🎨 [error]网站结构发生变化

OthertCrawler/0x05quanjing/quanjingwang.py

@@ -1,23 +1,23 @@
-#-*- coding:utf-8 -*-
+# -*- coding:utf-8 -*-
 # 多线程，自动创建文件夹，每个页面单独存储一个文件夹
 
-import requests
-import threading
+import os
+import queue
 import re
+import threading
 import time
-import queue
-import os
-from bs4 import BeautifulSoup
 
+import requests
+from bs4 import BeautifulSoup
 
 string = 'https://www.quanjing.com/category/1286521/'
 url_queue = queue.Queue()
-pipei = re.compile('lowsrc="(.*?)" m=')     #
+pipei = re.compile('lowsrc="(.*?)" m=')  #
 
 
 def get_url(page):
-    for i in range(1, page+1):
-        url = string +'{}.html'.format(i) #更改网址拼接形式
+    for i in range(1, page + 1):
+        url = string + '{}.html'.format(i)  # 更改网址拼接形式
         url_queue.put(url)
     # print(url_queue.queue)
 
@@ -29,16 +29,16 @@ def spider(url_queue):
         floder_name = floder_count[1]
     else:
         floder_name = floder_count
-    os.mkdir('第{0}页'.format(floder_name)) # mkdir只能创建一级目录，makedirs可以创建多级目录,可能是以参数中的‘/’分级
-    html = requests.get(url=url).text
+    os.mkdir('第{0}页'.format(floder_name))  # mkdir只能创建一级目录，makedirs可以创建多级目录,可能是以参数中的‘/’分级
+    html = requests.get(url=url, verify=False).text
     soup = BeautifulSoup(html, 'lxml')
     ul = soup.find_all(attrs={"class": "gallery_list"})
     # print(ul)
-    lianjies = re.findall(pipei, str(ul))       # 正则匹配必须是字符串类型
+    lianjies = re.findall(pipei, str(ul))  # 正则匹配必须是字符串类型
     i = 1
     for lianjie in lianjies:
         # print(lianjie)
-        result = requests.get(url=lianjie).content
+        result = requests.get(url=lianjie, verify=False).content
         with open('第{0}页\{1}.jpg'.format(floder_name, i), 'ab') as f:
             f.write(result)
         print('第{0}页第{1}张存储完成'.format(floder_name, i))
@@ -52,7 +52,7 @@ def main():
     queue_list = []
     queue_count = 3
     for i in range(queue_count):
-        t = threading.Thread(target=spider, args=(url_queue, ))
+        t = threading.Thread(target=spider, args=(url_queue,))
         queue_list.append(t)
     for t in queue_list:
         t.start()