Files
NScrapy/NScrapy.Project/appsetting.json
Elendil 2703e6d174 refactor zookeeper config provider
Also use a more elegent way to exit in memory Nscrapy Crawl mode
2018-07-09 23:42:03 +08:00

50 lines
1.7 KiB
JSON

{
"AppSettings": {
//"ConfigProvider": "Zookeeper",
//"ZookeeperEndpoint": "192.168.0.103:2181",
//"Scheduler": {
// "SchedulerType": "NScrapy.Scheduler.RedisExt.RedisScheduler"
//},
"Scheduler.RedisExt": {
"RedisServer": "192.168.0.106",
"RedisPort": "6379",
"ReceiverQueue": "NScrapy.Downloader",
"ResponseQueue": "NScrapy.ResponseQueue"
},
"DownloaderMiddlewares": [
{
"Middleware": "NScrapy.Downloader.Middleware.HttpUserAgentPoolMiddleware"
},
{
"RemovedMiddleware": "test3"
}
],
"Pipelines": [
{ "Pipeline": "NScrapy.Project.MongoItemPipeline" },
{ "Pipeline": "NScrapy.Project.CSVItemPipeline" }
],
"DownloaderPoolCapbility": 1000,
"HttpHeader": {
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Encoding": "gzip,deflate",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36"
},
"SpiderProject": "NScrapy.Project",
"UserAgentPool": [
{
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko"
},
{
"User-Agent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)"
},
{
"User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)"
},
{
"User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)"
}
]
}
}