Generate movie data as json from Wikipedia (Base Layout) further improvements are welcome.

wiki_movie_generator_data_generator.py

'''
Generate movie data as json from Wikipedia
'''
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
import re
import json

  
#url of the page we want to scrape
class MovieDataFetcher:

    url='';
    name='';
    html='';
    page='';

    def __init__(self,urlX):
        global url;
        url = urlX
        print("Hello World");
        self.loadDriver();
        response = self.processPage();
        return response;


    def loadDriver(self):
        global url,html;
        print("Loading Drivers...");
        # url = "https://www.wikidata.org/wiki/Q73028"
  
        # initiating the webdriver. Parameter includes the path of the webdriver.
        driver = webdriver.Chrome('./chromedriver') 
        driver.get(url) 
        
        
        # this is just to ensure that the page is loaded
        time.sleep(5) 
        
        
        html = driver.page_source
        driver.close();
        print("Page fetching..");


    def processPage(self):
        time.sleep(2)
        print("Processing page..");
        global html,name,page;
        page = requests.get(url);
        soup = BeautifulSoup(page.content, "html.parser")
        # taking the page content directly
        title_res = soup.find(id="content")
        title = title_res.find_all("span",class_="wikibase-title-label")
        print("Movie :: "+title[0].text)
        results = soup.find(id="mw-content-text")
        # wikidata is split as list of key value pair based on wikidata properties 
        propGrps = results.find_all("div",class_="wikibase-statementgroupview")
        td_tag_list =[];
        # iterating through each property 
        for prop in propGrps:
            temp = prop.find_all("a")
            temp_list=[];
            # each property contains first value as property name and remaining as values
            for i in range(0,len (temp),1):
                temp_val =temp[i].text;
                # some of the data present is invalid and only required for Wikipedia 
                if re.search(r'(.*?)Wikimedia(.*?)|(.+?)Wikipedia|inferred from|retrieved|(.*?)URL|Category:(.*?)',temp_val) is  None:
                    temp_list.append(temp_val);
            # combining all properties to a list
            td_tag_list.append(temp_list);

        dicts = {}
        for i in range(0,len(td_tag_list),1):
            key = td_tag_list[i].pop(0);
            value = td_tag_list[i];
            dicts[key] = value;
            
        # print(dicts)
        jsonStr = json.dumps(dicts,ensure_ascii=False)
        print(jsonStr)

        with open(title[0].text.replace(' ','_')+'.json', 'w', encoding='utf-8') as f:
            json.dump(dicts, f, ensure_ascii=False)
            print("Saved  successfully in "+title[0].text.replace(' ','_')+'.json')