scrap first 50 images and make csv

.gitignore

@@ -1,4 +1,4 @@
-images
+data
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

scrape_data.py

@@ -2,6 +2,7 @@ import requests
 from bs4 import BeautifulSoup
 from lxml import etree
 import os 
+import csv  
 
 ROOT_URL = "https://myanimelist.net/character.php"
 
@@ -12,6 +13,12 @@ def get_page_xpath_result(url, xpath_str):
     dom = etree.HTML(str(soup))
     return dom.xpath(xpath_str)
 
+def createDirectory(path):
+    isExist = os.path.exists(path)
+    if not isExist:
+        os.makedirs(path) 
+        print(f"The {path} is created!")
+
 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]
@@ -19,17 +26,33 @@ character_names = [link.text for link in character_names]
 character_img_urls = [get_page_xpath_result(link, '//td/div/a/img/@data-src')[0] 
                     for link in character_links]
 
-path = './images' 
-isExist = os.path.exists(path)
-if not isExist:
-  os.makedirs(path) 
-  print("The images directory is created!")
+createDirectory('./data')
+createDirectory('./data/images')
 
-for name, url in zip(character_names, character_img_urls):
+csv_header = ['name', 'file', 'link']
+data_rows = []
+
+for name, url, link in zip(character_names, character_img_urls, character_links):    
     img_data = requests.get(url).content
-    with open(f'images/{name}.jpg', 'wb') as handler:
-        handler.write(img_data)
-    handler.close()
-    print(f'{name}.jpg downloaded')
+    img_path = f'./data/images/{name}.jpg'
+    img_path_exist = os.path.exists(img_path)
 
+    if not img_path_exist:
+        with open(img_path, 'wb') as handler:
+            handler.write(img_data)
+        handler.close()
+        print(f'{name}.jpg downloaded')
 
+        data_row = [name, f'{name}.jpg', link]
+        data_rows.append(data_row)
+
+csv_path = './data/anime-faces.csv'
+if len(data_rows) > 0:
+    csv_file_exist = os.path.exists(csv_path)
+    with open(csv_path, 'a', encoding='UTF8') as f:
+        writer = csv.writer(f)
+        if not csv_file_exist:
+            writer.writerow(csv_header)
+        writer.writerows(data_rows)
+
+print("finish!")