def process_request(self, request, spider): if get_ip_proxy(): if request.meta.has_key('tried'): request.meta['tried'] = int(request.meta['tried']) + 1 else: proxy = random.choice(get_ip_proxy()) request.meta['proxy'] = "http://%s:%s" % (proxy['ip'], proxy['port']) request.meta['ip'] = proxy['ip'] request.meta['port'] = proxy['port'] request.meta['tried'] = 1 print utils.get_time_now(), "use ip: %s proxy: %s, try for %s times" % (request.url, request.meta['proxy'], request.meta['tried'] )
def process_request(self, request, spider): if get_ip_proxy(): if request.meta.has_key('tried'): request.meta['tried'] = int(request.meta['tried']) + 1 else: proxy = random.choice(get_ip_proxy()) request.meta['proxy'] = "http://%s:%s" % (proxy['ip'], proxy['port']) request.meta['ip'] = proxy['ip'] request.meta['port'] = proxy['port'] request.meta['tried'] = 1 print utils.get_time_now( ), "use ip: %s proxy: %s, try for %s times" % ( request.url, request.meta['proxy'], request.meta['tried'])
def process_request(self, request, spider): if get_ip_proxy(): if request.meta.has_key("tried"): request.meta["tried"] = int(request.meta["tried"]) + 1 else: proxy = random.choice(get_ip_proxy()) request.meta["proxy"] = "http://%s:%s" % (proxy["ip"], proxy["port"]) request.meta["ip"] = proxy["ip"] request.meta["port"] = proxy["port"] request.meta["tried"] = 1 print utils.get_time_now(), "use ip: %s proxy: %s, try for %s times" % ( request.url, request.meta["proxy"], request.meta["tried"], )
DOWNLOADER_MIDDLEWARES = { 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 200, 'base_location.middlewares.ProxyMiddleware': 150, 'base_location.middlewares.RandomUserAgent': 100, } #mysql MYSQL_HOST = '10.122.202.19' MYSQL_PROXY_DBNAME = 'ip_proxy_db' MYSQL_LOC_DBNAME = 'base_station_location_db' MYSQL_USER = '******' MYSQL_PASSWD = '1qazxsw2' from spiders.rules import get_ip_proxy PROXY = get_ip_proxy() USER_AGENTS = [ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",