sehuatang pdf 优化

2025-12-25 15:36:02 +08:00
parent 408bf12342
commit f5a51fa2ec
3 changed files with 42 additions and 25 deletions
--- a/robot.py
+++ b/robot.py
@@ -702,12 +702,9 @@ class Robot:
    async def generate_sehuatang_pdf(self):
        try:
            self.LOG.info("开始生成PDF,generate_sehuatang_pdf")
-            try:
-                path = pdf_file_path()
-            except Exception as e:
-                self.LOG.error(f"generate_sehuatang_pdf error: {e}")
-                path = pdf_file_path_undetected()
-
+            tag, path = pdf_file_path()
+            if not tag:
+                tag, path = pdf_file_path_undetected()
            # 暂时只发4K群
            await self.send_group_file_message(path, Feature.PDF_CAPABILITY)
        except Exception as e:
--- a/utils/sehuatang/shehuatang.py
+++ b/utils/sehuatang/shehuatang.py
@@ -23,6 +23,7 @@ from PyPDF2 import PdfReader, PdfWriter

 from loguru import logger

+
 # download_image 函数保持不变
 def download_image(url):
    """下载大于100KB的图片并返回临时文件路径，仅支持jpg、jpeg和png格式"""
@@ -81,12 +82,14 @@ def fetch_and_create_pdf(url):
        # 获取目标页面
        driver.get(url)
        try:
-            enter_button = WebDriverWait(driver, 5).until(EC.element_to_be_clickable((By.XPATH, '//a[contains(text(), "满18岁，请点此进入")]')))
+            enter_button = WebDriverWait(driver, 5).until(
+                EC.element_to_be_clickable((By.XPATH, '//a[contains(text(), "满18岁，请点此进入")]')))
            enter_button.click()
            logger.debug("点击了满18岁按钮")
        except Exception as e:
            logger.warning(f"未找到满18岁按钮，跳过此步骤: {e}")
-        WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, 'tbody[id^="normalthread"]')))
+        WebDriverWait(driver, 10).until(
+            EC.presence_of_all_elements_located((By.CSS_SELECTOR, 'tbody[id^="normalthread"]')))

        # 处理年龄验证按钮
        try:
@@ -133,8 +136,8 @@ def fetch_and_create_pdf(url):
        # 设置PDF
        # 修改PDF文件路径到项目根目录的temp目录下
        pdf_filename = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))),
-                                   'temp', 
-                                   f"JAV-{today}-{len(today_posts)}.pdf")
+                                    'temp',
+                                    f"JAV-{today}-{len(today_posts)}.pdf")
        doc = SimpleDocTemplate(pdf_filename, pagesize=A3)

        # 计算内容区域的宽度和高度
@@ -222,7 +225,8 @@ def fetch_and_create_pdf(url):
                                        # 添加图片到内容中，使用计算后的尺寸
                                        content.append(Image(img_stream, width=new_width, height=new_height))
                                        content.append(Spacer(1, 4))
-                                        logger.debug(f"处理图片: 原始尺寸 {img_width}x{img_height}, 新尺寸 {new_width}x{new_height}")
+                                        logger.debug(
+                                            f"处理图片: 原始尺寸 {img_width}x{img_height}, 新尺寸 {new_width}x{new_height}")
                                except Exception as e:
                                    logger.error(f"处理图片时出错: {e}")

@@ -264,6 +268,7 @@ def fetch_and_create_pdf(url):
                except Exception as e2:
                    logger.error(f"强制终止Chrome进程失败: {e2}")

+
 # add_pdf_encryption 和 pdf_file_path 函数保持不变
 def add_pdf_encryption(pdf_file, password="4000"):
    """使用PyPDF2为PDF添加加密保护"""
@@ -282,21 +287,21 @@ def add_pdf_encryption(pdf_file, password="4000"):

 def pdf_file_path():
    try:
-        url = 'https://www.sehuatang.org/forum.php?mod=forumdisplay&fid=103&filter=typeid&typeid=481'
+        url = 'https://www.sehuatang.net/forum.php?mod=forumdisplay&fid=103&filter=typeid&typeid=481'
        pdf_path = fetch_and_create_pdf(url)
        if pdf_path:
            logger.info(f"返回的PDF文件路径：{pdf_path}")
-            return pdf_path
+            return True, pdf_path
        else:
            # 如果生成失败，返回一个默认的PDF路径
            default_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "default.pdf")
            logger.info(f"PDF生成失败，返回默认路径: {default_path}")
-            return default_path
+            return False, default_path
    except Exception as e:
        logger.error(f"生成PDF路径时出错: {e}")
        # 返回一个默认路径
        default_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "default.pdf")
-        return default_path
+        return False, default_path


 if __name__ == "__main__":
--- a/utils/sehuatang/shehuatang_undetected.py
+++ b/utils/sehuatang/shehuatang_undetected.py
@@ -3,6 +3,7 @@ import os
 import requests
 from io import BytesIO
 import undetected_chromedriver as uc
+
 if os.name == 'nt':
    try:
        uc.Chrome.__del__ = lambda self: None
@@ -172,8 +173,22 @@ def fetch_and_create_pdf(url):


 def pdf_file_path_undetected():
-    url = 'https://www.sehuatang.net/forum.php?mod=forumdisplay&fid=103&filter=typeid&typeid=481'
-    return fetch_and_create_pdf(url)
+    try:
+        url = 'https://www.sehuatang.net/forum.php?mod=forumdisplay&fid=103&filter=typeid&typeid=481'
+        pdf_path = fetch_and_create_pdf(url)
+        if pdf_path:
+            logger.info(f"返回的PDF文件路径：{pdf_path}")
+            return True, pdf_path
+        else:
+            # 如果生成失败，返回一个默认的PDF路径
+            default_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "default.pdf")
+            logger.info(f"PDF生成失败，返回默认路径: {default_path}")
+            return False, default_path
+    except Exception as e:
+        logger.error(f"生成PDF路径时出错: {e}")
+        # 返回一个默认路径
+        default_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "default.pdf")
+        return False, default_path


 if __name__ == "__main__":