update

Author: hoshaeyah

spider/proxymiddlewares.py

@@ -3,12 +3,10 @@
 
 class ProxyMiddleware(object):
 
-    proxyList = ['127.0.0.1:1087']
+    proxyList = ['127.0.0.1:7890']
 
     def process_request(self, request, spider):
         # Set the location of the proxy
         pro_adr = random.choice(self.proxyList)
         print("USE PROXY -> " + pro_adr)
         request.meta['proxy'] = "http://" + pro_adr
-
-

spider/spiders/smart_contract_spider.py

@@ -1,5 +1,5 @@
 import scrapy
-from scrapy import log
+# from scrapy import log
 import logging
 
 from spider.items import SmartContractItem
@@ -19,7 +19,7 @@ def start_requests(self):
 
     def parseToken(self, response):
 
-        for each in response.xpath('//h5'):
+        for each in response.xpath('//h3'):
             token_str     = each.xpath('./a/@href').extract_first()
             token         = token_str.split("/")[2]
             sub_url       = self.base_url + 'address/'+ token + '#code'
@@ -38,6 +38,6 @@ def parseCode(self, response):
         item['name']          = name.split('(')[0] + '_' + name.split('(')[1] + '_' + item['token']
 
 
-        log.msg('token: ' + item['token'] + '\n' + 'name：' + item['name'], level=logging.DEBUG)
+        logging.log(logging.DEBUG, 'token: ' + item['token'] + '\n' + 'name：' + item['name'])
 
         yield item

spider/useragent.py

@@ -1,5 +1,5 @@
 # -*-coding:utf-8-*-
-from scrapy import log
+# from scrapy import log
 import logging
 import random
 from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware
@@ -15,7 +15,7 @@ def process_request(self, request, spider):
             #显示当前使用的useragent
             #print "********Current UserAgent:%s************" %ua
             #记录
-            log.msg('Current UserAgent: '+ua, level=logging.DEBUG)
+            logging.log(logging.DEBUG, 'Current UserAgent: '+ua)
             request.headers.setdefault('User-Agent', ua)
 
     #the default user_agent_list composes chrome,I E,firefox,Mozilla,opera,netscape