giantessbooru-tag-scraper/scrape.py

#!/usr/bin/env python3
from playwright.sync_api import sync_playwright

root = 'https://giantessbooru.com/'
cookies = []
with open('cookies.txt') as f:
    lines = [line.rstrip().split("=", 1) for line in f]
    cookies = [{'name':k, 'value':v, 'url':root} for k,v in lines]

with sync_playwright() as p:
    browser = p.chromium.launch()\
               .new_context(**p.devices['Desktop Chrome'])
    browser.add_cookies(cookies)
    page = browser.new_page()

    page.goto(root+"post/list")
    pages = int(page.locator('#paginator a').nth(-2).inner_text())
    for i in range(pages+1):
        page.goto(root+f"post/list/{i}")
        print(i,page.title())
        thumbs = page.locator('#mai > .thumb > a > img')
        for i in range(thumbs.count()):
            thumb = thumbs.nth(i)
            tags  = thumb.get_attribute('title').split('//')[0].rstrip().split(' ')
            md5   = thumb.get_attribute('src').split('/')[2]
            with open(f"data/{md5}.tags.txt",'w',encoding="utf-8") as f:
                f.write('\n'.join(tags) + '\n')
        page.wait_for_timeout(1000)

    browser.close()