auto/manual/zhuimh/main.py

# -*- coding: utf-8 -*-
# https://www.zhuimh.com/comic/419025
# 获取 zhuimh
import time
import os
import psycopg2

from playwright.sync_api import sync_playwright


class Zhuimh:
    def __init__(self):
        self.comico_id = 419025
        self.base_url = 'https://www.zhuimh.com'
        self.href_url = '/comic/'
        self.target_url = self.base_url + self.href_url + str(self.comico_id)

    def window_scroll(self, page):
        # 获取页面高度
        page_height = page.evaluate('() => document.body.scrollHeight')
        # 获取视口高度
        viewport_height = page.evaluate('() => window.innerHeight')

        # 计算需要滚动的距离
        scroll_distance = page_height - viewport_height

        # 模拟鼠标滚轮操作，滚动到页面底部
        page.mouse.wheel(0, scroll_distance)

    def get_chapter_img(self, chapter_name_list, chapter_url_list, path):
        for chapter_name, chapter_url in zip(chapter_name_list, chapter_url_list):
            print(f'章节名: {chapter_name}, 章节url: {chapter_url}')
            with sync_playwright() as playwright:
                browser = playwright.chromium.launch(headless=False)  # headless=False 可以开启浏览器界面，便于调试
                page = browser.new_page()

                page.goto(chapter_url)

                self.window_scroll(page)

                # for _ in range(5):
                #     page.evaluate('''() => {window.scrollTo(0, document.body.scrollHeight);}''')
                #
                #     time.sleep(0.2)
                #
                # page.wait_for_timeout(1000)

                page.wait_for_timeout(3)

                element = page.query_selector('body > div.chpater-images')

                links = element.query_selector_all('img')

                time.sleep(5)

                chapter_file = os.path.join(path, chapter_name)
                if not os.path.exists(chapter_file):
                    os.mkdir(chapter_file)

                #图片后缀都是webp
                img_suffix = '.webp'

                img_count = 1

                for link in links:
                    # 获取每个 <a> 标签的 href 属性
                    img_src = link.get_attribute('src')
                    if 'blob:' in img_src:
                        # 这里开始保存图片
                        # 检测一下图片是否有下载过， 如果有就跳过
                        img_name = str(img_count).zfill(4)+img_suffix
                        img_path = os.path.join(chapter_file, img_name)
                        if not os.path.exists(img_path):
                            # 使用fetch API获取blob数据
                            self.save_blob_as_file(page, img_src, img_path)
                            img_count += 1
                        else:
                            img_count += 1

    def save_blob_as_file(self, page, blob_url, file_path):
        # 使用 playwright 的 evaluate 方法来获取 blob 数据
        buffer = page.evaluate(f"""
            () => {
                const response = fetch('{blob_url}');
                const blob = response.blob();
                const reader = new FileReader();
                reader.readAsArrayBuffer(blob);
                return new Promise((resolve) => {
                    reader.onloadend = () => resolve(reader.result);
                });
            }
        """)
        # 将 ArrayBuffer 转换为 Node.js 的 Buffer 对象
        with open(file_path, 'wb') as file:
            file.write(buffer)

    def get_chapter(self):
        with sync_playwright() as playwright:
            browser = playwright.chromium.launch(headless=True)  # headless=False 可以开启浏览器界面，便于调试
            page = browser.new_page()

            page.goto(self.target_url)

            title = page.title()
            target_name = title.split('漫画免费')[0]
            current_path = os.path.dirname(os.path.abspath(__file__))

            path = os.path.join(current_path, 'zhuimh', target_name)
            if not os.path.exists(path):
                os.makedirs(path)

            element = page.query_selector('body > div.tbox.tabs > div.tabs_block > ul')

            chapter_name_list = []
            chapter_url_list = []

            if element:
                # 执行你需要的操作，例如获取元素的文本内容
                text = element.text_content()
                for line in text.split('\n'):
                    if line.strip():
                        chapter_name_list.append(line.strip())

                links = element.query_selector_all('a')
                for link in links:
                    # 获取每个 <a> 标签的 href 属性
                    href = link.get_attribute('href')
                    if href:
                        chapter_url_list.append(self.base_url + href)
                    else:
                        print('没有找到 href 属性')
            else:
                print('元素未找到')
                exit(0)

            return chapter_name_list, chapter_url_list, path

    def main(self):
        chapter_name_list, chapter_url_list, path = self.get_chapter()
        self.get_chapter_img(chapter_name_list, chapter_url_list, path)


if __name__ == '__main__':
    zhuimh = Zhuimh()
    zhuimh.main()