GetImg/eh_art.py

# -*- coding: utf-8 -*-
# download file
import os
import re
import time
import httpx
from pathlib import Path
from playwright.sync_api import sync_playwright

# 确保保存图片的目录存在
save_dir = Path("downloaded_images")
save_dir.mkdir(parents=True, exist_ok=True)

base_url = "https://e-hentai.org/g/"
href_url = "3055404/7ce423edd8"  # 每次改这个
change_page = '?p='

with sync_playwright() as playwright:
    browser = playwright.webkit.launch(headless=True)  # 启动浏览器，headless=True 表示无头模式
    page = browser.new_page()  # 创建新页面

    # 导航到网页
    page.goto(base_url + href_url)
    time.sleep(0.5)

    # 获取页面标题
    title = page.title()
    img_file = Path(f"{save_dir}/{title}")

    all_url_data = {}
    # TODO 此处循环获取每个页面的所有图片链接
    # 获取页面的 HTML 内容
    content = page.content()

    # print(content)

    view_img_list = re.findall('no-repeat"><a href="(.*?)">', content)
    all_view_img_list = [i for i in view_img_list]

    max_page_mun = re.findall('onclick="return false">(\\d*?)</a></td>', content)

    if max_page_mun:
        max_page_mun = int(max(max_page_mun))

    for view_page in range(1, max_page_mun):
        page.goto(base_url + href_url + change_page + str(view_page))
        content = page.content()
        view_img_list = re.findall('no-repeat"><a href="(.*?)">', content)
        for i in view_img_list:
            all_view_img_list.append(i)

    print(list(set(all_view_img_list)))
    # # 访问内层图片链接
    # for n, img_url in enumerate(view_img_list):
    #     page.goto(img_url)
    #     img_content = page.content()
    #     b_img = re.findall('<img id="img" src="(.*?)">', content)
    #     if b_img:
    #         all_url_data.update({str(n).zfill(4): b_img[0]})
    #
    # print(all_url_data)

    # 关闭浏览器
    browser.close()