问从行中提取名称

EN

import itertools

# this list of languages could be longer and should read from a file
languages = ["English", "Spanish", "Italian", "Japanese", "French",
             "Standard Chinese", "Chinese", "Hindi", "Standard Arabic", "Russian"]

languages = [language.lower() for language in languages]

# Loop through US.txt and format it. Download from geonames.org.
cities = []
with open('US.txt', 'r') as us_data:
    for line in us_data:
        line_split = line.split("\t")
        cities.append("{}:{}".format(line_split[4], line_split[2]))

# This is the dataset
with open('state-teachers.txt', 'r') as teachers:
    next(teachers)  # skip header

    for line in teachers:
        # Replace all double spaces with single spaces
        while line.find("  ") != -1:
            line = line.replace("  ", " ")

        line_split = line.split(" ")

        # Lat/Lon are the last 2 items
        longitude = line_split.pop().strip()
        latitude = line_split.pop().strip()

        # Search for potential languages and trim off the line as we find them
        teacher_languages = []

        while True:
            language_check = line_split[-1]
            if language_check.lower().replace(",", "").strip() in languages:
                teacher_languages.append(language_check)
                del line_split[-1]
            else:
                break

        # Rejoin everything and then use phone number as the special key to split on
        line = " ".join(line_split)

        phone_start = line.find("(")
        phone = line[phone_start:phone_start+14].strip()

        after_phone = line[phone_start+15:]

        # Certifications can be recognized as acronyms
        # Anything else is assumed to be an area of practice
        certifications = []
        areas_of_practice = []

        specialties = after_phone.split(",")
        for specialty in specialties:
            specialty = specialty.strip()
            if specialty[0:2].upper() == specialty[0:2]:
                certifications.append(specialty)
            else:
                areas_of_practice.append(specialty)

        before_phone = line[0:phone_start-1]
        line_split = before_phone.split(" ")

        # State is the last column before phone
        state = line_split.pop()

        # Name should be the first 2 columns, at least. This is a basic guess.
        name = line_split[0] + " " + line_split[1]

        line_split = line_split[2:]

        # Add initials
        if len(line_split[0].strip()) == 1:
            name += " " + line_split[0].strip()
            line_split = line_split[1:]

        # Combo of all potential word combinations to see if we're dealing with a city or a name
        combos = [" ".join(combo) for combo in set(itertools.permutations(line_split))] + line_split

        line = " ".join(line_split)
        city = ""

        # See if the state:city combo is valid. If so, set it and let everything else be the name
        for combo in combos:
            if "{}:{}".format(state, combo) in cities:
                city = combo
                line = line.replace(combo, "")
                break

        # Remaining data must be a name
        if line.strip() != "":
            name += " " + line

        # Clean up names
        last_name, first_name = [piece.strip() for piece in name.split(",")]

        print first_name, last_name