colly文档

2019-08-13 本文已影响0人 ArtioL

c.OnRequest(func(r *colly.Request) {
    fmt.Println("Visiting", r.URL)
})

c.OnError(func(_ *colly.Response, err error) {
    log.Println("Something went wrong:", err)
})

c.OnResponse(func(r *colly.Response) {
    fmt.Println("Visited", r.Request.URL)
})

c.OnHTML("a[href]", func(e *colly.HTMLElement) {
    e.Request.Visit(e.Attr("href"))
})

c.OnHTML("tr td:nth-of-type(1)", func(e *colly.HTMLElement) {
    fmt.Println("First column of a table row:", e.Text)
})

c.OnXML("//h1", func(e *colly.XMLElement) {
    fmt.Println(e.Text)
})

c.OnScraped(func(r *colly.Response) {
    fmt.Println("Finished", r.Request.URL)
})

OnRequest
Called before a request

c.OnRequest(func(r *colly.Request) {
        fmt.Println("Visiting", r.URL.String())
    })

OnError
Called if error occured during the request

c.OnError(func(r *colly.Response, err error) {
        fmt.Println("Request URL:", r.Request.URL, "failed with response:", r, "\nError:", err)
    })

OnResponse
Called after response received

c.OnResponse(func(r *colly.Response) {
        log.Println("response received", r.StatusCode)
    })

OnHTML
Called right after OnResponse if the received content is HTML
OnXML
Called right after OnHTML if the received content is HTML or XML
OnScraped
Called after OnXML callbacks

1.Collector参数

设置User-Agent
colly.NewCollector( colly.UserAgent("xy"))
c2 := colly.NewCollector();c2.UserAgent="xy"
动态设置User-Agent
c := colly.NewCollector();c.OnRequest(func(r *colly.Request){r.Headers.Set("User-Agent", RandomString()) })

设置url不去重
colly.AllowURLRevisit()
c2 := colly.NewCollector();c2.AllowURLRevisit=true
收集器配置项
ALLOWED_DOMAINS (comma separated list of domains) // 允许的域名

c := colly.NewCollector(
        // Visit only domains: hackerspaces.org, wiki.hackerspaces.org
        colly.AllowedDomains("hackerspaces.org", "wiki.hackerspaces.org"),
    )

CACHE_DIR (string) // 缓存dir

colly.NewCollector(
    colly.CacheDir("./cache"))

DETECT_CHARSET (y/n)
DISABLE_COOKIES (y/n)
DISALLOWED_DOMAINS (comma separated list of domains)
IGNORE_ROBOTSTXT (y/n)
MAX_BODY_SIZE (int)
MAX_DEPTH (int - 0 means infinite)

c := colly.NewCollector(
        // MaxDepth is 1, so only the links on the scraped page
        // is visited, and no further links are followed
        colly.MaxDepth(1),
    )

PARSE_HTTP_ERROR_RESPONSE (y/n)
USER_AGENT (string)


// HTTP设置
c := colly.NewCollector()
c.WithTransport(&http.Transport{
    Proxy: http.ProxyFromEnvironment,
    DialContext: (&net.Dialer{
        Timeout:   30 * time.Second,
        KeepAlive: 30 * time.Second,
        DualStack: true,
    }).DialContext,
    MaxIdleConns:          100,
    IdleConnTimeout:       90 * time.Second,
    TLSHandshakeTimeout:   10 * time.Second,
    ExpectContinueTimeout: 1 * time.Second,
}

开启debug

import (
    "github.com/gocolly/colly"
    "github.com/gocolly/colly/debug"
)

func main() {
    c := colly.NewCollector(colly.Debugger(&debug.LogDebugger{}))
    // [..]
}

设置代理

package main

import (
    "github.com/gocolly/colly"
    "github.com/gocolly/colly/proxy"
)

func main() {
    c := colly.NewCollector()

    if p, err := proxy.RoundRobinProxySwitcher(
        "socks5://127.0.0.1:1337",
        "socks5://127.0.0.1:1338",
        "http://127.0.0.1:8080",
    ); err == nil {
        c.SetProxyFunc(p)
    }
    // ...
}

自定义代理切换器

var proxies []*url.URL = []*url.URL{
    &url.URL{Host: "127.0.0.1:8080"},
    &url.URL{Host: "127.0.0.1:8081"},
}

func randomProxySwitcher(_ *http.Request) (*url.URL, error) {
    return proxies[random.Intn(len(proxies))], nil
}

// ...
c.SetProxyFunc(randomProxySwitcher)```

代理完整DEMO

package main

import (
    "bytes"
    "log"

    "github.com/gocolly/colly"
    "github.com/gocolly/colly/proxy"
)

func main() {
    // Instantiate default collector
    c := colly.NewCollector(colly.AllowURLRevisit())

    // Rotate two socks5 proxies
    rp, err := proxy.RoundRobinProxySwitcher("socks5://127.0.0.1:1337", "socks5://127.0.0.1:1338")
    if err != nil {
        log.Fatal(err)
    }
    c.SetProxyFunc(rp)

    // Print the response
    c.OnResponse(func(r *colly.Response) {
        log.Printf("%s\n", bytes.Replace(r.Body, []byte("\n"), nil, -1))
    })

    // Fetch httpbin.org/ip five times
    for i := 0; i < 5; i++ {
        c.Visit("https://httpbin.org/ip")
    }
}

使用Clone方法复制相似配置的收集器

c := colly.NewCollector(
    colly.UserAgent("myUserAgent"),
    colly.AllowedDomains("foo.com", "bar.com"),
)
// Custom User-Agent and allowed domains are cloned to c2

c2 := c.Clone()

使用context传递上下文

c.OnResponse(func(r *colly.Response) {
    r.Ctx.Put(r.Headers.Get("Custom-Header"))
    c2.Request("GET", "https://foo.com/", nil, r.Ctx, nil)
})

特别注意设置代理与设置缓存文件目前是冲突的.
禁止 keep-alive

c := colly.NewCollector()
c.WithTransport(&http.Transport{
    DisableKeepAlives: true,
})

异步收集

c := colly.NewCollector(
        colly.Async(true),
    )

Collector.Async = true
// 记住使用c.Wait()

异步收集完整Demo

import (
    "fmt"

    "github.com/gocolly/colly"
)

func main() {
    // Instantiate default collector
    c := colly.NewCollector(
        // MaxDepth is 2, so only the links on the scraped page
        // and links on those pages are visited
        colly.MaxDepth(2),
        colly.Async(true),
    )

    // Limit the maximum parallelism to 2
    // This is necessary if the goroutines are dynamically
    // created to control the limit of simultaneous requests.
    //
    // Parallelism can be controlled also by spawning fixed
    // number of go routines.
    c.Limit(&colly.LimitRule{DomainGlob: "*", Parallelism: 2})

    // On every a element which has href attribute call callback
    c.OnHTML("a[href]", func(e *colly.HTMLElement) {
        link := e.Attr("href")
        // Print link
        fmt.Println(link)
        // Visit link found on page on a new thread
        e.Request.Visit(link)
    })

    // Start scraping on https://en.wikipedia.org
    c.Visit("https://en.wikipedia.org/")
    // Wait until threads are finished
    c.Wait()
}

colly自带的插件

import (
    "log"

    "github.com/gocolly/colly"
    "github.com/gocolly/colly/extensions"
)

func main() {
    c := colly.NewCollector()
    visited := false

    extensions.RandomUserAgent(c) // 随机UA
    extensions.Referrer(c) // referer自动填写

    c.OnResponse(func(r *colly.Response) {
        log.Println(string(r.Body))
        if !visited {
            visited = true
            r.Request.Visit("/get?q=2")
        }
    })

    c.Visit("http://httpbin.org/get")
}

目前支持的插件

func RandomUserAgent

func Referer

func URLLengthFilter

Post表单

func generateFormData() map[string][]byte {
    f, _ := os.Open("gocolly.jpg")
    defer f.Close()

    imgData, _ := ioutil.ReadAll(f)

    return map[string][]byte{
        "firstname": []byte("one"),
        "lastname":  []byte("two"),
        "email":     []byte("onetwo@example.com"),
        "file":      imgData,
    }
}
c.PostMultipart("http://localhost:8080/", generateFormData())

PostJson

c.OnRequest(func(r *colly.Request) {
        r.Headers.Set("Content-Type", "application/json;charset=UTF-8")
    })
c.PostRaw(fmt.Sprintf(amac_list_post_url, page), []byte("{}"))

队列Queue

package main

import (
    "fmt"

    "github.com/gocolly/colly"
    "github.com/gocolly/colly/queue"
)

func main() {
    url := "https://httpbin.org/delay/1"

    // Instantiate default collector
    c := colly.NewCollector()

    // create a request queue with 2 consumer threads
    q, _ := queue.New(
        2, // Number of consumer threads
        &queue.InMemoryQueueStorage{MaxSize: 10000}, // Use default queue storage
    )

    c.OnRequest(func(r *colly.Request) {
        fmt.Println("visiting", r.URL)
    })

    for i := 0; i < 5; i++ {
        // Add URLs to the queue
        q.AddURL(fmt.Sprintf("%s?n=%d", url, i))
    }
    // Consume URLs
    q.Run(c)

}

随机延迟

package main

import (
    "fmt"
    "time"

    "github.com/gocolly/colly"
    "github.com/gocolly/colly/debug"
)

func main() {
    url := "https://httpbin.org/delay/2"

    // Instantiate default collector
    c := colly.NewCollector(
        // Attach a debugger to the collector
        colly.Debugger(&debug.LogDebugger{}),
        colly.Async(true),
    )

    // Limit the number of threads started by colly to two
    // when visiting links which domains' matches "*httpbin.*" glob
    c.Limit(&colly.LimitRule{
        DomainGlob:  "*httpbin.*",
        Parallelism: 2,
        RandomDelay: 5 * time.Second,
    })

    // Start scraping in four threads on https://httpbin.org/delay/2
    for i := 0; i < 4; i++ {
        c.Visit(fmt.Sprintf("%s?n=%d", url, i))
    }
    // Start scraping on https://httpbin.org/delay/2
    c.Visit(url)
    // Wait until threads are finished
    c.Wait()
}

并发限制

package main

import (
    "fmt"

    "github.com/gocolly/colly"
    "github.com/gocolly/colly/debug"
)

func main() {
    url := "https://httpbin.org/delay/2"

    // Instantiate default collector
    c := colly.NewCollector(
        // Turn on asynchronous requests
        colly.Async(true),
        // Attach a debugger to the collector
        colly.Debugger(&debug.LogDebugger{}),
    )

    // Limit the number of threads started by colly to two
    // when visiting links which domains' matches "*httpbin.*" glob
    c.Limit(&colly.LimitRule{
        DomainGlob:  "*httpbin.*",
        Parallelism: 2,
        //Delay:      5 * time.Second,
    })

    // Start scraping in five threads on https://httpbin.org/delay/2
    for i := 0; i < 5; i++ {
        c.Visit(fmt.Sprintf("%s?n=%d", url, i))
    }
    // Wait until threads are finished
    c.Wait()
}

Redis做队列

package main

import (
    "log"

    "github.com/gocolly/colly"
    "github.com/gocolly/colly/queue"
    "github.com/gocolly/redisstorage"
)

func main() {
    urls := []string{
        "http://httpbin.org/",
        "http://httpbin.org/ip",
        "http://httpbin.org/cookies/set?a=b&c=d",
        "http://httpbin.org/cookies",
    }

    c := colly.NewCollector()

    // create the redis storage
    storage := &redisstorage.Storage{
        Address:  "127.0.0.1:6379",
        Password: "",
        DB:       0,
        Prefix:   "httpbin_test",
    }

    // add storage to the collector
    err := c.SetStorage(storage)
    if err != nil {
        panic(err)
    }

    // delete previous data from storage
    if err := storage.Clear(); err != nil {
        log.Fatal(err)
    }

    // close redis client
    defer storage.Client.Close()

    // create a new request queue with redis storage backend
    q, _ := queue.New(2, storage)

    c.OnResponse(func(r *colly.Response) {
        log.Println("Cookies:", c.Cookies(r.Request.URL.String()))
    })

    // add URLs to the queue
    for _, u := range urls {
        q.AddURL(u)
    }
    // consume requests
    q.Run(c)
}

上下文管理

package main

import (
    "fmt"

    "github.com/gocolly/colly"
)

func main() {
    // Instantiate default collector
    c := colly.NewCollector()

    // Before making a request put the URL with
    // the key of "url" into the context of the request
    c.OnRequest(func(r *colly.Request) {
        r.Ctx.Put("url", r.URL.String())
    })

    // After making a request get "url" from
    // the context of the request
    c.OnResponse(func(r *colly.Response) {
        fmt.Println(r.Ctx.Get("url"))
    })

    // Start scraping on https://en.wikipedia.org
    c.Visit("https://en.wikipedia.org/")
}

爬虫服务器

package main

import (
    "encoding/json"
    "log"
    "net/http"

    "github.com/gocolly/colly"
)

type pageInfo struct {
    StatusCode int
    Links      map[string]int
}

func handler(w http.ResponseWriter, r *http.Request) {
    URL := r.URL.Query().Get("url")
    if URL == "" {
        log.Println("missing URL argument")
        return
    }
    log.Println("visiting", URL)

    c := colly.NewCollector()

    p := &pageInfo{Links: make(map[string]int)}

    // count links
    c.OnHTML("a[href]", func(e *colly.HTMLElement) {
        link := e.Request.AbsoluteURL(e.Attr("href"))
        if link != "" {
            p.Links[link]++
        }
    })

    // extract status code
    c.OnResponse(func(r *colly.Response) {
        log.Println("response received", r.StatusCode)
        p.StatusCode = r.StatusCode
    })
    c.OnError(func(r *colly.Response, err error) {
        log.Println("error:", r.StatusCode, err)
        p.StatusCode = r.StatusCode
    })

    c.Visit(URL)

    // dump results
    b, err := json.Marshal(p)
    if err != nil {
        log.Println("failed to serialize response:", err)
        return
    }
    w.Header().Add("Content-Type", "application/json")
    w.Write(b)
}

func main() {
    // example usage: curl -s 'http://127.0.0.1:7171/?url=http://go-colly.org/'
    addr := ":7171"

    http.HandleFunc("/", handler)

    log.Println("listening on", addr)
    log.Fatal(http.ListenAndServe(addr, nil))
}

URL正则过滤

package main

import (
    "fmt"
    "regexp"

    "github.com/gocolly/colly"
)

func main() {
    // Instantiate default collector
    c := colly.NewCollector(
        // Visit only root url and urls which start with "e" or "h" on httpbin.org
        colly.URLFilters(
            regexp.MustCompile("http://httpbin\\.org/(|e.+)$"),
            regexp.MustCompile("http://httpbin\\.org/h.+"),
        ),
    )

    // On every a element which has href attribute call callback
    c.OnHTML("a[href]", func(e *colly.HTMLElement) {
        link := e.Attr("href")
        // Print link
        fmt.Printf("Link found: %q -> %s\n", e.Text, link)
        // Visit link found on page
        // Only those links are visited which are matched by  any of the URLFilter regexps
        c.Visit(e.Request.AbsoluteURL(link))
    })

    // Before making a request print "Visiting ..."
    c.OnRequest(func(r *colly.Request) {
        fmt.Println("Visiting", r.URL.String())
    })

    // Start scraping on http://httpbin.org
    c.Visit("http://httpbin.org/")
}

colly文档

目前支持的插件

func RandomUserAgent

func Referer

func URLLengthFilter

猜你喜欢

热点阅读