From 510b4bf0d4014f998e91253e4cc5954287171bc6 Mon Sep 17 00:00:00 2001
From: vincent <vincent0214@qq.com>
Date: Sun, 20 Aug 2023 01:05:56 +0800
Subject: [PATCH] update

---
 __pycache__/requester.cpython-310.pyc       | Bin 3694 -> 3694 bytes
 __pycache__/web_img.cpython-310.pyc         | Bin 472 -> 472 bytes
 __pycache__/web_img_manager.cpython-310.pyc | Bin 0 -> 2415 bytes
 __pycache__/web_parser.cpython-310.pyc      | Bin 898 -> 893 bytes
 img_manager.py                              |  62 ++++++++++
 main.py                                     | 128 ++------------------
 web_img_manager.py                          |  63 ++++++++++
 web_parser.py                               |   6 +-
 8 files changed, 135 insertions(+), 124 deletions(-)
 create mode 100644 __pycache__/web_img_manager.cpython-310.pyc
 create mode 100644 img_manager.py
 create mode 100644 web_img_manager.py

diff --git a/__pycache__/requester.cpython-310.pyc b/__pycache__/requester.cpython-310.pyc
index 86d062fa4e87f7969015a8f4e5b49bd536333313..5b90c8104a3083e200a59048f71905b8b6f6f7b7 100644
GIT binary patch
delta 370
zcmaDS^G=2<pO=@50SJn}Zsf{iQjB5`PAx9Z%+HJBNK8pAC`m0Uj^g$R2?=n7@S-Nq
zWXfX{+swf{liiC4sIQ0@NZevi&d)1J%_}M52MGxP2~D;lK@eLCM1X9##afhFQdC(a
z0um4f5n^yceDZ6qhYpG$J|~C(82~ow7E4NENunkz#4II{Fb9ZG1`%MT$cFInoKaH&
z%4jk})T;v7w>VNOQj<$d@{3UH`^S^dC^<QgS6^QOWE9wHRuBuM{}xM5W^qZ828fR^
rAIuV;e1=z>F>3M;UM0OK<^WHhA{LMarp){zu<O8Puwm8c!KVfQ6m(1s

delta 370
zcmaDS^G=2<pO=@50SFu)Zsf{iQoO|;oLXF*nV)xyBQYhhpd_`Z_!hTENJxMqgm-K5
zOr|_Wsm&bBGugcafclCAfy6EL<ovvn)Vz`+VUUmrkkDi+5(Tm4Km^E!TdYN?B}J7*
z5+DId5FrI8q$j`Tdg!1E;&XxskO5$$Zn2~!mLzJjLd;SF33Gr5br1noifjlE&lxoh
zpo}InM7<`EeTyTtA~m_RB)<s7zJEOVjIxvSc=h#VKt_SBW(Bc8`fsu1WEPhc>45kM
s^T90X$!B=A8E;Mg!K<Wqi#fp4r-%ilfhjY;2<$qr8EjZJdhn?M0PYY^Y5)KL

diff --git a/__pycache__/web_img.cpython-310.pyc b/__pycache__/web_img.cpython-310.pyc
index dd09ba53676ab28cd6f51289f916e481465f405d..7d88d0e82eb1bcef7ad68a32acd26b7299cb48ac 100644
GIT binary patch
delta 19
Zcmcb?e1n-QpO=@50SFSFZsa=02mmr{1tS0e

delta 19
Zcmcb?e1n-QpO=@50SKO7+Q@Z|5dbwe1(yH-

diff --git a/__pycache__/web_img_manager.cpython-310.pyc b/__pycache__/web_img_manager.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..514bd33a857d8ed1fa94dd2d7e86141966da2820
GIT binary patch
literal 2415
zcma)7-D@0G6u)0HJ3HCbnts?;T4N~cil+5R)EY`{DFKbrK#NPtFxflV>~?l%bLXx}
zmKmugAR_wai=mQ$edwdmN6~*n?vo&G&65v;4}#Ql?rc6A#k<V8XYc3vo%1{ACd0!%
zf%e9qzsSBv$glWkcjNHqB7Es}5Ryn5lQykUiaLu~o7cG2c`Vva&9S<O-I}{^etX|l
zA|2_j66vn6T1kp&QY~%5*`!KM`C7Eli&7ma_~YJ)W+&SX(45J3*oda;xN3LXwrv7N
zBT}Q1)R?3ZkHkqb$0U<{Rn#0Qq_axEB3G86FG)|9q4%UOhoCRZ3fM4ge7Nkrumd+K
zQ)#vvK~Kd&+)Q;H@7ZdoGx*+tFFge!qZtWE#z2C$&Nc{WT#{*Wk4{yEa$$`r>oC0)
zbi#IIMuVMuf}pOVP)EUHG#lWRc%AXKv?@0ujp8|bhJxsjdqh>B`|IMBH)raJjAq))
zf$h74zMiz3^<XwhZUr(~?8HeZBQ>*ie7k@*-d#3c5HveY9Rx#gUW!J#)TM`L|HzJc
z<6CR$6y~>@00lqmftNvPkQ|V=$YpYKIA<Dlma!F<^Ng<ZjBfy27MzSu6IFuc1D`1L
zqy=T%u-lC~5+=|Xg@iO5yl*&o!U8VDFig~r9q6>fFqPs)L48_*pP>EGJxC7l^d49k
zR5Z!LIu42^D+r9PTR;c`gIYk~3YVL)*-+Q#gSiN06G@r|I<b*VW?MFz7EP5|WTvdP
z_`MI68F})gXW)hu9qrP?w10XRm?zinL4piHS6C!JgVLYWkhqeq0ySIoGFhQ3G^ZNU
zW8WClyd|UnN;60wNYgKQ&SfbV#lD+kxuf~IquupV=Cr&Gx<PX{b6e#ZmX~r5_LWW$
z>762ZIpgbo=4Rzg%&`qdNhUJyb&`vPvl+hueiTFxE#IOf_bKTg$Ma?BBxzOhAw8T8
ztr1zy{55iiuYligkPnIUbN^#s`qKk#kuH+zQ13;=Iyz_%zWwyk+Wm)L{P6IryPIGC
z^kD7BN1uPTJ-f$87(OI@3f~`RL3{$f0s2x+*1<DCTiOzcujO1PKwq{Kdskslj7Wg9
zhBXsYy0omLbn<;8WT->qEH<T{zsC$4KW|Ed)Y~8L@`Xm!iI%!*;(4?HbDP~3<S6wY
z_utwT>Uz?tLxJdEkr)u{qe$syJ&fb!@e6SRN;)yVecHc*RL9_og1iL)g&bE%GIavQ
zNf5@JkD85nt)9gZ<k3#zsWb2wJ*A!lVfeMHm#Td8F%FDv39QxiBu<pVg0YEC?%@ru
zj21yDBJ$w7?|-|0_xB&ZnW`Q#yd5qLGCu9K3)k{aw0NL-B5n2~<8(uKB24+pQa$SG
zX3{CDh|^Wgj;>Y)sRri;HWIapPIMRt1vKNwNvBcxvgR!Z$=qBTX>}SQJPo2&hMF_j
z=%ZR}t9eU<rG`fKzJ2a7r~fll=+N{$2qruxsQ1|8D23xw*UAxFw+@4J*&$Y;BT$RI
z+wAZDOaGS*PlVoq>ue2p0Tg(e$i|?aNn6n*gM8zVY5a~Y(a7+snCh33p6>SaIUB>i
z81Hr(P?^uc8Sol~z&@-k)&+yIre4K?y=*a0;nHBo*KflbTg^OrhW1bG0<~}9RMp4F
z3E#>fFn$oU6WNPVuLQwDFN_B>!oHO})k+=0`^zYfqCivCYbbVXvKqc03cZ2|QXKNg
z2=yGV<cZ3dovC{22(Civ7No#8!SD|z-?iK<5(dvW=y2m*D6E}8{-<bHg}`gXJo_e%
G@P7b-Nj(1m

literal 0
HcmV?d00001

diff --git a/__pycache__/web_parser.cpython-310.pyc b/__pycache__/web_parser.cpython-310.pyc
index e33cb9c859b8f2e74b427a176606b55e3baa117e..2ca776b64f6b54bdb6385d57f24f6c571c31f590 100644
GIT binary patch
delta 85
zcmZo-|I5ag&&$ij00g?9AEf+eoXEGHk!|9^wT%3mix?Fc1qISmOX4$g)8k8va^iC`
Zi%TXiWRj2&4@fL3PA$^Iki5jS0RWj39p3-|

delta 90
zcmey%*2K=2&&$ij00cb`9;C1^P2^k8!Wo{LG;!Zr79k+LIfqe!k)N+1v8XsTJ~KBx
bzO*Q(c=B8(2}uc{Yye2ONDoc+EYk)60SF%H

diff --git a/img_manager.py b/img_manager.py
new file mode 100644
index 0000000..090b2b3
--- /dev/null
+++ b/img_manager.py
@@ -0,0 +1,62 @@
+from requester import Requester
+from web_img import WebImg
+
+from PIL import Image
+import io
+from web_img import WebImg
+from requester import Requester
+
+
+class ImgManager:
+    def __init__(self, img_url_list: list[str]):
+        self.img_url_list = img_url_list
+        self.img_list = self.__create_web_img_list()
+
+    def __create_web_img_list(self):
+        img_list = []
+        for url in self.img_url_list:
+            img = WebImg(self.task_name, url)
+            img_list.append(img)
+        return img_list
+
+    def batch_fetch_images(self):
+        requester = Requester()
+        requester.batch_fetch_images_to_img_obj_list(self.img_list)
+
+    def concatenate_images_vertically(self):
+        """
+        垂直拼接长图片
+        """
+        try:
+            # 计算拼接后的长图宽度和总高度
+            max_width = max(
+                Image.open(io.BytesIO(web_img.data)).width for web_img in self.img_list
+            )
+            total_height = sum(
+                Image.open(io.BytesIO(web_img.data)).height for web_img in self.img_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 web_img in self.img_list:
+                img = Image.open(io.BytesIO(web_img.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
+
+            return long_image
+
+        except Exception as e:
+            task_name = self.img_list[0].task_name
+            print(f"{task_name}, 拼接图片失败：{e}")
+            return None
+
+    def save_long_image(self):
+        long_image = self.concatenate_images_vertically()  # 垂直拼接长图片
+        long_image.save(f"output/{self.img_list[0].task_name}.png")  # 保存长图到本地
diff --git a/main.py b/main.py
index 132c6f3..213cff9 100644
--- a/main.py
+++ b/main.py
@@ -1,118 +1,7 @@
 from concurrent.futures import ThreadPoolExecutor
-from PIL import Image
-import io
-from web_img import WebImg
 from requester import Requester
-from web_parser import WebParser
-
-
-# def fetch_image(img_url: str, max_retries=5):
-#     """
-#     通过给定的图片URL下载图片内容。
-
-#     参数：
-#         img_url (str): 图片的URL地址。
-#         max_retries (int, 可选): 下载失败时的最大重试次数。默认为5次。
-
-#     返回值：
-#         bytes or None: 成功下载图片的二进制数据，若下载失败则返回None。
-
-#     注解：
-#         这个函数通过发送HTTP请求下载图片文件。它使用`requests`库来获取URL返回的响应。
-#         如果下载成功，函数将返回图片的二进制内容（bytes格式）。
-#         如果下载失败，函数将尝试最多`max_retries`次重试，直到成功或达到重试次数上限。
-#         在每次重试之间，函数会打印错误消息来指示重试进度。
-#         如果重试次数用尽后仍然无法下载图片，函数将输出失败消息并返回None。
-
-#         例子：
-#         ```
-#         image_url = "https://example.com/image.jpg"
-#         image_data = download_image(image_url)
-#         if image_data:
-#             # 处理图片数据...
-#         else:
-#             print("无法下载图片，下载失败。")
-#         ```
-#     """
-#     for retry in range(max_retries):
-#         try:
-#             with requests.get(img_url, stream=True) as response:
-#                 response.raise_for_status()
-#                 return response.content
-#         except Exception as e:
-#             if retry < max_retries - 1:
-#                 print(
-#                     f"Failed to download image, retrying ({retry+1}/{max_retries})..."
-#                 )
-#             else:
-#                 print("Failed to download image after multiple retries, skipping.")
-#                 return None
-
-
-def create_web_img_list(img_url_list, task_name):
-    img_obj_list = []
-    for url in img_url_list:
-        img = WebImg(task_name, url)
-        img_obj_list.append(img)
-
-    return img_obj_list
-
-
-# def fetch_images_to_img_obj(web_img: WebImg):
-#     url = web_img.url
-#     data = fetch_image(url)
-#     if data is None:
-#         task_name = web_img.task_name
-#         print(f"{task_name}, 下载图片失败")
-#         raise Exception(f"{task_name}, 下载图片失败")
-#     web_img.data = data
-
-
-# def batch_fetch_images_to_img_obj_list(web_img_list: list[WebImg]):
-#     """
-#     使用 ThreadPoolExecutor 创建线程池，对 img_obj_list 中的每个图片对象调用 set_img_obj_data 函数。
-
-#     Args:
-#         img_obj_list (list): 图片对象列表，每个对象包含图片的数据等信息。
-
-#     Returns:
-#         None
-#     """
-#     with ThreadPoolExecutor() as executor:
-#         executor.map(fetch_images_to_img_obj, web_img_list)
-
-
-def concatenate_images_vertically(web_img_list: list[WebImg]):
-    """
-    垂直拼接长图片
-    """
-    try:
-        # 计算拼接后的长图宽度和总高度
-        max_width = max(
-            Image.open(io.BytesIO(web_img.data)).width for web_img in web_img_list
-        )
-        total_height = sum(
-            Image.open(io.BytesIO(web_img.data)).height for web_img in web_img_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 web_img in web_img_list:
-            img = Image.open(io.BytesIO(web_img.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
-
-        return long_image
-
-    except Exception as e:
-        task_name = web_img_list[0].task_name
-        print(f"{task_name}, 拼接图片失败：{e}")
-        return None
+from web_parser import Parser
+from web_img_manager import ImgManager
 
 
 def pre_batch_task(lines: list[str]):
@@ -122,15 +11,14 @@ def pre_batch_task(lines: list[str]):
     for line in lines:
         line = line.strip()  # 去掉每行开头和结尾的空白字符
         if line:
-            requester = Requester()
             task_name, _, url = line.partition(" - ")  # 解析出 HTML 文件名和 URL 地址
             print(f"{task_name}, 开始下载")
-            html_content = requester.fetch_html(url, task_name)
-            img_url_list = WebParser(html_content).parse_img_urls()
-            web_img_list = create_web_img_list(img_url_list, task_name)
-            requester.batch_fetch_images_to_img_obj_list(web_img_list)
-            long_image = concatenate_images_vertically(web_img_list)  # 垂直拼接长图片
-            long_image.save(f"output/{task_name}.png")  # 保存长图到本地
+            html_content = Requester().fetch_html(url, task_name)
+            img_url_list = Parser(html_content).get_img_url_list()
+
+            img_manager = ImgManager(img_url_list, task_name)
+            img_manager.batch_fetch_images()
+            img_manager.save_long_image()
             print(f"{task_name}, 完成!!")
 
 
diff --git a/web_img_manager.py b/web_img_manager.py
new file mode 100644
index 0000000..a6bccc0
--- /dev/null
+++ b/web_img_manager.py
@@ -0,0 +1,63 @@
+from requester import Requester
+from web_img import WebImg
+
+from PIL import Image
+import io
+from web_img import WebImg
+from requester import Requester
+
+
+class ImgManager:
+    def __init__(self, img_url_list: list[str], task_name):
+        self.img_url_list = img_url_list
+        self.task_name = task_name
+        self.img_list = self.__create_web_img_list()
+
+    def __create_web_img_list(self):
+        img_list = []
+        for url in self.img_url_list:
+            img = WebImg(self.task_name, url)
+            img_list.append(img)
+        return img_list
+
+    def batch_fetch_images(self):
+        requester = Requester()
+        requester.batch_fetch_images_to_img_obj_list(self.img_list)
+
+    def concatenate_images_vertically(self):
+        """
+        垂直拼接长图片
+        """
+        try:
+            # 计算拼接后的长图宽度和总高度
+            max_width = max(
+                Image.open(io.BytesIO(web_img.data)).width for web_img in self.img_list
+            )
+            total_height = sum(
+                Image.open(io.BytesIO(web_img.data)).height for web_img in self.img_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 web_img in self.img_list:
+                img = Image.open(io.BytesIO(web_img.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
+
+            return long_image
+
+        except Exception as e:
+            task_name = self.img_list[0].task_name
+            print(f"{task_name}, 拼接图片失败：{e}")
+            return None
+
+    def save_long_image(self):
+        long_image = self.concatenate_images_vertically()  # 垂直拼接长图片
+        long_image.save(f"output/{self.img_list[0].task_name}.png")  # 保存长图到本地
diff --git a/web_parser.py b/web_parser.py
index 39d23ea..7d5c484 100644
--- a/web_parser.py
+++ b/web_parser.py
@@ -2,11 +2,11 @@ from bs4 import BeautifulSoup
 from web_img import WebImg
 
 
-class WebParser:
+class Parser:
     def __init__(self, html_content: str):
         self.html_content = html_content
 
-    def parse_img_urls(self):
+    def get_img_url_list(self):
         soup = BeautifulSoup(self.html_content, "html.parser")
         img_tags = soup.find("div", class_="reading-content").find_all("img")
         img_urls = []
@@ -14,5 +14,3 @@ class WebParser:
             img_url = img_tag.attrs["data-src"]
             img_urls.append(img_url)
         return img_urls
-
-