更新wz

python/spider/blog/wz.py

@@ -2,24 +2,29 @@ import requests
 from threading import Thread
 from lxml import etree
 import re
+import os
 
 
 def get_html(url):
+    if not os.path.exists("wz"):
+        os.mkdir("wz")
     resp = requests.get(url)
     resp.close()
     html = etree.HTML(resp.text)
     title = html.xpath('/html/body/div[2]/div/main/div[1]/div/h1/text()')
     content = html.xpath('/html/body/div[2]/div/main/article/div')
     title = ''.join(list(title[0]))
-    file = open(f"wz\\{title}.txt", "a+")
-    file.write(f"URL : {url}\n")
+    file = open(f"wz\\{title}.txt", "a+", errors='ignore')
+    URL = (f"URL : {url}\n")
+    file.write(URL)
+    print(f"正在抓取{title}")
     ## 获取内容
     for i in content:
         text = i.xpath('.//text()')
         for word in text:
-            word_encode = word.encode('utf-8')
             file.write(word)
     file.close()
+    print(f"{title}抓取成功")
 
 
 for index in range(1, 4):