[python] ToonKor V2 Crawling

import bs4, codecs
import requests
import base64
import os
import io
import sys
 
requests.packages.urllib3.disable_warnings(requests.packages.urllib3.exceptions.InsecureRequestWarning)
image_ext = None
request_headers = {
    'User-Agent': ('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 '
                   '(KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'),
}

def safeFileName(filename):
    return filename.replace(":","_").replace("?","_").replace("<","_").replace(">","_").strip()

def getFile(url):
    with codecs.open(url,'r', encoding='utf8') as f:
        html = f.read()
    return bs4.BeautifulSoup(html, 'html.parser')
 
def getUrl(url, headers={}, params=()):
    resp = requests.get(url, verify=False, headers=headers, params=params)
    #resp.headers
    #html = resp.content.decode('utf8')
    html = resp.text
    return bs4.BeautifulSoup(html, 'html.parser')
 
def getUrlHtml(url, headers={}, params=()):
    resp = requests.get(url, verify=False, headers=headers, params=params)
    return bs4.BeautifulSoup(resp.text, 'html.parser'), resp.content.decode('utf8')
 
def urlToFile(url, file_name):
    resp = requests.get(url, verify=False, headers=request_headers, params=())
    with open(file_name, "wb") as f:
        f.write(resp.content)
 
def extractTag(bs,tag):
    [s.extract() for s in bs(tag)]
 
def getToonKor( comicsUrl, baseUrl, baseDir):
    while True:
        try:
            doc = getUrl(comicsUrl)
            table = doc.select("table.bt_view2")[0]
            elist = table.select("td.bt_title")
            title = elist[0].text
            break
        except:
            print(comicsUrl, "-> retry")
            continue
 
    table = doc.select("table.web_list")[0]
    elist = table.select("td.content__title")
 
    new_dir = os.path.join(baseDir, safeFileName(title))
    if not os.path.isdir(new_dir): os.mkdir(new_dir)
 
    for e in elist:
        url = baseUrl + e['data-role']
        title = e['alt']
        while True:
            try:
                bs_img, html_img = getUrlHtml(url, request_headers)
                begin = html_img.index("var tnimg = '")
                break
            except:
                print( url, "-> retry")
                continue
        end = html_img.index("';",begin)
        data = html_img[begin + 13: end]
        img_list = base64.b64decode(data.encode("UTF-8")).decode("UTF-8")
        doc_imgs = bs4.BeautifulSoup(img_list, 'html.parser')
        imgs = doc_imgs.select("img")
        
        #sub_dir = os.path.join(new_dir, title.replace(":","_"))
        #if not os.path.isdir(sub_dir): os.mkdir(sub_dir)
 
        html_file = os.path.join(new_dir, safeFileName(title) + ".html")
        print(html_file)
        f = open( html_file, "w" )
        f.write('<meta name="referrer" content="no-referrer" /><br>\n')
        k = 1;
        for img in imgs:
            img_url = img.get('src')
            if not img_url: continue
            if image_ext == None or img_url.endswith(image_ext):
                if( not img_url.startswith("http") ):
                    img_url = baseUrl + img_url
                #file_name = "img_%04d.jpg" % k
                #urlToFile( img_url, os.path.join( sub_dir, file_name) )
                #print( img_url + " -> " + file_name )
                print( img_url  )
                f.write('<img src="' + img_url + '" /><br>\n')
                k = k + 1
        f.close()
        
if __name__ == "__main__":
    urls = []
    if len(sys.argv) > 1:
        for i in range(1,len(sys.argv)):
            urls.append(sys.argv[i])
    else:
        urls.append(
            #"https://tkr035.com/webtoon/2939" #사내맞선
            #"https://tkr035.com/webtoon/826" #황제의 외동딸
            #"https://tkr035.com/webtoon/2794" #그만바의 자취방
            #"https://tkr035.com/webtoon/2647" #첩
            "https://tkr035.com/webtoon/6117" #외모지상주의
        )
    iurl = "https://tkr035.com"
    bdir = "D:/Temp2/"
    for url in urls:
        getToonKor(url, iurl, bdir)
    print("END")