dt_checker.py

import requests
from lxml import html


def get_downtowns():
    result = {}
    page = requests.get("https://en.wikipedia.org/wiki/Downtown")
    phtml = html.fromstring(page.content)

    for i in phtml.iterlinks():
        if i[2].startswith("/wiki/Downtown_"):
            key = i[2].replace("/wiki/Downtown_", "")

            # Some sub-districts
            if "Historic_District" in key:
                continue
            # Some subcategories
            if "(" in key:
                continue
            # What?
            if key == "music":
                continue

            result[key] = "https://en.wikipedia.org%s" % i[2]
    return result


def mirror_mirror_on_the_wall_who_is_me_and_who_is_wrong():
    downtowns = get_downtowns()

    total = 0
    bdist = 0
    nobd = 0

    for city in downtowns.keys():
        page = requests.get(downtowns[city])
        phtml = html.fromstring(page.content)
        value = phtml.get_element_by_id("mw-content-text").text_content()[0:1000]
        if "business district" in value.lower() or "financial district" in value.lower():
            print("%s: Success" % city)
            bdist += 1
        else:
            print("%s: Fail" % city)
            nobd += 1
        total += 1


    print("We checked %s cities. %s from them defined their Downtowns as " \
          "Bussines District, what is  %s percent from all checked cities." % 
        (total, bdist, bdist/total * 100)
    )


mirror_mirror_on_the_wall_who_is_me_and_who_is_wrong()