joeface

import difflib
import json
import os
import re
import requests
import sys

from datetime import datetime, timedelta

from pprint import pprint

joeface

FROM python:3.8

ENV PYTHONDONTWRITEBYTECODE 1
ENV PYTHONUNBUFFERED 1

ADD main.py /
ADD requirements.txt /

# Set up and activate virtual environment
ENV VIRTUAL_ENV "/venv"

joeface

'''
Fetchs COVID-19 spread data from 4 sources:
1. CSSE at JHU ArcGIS,
2. CSSE at JHU github repo
3. Worldometer website
4. Manual Input from Google Spreadsheet

Combines the data and uploads on a Amazon S3-type Cloud-Storage

'''

joeface

"""
Fetch and parse data from Google Spreadsheet CSV
Requires requests package to be installed: pip install requests

Spreadsheet URL: https://docs.google.com/spreadsheets/d/10Xlr25Qtb-sRDJPqX66zqPPEP8yignUsPxxhT0O9Zb0/edit?usp=sharing
CSV export URL: https://docs.google.com/spreadsheets/d/e/2PACX-1vSZ_YhO6H0Q-dBX1sifVmDN9nonyx0xBePvqsU6NdsJJVO-B1MdBRXRCjHo9NBlYpl96AZai8_HGXKa/pub?gid=0&single=true&output=csv

"""

from io import StringIO

joeface

from bs4 import BeautifulSoup

# Initialize a bs4 instance with a HTML-source
page_dom = BeautifulSoup(page_html, "html.parser")

# Iterate over all DIVs with class hentry_event
for line in page_dom.find_all('div', class_="hentry_event"):
    
    # Find first A inside the DIV and get innerText
    title = line.find('a').contents[0]

joeface

import requests

# Retrieving Vladimir Putin's interviews from Kremlin website 
response = requests.get('http://en.kremlin.ru/search', params={'query': 'interview'}, timeout=40)

# Checking response status code
if response.status_code == requests.codes.ok:
    # Output response content as a string
    print response.text
else: