更新 'jcomic/main.py'

jcomic/main.py

@@ -1,84 +1,84 @@
 import os
 import time
-from playwright.sync_api import sync_playwright
+import httpx
+from bs4 import BeautifulSoup
 
-
-use_proxy = 1
+use_proxy = 0
 base_url = 'https://jcomic.net'
 herf_url = '/eps/'
-comico_url = '%E7%99%BE%E5%90%88%E3%83%95%E3%82%A7%E3%83%81LIFE'
+# comico_url = '%E7%99%BE%E5%90%88%E3%83%95%E3%82%A7%E3%83%81LIFE'
+comico_url = '神崎咲良ハーレム化計画'
 target_url = base_url + herf_url + comico_url
-scroll_speed = 5
 
+def save_img(folder_path, img_links):
+    with httpx.Client() as client:
+        for index, img_url in enumerate(img_links, start=1):
+            try:
+                # 发送请求获取图片内容
+                response = client.get(img_url)
+                if response.status_code != 200:
+                    print(f"无法下载图片 {img_url}，状态码: {response.status_code}")
+                    continue
+
+                # 生成文件名，例如 0001.png, 0002.png
+                file_name = f"{str(index).zfill(4)}.png"
+                file_path = os.path.join(folder_path, file_name)
 
-def scroll_to_percentage(page):
-    # 滚动浏览器页面
-    percentage_list = [i for i in range(5, 101, scroll_speed)]
-    for percentage in percentage_list:
-        # 计算页面的指定百分比高度
-        height = page.evaluate("() => document.body.scrollHeight")
-        scroll_position = height * (percentage / 100)
-        # 跳转到指定的百分比位置
-        page.evaluate(f"window.scrollTo({0}, {scroll_position})")
-        time.sleep(0.5)
+                # 保存图片到本地
+                with open(file_path, 'wb') as file:
+                    file.write(response.content)
 
+                print(f"图片已保存: {file_path}")
+            except Exception as e:
+                print(f"下载图片 {img_url} 时出错: {e}")
+            time.sleep(1)
 
 def get_imgs(folder_path, chapter_data):
-    with sync_playwright() as p:
+    img_links = []
+    with httpx.Client() as client:
         for chapter_name, url in chapter_data.items():
             # 创建文件夹
             chapter_folder = os.path.join(folder_path, chapter_name)
             if not os.path.exists(chapter_folder):
                 os.makedirs(chapter_folder)
 
-            # 遍历章节数据，依次下载图片
-            
-            if use_proxy:
-                browser = p.chromium.launch(headless=True, proxy={"server": "http://127.0.0.1:7890"})
-            else:
-                browser = p.chromium.launch(headless=True)
-            page = browser.new_page()
+            # 发送请求获取页面内容
+            response = client.get(url)
+            if response.status_code != 200:
+                print(f"无法访问 {url}，状态码: {response.status_code}")
+                continue
 
-            page.goto(url)
-
-            time.sleep(1)
-            print(f'滚动 {chapter_name}')
-            scroll_to_percentage(page)
-            print(f'滚动 {chapter_name}完成')
+            # 解析 HTML
+            soup = BeautifulSoup(response.text, 'html.parser')
 
             # 获取图片的上一层元素
-            parent_locator = page.locator('body > div.container > div.row.col-lg-12.col-md-12.col-xs-12')
-
-            # 获取匹配的图片元素数量
-            total_images = parent_locator.locator('img').count()
+            parent_element = soup.select_one('body > div.container > div.row.col-lg-12.col-md-12.col-xs-12')
+            if not parent_element:
+                print(f"{chapter_name} 未找到图片容器")
+                continue
+
+            # 获取所有图片元素
+            img_elements = parent_element.select('img')
+            total_images = len(img_elements)
             print(f'{chapter_name} 共 {total_images} 张图片')
 
-            n = 1
-            # 遍历图片元素并截图保存
-            for page_num in range(1, total_images + 1):
-                img_locator = f'body > div.container > div.row.col-lg-12.col-md-12.col-xs-12 > img:nth-child({page_num})'
-                img_path = os.path.join(
-                    chapter_folder, f'{str(n).zfill(3)}.png')
-                try:
-                    # 先不截图, 获取图片的src
-                    src_urls = page.query_selector_all(img_locator)
-                    for src_url in src_urls:
-                        src = src_url.get_attribute('src')
-                        if src:
-                            page.locator(img_locator).screenshot(path=img_path)
-                            n += 1
-                except Exception:
-                    continue
-            print(f'{chapter_name} 保存完成')
-
-        browser.close()
+            # 输出图片的 URL
+            for img in img_elements:
+                img_url = img.get('src')
+                if img_url:
+                    img_links.append(img_url)
+    return img_links
 
+def save_urls(folder_path, img_links):
+    # 定义保存文件路径
+    save_path = os.path.join(folder_path, 'img_links.txt')
 
-def save_urls(folder_path, chapter_data):
-    with open(os.path.join(folder_path, 'urls.txt'), 'w') as file:
-        for chapter_name, url in chapter_data.items():
-            file.write(f"{chapter_name}: {url}\n")
+    # 将图片链接写入文件
+    with open(save_path, 'w', encoding='utf-8') as file:
+        for link in img_links:
+            file.write(link + '\n')
 
+    print(f"图片链接已保存到: {save_path}")
 
 def new_folder(page_title):
     # 获取当前脚本所在的目录
@@ -97,61 +97,43 @@ def new_folder(page_title):
 
         return folder_path
 
-
 def get_chapter_data():
     result = {}
     page_title = ''
-    with sync_playwright() as p:
-        if use_proxy:
-            browser = p.chromium.launch(
-                headless=True, proxy={"server": "http://127.0.0.1:7890"})
-        else:
-            browser = p.chromium.launch(headless=True)
-        page = browser.new_page()
-
-        # 打开目标页面
-        page.goto(target_url)
-
-        # 等待页面加载完成
-        page.wait_for_selector('body > div.container > div:nth-child(3) > div:nth-child(2)')
-
-        # 获取页面标题
-        page_title = page.title()
-        if page_title:
-            page_title = page_title.replace('JComic - ', '')
-            page_title = page_title.replace(' ', '')
 
-        # 获取指定选择器下的所有元素
-        elements = page.query_selector_all('body > div.container > div:nth-child(3) > div:nth-child(2) a')
+    # 使用 httpx 发送请求
+    with httpx.Client() as client:
+        response = client.get(target_url)
+        if response.status_code == 200:
+            soup = BeautifulSoup(response.text, 'html.parser')
 
-        # 提取每个元素的 URL 和文本
-        for element in elements:
-            url = element.get_attribute('href')
-            text = element.inner_text()
-            result[text] = base_url + url
+            # 获取指定选择器下的所有元素
+            elements = soup.select('body > div.container > div:nth-child(3) > div:nth-child(2) a')
 
-        # 关闭浏览器
-        browser.close()
-    return page_title, result
+            # 提取每个元素的 URL 和文本
+            for element in elements:
+                url = element.get('href')
+                text = element.get_text()
+                result[text] = base_url + url
 
+    return result
 
 def main():
-    # 1, 获取页面 title 和章节数据
-    page_title, chapter_data = get_chapter_data()
-    if not page_title:
-        print('获取页面标题失败')
-        exit(0)
+    # 1, 获取页面章节数据
+    chapter_data = get_chapter_data()
 
     # 2, 在当前文件夹下创建一个文件夹，用来保存图片, 文件名称是 title
-    folder_path = new_folder(page_title)
+    folder_path = new_folder(comico_url)
 
-    # 3, 保存url到新建的文件夹中
-    save_urls(folder_path, chapter_data)
+    # 3, 遍历章节数据，获取img的链接
+    img_links = get_imgs(folder_path, chapter_data)
 
-    # 4, 遍历章节数据，依次下载图片
-    get_imgs(folder_path, chapter_data)
+    # 4, 保存url到新建的文件夹中
+    save_urls(folder_path, img_links)
 
+    # 5，遍历 img_links ，将图片保存到 folder_path中， 保存的文件名类似 0001.png
+    save_img(folder_path, img_links)
 
 if __name__ == '__main__':
     main()
-    print('done!')
+    print('done!')