scrap n images depends on argv param

scrape_data.py

@@ -3,8 +3,12 @@ from bs4 import BeautifulSoup
 from lxml import etree
 import os 
 import csv  
+import sys
 
-ROOT_URL = "https://myanimelist.net/character.php"
+if len(sys.argv) > 1:
+    IMG_N = int(sys.argv[1])
+else:
+    IMG_N = 50
 
 def get_page_xpath_result(url, xpath_str):
     HEADERS = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
@@ -19,6 +23,12 @@ def createDirectory(path):
         os.makedirs(path) 
         print(f"The {path} is created!")
 
+n = IMG_N // 50
+
+for i in range(n):
+    ROOT_URL = f'https://myanimelist.net/character.php?limit={(i)*50}'
+    print(ROOT_URL)
+    
     character_links = get_page_xpath_result(ROOT_URL, '//div[@class="information di-ib mt24"]/a/@href')
     character_names = get_page_xpath_result(ROOT_URL, '//div[@class="information di-ib mt24"]/a')
     character_names = [link.text for link in character_names]