51', 'sport': 'Soccer', 'team': 'Cowboyws', 'username': 'Kevin'},
{'age': '20', 'sport': 'Racing', 'team': 'Sonics', 'username': 'Kevin'}],
'Leslie': [{'age': '34', 'sport': 'Baseball', 'team': 'Wolves', 'username': 'Leslie'}]
}
Use groupby and apply. Inside the apply, call to_dict with the "records" orient (similar to what you've figured out already).
df.groupby('username').apply(lambda x: x.to_dict(orient='r')).to_dict()
I prefer using for loop here , also you may want to drop the username columns , since it is redundant
d = {x: y.drop('username',1).to_dict('r') for x , y in df.groupby('username')}
d
Out[212]:
{'John': [{'age': '32', 'sport': 'Football', 'team': 'Packers'},
{'age': '19', 'sport': 'Tennis', 'team': 'Raiders'},
{'age': '27', 'sport': 'Bowling', 'team': 'Lakers'}],
'Kevin': [{'age': '51', 'sport': 'Soccer', 'team': 'Cowboyws'},
{'age': '20', 'sport': 'Racing', 'team': 'Sonics'}],
'Leslie': [{'age': '34', 'sport': 'Baseball', 'team': 'Wolves'}]}

Categories

Resources