Пример #1
0
class Getter():
    def __init__(self):
        self.redis = RedisClient()
        self.crawler = Crawler()

    def is_over_threshold(self):
        """ Check if the mount of proxies is over threshold."""
        if self.redis.count() >= POOL_UPPER_THRESHOLD:
            return True
        else:
            return False

    def run(self):
        print('Getter started.')
        if PRIVATE_PROXY_ENABLE:
            proxies = PrivateProxy().get_proxies()
            for proxy in proxies:
                print('Add private proxy {}'.format(proxy))
                self.redis.add(proxy)
        else:
            if not self.is_over_threshold():
                for callback_label in range(self.crawler.__CrawlFuncCount__):
                    callback = self.crawler.__CrawlFunc__[callback_label]
                    # 获取代理
                    proxies = self.crawler.get_proxies(callback)
                    sys.stdout.flush()
                    for proxy in proxies:
                        self.redis.add(proxy)
Пример #2
0
class Tester(object):
    def __init__(self):
        self.redis = RedisClient()
    
    async def test_single_proxy(self, proxy):
        """
        测试单个代理
        :param proxy:
        :return:
        """
        headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"}
        conn = aiohttp.TCPConnector(verify_ssl=False)
        async with aiohttp.ClientSession(connector=conn) as session:
            try:
                if isinstance(proxy, bytes):
                    proxy = proxy.decode('utf-8')
                real_proxy = 'http://' + proxy
                print('正在测试', proxy)
                async with session.get(TEST_URL, proxy=real_proxy,headers=headers, timeout=15, allow_redirects=False) as response:
                    if response.status in VALID_STATUS_CODES:
                        self.redis.max(proxy)
                        print('代理可用', proxy)
                    else:
                        self.redis.decrease(proxy)
                        print('请求响应码不合法 ', response.status, 'IP', proxy)
            except (ClientError, aiohttp.client_exceptions.ClientConnectorError, asyncio.TimeoutError, AttributeError):
                self.redis.decrease(proxy)
                print('代理请求失败', proxy)
    
    def run(self):
        """
        测试主函数
        :return:
        """
        print('测试器开始运行')
        try:
            count = self.redis.count()
            print('当前剩余', count, '个代理')
            for i in range(0, count, BATCH_TEST_SIZE):
                start = i
                stop = min(i + BATCH_TEST_SIZE, count)
                print('正在测试第', start + 1, '-', stop, '个代理')
                test_proxies = self.redis.batch(start, stop)
                loop = asyncio.get_event_loop()
                tasks = [self.test_single_proxy(proxy) for proxy in test_proxies]
                loop.run_until_complete(asyncio.wait(tasks))
                sys.stdout.flush()
                time.sleep(5)
        except Exception as e:
            print('测试器发生错误', e.args)
Пример #3
0
class Tester(object):
    def __init__(self):
        self.redis = RedisClient()
    
    async def test_single_proxy(self, proxy):
        """
        测试单个代理
        :param proxy:
        :return:
        """
        conn = aiohttp.TCPConnector(verify_ssl=False)
        async with aiohttp.ClientSession(connector=conn) as session:
            try:
                if isinstance(proxy, bytes):
                    proxy = proxy.decode('utf-8')
                real_proxy = 'http://' + proxy
                print('正在测试', proxy)
                async with session.get(TEST_URL, proxy=real_proxy, timeout=15, allow_redirects=False) as response:
                    if response.status in VALID_STATUS_CODES:
                        self.redis.max(proxy)
                        print('代理可用', proxy)
                    else:
                        self.redis.decrease(proxy)
                        print('请求响应码不合法 ', response.status, 'IP', proxy)
            except (ClientError, aiohttp.client_exceptions.ClientConnectorError, asyncio.TimeoutError, AttributeError):
                self.redis.decrease(proxy)
                print('代理请求失败', proxy)
    
    def run(self):
        """
        测试主函数
        :return:
        """
        print('测试器开始运行')
        try:
            count = self.redis.count()
            print('当前剩余', count, '个代理')
            for i in range(0, count, BATCH_TEST_SIZE):
                start = i
                stop = min(i + BATCH_TEST_SIZE, count)
                print('正在测试第', start + 1, '-', stop, '个代理')
                test_proxies = self.redis.batch(start, stop)
                loop = asyncio.get_event_loop()
                tasks = [self.test_single_proxy(proxy) for proxy in test_proxies]
                loop.run_until_complete(asyncio.wait(tasks))
                sys.stdout.flush()
                time.sleep(5)
        except Exception as e:
            print('测试器发生错误', e.args)
Пример #4
0
class Getter():
    def __init__(self):
        self.redis = RedisClient()
        self.crawler = Crawler()
    
    def is_over_threshold(self):
        """
        判断是否达到了代理池限制
        """
        if self.redis.count() >= POOL_UPPER_THRESHOLD:
            return True
        else:
            return False
    
    def run(self):
        print('获取器开始执行')
        if not self.is_over_threshold():
            for callback_label in range(self.crawler.__CrawlFuncCount__):
                callback = self.crawler.__CrawlFunc__[callback_label]
                # 获取代理
                proxies = self.crawler.get_proxies(callback)
                sys.stdout.flush()
                for proxy in proxies:
                    self.redis.add(proxy)