世界机场三字码

import requests
from bs4 import BeautifulSoup
import json
import threading


def scrape_page(page):
    text = requests.get("https://airportcode.bmcx.com/" + str(page) + "__airportcode/")
    res = text.text
    soup = BeautifulSoup(res, features="lxml")
    arr = soup.findAll(name="table")[0].findAll(name="tr")
    for i in arr[2:]:
        t = i.findAll(name="td")
        v = ""
        if t[3].string is not None:
            v = t[3].string
        with lock:
            dic[t[1].string] = v


dic = {}
lock = threading.Lock()
n = 290
threads = []

for i in range(1, n):
    thread = threading.Thread(target=scrape_page, args=(i,))
    thread.start()
    threads.append(thread)

for thread in threads:
    thread.join()

s = json.dumps(dic, ensure_ascii=False)
print(s)

with open('json.json', 'w') as f:
    f.write(s)