From 1b5efdbf3ed1fde116c60e941fab2369048121d6 Mon Sep 17 00:00:00 2001
From: sss011317 <sss011317@gmail.com>
Date: Fri, 11 Dec 2020 14:39:34 +0800
Subject: [PATCH] =?UTF-8?q?=E7=88=AC=E5=8F=96169=E5=9B=BE=E7=89=87?=
 =?UTF-8?q?=E7=BD=91=E7=AB=99=EF=BC=8C=E8=B5=B7=E5=A7=8B=E9=A0=81=E6=95=B8?=
 =?UTF-8?q?=E8=88=87=E7=B5=90=E6=9D=9F=E9=A0=81=E6=95=B8=E7=84=A1=E6=B3=95?=
 =?UTF-8?q?=E5=B0=8D=E6=87=89class?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 ...76\347\211\207\347\275\221\347\253\231.py" | 39 ++++++++++---------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git "a/\347\210\254\345\217\226169\345\233\276\347\211\207\347\275\221\347\253\231.py" "b/\347\210\254\345\217\226169\345\233\276\347\211\207\347\275\221\347\253\231.py"
index 4546759..8680ae7 100644
--- "a/\347\210\254\345\217\226169\345\233\276\347\211\207\347\275\221\347\253\231.py"
+++ "b/\347\210\254\345\217\226169\345\233\276\347\211\207\347\275\221\347\253\231.py"
@@ -7,6 +7,8 @@ headers={
 
 #下载图片的模块
 def Download_the_module(file,tehurl):
+    # 輸入您要放置的檔案位置
+    savePath = "C:/Users/user-50/source/python/crawlerResource/"
     count = 1
     # 进入网站下载图片
     The_second_request = requests.get(tehurl, headers=headers).text
@@ -19,36 +21,37 @@ def Download_the_module(file,tehurl):
         save=i.attr('src')
         #print(save)
         The_sponse=requests.get(save,headers=headers)
-        The_name='F:/图片/'+file
+        The_name=savePath+file
         Save_the_address = str(The_name)
         # 检测是否有image目录没有则创建
         if not os.path.exists(Save_the_address):
 
 
-            os.makedirs('F:/图片/' + file)
+            os.makedirs(savePath + file)
         else:
 
 
             with open(Save_the_address+'/%s.jpg'%count,'wb')as f:
                 f.write(The_sponse.content)
-                print('已经下载了%s张'%count)
+                print('將資料下載到%s | 並下載了%s張'%(Save_the_address,count))
             count += 1
 #爬取地址
-def Climb_to_address(page):
-
-    URL='https://www.169tp.com/gaogensiwa/list_3_%s.html'%page
-    sponse=requests.get(URL,headers=headers)
-    sponse.encoding='gbk'
-    encodin=sponse.text
-    doc=pq(encodin)
-    extract=doc('.pic').items()
-    for i in extract:
-        #文件名
-        The_file_name=i.text()
-        #提取到的网站
-        The_url=i.attr('href')
-
-        Download_the_module(The_file_name,The_url)
+def Climb_to_address(Startpage,Endpage):
+    print("起始頁數:%s,結束頁數:%s,總共找尋頁數:%s" %(Startpage,Endpage,Endpage-Startpage))
+    for page in range(Startpage,Endpage):
+        URL='https://www.169tp.com/gaogensiwa/list_3_%s.html'%page
+        sponse=requests.get(URL,headers=headers)
+        sponse.encoding='gbk'
+        encodin=sponse.text
+        doc=pq(encodin)
+        extract=doc('.pic').items()
+        for i in extract:
+            #文件名
+            The_file_name=i.text()
+            #提取到的网站
+            The_url=i.attr('href')
+
+            Download_the_module(The_file_name,The_url)
 
 #一共有616页
 a=int(input('请输入开始爬取的页数:'))
-- 
Gitee