From dacae684d7d4ef9531421064343cbee646aa05fc Mon Sep 17 00:00:00 2001
From: vincent <vincent0214@qq.com>
Date: Sat, 19 Aug 2023 23:39:18 +0800
Subject: [PATCH] =?UTF-8?q?=E6=90=AC=E7=A7=BB=E5=87=BD=E6=95=B0?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .vscode/launch.json                    |  16 ++
 __pycache__/requester.cpython-310.pyc  | Bin 0 -> 3694 bytes
 __pycache__/web_img.cpython-310.pyc    | Bin 0 -> 472 bytes
 __pycache__/web_parser.cpython-310.pyc | Bin 0 -> 898 bytes
 main.py                                | 194 +++++++++++--------------
 requester.py                           |  78 ++++++++++
 test.py                                |   7 +
 web_img.py                             |   5 +
 web_parser.py                          |  18 +++
 9 files changed, 207 insertions(+), 111 deletions(-)
 create mode 100644 .vscode/launch.json
 create mode 100644 __pycache__/requester.cpython-310.pyc
 create mode 100644 __pycache__/web_img.cpython-310.pyc
 create mode 100644 __pycache__/web_parser.cpython-310.pyc
 create mode 100644 requester.py
 create mode 100644 test.py
 create mode 100644 web_img.py
 create mode 100644 web_parser.py

diff --git a/.vscode/launch.json b/.vscode/launch.json
new file mode 100644
index 0000000..f2a24d0
--- /dev/null
+++ b/.vscode/launch.json
@@ -0,0 +1,16 @@
+{
+	// 使用 IntelliSense 了解相关属性。 
+	// 悬停以查看现有属性的描述。
+	// 欲了解更多信息，请访问: https://go.microsoft.com/fwlink/?linkid=830387
+	"version": "0.2.0",
+	"configurations": [
+		{
+			"name": "Python: Current File",
+			"type": "python",
+			"request": "launch",
+			"program": "main.py",
+			"console": "integratedTerminal",
+			"justMyCode": true
+		}
+	]
+}
\ No newline at end of file
diff --git a/__pycache__/requester.cpython-310.pyc b/__pycache__/requester.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..86d062fa4e87f7969015a8f4e5b49bd536333313
GIT binary patch
literal 3694
zcma)9|4$sp72nw}w|mEzV&Z&jlWL3Gl#38nrS=!pR&g8JSaOgRs8Fx2mgRPU!*{pm
z**yWLBO*Wzj!hu)w*n>w6(?@h0#RIIW4`<!`%|mjE_Xlq_e4ti-tHYfBSW&Moq2C|
z=FOYWd}iJ|v#u_}!E@$+|25Ke9QOq()sFzm8}M2&C=AXZNiG)DBt}5zlYB~u2?X1O
zq?nRok}r$NP)d%;zD$xzOo8uGGMtLUB82-rXM_xSk~8E9K2~FpPA;mHz&_UzB~IOM
zsGhYGec5EEnaw~$W7hzqx^dn#lkLMap0!N|t<u?)-cLaYb<^Inss1>QuYM#@-hkIS
z4+Z7W+Zb=0FnB5$0u}m1Lo}pGDJB|?h73AyC`K4`$%xPpXf;Odq!^QpI;zmn%N(@S
z8{dPLu+aeiKIeqrp_j7MvMDPeNRE(YNhfUU)<rF?r)XS+#>%6BfH?maUTYExn_DI;
z+^A@CgZ!Y77Ys5(My0&CEE;@XTHy)j%R(UM>Ohn7WQB}|@}cF>3J2dqgK{_5$%&k;
zjGQ6dC}5pCVTTPdPZj~|yu8RQi4%mt_dE|Rp(TETi~|az^1Jd78RDWc!d;Wnhc!lR
zmY`Nn9<c39+v(Fe1qBPG=61$Rrke41mN9CmLj#E<Rr{zNA4sJ8)wjCdKBx9EGo|ME
zHZ}VatgS^Ye(<?FduxB^!_vxs2JBSQUH!Cp|86wmC@jFta^y~GSqU@kD7v9%07T2F
zd8@1I{Fy*=q?DOW+m6srZKr|h35#ldCetiix3iWb+H}}<!tKLxnz7M}lwpaq9aS9B
zqRBpnc(X7Th`J+N<;mpoWax;MG1C@x2>l1gz7M^=Y-?}35H}5aAvL1;b*5a$%~T?;
z^_u2I%`k`3NmDl{yHH*VWv!VJC*lL5;bLpRmW2itQcr5($MX@Qz^|U1gjX5kzs{XJ
z;7;q4fhA<DBPUY*8c->Yq^dk25YVpApKTCqE)To;Cimy=Q6YEACWCyQ7{uUb_}Ru$
z5!fR591#b_ZjOhODFRO>;FO|9fHgnktW!h44gCEP-fr%a2uzYj{sc^d6P$Z3FXVYc
ze2Kfrv35HId=d=tMGkr7vq@f(kXz|m_@<!L4R#D+RC*WBztCBwUlN0M<Q#s9hO>*X
z)QDPsN@EMfy{Y|2^X}Th{=%fYxVwL4>JRUnD?GSb+}R0K_wrxdwTEAfjYkfKxwGTm
z&5g&~3kNL~gO$3Bq}puREZU|9mS6_3?cUjNm&VXurSsvs>R71Fz^xY5on0@DT>(R7
z$9z(Iw>QC}cW2C9{iHNCQ(V94{c8pM0@I~Oe=V-979MQ<0-Bz3y|{P7UHr%$+dj_w
z-VvKxDjdBIGfmr6Z+gys|8Lcpz`TX6YsI}qcX|_M^k&u`Z(l23y<6>`J3SvvhDM(9
z!Tao9@sqzF=Rk39zVP6m?$iz#5BA8N{jfCl9v;);`sd!K<JI1Hx26h@Hem{PZKANV
zw}0baPvx-pxLen~rMtnc0N@86;Z|Rtakp-uTZhrF=<dhk-bZ(Wc>)Arje$$<#^o}O
zK4GfS2-xy?d)mj)Ti$lJXCH50`K}WM*H!gI?#2@CEbj6`PZcwIU}u9}hu-^(_uc7@
zz)NrXR&jS1)M`!?9=u<gpF7rzJNLZx*#o16hgVCt?;ki)*k16iTz6+SN;l?<>+9a;
zwD;aR0P9_w+F#uYW<ok_eSGX3KBU!t!Ctu=JMP>Eg-0{{lbhb{W$&|_)q8v30b;&;
z-JRMBAPPKiA8sDOvC1x1>cZ|-_uq5JajvJQ=SVIjFyQ0WsQyZAs>CNctfw+b+6s5{
zX}?43V5Yz6TWlD*t%H%uWv=-Hn-A<qj~?Eq2EEWi+mYQW>#fwMRCjf9f9`T{0|jTb
zwYBxg@ib}C?{3`>ea%hJ+_vhw07%hv^wO%4@4~bSE={VZI!Xk>P436P(;@5|s%;*i
z79i20V(u`4sX+6W<aADq!oqTGM|D^AK8W>dDx0(uux<WeNIY6p>tZ640V}Oh*^!u@
z?xzd`9&5nj1Qd=OH`6vv+w3`PItfKI#GXg_hgkT5Uh<t`n1!&HvA{SS6h8pTsR^R3
zzlZqUYJ#Hn6`nLed=|;;U)Ku|uOUu{zEQ*mQu`G~Yw@ex^M~WLZ^4m=XfKebKhA@h
z%7alHW49lx-vl8~2Dwo_4;f#chYSw0Jub_!SD~GU3{c365LF3gXOOEw?5=3z1Y$7J
zBm?4gl<&yml3Oal$G`K+c~vOLcYXrjgQN$0`Y<^n5;ZCXIK76=eroj7gRX}Fda(*1
zOS4T}oo4n9`irTDQ6YlKOb8O0dXREIdL}T{Bc0kZNLn&s*-s&bD4{#P@iq`_Zi1U_
z0IYbx3NmBJcp($+<_ySQg8T)sfZXMU>fFW0hjc^*h6WuWrDs?(NYLQZBZ{pGE&p{m
zOo^sm9a35Ch;{o;p92FHreF&2r0JVn%acWa`(VhinT*~L_9|A81Z(~u1Wj`ynwBz+
zY?6Xpt7(_AdJ_LSfF{7{W3NDe=I<(U%3qTsB8sd9^(R~BOGt2rUgAlxuu!;@q@lk4
z^%uf^d$iW!P0K%4j?ioUoFQwSMmSb}YM-`S`?7Wx65}$C=g*#F_$S8U6DISy<GX=V
eJZo-8`DL(}U*nBo;lWh^G0cE#fiktEQTRU~x4G*8

literal 0
HcmV?d00001

diff --git a/__pycache__/web_img.cpython-310.pyc b/__pycache__/web_img.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..dd09ba53676ab28cd6f51289f916e481465f405d
GIT binary patch
literal 472
zcmY*U!AiqG5S`tGn1mLgi2smF&mtlP5%JQC2O$)OG_x(CNw;QON+maY_CNd`k9!h&
z@E<%mn^>p=@4d{-&g6~m_haDr{`{hM)`Lq<!{cPcFaxFsARw`4yvY<uK0)H;T>lr6
zvk}8wFeyj{K`Kd*+(YV-$1}bSp4IfRn&)o&G2FMCy<?b5rbaY?&`4(9!7K@QT8tCV
zM(fNhaG6!gdYihmK4t5S>%LLt%to`KRBg9*TR)&aWBIwdzn<ip)TG*BtE)fFbyegz
z)p~)Xx64vzr0U65O|huv!`04)h{dv4BRYd7U<yPaV)1(39Wp%j$9x<=cE%8Gj96*f
zuotvF#FtH0cAYxn6|Jcg3SCVwIT)WQgq~<C<D}D**Y2X)jo9#}`^jxP=Nt~;7hQ2?
A%m4rY

literal 0
HcmV?d00001

diff --git a/__pycache__/web_parser.cpython-310.pyc b/__pycache__/web_parser.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..e33cb9c859b8f2e74b427a176606b55e3baa117e
GIT binary patch
literal 898
zcmY*XO>Yx15VhCd%{FX{RC<6bw?%4BoB$!jr?^B&Js_=uENAV64f~PW8>&W|Q*(s>
zP>%d1pDJ<UFK}YUNkg#Y@p#65e)Go7;bEV^_;z!nctFT6-0Tkqn-?(cBQT06T9S%p
zl%gM$LB%pg$vdK$;%lP#RgiHNo{=>A4d+Qp-Qi0u7i}?FlxNLi4uR;S9>1@qIp+7r
z?xlwi)g+^eWPzfZO#&4tw&s8g*lUu7DuNe!?f{TJNMp5e$>+8zMc&k{uG<_6*$wn@
zzJh77){b^W0DXX<!<3p3Vrk&G)#b!*eiGAz*q^6wo{aKF=}~nF$gs}0Yu;2vF2+ss
zMX2VYE*q(|8C~eHn0q#Z`K616DC(jWBEol(K%Xv;cZ3JG>6}99cHmhK({p_bPD?s6
zql#VyE85YS7eevx!8KFi54sAbWW~DRHTjgRc*kd4MGwd-?AUeKL7tNHla8TO!{r?m
zXt3eum@2+5?;0&tQBO~|s$pyLQd%n<E2`--R<f0+*5qkqkiXZ)@kvoD7o!!jEL|wu
z)>s$G`CQiuj$#cUCiFUs0Y<cPYB%1(ls4;aW6nDe@>*|9j8~65M}f!i!U4qW5txLY
zP)=jorwOdf`~Rf;|H3ehQ2bg}S_sz{qH5HlL_ZPYd?CwihS}B_L^t=)V8{0iQZd*H
y{2dl+ipdd8n2!z9(6O<7>}7F1Y&_64_<?<X568p$y5eUWBG0km9x;KMj@e(KwAQNt

literal 0
HcmV?d00001

diff --git a/main.py b/main.py
index 9b8df50..132c6f3 100644
--- a/main.py
+++ b/main.py
@@ -1,127 +1,98 @@
-import os
-import requests
-from bs4 import BeautifulSoup
 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 get_html(url, file_name, max_retries=3):
-    session = requests.Session()
-    adapter = requests.adapters.HTTPAdapter(max_retries=max_retries)
-    session.mount("http://", adapter)
-    session.mount("https://", adapter)
+# def fetch_image(img_url: str, max_retries=5):
+#     """
+#     通过给定的图片URL下载图片内容。
 
-    try:
-        response = session.get(url)
-        response.raise_for_status()
-        return response.text
-    except Exception as e:
-        print(f"Error occurred while fetching HTML from {url}: {e}")
-        raise Exception(f"{file_name}, 获取网页html失败")
+#     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 download_image(img_url, 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 get_img_urls(html_content):
-    soup = BeautifulSoup(html_content, "html.parser")
-    img_tags = soup.find("div", class_="reading-content").find_all("img")
-
-    img_urls = []
-    for img_tag in img_tags:
-        img_url = img_tag.attrs["data-src"]
-        img_urls.append(img_url)
-    return img_urls
-
-
-def create_img_obj_list(img_url_list, file_name):
+def create_web_img_list(img_url_list, task_name):
     img_obj_list = []
     for url in img_url_list:
-        obj = dict()
-        obj["file_name"] = file_name
-        obj["url"] = url
-        obj["data"] = None
-        img_obj_list.append(obj)
+        img = WebImg(task_name, url)
+        img_obj_list.append(img)
 
     return img_obj_list
 
 
-def download_images_to_img_obj(img_obj):
-    url = img_obj["url"]
-    data = download_image(url)
-    if data is None:
-        file_name = img_obj["file_name"]
-        print(f"{file_name}, 下载图片失败")
-        raise Exception(f"{file_name}, 下载图片失败")
-    img_obj["data"] = data
+# 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_download_images_to_img_obj_list(img_obj_list):
-    """
-    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。
+# 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。
+#     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(download_images_to_img_obj, img_obj_list)
+#     Returns:
+#         None
+#     """
+#     with ThreadPoolExecutor() as executor:
+#         executor.map(fetch_images_to_img_obj, web_img_list)
 
 
-def concatenate_images_vertically(img_obj_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(img_obj["data"])).width for img_obj in img_obj_list
+            Image.open(io.BytesIO(web_img.data)).width for web_img in web_img_list
         )
         total_height = sum(
-            Image.open(io.BytesIO(img_obj["data"])).height for img_obj in img_obj_list
+            Image.open(io.BytesIO(web_img.data)).height for web_img in web_img_list
         )
 
         # 创建一张新的长图
@@ -129,8 +100,8 @@ def concatenate_images_vertically(img_obj_list):
 
         # 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"]))
+        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))
@@ -139,27 +110,28 @@ def concatenate_images_vertically(img_obj_list):
         return long_image
 
     except Exception as e:
-        file_name = img_obj_list[0]["file_name"]
-        print(f"{file_name}, 拼接图片失败：{e}")
+        task_name = web_img_list[0].task_name
+        print(f"{task_name}, 拼接图片失败：{e}")
         return None
 
 
-def pre_batch_task(lines):
+def pre_batch_task(lines: list[str]):
     """
     每个线程的批次任务
     """
     for line in lines:
         line = line.strip()  # 去掉每行开头和结尾的空白字符
         if line:
-            file_name, _, url = line.partition(" - ")  # 解析出 HTML 文件名和 URL 地址
-            print(f"{file_name}, 开始下载")
-            html_content = get_html(url, file_name)
-            img_url_list = get_img_urls(html_content)
-            img_obj_list = create_img_obj_list(img_url_list, file_name)
-            batch_download_images_to_img_obj_list(img_obj_list)
-            long_image = concatenate_images_vertically(img_obj_list)  # 垂直拼接长图片
-            long_image.save(f"output/{file_name}.png")  # 保存长图到本地
-            print(f"{file_name}, 完成!!")
+            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
+            print(f"{task_name}, 完成!!")
 
 
 def read_lines_from_file(task_file):
@@ -167,7 +139,7 @@ def read_lines_from_file(task_file):
     从文件中读取所有行并返回一个包含行的列表。
 
     参数：
-        file_name (str): 要读取的文件名。
+        task_file (file): 任务文件。
 
     返回值：
         lines (list): 包含文件中所有行的列表。
diff --git a/requester.py b/requester.py
new file mode 100644
index 0000000..27cf08b
--- /dev/null
+++ b/requester.py
@@ -0,0 +1,78 @@
+import os
+import requests
+from bs4 import BeautifulSoup
+from concurrent.futures import ThreadPoolExecutor
+from PIL import Image
+import io
+from web_img import WebImg
+
+
+class Requester:
+    def fetch_html(self, url: str, task_name: str, max_retries=3):
+        session = requests.Session()
+        adapter = requests.adapters.HTTPAdapter(max_retries=max_retries)
+        session.mount("http://", adapter)
+        session.mount("https://", adapter)
+
+        try:
+            response = session.get(url)
+            response.raise_for_status()
+            return response.text
+        except Exception as e:
+            print(f"Error occurred while fetching HTML from {url}: {e}")
+            raise Exception(f"{task_name}, 获取网页html失败")
+
+    def fetch_image(self, 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 fetch_images_to_img_obj(self, web_img: WebImg):
+        url = web_img.url
+        data = self.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(self, web_img_list: list[WebImg]):
+        with ThreadPoolExecutor() as executor:
+            executor.map(self.fetch_images_to_img_obj, web_img_list)
diff --git a/test.py b/test.py
new file mode 100644
index 0000000..b441c78
--- /dev/null
+++ b/test.py
@@ -0,0 +1,7 @@
+from web_img import WebImg
+
+
+def main():
+    i = WebImg("name", "url.com")
+    print(i)
+main()
\ No newline at end of file
diff --git a/web_img.py b/web_img.py
new file mode 100644
index 0000000..3550c7a
--- /dev/null
+++ b/web_img.py
@@ -0,0 +1,5 @@
+class WebImg:
+    def __init__(self, file_name, url):
+        self.task_name = file_name
+        self.url = url
+        self.data = None
diff --git a/web_parser.py b/web_parser.py
new file mode 100644
index 0000000..39d23ea
--- /dev/null
+++ b/web_parser.py
@@ -0,0 +1,18 @@
+from bs4 import BeautifulSoup
+from web_img import WebImg
+
+
+class WebParser:
+    def __init__(self, html_content: str):
+        self.html_content = html_content
+
+    def parse_img_urls(self):
+        soup = BeautifulSoup(self.html_content, "html.parser")
+        img_tags = soup.find("div", class_="reading-content").find_all("img")
+        img_urls = []
+        for img_tag in img_tags:
+            img_url = img_tag.attrs["data-src"]
+            img_urls.append(img_url)
+        return img_urls
+
+