func main() {
// POST data
post_arg := url.Values{
"name": {"admin"},
"pwd": {"admin"},
}
// http header
header := make(http.Header)
header.Set("Content-Type", "application/x-www-form-urlencoded")
// Spider input:
// PageProcesser ;
// Task name used in Pipeline for record;
// AddRequest Params:
// 1. Url.
// 2. Responce type is "html" or "json" or "jsonp" or "text".
// 3. The urltag is name for marking url and distinguish different urls in PageProcesser and Pipeline.
// 4. The method is POST or GET.
// 5. The postdata is body string sent to sever.
// 6. The header is header for http request.
// 7. Cookies
// 8. Http redirect function
req := request.NewRequest("http://backadmin.hucong.net/main/user/login", "html", "site_login", "POST", post_arg.Encode(), header, nil, myRedirect, nil)
spider.NewSpider(NewMyPageProcesser(), "TaskName").
AddRequest(req).
AddPipeline(pipeline.NewPipelineConsole()). // Print result on screen
SetThreadnum(3). // Crawl request by three Coroutines
Run()
}
func (w *SocialWorker) SpiderMain() {
spider.NewSpider(NewMyPageProcesser(w), "TaskName").
AddUrlWithHeaderFile(crawlUrl.Url, "html", "./header_1.json"). // Start url, html is the responce type ("html" or "json" or "jsonp" or "text")
AddPipeline(pipeline.NewPipelineConsole()). // Print result on screen
SetThreadnum(1). // Crawl request by three Coroutines
Run()
}
func main() {
// spider input:
// PageProcesser ;
// config path(default: WD/etc/main.conf);
// task name used in Pipeline for record;
sp := spider.NewSpider(NewMyPageProcesser(), "", "TaskName")
pageItems := sp.Get("http://baike.baidu.com/view/1628025.htm?fromtitle=http&fromid=243074&type=syn", "html") // url, html is the responce type ("html" or "json")
url := pageItems.GetRequest().GetUrl()
println("-----------------------------------spider.Get---------------------------------")
println("url\t:\t" + url)
for name, value := range pageItems.GetAll() {
println(name + "\t:\t" + value)
}
println("\n--------------------------------spider.GetAll---------------------------------")
urls := []string{
"http://baike.baidu.com/view/1628025.htm?fromtitle=http&fromid=243074&type=syn",
"http://baike.baidu.com/view/383720.htm?fromtitle=html&fromid=97049&type=syn",
}
pageItemsArr := sp.SetThreadnum(2).GetAll(urls, "html")
for _, item := range pageItemsArr {
url = item.GetRequest().GetUrl()
println("url\t:\t" + url)
fmt.Printf("item\t:\t%s\n", item.GetAll())
}
}
func main() {
// Spider input:
// PageProcesser ;
// Task name used in Pipeline for record;
f, err := os.Open("./formated_bookmark")
if err != nil {
panic("f open error")
}
defer f.Close()
sp := spider.NewSpider(NewMyPageProcesser(), "BookMarkSearch")
br := bufio.NewReader(f)
urls := make(map[string]string)
line, err := br.ReadString('\n')
for ; err == nil; line, err = br.ReadString('\n') {
data := strings.Split(line, "||")
url := data[1]
urltag := data[0] + "||" + strings.Trim(data[2], "\n")
urls[url] = urltag
}
sp.AddUrls(urls, "html")
// sp.AddPipeline(pipeline.NewPipelineConsole()).
sp.AddPipeline(pipeline.NewPipelineFile("./crawler_result.dat")).
SetThreadnum(3). // Crawl request by three Coroutines
Run()
}
func main() {
start_url := "http://www.jiexieyin.org"
thread_num := uint(16)
redisAddr := "127.0.0.1:6379"
redisMaxConn := 10
redisMaxIdle := 10
proc := &MyProcessor{}
sp := spider.NewSpider(proc, "redis_scheduler_example").
//SetSleepTime("fixed", 6000, 6000).
//SetScheduler(scheduler.NewQueueScheduler(true)).
SetScheduler(scheduler.NewRedisScheduler(redisAddr, redisMaxConn, redisMaxIdle, true)).
AddPipeline(pipeline.NewPipelineConsole()).
SetThreadnum(thread_num)
init := false
for _, arg := range os.Args {
if arg == "--init" {
init = true
break
}
}
if init {
sp.AddUrl(start_url, "html")
mlog.LogInst().LogInfo("重新开始爬")
} else {
mlog.LogInst().LogInfo("继续爬")
}
sp.Run()
}
func main() {
var startUrl = "http://baike.baidu.com/subview/412610/19548276.htm"
sp := spider.NewSpider(plant.NewPlantProcesser(), "TaskName").
SetScheduler(scheduler.NewQueueScheduler(true)).
AddPipeline(pipeline.NewPipelineFile("result.txt"))
sp.AddUrl(startUrl, "html")
sp.Run()
}
func main() {
// Spider input:
// PageProcesser ;
// Task name used in Pipeline for record;
spider.NewSpider(NewMyPageProcesser(), "TaskName").
AddUrl("https://github.com/hu17889?tab=repositories", "html"). // Start url, html is the responce type ("html" or "json" or "jsonp" or "text")
AddPipeline(pipeline.NewPipelineConsole()). // Print result on screen
SetThreadnum(3). // Crawl request by three Coroutines
Run()
}
func main() {
flag.Parse()
// chan init
exitChan = make(chan struct{})
getURL = make(chan string, *threadNum)
releaseSlot = make(chan int, *threadNum)
// repetition and urlstor initialization
c := redis.NewClient(&redis.Options{
Addr: *redisURL,
Password: *redisPWD,
DB: *redisDB,
})
rep = repetition.RepetitionJudgement{}
err := rep.InitializeVisited(c, "repetition")
if err != nil {
log.Fatal("redis error, ", err)
}
urlstr = urlstore.URLCrawlerStore{}
_, err = urlstr.InitialURLsStore(c, "colNeedCrawl", "colNeedCommit", "colNeedCrawl", "colNeedCommit")
visited, _ := rep.CheckIfVisited("http://www.dianping.com/")
if !visited {
rep.VisitedNewNode("http://www.dianping.com/")
urlstr.UploadURL("http://www.dianping.com/")
}
if err != nil {
log.Fatal("urlstore initialzation error, ", err)
}
// db initilization
dbSession, err := storage.Link2Db(*databaseURL)
defer dbSession.Close()
if err != nil {
log.Fatal("mongodb error, ", err)
}
collection = storage.Link2Collection(dbSession, *databaseName, *databaseUser, *databasePwd, *collectionName, *databaseAuth)
go distributeURL(*threadNum, urlstr)
// url initilziation
for i := 0; i < *threadNum; i++ {
releaseSlot <- 1
}
rootURL := GetOneURL()
// Spider input:
// PageProcesser ;
// Task name used in Pipeline for record;
spider.NewSpider(NewMyPageProcesser(), "TaskName").
AddUrl(rootURL, "html"). // Start url, html is the responce type ("html" or "json" or "jsonp" or "text")
AddPipeline(pipeline.NewPipelineConsole()). // Print result on screen
SetThreadnum((uint)(*threadNum)). // Crawl request by three Coroutines
Run()
}
func main() {
// spider input:
// PageProcesser ;
// config path(default: WD/etc/main.conf);
// task name used in Pipeline for record;
spider.NewSpider(NewMyPageProcesser(), "", "TaskName").
AddUrl("https://github.com/hu17889?tab=repositories", "html"). // start url, html is the responce type ("html" or "json")
AddPipeline(pipeline.NewPipelineConsole()). // print result on screen
SetThreadnum(3). // crawl request by three Coroutines
Run()
}
func main() {
// Spider input:
// PageProcesser ;
// Task name used in Pipeline for record;
req_url := "http://weixin.sogou.com/weixin?query=%E4%BA%91%E6%B5%AE&type=1&page=1&ie=utf8"
spider.NewSpider(NewMyPageProcesser(), "TaskName").
AddUrlWithHeaderFile(req_url, "html", "weixin.sogou.com.json"). // Start url, html is the responce type ("html" or "json" or "jsonp" or "text")
AddPipeline(pipeline.NewPipelineConsole()). // Print result on screen
SetThreadnum(3). // Crawl request by three Coroutines
Run()
}
func main() {
// spider input:
// PageProcesser ;
// task name used in Pipeline for record;
spider.NewSpider(NewMyPageProcesser(), "TaskName").
AddUrls(getUrls(), "html"). // start url, html is the responce type ("html" or "json")
AddPipeline(pipeline.NewPipelineConsole()). // print result on screen
SetThreadnum(1000). // crawl request by three Coroutines
CloseStrace().
OpenFileLog("/Users/tywei/workspace/devLanguage/go/crawl/logs").
Run()
}
func main() {
// spider input:
// PageProcesser ;
// task name used in Pipeline for record;
spider.NewSpider(NewMyPageProcesser(), "sina_stock_news").
AddUrl("http://live.sina.com.cn/zt/api/l/get/finance/globalnews1/index.htm?format=json&id=63621&pagesize=10&dire=f", "json"). // start url, html is the responce type ("html" or "json" or "jsonp" or "text")
AddPipeline(pipeline.NewPipelineConsole()). // Print result to std output
AddPipeline(pipeline.NewPipelineFile("/tmp/sinafile")). // Print result in file
OpenFileLog("/tmp"). // Error info or other useful info in spider will be logged in file of defalt path like "WD/log/log.2014-9-1".
SetSleepTime("rand", 1000, 3000). // Sleep time between 1s and 3s.
Run()
//AddPipeline(pipeline.NewPipelineFile("/tmp/tmpfile")). // print result in file
}
func main() {
req := request.NewRequest(wkSohuUrl, "html", "index", "GET", "", nil, nil, nil, nil)
sohuSpider := spider.NewSpider(NewMyPageProcesser(), "Sohu").
AddRequest(req).
SetSleepTime("rand", 500, 1000).
SetThreadnum(2)
for i := 1; i < maxWKSouhuLayer; i++ {
url := fmt.Sprintf("http://yule.sohu.com/gossip/index_%d.shtml", 5301-i) // magic num
req := request.NewRequest(url, "html", "index", "GET", "", nil, nil, nil, nil)
sohuSpider.AddRequest(req)
}
sohuSpider.Run()
}
func main() {
// spider input:
// PageProcesser ;
// task name used in Pipeline for record;
sp := spider.NewSpider(NewMyPageProcesser(), "TaskName")
// GetWithParams Params:
// 1. Url.
// 2. Responce type is "html" or "json" or "jsonp" or "text".
// 3. The urltag is name for marking url and distinguish different urls in PageProcesser and Pipeline.
// 4. The method is POST or GET.
// 5. The postdata is body string sent to sever.
// 6. The header is header for http request.
// 7. Cookies
req := request.NewRequest("http://baike.baidu.com/view/1628025.htm?fromtitle=http&fromid=243074&type=syn", "html", "", "GET", "", nil, nil, nil, nil)
pageItems := sp.GetByRequest(req)
//pageItems := sp.Get("http://baike.baidu.com/view/1628025.htm?fromtitle=http&fromid=243074&type=syn", "html")
url := pageItems.GetRequest().GetUrl()
println("-----------------------------------spider.Get---------------------------------")
println("url\t:\t" + url)
for name, value := range pageItems.GetAll() {
println(name + "\t:\t" + value)
}
println("\n--------------------------------spider.GetAll---------------------------------")
urls := []string{
"http://baike.baidu.com/view/1628025.htm?fromtitle=http&fromid=243074&type=syn",
"http://baike.baidu.com/view/383720.htm?fromtitle=html&fromid=97049&type=syn",
}
var reqs []*request.Request
for _, url := range urls {
req := request.NewRequest(url, "html", "", "GET", "", nil, nil, nil, nil)
reqs = append(reqs, req)
}
pageItemsArr := sp.SetThreadnum(2).GetAllByRequest(reqs)
//pageItemsArr := sp.SetThreadnum(2).GetAll(urls, "html")
for _, item := range pageItemsArr {
url = item.GetRequest().GetUrl()
println("url\t:\t" + url)
fmt.Printf("item\t:\t%s\n", item.GetAll())
}
}
func main() {
pageProcess := NewMyPageProcesser()
pageProcess.Init()
diandianSpider := spider.NewSpider(pageProcess, "TaskName").
AddUrl("http://shinichr.diandian.com/", "html"). // Start url, html is the responce type ("html" or "json" or "jsonp" or "text")
AddPipeline(pipeline.NewPipelineConsole()). // Print result on screen
AddPipeline(pipeline.NewPipelineFile("/home/shinichr/spider.tmp")).
SetThreadnum(10000) // Crawl request by three Coroutines
for i := 2; i < 10; i++ {
url := fmt.Sprintf("http://shinichr.diandian.com/page/%d", i)
diandianSpider.AddUrl(url, "html")
}
diandianSpider.Run()
for url, _ := range pageProcess.visit_url {
fmt.Println("spider:", url)
}
}
/*
* Main
*/
func main() {
var header http.Header = make(http.Header)
header.Add("User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.115 Safari/537.36")
for i := 0; i < 20; i++ {
url := ""
if i == 0 {
url = "http://www.lizhi.fm/1560327/"
} else {
url = fmt.Sprintf("http://www.lizhi.fm/1560327/p/%d.html", i+1)
}
fmt.Printf("Page:%d, Url: %s\n", i, url)
req := request.NewRequest(url, "html", "index", "GET", "", header, nil, nil, nil)
siteSpider := spider.NewSpider(NewSitePageProcesser("Tonghuashu"), "Tonghuashu").
AddRequest(req).
SetSleepTime("rand", 1000, 2000).
SetThreadnum(2)
siteSpider.Run()
}
}
