Tag: politiken.dk

# -*- coding: utf-8 -*-
# Author: Morten Helmstedt. E-mail: helmstedt@gmail.com
# THIS PROGRAM POSTS NEW SHARED ARTICLES FROM ZETLAND.DK AND POLITIKEN.DK TO TWITTER

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import json
import time
from nested_lookup import nested_lookup
from TwitterAPI import TwitterAPI

articlestopost = []

# API LOGIN - INSERT YOUR OWN VALUES HERE
client_key = ''
client_secret = ''
access_token = ''
access_secret = ''
api = TwitterAPI(client_key, client_secret, access_token, access_secret)


# POLITIKEN.DK SEARCH #
SEARCH_TERM = 'url:"politiken.dk/del/"'
PRODUCT = '30day'
LABEL = 'prod'

r = api.request('tweets/search/%s/:%s' % (PRODUCT, LABEL), 
                {'query':SEARCH_TERM})

tweet_data = json.loads(r.text)
prettyjson = json.dumps(tweet_data, ensure_ascii=False, indent=4) # Only needed for debugging to pretify json

# Looks for all instances of expanded_url in json	
linklist = list(set(nested_lookup('expanded_url', tweet_data)))

urllist = []
for link in linklist:
	if "politiken.dk/del" in link:
		urllist.append(link)

# Request articles and get titles and dates and sort by dates
articlelist = []
titlecheck = []

for url in urllist:
	try:
		data = requests.get(url)
		result = data.text
		if '"isAccessibleForFree": "True"' not in result:
			soup = BeautifulSoup(result, "lxml")
			# Finds titles and timestamps
			title = soup.find('meta', attrs={'property':'og:title'})
			title = title['content']
			timestamp = soup.find('meta', attrs={'property':'article:published_time'})
			timestamp = timestamp['content']
			dateofarticle = datetime.strptime(timestamp, '%Y-%m-%dT%H:%M:%S%z')
			realurl = data.history[0].headers['Location']
			if title not in titlecheck:
				articlelist.append({"title": title, "url": realurl, "date": dateofarticle})
				titlecheck.append(title)			
	except:
		print(url)
			
articlelist_sorted = sorted(articlelist, key=lambda k: k['date'], reverse=True) 

# Check if article is already posted and update list of posted articles
with open("./pol_published.json", "r", encoding="utf8") as fin:
	alreadypublished = list(json.load(fin))
	for art in articlelist_sorted:
		url = art['url']
		token = url.index("?shareToken")
		url = url[:token]
		if url not in alreadypublished:
			alreadypublished.append(url)
			articlestopost.append(art)
	# Save updated already published links
	with open("./pol_published.json", "wt", encoding="utf8") as fout:
		alreadypublishedjson = json.dumps(alreadypublished)
		fout.write(alreadypublishedjson)

# ZETLAND.DK SEARCH #
SEARCH_TERM = 'url:"zetland.dk/historie"'
PRODUCT = '30day'
LABEL = 'prod'

r = api.request('tweets/search/%s/:%s' % (PRODUCT, LABEL), 
                {'query':SEARCH_TERM})

tweet_data = json.loads(r.text)
prettyjson = json.dumps(tweet_data, ensure_ascii=False, indent=4) # Only needed for debugging to pretify json

# Looks for all instances of expanded_url in json	
linklist = list(set(nested_lookup('expanded_url', tweet_data)))

urllist = []
for link in linklist:
	if "zetland.dk/historie" in link:
		urllist.append(link)

# Request articles and get titles and dates and sort by dates
articlelist = []
titlecheck = []

for url in urllist:
	try:
		data = requests.get(url)
		result = data.text

		# Soup site and create a dictionary of links and their titles and dates
		articledict = {}
		soup = BeautifulSoup(result, "lxml")

		title = soup.find('meta', attrs={'property':'og:title'})
		title = title['content']
		
		timestamp = soup.find('meta', attrs={'property':'article:published_time'})
		timestamp = timestamp['content']
		timestamp = timestamp[:timestamp.find("+")]
		dateofarticle = datetime.strptime(timestamp, '%Y-%m-%dT%H:%M:%S.%f')
		
		if title not in titlecheck:
			articlelist.append({"title": title, "url": url, "date": dateofarticle})
			titlecheck.append(title)
	except:
		print(url)
			
articlelist_sorted = sorted(articlelist, key=lambda k: k['date'], reverse=True) 

# Check if article is already posted and update list of posted articles
with open("./zet_published.json", "r", encoding="utf8") as fin:
	alreadypublished = list(json.load(fin))
	for art in articlelist_sorted:
		title = art['title']
		if title not in alreadypublished:
			alreadypublished.append(title)
			articlestopost.append(art)
	# Save updated already published links
	with open("./zet_published.json", "wt", encoding="utf8") as fout:
		alreadypublishedjson = json.dumps(alreadypublished, ensure_ascii=False)
		fout.write(alreadypublishedjson)


# POST TO TWITTER #
if articlestopost:
	for art in articlestopost:
		if "zetland" in art['url']:
			medium = "Zetland"
		else:
			medium = "Politiken"
		status = "En flink abonnent på " + medium + " har delt en betalingsartikel. God fornøjelse! " + art['url']
		r = api.request('statuses/update', {'status': status})
		time.sleep(5)