里程碑v2

main.py

@@ -3,10 +3,12 @@ import requests
 from bs4 import BeautifulSoup
 from concurrent.futures import ThreadPoolExecutor
 
+
 from PIL import Image
 import io
 from reportlab.lib.pagesizes import letter
 from reportlab.pdfgen import canvas
+from utils import ArrayUtil
 
 
 def get_html(url, max_retries=3):
@@ -24,7 +26,7 @@ def get_html(url, max_retries=3):
         raise Exception("获取网页html失败")
 
 
-def download_image(img_url, max_retries=3):
+def download_image(img_url, max_retries=5):
     for retry in range(max_retries):
         try:
             with requests.get(img_url, stream=True) as response:
@@ -59,13 +61,10 @@ def create_img_obj_list(img_url_list):
         obj["data"] = None
         img_obj_list.append(obj)
 
-        # TODO remember to delete
-        if len(img_obj_list) > 2:
-            break
     return img_obj_list
 
 
-def fill_img_obj(img_obj):
+def set_img_obj_data(img_obj):
     url = img_obj["url"]
     data = download_image(url)
     if data is None:
@@ -104,7 +103,7 @@ def generate_pdf_from_images(img_obj_list, output_file):
 
         for img_obj in img_obj_list:
             # 从图片对象的 data 字段中创建图像对象
-            img_data = img_obj['data']
+            img_data = img_obj["data"]
             img = Image.open(io.BytesIO(img_data))
 
             # 将图像大小调整为 PDF 页面大小
@@ -125,6 +124,38 @@ def generate_pdf_from_images(img_obj_list, output_file):
     except Exception as e:
         print(f"PDF 生成失败：{e}")
 
+
+def concatenate_images_vertically(img_obj_list, output_file):
+    try:
+        # 计算拼接后的长图宽度和总高度
+        max_width = max(
+            Image.open(io.BytesIO(img_obj["data"])).width for img_obj in img_obj_list
+        )
+        total_height = sum(
+            Image.open(io.BytesIO(img_obj["data"])).height for img_obj in img_obj_list
+        )
+
+        # 创建一张新的长图
+        long_image = Image.new("RGB", (max_width, total_height), color=(255, 255, 255))
+
+        # 依次将图片在垂直方向上拼接起来
+        y_offset = 0
+        for img_obj in img_obj_list:
+            img = Image.open(io.BytesIO(img_obj["data"]))
+            img_width, img_height = img.size
+            x_offset = (max_width - img_width) // 2  # 居中拼接
+            long_image.paste(img, (x_offset, y_offset))
+            y_offset += img_height
+
+        # 保存拼接后的长图到本地
+        # long_image.save(output_file)
+        
+
+    except Exception as e:
+        print(f"拼接图片失败：{e}")
+        return None
+
+
 def process_batch(lines):
     for line in lines:
         line = line.strip()  # 去掉每行开头和结尾的空白字符
@@ -138,10 +169,12 @@ def process_batch(lines):
             # 使用 ThreadPoolExecutor 创建线程池
             with ThreadPoolExecutor() as executor:
                 # 多线程处理图片下载和替换
-                executor.map(fill_img_obj, img_obj_list)
+                executor.map(set_img_obj_data, img_obj_list)
 
             # save_images_to_directory(img_obj_list, directory_path="imgs")
-            generate_pdf_from_images(img_obj_list, output_file=f"imgs/{file_name}.pdf")
+            concatenate_images_vertically(
+                img_obj_list, output_file=f"imgs/{file_name}.pdf"
+            )
 
 
 if __name__ == "__main__":