.

chapter1/crawler/taobao/spiders/jd.py

@@ -85,12 +85,12 @@ class JdSpider(scrapy.Spider):
             # time.sleep(10)
 
             if page>settings['COMMENT_MAX_PAGE']:
-                print("评论抓取达到最大深度, %s, 页数: %d", product_id, page)
+                print("评论抓取达到最大深度, %s, 页数: %d" % (product_id, page))
             else:
                 yield Request(next_comment_url, self.parse_comment,
                           meta={'product_id': product_id, 'page': page})
         else:
-            print("评论抓取完成, %s, 页数: %d", product_id, page)
+            print("评论抓取完成, %s, 页数: %d" % (product_id, page))
 
     def parse(self, response):
         items = response.xpath('//div[@id="plist"]//li[@class="gl-item"]')

chapter2/mysite/myapp/scrapy_client.py

@@ -7,42 +7,42 @@ import happybase
 
 
 def get_crawl_data_info():
-		connection = happybase.Connection('106.75.85.84', port=40009)
+  connection = happybase.Connection('106.75.85.84', port=40009)
-		table = connection.table('jd')
+  table = connection.table('jd')
-		num = 0
+  num = 0
-		for i in table.scan(scan_batching=True):
+  for i in table.scan(scan_batching=True):
-				num += 1
+    num += 1
-		return num
+  return num
-
+ 
 
 def do_telnet(Host, finish):
-    '''Telnet远程登录：Windows客户端连接Linux服务器'''
+  '''Telnet远程登录：Windows客户端连接Linux服务器'''
 
-    # 连接Telnet服务器
+  # 连接Telnet服务器
-    tn = telnetlib.Telnet(Host, port=6023, timeout=10)
+  tn = telnetlib.Telnet(Host, port=6023, timeout=10)
-    tn.set_debuglevel(2)
+  tn.set_debuglevel(2)
 
-    # 输入登录用户名
+  # 输入登录用户名
-    out = tn.read_until(finish)
+  out = tn.read_until(finish)
-    tn.write(b'est()\n')
+  tn.write(b'est()\n')
 
-    # 输入登录密码
+  # 输入登录密码
-    out = tn.read_until(finish)
+  out = tn.read_until(finish)
 
-    tn.close()  # tn.write('exit\n')
+  tn.close()  # tn.write('exit\n')
 
-    return out.decode('utf8')
+  return out.decode('utf8')
 
 def get_scrapy_info():
-	  try:
+  try:
-			response = do_telnet('127.0.0.1', b'>>> ')
+    response = do_telnet('127.0.0.1', b'>>> ')
-			mm = re.findall(r'(.+?)\s+?:\s+?(.+?)\s+', response)
+    mm = re.findall(r'(.+?)\s+?:\s+?(.+?)\s+', response)
-			info = {}
+    info = {}
-			for m in mm:
+    for m in mm:
-				info[m[0]] = m[1]
+      info[m[0]] = m[1]
-			return info
+    return info
-		except:
+  except:
-			return {}
+  	return {}
 
 if __name__ == "__main__":
-		print(get_crawl_data_info())
+  print(get_crawl_data_info())