From e59b6d0b483ff9360d7ce6710d77ac5638f7669e Mon Sep 17 00:00:00 2001
From: shingyu <git@x1v.icu>
Date: Mon, 13 Nov 2023 23:06:10 +0800
Subject: [PATCH] =?UTF-8?q?feat(epub):=20=E6=96=B0=E5=A2=9Eepub=E6=A8=A1?=
 =?UTF-8?q?=E5=BC=8F=E4=B8=93=E7=94=A8=E8=8E=B7=E5=8F=96=E4=BB=A3=E7=A0=81?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 src/epub_bookinfo.py | 101 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 101 insertions(+)
 create mode 100644 src/epub_bookinfo.py

diff --git a/src/epub_bookinfo.py b/src/epub_bookinfo.py
new file mode 100644
index 0000000..765b3aa
--- /dev/null
+++ b/src/epub_bookinfo.py
@@ -0,0 +1,101 @@
+
+# 开发者注意:
+# 七猫网页在点击类名为：tab-inner 的”作品目录“按钮后
+# 才会显示目录内容
+# TODO: 实现获取EPUB格式需要的书籍信息
+
+import asyncio
+import os
+import public as p
+from bs4 import BeautifulSoup
+import re
+
+# 设置镜像下载地址
+os.environ["PYPPETEER_DOWNLOAD_HOST"] = "https://mirrors.huaweicloud.com"
+from pyppeteer import launch  # noqa: E402
+
+
+async def get_book_info(url):
+    # 创建一个Pyppeteer的Browser实例
+    browser = await launch()
+
+    # 创建一个新的页面
+    page = await browser.newPage()
+
+    # 访问网页
+    await page.goto(url)
+
+    # 等待加载完成
+    await page.waitForSelector('.tab-inner')
+
+# ==================== 获取简介 ====================
+
+    # 在获取目录前，先获取小说简介
+    html = await page.content()
+    soup = BeautifulSoup(html, "html.parser")
+    intro = soup.find('p', class_='intro').get_text().replace(' ', '\n')
+
+# ==================== 获取简介结束 ====================
+
+    # 模拟点击目录按钮，切换网页内容
+    # 在页面上执行JavaScript代码，模拟点击目录
+    await page.evaluate('''() => {
+        var elements = document.getElementsByClassName('tab-inner');
+        for(var i=0; i<elements.length; i++){
+            elements[i].click();
+        }
+    }''')
+
+    # 等待页面加载
+    await asyncio.sleep(1)
+
+    # 获取网页源代码
+    html = await page.content()
+
+    # 解析网页源码
+    soup = BeautifulSoup(html, "html.parser")
+
+# ==================== 获取标题 ====================
+
+    # 获取小说标题
+    title = soup.find('div', {'class': 'title clearfix'}).find('span', {'class': 'txt'}).text
+    # , class_ = "info-name"
+    # 替换非法字符
+    title = p.rename(title)
+
+# ==================== 获取标题结束 ====================
+
+# ==================== 获取信息 ====================
+
+    info_div = soup.find('div', class_='wrap-txt')
+
+    # 在每个div标签中，找到类为'btns-wrap clearfix'的div标签
+    btn = info_div.find('div', class_='btns-wrap clearfix')
+
+    # 如果找到了btn标签，就从原div标签中移除它
+    if btn is not None:
+        btn.extract()
+
+    # 获取剩余的文本
+    info_text = info_div.get_text()
+
+    # 使用re模块的sub函数，将text中的多个连续的空格替换为一个空格
+    info_text = re.sub(r'\s+', ' ', info_text)
+
+    info = info_text + '\n'
+
+# ==================== 获取信息结束 ====================
+
+    # 匹配类名，找出目录标签，获取目录列表
+    chapters = soup.select('li[class^="clearfix ref-catalog-li-"]')
+
+    # epub模式需要获取作者名
+    author_name = soup.find('div', {'class': 'sub-title'}).find('a').text.strip()
+
+    # 关闭Browser实例
+    await browser.close()
+
+    return {'intro': intro, 'title': title, 'info': info, 'chapters': chapters, 'author': author_name}
+
+# 运行异步任务
+# asyncio.run(main())