删除无效爬虫

enuiai · enuiai · commit 865a13e06cbb · 2018-11-19T22:56:50.000+08:00
diff --git a/proxypool/crawler.py b/proxypool/crawler.py
@@ -23,15 +23,7 @@ def get_proxies(self, callback):
             print('成功获取到代理', proxy)
             proxies.append(proxy)
         return proxies
-        
-    # def crawl_daxiang(self):
-    #     url = 'http://vtp.daxiangdaili.com/ip/?tid=559363191592228&num=50&filter=on'
-    #     html = get_page(url)
-    #     if html:
-    #         urls = html.split('\n')
-    #         for url in urls:
-    #             yield url
-          
+       
     def crawl_daili66(self, page_count=4):
         """
         获取代理66
@@ -51,47 +43,6 @@ def crawl_daili66(self, page_count=4):
                     port = tr.find('td:nth-child(2)').text()
                     yield ':'.join([ip, port])
 
-    def crawl_proxy360(self):
-        """
-        获取Proxy360
-        :return: 代理
-        """
-        start_url = 'http://www.proxy360.cn/Region/China'
-        print('Crawling', start_url)
-        html = get_page(start_url)
-        if html:
-            doc = pq(html)
-            lines = doc('div[name="list_proxy_ip"]').items()
-            for line in lines:
-                ip = line.find('.tbBottomLine:nth-child(1)').text()
-                port = line.find('.tbBottomLine:nth-child(2)').text()
-                yield ':'.join([ip, port])
-
-    def crawl_goubanjia(self):
-        """
-        获取Goubanjia
-        :return: 代理
-        """
-        start_url = 'http://www.goubanjia.com/free/gngn/index.shtml'
-        html = get_page(start_url)
-        if html:
-            doc = pq(html)
-            tds = doc('td.ip').items()
-            for td in tds:
-                td.find('p').remove()
-                yield td.text().replace(' ', '')
-
-    def crawl_ip181(self):
-        start_url = 'http://www.ip181.com/'
-        html = get_page(start_url)
-        ip_address = re.compile('<tr.*?>\s*<td>(.*?)</td>\s*<td>(.*?)</td>')
-        # \s* 匹配空格，起到换行作用
-        re_ip_address = ip_address.findall(html)
-        for address,port in re_ip_address:
-            result = address + ':' + port
-            yield result.replace(' ', '')
-
-
     def crawl_ip3366(self):
         for page in range(1, 4):
             start_url = 'http://www.ip3366.net/free/?stype=1&page={}'.format(page)
@@ -102,42 +53,6 @@ def crawl_ip3366(self):
             for address, port in re_ip_address:
                 result = address+':'+ port
                 yield result.replace(' ', '')
-
-
-    def crawl_kxdaili(self):
-        for i in range(1, 11):
-            start_url = 'http://www.kxdaili.com/ipList/{}.html#ip'.format(i)
-            html = get_page(start_url)
-            ip_address = re.compile('<tr.*?>\s*<td>(.*?)</td>\s*<td>(.*?)</td>')
-            # \s* 匹配空格，起到换行作用
-            re_ip_address = ip_address.findall(html)
-            for address, port in re_ip_address:
-                result = address + ':' + port
-                yield result.replace(' ', '')
-
-
-    def crawl_premproxy(self):
-        for i in ['China-01','China-02','China-03','China-04','Taiwan-01']:
-            start_url = 'https://premproxy.com/proxy-by-country/{}.htm'.format(i)
-            html = get_page(start_url)
-            if html:
-                ip_address = re.compile('<td data-label="IP:port ">(.*?)</td>') 
-                re_ip_address = ip_address.findall(html)
-                for address_port in re_ip_address:
-                    yield address_port.replace(' ','')
-
-    def crawl_xroxy(self):
-        for i in ['CN','TW']:
-            start_url = 'http://www.xroxy.com/proxylist.php?country={}'.format(i)
-            html = get_page(start_url)
-            if html:
-                ip_address1 = re.compile("title='View this Proxy details'>\s*(.*).*")
-                re_ip_address1 = ip_address1.findall(html)
-                ip_address2 = re.compile("title='Select proxies with port number .*'>(.*)</a>") 
-                re_ip_address2 = ip_address2.findall(html)
-                for address,port in zip(re_ip_address1,re_ip_address2):
-                    address_port = address+':'+port
-                    yield address_port.replace(' ','')
     
     def crawl_kuaidaili(self):
         for i in range(1, 4):
@@ -206,15 +121,6 @@ def crawl_iphai(self):
                     address_port = address+':'+port
                     yield address_port.replace(' ','')
 
-    def crawl_89ip(self):
-        start_url = 'http://www.89ip.cn/apijk/?&tqsl=1000&sxa=&sxb=&tta=&ports=&ktip=&cf=1'
-        html = get_page(start_url)
-        if html:
-            find_ips = re.compile('(\d+\.\d+\.\d+\.\d+:\d+)', re.S)
-            ip_ports = find_ips.findall(html)
-            for address_port in ip_ports:
-                yield address_port
-
     def crawl_data5u(self):
         start_url = 'http://www.data5u.com/free/gngn/index.shtml'
         headers = {
