wko_anime-face-similarity/scrape_data.py

import requests
from bs4 import BeautifulSoup
from lxml import etree
import os 

ROOT_URL = "https://myanimelist.net/character.php"

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'}
    page = requests.get(url, headers=HEADERS)
    soup = BeautifulSoup(page.content, "html.parser")
    dom = etree.HTML(str(soup))
    return dom.xpath(xpath_str)

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]

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')