ResourceCollection/flaticon/main.py

# -*- coding: utf-8 -*-
import sys
import os
import time

sys.path.append(os.path.join(os.path.abspath(__file__).split('ResourceCollection')[0] + 'ResourceCollection'))
import httpx
from playwright.sync_api import sync_playwright

target_url = 'https://www.flaticon.com/packs/medicine-103'

title_selector = '#pack-view__inner > section.pack-view__header > h1'
selector = '#pack-view__inner > section.search-result > ul > li:nth-child({}) > div > a'
img_selector = '#detail > div > div.row.detail__top.mg-none > section > div > div > div.row.row--vertical-center.mg-none.full-height.detail__icon__inner > div > div > img'
img_count_selector = '#pack-view__inner > section.pack-view__header > p'


def main():
    with sync_playwright() as playwright:
        browser = playwright.chromium.launch(
            headless=True,
            proxy={"server": "http://127.0.0.1:7890"}
        )
        context = browser.new_context(viewport={'width': 1280, 'height': 700})
        page = context.new_page()

        page.goto(target_url)

        # 获取title
        page.wait_for_selector(title_selector, state="attached", timeout=10000)
        title = page.query_selector(title_selector).inner_text()

        img_count = page.query_selector(img_count_selector).inner_text()
        img_count = int(img_count.split(' ')[0])

        invalid_chars = ['<', '>', ':', '"', '/', '\\', '|', '?', '*', '.', '  ', 'Icon Pack ']
        for char in invalid_chars:
            title = title.replace(char, '')

        img_name = title.replace(' ', '_')

        current_path = os.getcwd()

        download_file_path = os.path.join(current_path, 'download')
        if not os.path.exists(download_file_path):
            os.mkdir(download_file_path)

        file_path = os.path.join(download_file_path, title)
        if not os.path.exists(file_path):
            os.mkdir(file_path)

        # 第一层 url
        urls = []
        for i in range(1, img_count + 1):
            # 选择所有的<a>标签
            elements = page.query_selector_all(selector.format(i))

            # 遍历所有<a>标签，提取href属性
            for element in elements:
                href = element.get_attribute('href')
                if href:
                    sequence = str(i).zfill(2)
                    urls.append({
                        'url': href,
                        'img': f'{img_name}_{sequence}'
                    })
        print('已获取第一层url')

        img_urls = []
        # 第二层 url
        for url in urls:
            # 如果png文件存在, 即已经下载过, 直接跳过
            img_png_name = url['img'] + 'png'
            img_png_path = os.path.join(file_path, img_png_name)
            if os.path.exists(img_png_path):
                continue

            page.goto(url['url'])
            page.wait_for_selector(img_selector, state="attached", timeout=10000)
            img_elements = page.query_selector_all(img_selector)
            for img_element in img_elements:
                img_url = img_element.get_attribute('src')
                img_urls.append({
                    'target_img_url': img_url,
                    'target_img_name': url['img'] + '.png'
                })

        print('已获取第二层url\n关闭浏览器')

        page.close()
        browser.close()

        print('正在下载图片')
        for img_url in img_urls:
            target_img_url = img_url['target_img_url']
            target_img_name = img_url['target_img_name']
            resp = httpx.get(target_img_url, headers={
                "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36"
            })
            with open(os.path.join(file_path, target_img_name), 'wb') as f:
                f.write(resp.content)
            print(f'已下载: {target_img_name}')
            time.sleep(1)

        print(f'{title} : 已下载完成')


if __name__ == "__main__":
    main()