Merge branch 'main' of https://git.wmi.amu.edu.pl/s444498/wko_anime-face-similarity

.gitignore

@@ -1,3 +1,5 @@
+images
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -157,4 +159,4 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+#.idea/

scrape_data.py

@@ -1,7 +1,7 @@
 import requests
 from bs4 import BeautifulSoup
 from lxml import etree
-import re
+import os 
 
 ROOT_URL = "https://myanimelist.net/character.php"
 
@@ -12,16 +12,24 @@ def get_page_xpath_result(url, xpath_str):
     dom = etree.HTML(str(soup))
     return dom.xpath(xpath_str)
 
-# 1. face image
-# 2. character name
-# 3. link
-
 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]
 
-print("character_links")
-print(character_links)
+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!")
+
+for name, url in zip(character_names, character_img_urls):
+    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')
+
 
-print("character_names")
-print(character_names)