liuwei_x_x/abot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sehuatang pdf 优化

Browse Source
This commit is contained in:
liuwei
2025-12-25 15:36:02 +08:00
parent 408bf12342
commit f5a51fa2ec
3 changed files with 42 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
robot.py
+3 -6
View File
@@ -702,12 +702,9 @@ class Robot:
async def generate_sehuatang_pdf(self): async def generate_sehuatang_pdf(self):
try: try:
self.LOG.info("开始生成PDF,generate_sehuatang_pdf") self.LOG.info("开始生成PDF,generate_sehuatang_pdf")
try: tag, path = pdf_file_path()
path = pdf_file_path() if not tag:
except Exception as e: tag, path = pdf_file_path_undetected()
self.LOG.error(f"generate_sehuatang_pdf error: {e}")
path = pdf_file_path_undetected()
# 暂时只发4K群 # 暂时只发4K群
await self.send_group_file_message(path, Feature.PDF_CAPABILITY) await self.send_group_file_message(path, Feature.PDF_CAPABILITY)
except Exception as e: except Exception as e:
utils/sehuatang/shehuatang.py
+22 -17
View File
@@ -23,6 +23,7 @@ from PyPDF2 import PdfReader, PdfWriter
from loguru import logger from loguru import logger
# download_image 函数保持不变 # download_image 函数保持不变
def download_image(url): 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""" """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"""
@@ -57,7 +58,7 @@ def fetch_and_create_pdf(url):
options.add_argument('--disable-logging') options.add_argument('--disable-logging')
options.add_argument('--log-level=3') options.add_argument('--log-level=3')
options.add_experimental_option('excludeSwitches', ['enable-automation', 'enable-logging']) options.add_experimental_option('excludeSwitches', ['enable-automation', 'enable-logging'])
# 根据操作系统选择不同的ChromeDriver路径处理方式 # 根据操作系统选择不同的ChromeDriver路径处理方式
if os.name == 'nt': # Windows if os.name == 'nt': # Windows
chrome_driver_path = os.path.join( chrome_driver_path = os.path.join(
@@ -66,7 +67,7 @@ def fetch_and_create_pdf(url):
) )
else: # Linux else: # Linux
chrome_driver_path = '/usr/bin/chromedriver' # 使用系统PATH中的chromedriver chrome_driver_path = '/usr/bin/chromedriver' # 使用系统PATH中的chromedriver
try: try:
if os.name == 'nt' and not os.path.exists(chrome_driver_path): if os.name == 'nt' and not os.path.exists(chrome_driver_path):
chrome_driver_path = ChromeDriverManager().install() chrome_driver_path = ChromeDriverManager().install()
@@ -81,12 +82,14 @@ def fetch_and_create_pdf(url):
# 获取目标页面 # 获取目标页面
driver.get(url) driver.get(url)
try: 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() enter_button.click()
logger.debug("点击了满18岁按钮") logger.debug("点击了满18岁按钮")
except Exception as e: except Exception as e:
logger.warning(f"未找到满18岁按钮，跳过此步骤: {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 # 处理年龄验证按钮
try: try:
@@ -132,16 +135,16 @@ def fetch_and_create_pdf(url):
# 设置PDF # 设置PDF
# 修改PDF文件路径到项目根目录的temp目录下 # 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__)))), pdf_filename = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))),
'temp', 'temp',
f"JAV-{today}-{len(today_posts)}.pdf") f"JAV-{today}-{len(today_posts)}.pdf")
doc = SimpleDocTemplate(pdf_filename, pagesize=A3) doc = SimpleDocTemplate(pdf_filename, pagesize=A3)
# 计算内容区域的宽度和高度 # 计算内容区域的宽度和高度
page_width, page_height = A3 page_width, page_height = A3
content_width = page_width - doc.rightMargin - doc.leftMargin content_width = page_width - doc.rightMargin - doc.leftMargin
content_height = page_height - doc.topMargin - doc.bottomMargin content_height = page_height - doc.topMargin - doc.bottomMargin
# 设置最大图片尺寸，留出一些边距 # 设置最大图片尺寸，留出一些边距
max_image_width = content_width * 0.95 max_image_width = content_width * 0.95
max_image_height = content_height * 0.7 # 留出足够空间给文本和其他元素 max_image_height = content_height * 0.7 # 留出足够空间给文本和其他元素
@@ -210,19 +213,20 @@ def fetch_and_create_pdf(url):
scale_width = max_image_width / img_width scale_width = max_image_width / img_width
scale_height = max_image_height / img_height scale_height = max_image_height / img_height
scale = min(scale_width, scale_height, 1.0) # 不超过原始大小 scale = min(scale_width, scale_height, 1.0) # 不超过原始大小
# 计算新的尺寸 # 计算新的尺寸
new_width = img_width * scale new_width = img_width * scale
new_height = img_height * scale new_height = img_height * scale
# 重置文件指针 # 重置文件指针
image.seek(0) image.seek(0)
img_stream = BytesIO(image.getvalue()) img_stream = BytesIO(image.getvalue())
# 添加图片到内容中，使用计算后的尺寸 # 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(Image(img_stream, width=new_width, height=new_height))
content.append(Spacer(1, 4)) 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: except Exception as e:
logger.error(f"处理图片时出错: {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: except Exception as e2:
logger.error(f"强制终止Chrome进程失败: {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 # add_pdf_encryption 和 pdf_file_path 函数保持不变
def add_pdf_encryption(pdf_file, password="4000"): def add_pdf_encryption(pdf_file, password="4000"):
"""使用PyPDF2为PDF添加加密保护""" """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(): def pdf_file_path():
try: 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) pdf_path = fetch_and_create_pdf(url)
if pdf_path: if pdf_path:
logger.info(f"返回的PDF文件路径：{pdf_path}") logger.info(f"返回的PDF文件路径：{pdf_path}")
return pdf_path return True, pdf_path
else: else:
# 如果生成失败，返回一个默认的PDF路径 # 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") 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}") 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: except Exception as e:
logger.error(f"生成PDF路径时出错: {e}") logger.error(f"生成PDF路径时出错: {e}")
# 返回一个默认路径 # 返回一个默认路径
default_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "default.pdf") default_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "default.pdf")
return default_path return False, default_path
if __name__ == "__main__": if __name__ == "__main__":
utils/sehuatang/shehuatang_undetected.py
+17 -2
View File
@@ -3,6 +3,7 @@ import os
import requests import requests
from io import BytesIO from io import BytesIO
import undetected_chromedriver as uc import undetected_chromedriver as uc
if os.name == 'nt': if os.name == 'nt':
try: try:
uc.Chrome.__del__ = lambda self: None uc.Chrome.__del__ = lambda self: None
@@ -172,8 +173,22 @@ def fetch_and_create_pdf(url):
def pdf_file_path_undetected(): def pdf_file_path_undetected():
url = 'https://www.sehuatang.net/forum.php?mod=forumdisplay&fid=103&filter=typeid&typeid=481' try:
return fetch_and_create_pdf(url) 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__": if __name__ == "__main__":