A quick and dirty bit of python to dump out headlines containing certain characters

proof-headlines.py

import requests
from urllib.parse import urlencode

languages = ["en"]
doneglyphs = " ABCDEFGHIJKLMNOPRQSTUVXYZabcdefghijklmnopqrstuvwxyz0123456789.,-"
API_TOKEN = "Use your own, not mine."

def get_a_page_of_headlines(page):
    params = urlencode(
        {"api_token": API_TOKEN, "languages": ",".join(languages), "page": page}
    )
    url = "https://api.marketaux.com/v1/news/all?{}".format(params)
    r = requests.get(url)
    r.raise_for_status()
    json = r.json()
    return (
        [x.get("title") for x in json["data"]],
        json["meta"]["found"] / json["meta"]["returned"],
    )


def filter_nicely(headline):
    # We could make exceptions for special cases here - check if we have
    # punctuation in our supported list and drop punctuation if not, etc.
    # But for now, the simple "do we have all the characters in the headline?"
    if all((g in doneglyphs) for g in headline):
        return headline

page = 1
while True:
    headlines, maxpage = get_a_page_of_headlines(page)
    for headline in headlines:
        if filter_nicely(headline):
            print(headline)
    page = page + 1
    if page > maxpage:
        break