s444498/wko_anime-face-similarity
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

scrap first 50 images

Browse Source
This commit is contained in:
Mateusz 2023-01-15 12:35:37 +01:00
parent 6333cff8e9
commit 850d74080d
2 changed files with 18 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored Normal file
View File

@ -0,0 +1 @@
images

26
scrape_data.py
View File

@ -1,7 +1,7 @@
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from lxml import etree from lxml import etree
import re import os
ROOT_URL = "https://myanimelist.net/character.php" ROOT_URL = "https://myanimelist.net/character.php"
@ -12,16 +12,24 @@ def get_page_xpath_result(url, xpath_str):
dom = etree.HTML(str(soup)) dom = etree.HTML(str(soup))
return dom.xpath(xpath_str) 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_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 = get_page_xpath_result(ROOT_URL, '//div[@class="information di-ib mt24"]/a')
character_names = [link.text for link in character_names] character_names = [link.text for link in character_names]
print("character_links") character_img_urls = [get_page_xpath_result(link, '//td/div/a/img/@data-src')[0]
print(character_links) 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)