Python parser za Sava Infond in Modra Zavarovalnica VEP vrednosti.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

66 lines
2.0 KiB

#!/usr/bin/env python3
import requests
from bs4 import BeautifulSoup
import pandas as pd
from multiprocessing import Process
# URLs to parse
modra_URL = "https://www.modra.si/skladi-in-podskladi/"
infond_URL = "https://www.infond.si/tecajnica-vzajemnih-skladov"
# Fake headers, otherwise Modra won't work
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
###############################################################################
# Parse Modra Zavarovalnica
#
def parse_modra():
a = requests.get(modra_URL, headers = headers)
df = pd.read_html(a.text, thousands=None)[0]
# Rename Columns
df.rename(columns = {'VEP ? Vrednost enote premoženja':'VEP', 'Sklad':'SKLAD'}, inplace = True)
# Drop all columns except the ones we want
df = df.filter(['SKLAD', 'VEP'])
# Drop all rows except the ones we want
return df[(df["SKLAD"]=="Dinamični podsklad") | (df["SKLAD"] =="Zajamčeni podsklad") ]
###############################################################################
# Parse Sava Infond Skladi
#
def parse_infond():
a = requests.get(infond_URL, headers = headers)
df = pd.read_html(a.text, thousands=None)[0]
# Drop all columns except the ones we want
df = df.filter(['SKLAD', 'VEP'])
# Cleanup the "SKLAD" name
a = df.at[23,'SKLAD']
df.at[23,'SKLAD'] = a.split()[0]+' '+a.split()[1]
df.at[23,'VEP'] = a.split()[2]
a = df.at[15,'SKLAD']
df.at[15,'SKLAD'] = a.split()[0]+' '+a.split()[1]
df.at[15,'VEP'] = a.split()[2]
# Drop all rows except the ones we want
return df[(df["SKLAD"]=="Infond Defensive") | (df["SKLAD"] =="Infond Technology") ]
###############################################################################
# Create new datatable and output it
#
if __name__ == '__main__':
output_table = pd.concat([parse_modra(), parse_infond()], axis=0)
output_table = output_table.reset_index(drop=True)
print(output_table)