Download collection of train icons from http://www.trainfrontview.net/.

getTrainIcons.py

import urllib
from urllib.request import urlretrieve
from urllib.request import urlopen
from bs4 import BeautifulSoup
import re
import os

baseUrl = "http://www.trainfrontview.net/"
trainUrl = "sozai.htm"
html = urlopen(baseUrl + trainUrl)
bsObj = BeautifulSoup(html, "html5lib")

links = bsObj.find("table",{"width":"750","border":"1"}).findAll("a",{"href":re.compile("sozai-\w+.+")})

dict = {}
key = ""
for i in range(len(links)):
    link = links[i]

    if len(link.text.split('[')) == 1:
        key = link.text
        dict[key] = []

    dict[key].append(baseUrl + link.get("href"))

for key in dict:
    path = "./" + key
    if os.path.isdir(path) == False:
        os.makedirs(path)
        
    for urlSozai in dict[key]:
        htmlSozai = urlopen(urlSozai)
        bsObjSozai = BeautifulSoup(htmlSozai, "html5lib")
        iconTables = bsObjSozai.find("table",{"class":"icon"}).findAll("td")

        iconUrls = {}
        pathIcon = ""
        for iconTD in iconTables:
            imageTD = iconTD.find("img")
            if(imageTD != None):
                title = iconTD.text.strip().replace("*","").replace("★","").replace('\n',"").replace("/","_")

                if(title not in iconUrls):
                    iconUrls[title] = []
                    pathIcon = path + "/" + title;
                    if(os.path.isdir(pathIcon) == False):
                        os.makedirs(pathIcon)

                    print("_______________________")
                    print(title)

                images = iconTD.findAll("img")
                for eachImage in images:
                    iconImageSrc = eachImage.get("src")
                    srcs = iconImageSrc.split("/")
                    iconName = srcs[len(srcs)-1]

                    iconUrl = baseUrl + iconImageSrc
                    f = open(pathIcon+"/"+iconName,'wb')
                    f.write(urlopen(iconUrl).read())
                    f.close()