Python Regelwiki-Crawler?

from queue import Queue
import requests
import os
import re
import threading




main_adress = "http://ulisses-regelwiki.de/"
html_folder = "WikiData"


class ThreadedManager:
    def __init__(self,adress,folder, limit):
        self.top_adress=adress
        self.main_folder = folder
        self.limit = limit
        self.threads =0
        self.q = Queue()
    
        
    def start(self):
        if not os.path.exists(self.main_folder):
            os.mkdir(self.main_folder)
        links=grabAllTopLinks(self.top_adress)
        for link,name in links:
            self.q.put([self.main_folder,link,name])
        while not self.q.empty() and self.threads<self.limit:
            parent_folder,link,name = self.q.get()
            thread = htmlThread(link,parent_folder,name,self.top_adress,self)
            self.threads +=1
            thread.start()    
        
    
    def finished(self,links,parent_folder):
        
        
        for link,name in links:
            self.q.put([parent_folder,link,name])
        self.finished_noData()

    def finished_noData(self):
        
        
        self.threads -= 1
        while not self.q.empty() and self.threads<self.limit:
            
            parent_folder,link,name = self.q.get()
            print("Starting new thread:", link)
            thread = htmlThread(link,parent_folder,name,self.top_adress,self)
            self.threads +=1
            thread.start()
        print("Queue size:",self.q.qsize())
        
        

class htmlThread(threading.Thread):
    
    def __init__(self,link,parent_folder,name,top_adress,parent):
        threading.Thread.__init__(self)
        self.link=link
        self.parent_folder=parent_folder
        self.name=name
        self.top_adress=top_adress
        self.parent = parent
        
    def run(self):
        new_adress=self.top_adress+self.link
        
        raw_data = getHTMLFile(new_adress)
        links = self.getLinks(raw_data)
        data = self.getData(raw_data)
        if len(data)>0:
                print("\nDATA FOUND: Writing:",self.parent_folder+"/"+self.name+".html")
                self.writeData(data,self.name,self.parent_folder)
    
        if len(links)>0:
                

            if not os.path.exists(self.parent_folder+"/"+self.name):
                os.mkdir(self.parent_folder+"/"+self.name)
            self.parent.finished(links,self.parent_folder+"/"+self.name)   
        else:
            self.parent.finished_noData()

    def writeData(self,data, name,folder):
        keepcharacters = (' ',"-",'_',"(",")")
        name="".join(c for c in name if c.isalnum() or c in keepcharacters).rstrip()
        self.save_obj(data, name,folder)
        return data            
    def save_obj(self,obj, name,folder ):
        with open(folder+"/"+ name + '.html', 'w+',encoding='utf8') as f:
            f.write(obj)
            f.close()

    

    def getData(self, toParse):
        temp=toParse
        start = temp.find('<div class="ce_text first')
        temp = temp[start:]
        end = temp.find("<footer id=")
        temp= temp[:end]

        
        return temp
  
    def getLinks(self, toParse):
        temp = toParse
        start = temp.find('ulStrikeOutH1')
        temp = temp[start:]
        end = temp.find("</nav>")
        temp = temp[:end]
        

        pattern = 'href=[\'\"]?([^\'\" >]+)[\'\"] title=[\'\"]([^\'\">]+)'
        prog = re.compile(pattern)
        result = prog.findall(temp)

        return result    




    

def grabAllTopLinks(adress):
    data = getHTMLFile(adress)
          

    pattern = 'href=[\'\"]?([^\'\" >]+)[\'\"] title=[\'\"]([^\'\">]+)'
    prog = re.compile(pattern)
    result = prog.findall(data)
    
    return result

    
def getHTMLFile(url):
    r = requests.get(url)
    return r.text     



grabber = ThreadedManager(main_adress,html_folder,10)
print("Grabbing Data...")
grabber.start()