Merge pull request #59 from bobobo80/bobo_dev

redis及getFreeProxy修改

DB/RedisClient.py

@@ -9,7 +9,7 @@ self.name为Redis中的一个key
 import json
 import random
 import redis
-
+import sys
 
 class RedisClient(object):
     """
@@ -33,7 +33,14 @@ class RedisClient(object):
         :return:
         """
         key = self.__conn.hgetall(name=self.name)
-        return random.choice(key.keys()) if key else None
+        # return random.choice(key.keys()) if key else None
+        # key.keys()在python3中返回dict_keys，不支持index，不能直接使用random.choice
+        # 另：python3中，redis返回为bytes,需要解码
+        rkey = random.choice(list(key.keys())) if key else None
+        if isinstance(rkey, bytes):
+            return rkey.decode('utf-8')
+        else:
+            return rkey
         # return self.__conn.srandmember(name=self.name)
 
     def put(self, key):
@@ -74,7 +81,12 @@ class RedisClient(object):
         self.__conn.hincrby(self.name, key, value)
 
     def getAll(self):
-        return self.__conn.hgetall(self.name).keys()
+        # return self.__conn.hgetall(self.name).keys()
+        # python3 redis返回bytes类型,需要解码
+        if sys.version_info.major == 3:
+            return [key.decode('utf-8') for key in self.__conn.hgetall(self.name).keys()]
+        else:
+            return self.__conn.hgetall(self.name).keys()
         # return self.__conn.smembers(self.name)
 
     def get_status(self):

ProxyGetter/getFreeProxy.py

@@ -66,7 +66,9 @@ class GetFreeProxy(object):
         url = "http://www.66ip.cn/mo.php?sxb=&tqsl={}&port=&export=&ktip=&sxa=&submit=%CC%E1++%C8%A1&textarea=".format(
                 proxy_number)
         request = WebRequest()
-        html = request.get(url).content
+        # html = request.get(url).content
+        # content为未解码，text为解码后的字符串
+        html = request.get(url).text
         for proxy in re.findall(r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}', html):
             yield proxy
 
@@ -112,8 +114,18 @@ class GetFreeProxy(object):
             page_url = url.format(page=page)
             tree = getHtmlTree(page_url)
             proxy_list = tree.xpath('//td[@class="ip"]')
+            # 此网站有隐藏的数字干扰，或抓取到多余的数字或.符号
+            # 需要过滤掉<p style="display:none;">的内容
+            xpath_str = """.//*[not(contains(@style, 'display: none'))
+                                and not(contains(@style, 'display:none'))
+                                and not(contains(@class, 'port'))
+                                ]/text()
+                        """
             for each_proxy in proxy_list:
-                yield ''.join(each_proxy.xpath('.//text()'))
+                # :符号裸放在td下，其他放在div span p中，先分割找出ip，再找port
+                ip_addr = ''.join(each_proxy.xpath(xpath_str))
+                port = each_proxy.xpath(".//span[contains(@class, 'port')]/text()")[0]
+                yield '{}:{}'.format(ip_addr, port)
 
 
 if __name__ == '__main__':
@@ -127,8 +139,8 @@ if __name__ == '__main__':
     # for e in gg.freeProxyThird():
     #     print e
 
-    for e in gg.freeProxyFourth():
-        print e
+    # for e in gg.freeProxyFourth():
+    #     print(e)
 
-        # for e in gg.freeProxyFifth():
-        #     print(e)
+    for e in gg.freeProxyFifth():
+         print(e)