A quick script to get rid of Google (UTM) tracking, as well as the tracking query strings on NYTimes URLs.

clean_trackers_url.py

from urllib.parse import parse_qs, urlparse, urlencode, urlunparse
import copy

def clean_trackers_url(url):

    url_obj = urlparse(url)
    raw_query = parse_qs(url_obj.query)
    clean_query = copy.deepcopy(raw_query)

    # add query keys to ban (exact matches)
    banned_keys = ["emc", "partner"]
    # add query key prefixes to ban
    banned_prefixes = ["utm_"]

    for key in raw_query:
        if key in banned_keys:
            del clean_query[key]
        for prefix in banned_prefixes:
            if key.startswith(prefix):
                del clean_query[key]

    assembled_query = urlencode({key: clean_query[key][0] for key in clean_query})

    url_obj = url_obj._replace(query=assembled_query)

    return urlunparse(url_obj)