update

crawler/collector.go

@@ -0,0 +1,28 @@
+// Package crawler ...
+//
+// Description : crawler ...
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 2021-12-20 4:46 PM
+package crawler
+
+import "github.com/gocolly/colly"
+
+// StartHTMLCollector 获取页面爬虫实例
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 4:47 PM 2021/12/20
+func StartHTMLCollector(domainList []string, visitURL string, requestHandler IRequestHandler) error {
+	c := colly.NewCollector()
+	// 设置域名白名单, 不设置, 默认所有均可访问
+	c.AllowedDomains = domainList
+	c.OnRequest(requestHandler.OnRequest())
+	c.OnError(requestHandler.OnError())
+	// html处理
+	c.OnHTML(requestHandler.OnHTML())
+	c.OnResponse(requestHandler.OnResponse())
+	c.OnScraped(requestHandler.OnScraped())
+	return c.Visit(visitURL)
+}

crawler/collector_test.go

@@ -0,0 +1,64 @@
+// Package crawler ...
+//
+// Description : crawler ...
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 2021-12-20 5:58 PM
+package crawler
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/gocolly/colly"
+)
+
+// TestStartCollector ...
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 5:59 PM 2021/12/20
+func TestStartCollector(t *testing.T) {
+	if err := StartHTMLCollector([]string{}, "https://go.zhangdeman.cn", &testHandler{}); nil != err {
+		panic("出现异常 : " + err.Error())
+	}
+}
+
+type testHandler struct {
+}
+
+func (t *testHandler) OnRequest() colly.RequestCallback {
+	return func(r *colly.Request) {
+		fmt.Println("开始请求 : ", r.URL)
+	}
+}
+
+func (t *testHandler) OnError() colly.ErrorCallback {
+	return func(response *colly.Response, err error) {
+		fmt.Println("请求异常 : " + err.Error())
+	}
+}
+
+func (t *testHandler) OnResponse() colly.ResponseCallback {
+	return func(response *colly.Response) {
+		fmt.Println("响应数据 : ", response.StatusCode)
+	}
+}
+
+func (t *testHandler) OnHTML() (string, colly.HTMLCallback) {
+	return "a[href]", func(e *colly.HTMLElement) {
+		link := e.Attr("href")
+
+		// Print link
+
+		fmt.Printf("Link found: %q -> %s\n", e.Text, link)
+
+	}
+}
+
+func (t *testHandler) OnScraped() colly.ScrapedCallback {
+	return func(response *colly.Response) {
+
+	}
+}

crawler/define.go

@@ -0,0 +1,8 @@
+// Package crawler ...
+//
+// Description : crawler ...
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 2021-12-20 4:41 PM
+package crawler

crawler/i_handler.go

@@ -0,0 +1,30 @@
+// Package crawler ...
+//
+// Description : crawler ...
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 2021-12-20 4:50 PM
+package crawler
+
+import (
+	"github.com/gocolly/colly"
+)
+
+// IRequestHandler 请求结果的处理
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 4:50 PM 2021/12/20
+type IRequestHandler interface {
+	// OnRequest 在发起请求前被调用
+	OnRequest() colly.RequestCallback
+	// OnError 请求过程中如果发生错误被调用
+	OnError() colly.ErrorCallback
+	// OnResponse 收到回复后被调用
+	OnResponse() colly.ResponseCallback
+	// OnHTML 在OnResponse之后被调用，如果收到的内容是HTML
+	OnHTML() (string, colly.HTMLCallback)
+	// OnScraped 在OnHTML之后被调用
+	OnScraped() colly.ScrapedCallback
+}

demo/context.go

@@ -0,0 +1,586 @@
+// Package demo ...
+//
+// Description : demo ...
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 2021-12-02 12:43 下午
+package demo
+
+import (
+	"errors"
+	"reflect"
+	"sync"
+	"sync/atomic"
+	"time"
+)
+
+// Copyright 2014 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// Package context defines the Context type, which carries deadlines,
+// cancellation signals, and other request-scoped values across API boundaries
+// and between processes.
+//
+// Incoming requests to a server should create a Context, and outgoing
+// calls to servers should accept a Context. The chain of function
+// calls between them must propagate the Context, optionally replacing
+// it with a derived Context created using WithCancel, WithDeadline,
+// WithTimeout, or WithValue. When a Context is canceled, all
+// Contexts derived from it are also canceled.
+//
+// The WithCancel, WithDeadline, and WithTimeout functions take a
+// Context (the parent) and return a derived Context (the child) and a
+// CancelFunc. Calling the CancelFunc cancels the child and its
+// children, removes the parent's reference to the child, and stops
+// any associated timers. Failing to call the CancelFunc leaks the
+// child and its children until the parent is canceled or the timer
+// fires. The go vet tool checks that CancelFuncs are used on all
+// control-flow paths.
+//
+// Programs that use Contexts should follow these rules to keep interfaces
+// consistent across packages and enable static analysis tools to check context
+// propagation:
+//
+// Do not store Contexts inside a struct type; instead, pass a Context
+// explicitly to each function that needs it. The Context should be the first
+// parameter, typically named ctx:
+//
+// 	func DoSomething(ctx context.Context, arg Arg) error {
+// 		// ... use ctx ...
+// 	}
+//
+// Do not pass a nil Context, even if a function permits it. Pass context.TODO
+// if you are unsure about which Context to use.
+//
+// Use context Values only for request-scoped data that transits processes and
+// APIs, not for passing optional parameters to functions.
+//
+// The same Context may be passed to functions running in different goroutines;
+// Contexts are safe for simultaneous use by multiple goroutines.
+//
+// See https://blog.golang.org/context for example code for a server that uses
+// Contexts.
+
+// A Context carries a deadline, a cancellation signal, and other values across
+// API boundaries.
+//
+// Context's methods may be called by multiple goroutines simultaneously.
+type Context interface {
+	// Deadline returns the time when work done on behalf of this context
+	// should be canceled. Deadline returns ok==false when no deadline is
+	// set. Successive calls to Deadline return the same results.
+	Deadline() (deadline time.Time, ok bool)
+
+	// Done returns a channel that's closed when work done on behalf of this
+	// context should be canceled. Done may return nil if this context can
+	// never be canceled. Successive calls to Done return the same value.
+	// The close of the Done channel may happen asynchronously,
+	// after the cancel function returns.
+	//
+	// WithCancel arranges for Done to be closed when cancel is called;
+	// WithDeadline arranges for Done to be closed when the deadline
+	// expires; WithTimeout arranges for Done to be closed when the timeout
+	// elapses.
+	//
+	// Done is provided for use in select statements:
+	//
+	//  // Stream generates values with DoSomething and sends them to out
+	//  // until DoSomething returns an error or ctx.Done is closed.
+	//  func Stream(ctx context.Context, out chan<- Value) error {
+	//  	for {
+	//  		v, err := DoSomething(ctx)
+	//  		if err != nil {
+	//  			return err
+	//  		}
+	//  		select {
+	//  		case <-ctx.Done():
+	//  			return ctx.Err()
+	//  		case out <- v:
+	//  		}
+	//  	}
+	//  }
+	//
+	// See https://blog.golang.org/pipelines for more examples of how to use
+	// a Done channel for cancellation.
+	Done() <-chan struct{}
+
+	// If Done is not yet closed, Err returns nil.
+	// If Done is closed, Err returns a non-nil error explaining why:
+	// Canceled if the context was canceled
+	// or DeadlineExceeded if the context's deadline passed.
+	// After Err returns a non-nil error, successive calls to Err return the same error.
+	Err() error
+
+	// Value returns the value associated with this context for key, or nil
+	// if no value is associated with key. Successive calls to Value with
+	// the same key returns the same result.
+	//
+	// Use context values only for request-scoped data that transits
+	// processes and API boundaries, not for passing optional parameters to
+	// functions.
+	//
+	// A key identifies a specific value in a Context. Functions that wish
+	// to store values in Context typically allocate a key in a global
+	// variable then use that key as the argument to context.WithValue and
+	// Context.Value. A key can be any type that supports equality;
+	// packages should define keys as an unexported type to avoid
+	// collisions.
+	//
+	// Packages that define a Context key should provide type-safe accessors
+	// for the values stored using that key:
+	//
+	// 	// Package user defines a User type that's stored in Contexts.
+	// 	package user
+	//
+	// 	import "context"
+	//
+	// 	// User is the type of value stored in the Contexts.
+	// 	type User struct {...}
+	//
+	// 	// key is an unexported type for keys defined in this package.
+	// 	// This prevents collisions with keys defined in other packages.
+	// 	type key int
+	//
+	// 	// userKey is the key for user.User values in Contexts. It is
+	// 	// unexported; clients use user.NewContext and user.FromContext
+	// 	// instead of using this key directly.
+	// 	var userKey key
+	//
+	// 	// NewContext returns a new Context that carries value u.
+	// 	func NewContext(ctx context.Context, u *User) context.Context {
+	// 		return context.WithValue(ctx, userKey, u)
+	// 	}
+	//
+	// 	// FromContext returns the User value stored in ctx, if any.
+	// 	func FromContext(ctx context.Context) (*User, bool) {
+	// 		u, ok := ctx.Value(userKey).(*User)
+	// 		return u, ok
+	// 	}
+	Value(key interface{}) interface{}
+}
+
+// Canceled is the error returned by Context.Err when the context is canceled.
+var Canceled = errors.New("context canceled")
+
+// DeadlineExceeded is the error returned by Context.Err when the context's
+// deadline passes.
+var DeadlineExceeded error = deadlineExceededError{}
+
+type deadlineExceededError struct{}
+
+func (deadlineExceededError) Error() string   { return "context deadline exceeded" }
+func (deadlineExceededError) Timeout() bool   { return true }
+func (deadlineExceededError) Temporary() bool { return true }
+
+// An emptyCtx is never canceled, has no values, and has no deadline. It is not
+// struct{}, since vars of this type must have distinct addresses.
+type emptyCtx int
+
+func (*emptyCtx) Deadline() (deadline time.Time, ok bool) {
+	return
+}
+
+func (*emptyCtx) Done() <-chan struct{} {
+	return nil
+}
+
+func (*emptyCtx) Err() error {
+	return nil
+}
+
+func (*emptyCtx) Value(key interface{}) interface{} {
+	return nil
+}
+
+func (e *emptyCtx) String() string {
+	switch e {
+	case background:
+		return "context.Background"
+	case todo:
+		return "context.TODO"
+	}
+	return "unknown empty Context"
+}
+
+var (
+	background = new(emptyCtx)
+	todo       = new(emptyCtx)
+)
+
+// Background returns a non-nil, empty Context. It is never canceled, has no
+// values, and has no deadline. It is typically used by the main function,
+// initialization, and tests, and as the top-level Context for incoming
+// requests.
+func Background() Context {
+	return background
+}
+
+// TODO returns a non-nil, empty Context. Code should use context.TODO when
+// it's unclear which Context to use or it is not yet available (because the
+// surrounding function has not yet been extended to accept a Context
+// parameter).
+func TODO() Context {
+	return todo
+}
+
+// A CancelFunc tells an operation to abandon its work.
+// A CancelFunc does not wait for the work to stop.
+// A CancelFunc may be called by multiple goroutines simultaneously.
+// After the first call, subsequent calls to a CancelFunc do nothing.
+type CancelFunc func()
+
+// WithCancel returns a copy of parent with a new Done channel. The returned
+// context's Done channel is closed when the returned cancel function is called
+// or when the parent context's Done channel is closed, whichever happens first.
+//
+// Canceling this context releases resources associated with it, so code should
+// call cancel as soon as the operations running in this Context complete.
+func WithCancel(parent Context) (ctx Context, cancel CancelFunc) {
+	if parent == nil {
+		panic("cannot create context from nil parent")
+	}
+	c := newCancelCtx(parent)
+	propagateCancel(parent, &c)
+	return &c, func() { c.cancel(true, Canceled) }
+}
+
+// newCancelCtx returns an initialized cancelCtx.
+func newCancelCtx(parent Context) cancelCtx {
+	return cancelCtx{Context: parent}
+}
+
+// goroutines counts the number of goroutines ever created; for testing.
+var goroutines int32
+
+// propagateCancel arranges for child to be canceled when parent is.
+func propagateCancel(parent Context, child canceler) {
+	done := parent.Done()
+	if done == nil {
+		return // parent is never canceled
+	}
+
+	select {
+	case <-done:
+		// parent is already canceled
+		child.cancel(false, parent.Err())
+		return
+	default:
+	}
+
+	if p, ok := parentCancelCtx(parent); ok {
+		p.mu.Lock()
+		if p.err != nil {
+			// parent has already been canceled
+			child.cancel(false, p.err)
+		} else {
+			if p.children == nil {
+				p.children = make(map[canceler]struct{})
+			}
+			p.children[child] = struct{}{}
+		}
+		p.mu.Unlock()
+	} else {
+		atomic.AddInt32(&goroutines, +1)
+		go func() {
+			select {
+			case <-parent.Done():
+				child.cancel(false, parent.Err())
+			case <-child.Done():
+			}
+		}()
+	}
+}
+
+// &cancelCtxKey is the key that a cancelCtx returns itself for.
+var cancelCtxKey int
+
+// parentCancelCtx returns the underlying *cancelCtx for parent.
+// It does this by looking up parent.Value(&cancelCtxKey) to find
+// the innermost enclosing *cancelCtx and then checking whether
+// parent.Done() matches that *cancelCtx. (If not, the *cancelCtx
+// has been wrapped in a custom implementation providing a
+// different done channel, in which case we should not bypass it.)
+func parentCancelCtx(parent Context) (*cancelCtx, bool) {
+	done := parent.Done()
+	if done == closedchan || done == nil {
+		return nil, false
+	}
+	p, ok := parent.Value(&cancelCtxKey).(*cancelCtx)
+	if !ok {
+		return nil, false
+	}
+	pdone, _ := p.done.Load().(chan struct{})
+	if pdone != done {
+		return nil, false
+	}
+	return p, true
+}
+
+// removeChild removes a context from its parent.
+func removeChild(parent Context, child canceler) {
+	p, ok := parentCancelCtx(parent)
+	if !ok {
+		return
+	}
+	p.mu.Lock()
+	if p.children != nil {
+		delete(p.children, child)
+	}
+	p.mu.Unlock()
+}
+
+// A canceler is a context type that can be canceled directly. The
+// implementations are *cancelCtx and *timerCtx.
+type canceler interface {
+	cancel(removeFromParent bool, err error)
+	Done() <-chan struct{}
+}
+
+// closedchan is a reusable closed channel.
+var closedchan = make(chan struct{})
+
+func init() {
+	close(closedchan)
+}
+
+// A cancelCtx can be canceled. When canceled, it also cancels any children
+// that implement canceler.
+type cancelCtx struct {
+	Context
+
+	mu       sync.Mutex            // protects following fields
+	done     atomic.Value          // of chan struct{}, created lazily, closed by first cancel call
+	children map[canceler]struct{} // set to nil by the first cancel call
+	err      error                 // set to non-nil by the first cancel call
+}
+
+func (c *cancelCtx) Value(key interface{}) interface{} {
+	if key == &cancelCtxKey {
+		return c
+	}
+	return c.Context.Value(key)
+}
+
+func (c *cancelCtx) Done() <-chan struct{} {
+	d := c.done.Load()
+	if d != nil {
+		return d.(chan struct{})
+	}
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	d = c.done.Load()
+	if d == nil {
+		d = make(chan struct{})
+		c.done.Store(d)
+	}
+	return d.(chan struct{})
+}
+
+func (c *cancelCtx) Err() error {
+	c.mu.Lock()
+	err := c.err
+	c.mu.Unlock()
+	return err
+}
+
+type stringer interface {
+	String() string
+}
+
+func contextName(c Context) string {
+	if s, ok := c.(stringer); ok {
+		return s.String()
+	}
+	return reflect.TypeOf(c).String()
+}
+
+func (c *cancelCtx) String() string {
+	return contextName(c.Context) + ".WithCancel"
+}
+
+// cancel closes c.done, cancels each of c's children, and, if
+// removeFromParent is true, removes c from its parent's children.
+func (c *cancelCtx) cancel(removeFromParent bool, err error) {
+	if err == nil {
+		panic("context: internal error: missing cancel error")
+	}
+	c.mu.Lock()
+	if c.err != nil {
+		c.mu.Unlock()
+		return // already canceled
+	}
+	c.err = err
+	d, _ := c.done.Load().(chan struct{})
+	if d == nil {
+		c.done.Store(closedchan)
+	} else {
+		close(d)
+	}
+	for child := range c.children {
+		// NOTE: acquiring the child's lock while holding parent's lock.
+		child.cancel(false, err)
+	}
+	c.children = nil
+	c.mu.Unlock()
+
+	if removeFromParent {
+		removeChild(c.Context, c)
+	}
+}
+
+// WithDeadline returns a copy of the parent context with the deadline adjusted
+// to be no later than d. If the parent's deadline is already earlier than d,
+// WithDeadline(parent, d) is semantically equivalent to parent. The returned
+// context's Done channel is closed when the deadline expires, when the returned
+// cancel function is called, or when the parent context's Done channel is
+// closed, whichever happens first.
+//
+// Canceling this context releases resources associated with it, so code should
+// call cancel as soon as the operations running in this Context complete.
+func WithDeadline(parent Context, d time.Time) (Context, CancelFunc) {
+	if parent == nil {
+		panic("cannot create context from nil parent")
+	}
+	if cur, ok := parent.Deadline(); ok && cur.Before(d) {
+		// The current deadline is already sooner than the new one.
+		return WithCancel(parent)
+	}
+	c := &timerCtx{
+		cancelCtx: newCancelCtx(parent),
+		deadline:  d,
+	}
+	propagateCancel(parent, c)
+	dur := time.Until(d)
+	if dur <= 0 {
+		c.cancel(true, DeadlineExceeded) // deadline has already passed
+		return c, func() { c.cancel(false, Canceled) }
+	}
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	if c.err == nil {
+		c.timer = time.AfterFunc(dur, func() {
+			c.cancel(true, DeadlineExceeded)
+		})
+	}
+	return c, func() { c.cancel(true, Canceled) }
+}
+
+// A timerCtx carries a timer and a deadline. It embeds a cancelCtx to
+// implement Done and Err. It implements cancel by stopping its timer then
+// delegating to cancelCtx.cancel.
+type timerCtx struct {
+	cancelCtx
+	timer *time.Timer // Under cancelCtx.mu.
+
+	deadline time.Time
+}
+
+func (c *timerCtx) Deadline() (deadline time.Time, ok bool) {
+	return c.deadline, true
+}
+
+func (c *timerCtx) String() string {
+	return contextName(c.cancelCtx.Context) + ".WithDeadline(" +
+		c.deadline.String() + " [" +
+		time.Until(c.deadline).String() + "])"
+}
+
+func (c *timerCtx) cancel(removeFromParent bool, err error) {
+	c.cancelCtx.cancel(false, err)
+	if removeFromParent {
+		// Remove this timerCtx from its parent cancelCtx's children.
+		removeChild(c.cancelCtx.Context, c)
+	}
+	c.mu.Lock()
+	if c.timer != nil {
+		c.timer.Stop()
+		c.timer = nil
+	}
+	c.mu.Unlock()
+}
+
+// WithTimeout returns WithDeadline(parent, time.Now().Add(timeout)).
+//
+// Canceling this context releases resources associated with it, so code should
+// call cancel as soon as the operations running in this Context complete:
+//
+// 	func slowOperationWithTimeout(ctx context.Context) (Result, error) {
+// 		ctx, cancel := context.WithTimeout(ctx, 100*time.Millisecond)
+// 		defer cancel()  // releases resources if slowOperation completes before timeout elapses
+// 		return slowOperation(ctx)
+// 	}
+func WithTimeout(parent Context, timeout time.Duration) (Context, CancelFunc) {
+	return WithDeadline(parent, time.Now().Add(timeout))
+}
+
+// WithValue returns a copy of parent in which the value associated with key is
+// val.
+//
+// Use context Values only for request-scoped data that transits processes and
+// APIs, not for passing optional parameters to functions.
+//
+// The provided key must be comparable and should not be of type
+// string or any other built-in type to avoid collisions between
+// packages using context. Users of WithValue should define their own
+// types for keys. To avoid allocating when assigning to an
+// interface{}, context keys often have concrete type
+// struct{}. Alternatively, exported context key variables' static
+// type should be a pointer or interface.
+func WithValue(parent Context, key, val interface{}) Context {
+	if parent == nil {
+		panic("cannot create context from nil parent")
+	}
+	if key == nil {
+		panic("nil key")
+	}
+	if !reflect.TypeOf(key).Comparable() {
+		panic("key is not comparable")
+	}
+	return &valueCtx{parent, key, val}
+}
+
+// A valueCtx carries a key-value pair. It implements Value for that key and
+// delegates all other calls to the embedded Context.
+type valueCtx struct {
+	Context
+	key, val interface{}
+}
+
+// stringify tries a bit to stringify v, without using fmt, since we don't
+// want context depending on the unicode tables. This is only used by
+// *valueCtx.String().
+func stringify(v interface{}) string {
+	switch s := v.(type) {
+	case stringer:
+		return s.String()
+	case string:
+		return s
+	}
+	return "<not Stringer>"
+}
+
+func (c *valueCtx) String() string {
+	return contextName(c.Context) + ".WithValue(type " +
+		reflect.TypeOf(c.key).String() +
+		", val " + stringify(c.val) + ")"
+}
+
+func (c *valueCtx) Value(key interface{}) interface{} {
+	if c.key == key {
+		return c.val
+	}
+	return c.Context.Value(key)
+}
+
+// ======================== 以上为 context.go 源码
+
+// MyContext 自定义 context
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 12:45 下午 2021/12/2
+type MyContext struct {
+	Context
+}

demo/context_test.go

@@ -0,0 +1,42 @@
+// Package demo ...
+//
+// Description : demo ...
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 2021-12-02 12:46 下午
+package demo
+
+import (
+	"fmt"
+	"reflect"
+	"testing"
+	"time"
+)
+
+// TestCancelCtx_UDC 测试自定义context
+//
+// Author : go_developer@163.com<白茶清欢>
+//
+// Date : 12:46 下午 2021/12/2
+func TestCancelCtx_UDC(t *testing.T) {
+	childCancel := true
+
+	parentCtx, parentFunc := WithCancel(Background())
+	mctx := MyContext{parentCtx}
+
+	childCtx, childFun := WithCancel(mctx)
+
+	if childCancel {
+		childFun()
+	} else {
+		parentFunc()
+	}
+
+	fmt.Println("parent context => ", parentCtx, reflect.TypeOf(parentCtx).String())
+	fmt.Println("my context => ", mctx, reflect.TypeOf(mctx).String())
+	fmt.Println("child context => ", childCtx, reflect.TypeOf(childCtx).String())
+
+	// 防止主协程退出太快，子协程来不及打印
+	time.Sleep(5 * time.Second)
+}

go.mod

@@ -14,6 +14,7 @@ require (
 	github.com/gin-gonic/gin v1.7.6
 	github.com/go-redis/redis/v8 v8.11.4
 	github.com/go-redis/redis_rate/v9 v9.1.2
+	github.com/gocolly/colly v1.2.0
 	github.com/lestrrat-go/file-rotatelogs v2.4.0+incompatible
 	github.com/pkg/errors v0.9.1
 	github.com/shirou/gopsutil v3.21.10+incompatible
@@ -31,7 +32,12 @@ require (
 )
 
 require (
+	github.com/PuerkitoBio/goquery v1.8.0 // indirect
 	github.com/StackExchange/wmi v1.2.1 // indirect
+	github.com/andybalholm/cascadia v1.3.1 // indirect
+	github.com/antchfx/htmlquery v1.2.4 // indirect
+	github.com/antchfx/xmlquery v1.3.9 // indirect
+	github.com/antchfx/xpath v1.2.0 // indirect
 	github.com/cespare/xxhash/v2 v2.1.2 // indirect
 	github.com/coreos/bbolt v1.3.4 // indirect
 	github.com/coreos/go-semver v0.3.0 // indirect
@@ -51,6 +57,7 @@ require (
 	github.com/go-playground/universal-translator v0.17.0 // indirect
 	github.com/go-playground/validator/v10 v10.4.1 // indirect
 	github.com/go-sql-driver/mysql v1.6.0 // indirect
+	github.com/gobwas/glob v0.2.3 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
 	github.com/golang/protobuf v1.5.2 // indirect
@@ -71,6 +78,7 @@ require (
 	github.com/jinzhu/now v1.1.2 // indirect
 	github.com/jonboulle/clockwork v0.2.2 // indirect
 	github.com/json-iterator/go v1.1.11 // indirect
+	github.com/kennygrant/sanitize v1.2.4 // indirect
 	github.com/klauspost/compress v1.13.6 // indirect
 	github.com/leodido/go-urn v1.2.0 // indirect
 	github.com/lestrrat-go/strftime v1.0.5 // indirect
@@ -87,6 +95,7 @@ require (
 	github.com/rcrowley/go-metrics v0.0.0-20201227073835-cf1acfcdf475 // indirect
 	github.com/richardlehane/mscfb v1.0.3 // indirect
 	github.com/richardlehane/msoleps v1.0.1 // indirect
+	github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca // indirect
 	github.com/soheilhy/cmux v0.1.5 // indirect
 	github.com/spf13/afero v1.6.0 // indirect
 	github.com/spf13/cast v1.4.1 // indirect
@@ -94,6 +103,7 @@ require (
 	github.com/spf13/pflag v1.0.5 // indirect
 	github.com/spf13/viper v1.9.0 // indirect
 	github.com/subosito/gotenv v1.2.0 // indirect
+	github.com/temoto/robotstxt v1.1.2 // indirect
 	github.com/tidwall/match v1.1.1 // indirect
 	github.com/tidwall/pretty v1.2.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.9 // indirect
@@ -105,10 +115,11 @@ require (
 	go.uber.org/atomic v1.7.0 // indirect
 	go.uber.org/multierr v1.6.0 // indirect
 	golang.org/x/crypto v0.0.0-20210920023735-84f357641f63 // indirect
-	golang.org/x/net v0.0.0-20210917221730-978cfadd31cf // indirect
+	golang.org/x/net v0.0.0-20211216030914-fe4d6282115f // indirect
 	golang.org/x/sys v0.0.0-20211123173158-ef496fb156ab // indirect
 	golang.org/x/text v0.3.7 // indirect
 	golang.org/x/time v0.0.0-20211116232009-f0f3c7e86c11 // indirect
+	google.golang.org/appengine v1.6.7 // indirect
 	google.golang.org/genproto v0.0.0-20210828152312-66f60bf46e71 // indirect
 	google.golang.org/grpc v1.40.0 // indirect
 	google.golang.org/protobuf v1.27.1 // indirect

go.sum

@@ -44,6 +44,8 @@ cloud.google.com/go/storage v1.10.0/go.mod h1:FLPqc6j+Ki4BU591ie1oL6qBQGu2Bl/tZ9
 dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
 github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
 github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
+github.com/PuerkitoBio/goquery v1.8.0 h1:PJTF7AmFCFKk1N6V6jmKfrNH9tV5pNE6lZMkG0gta/U=
+github.com/PuerkitoBio/goquery v1.8.0/go.mod h1:ypIiRMtY7COPGk+I/YbZLbxsxn9g5ejnI2HSMtkjZvI=
 github.com/Shopify/sarama v1.30.0 h1:TOZL6r37xJBDEMLx4yjB77jxbZYXPaDow08TSK6vIL0=
 github.com/Shopify/sarama v1.30.0/go.mod h1:zujlQQx1kzHsh4jfV1USnptCQrHAEZ2Hk8fTKCulPVs=
 github.com/Shopify/toxiproxy/v2 v2.1.6-0.20210914104332-15ea381dcdae h1:ePgznFqEG1v3AjMklnK8H7BSc++FDSo7xfK9K7Af+0Y=
@@ -55,6 +57,14 @@ github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuy
 github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
 github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
 github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d/go.mod h1:rBZYJk541a8SKzHPHnH3zbiI+7dagKZ0cgpgrD7Fyho=
+github.com/andybalholm/cascadia v1.3.1 h1:nhxRkql1kdYCc8Snf7D5/D3spOX+dBgjA6u8x004T2c=
+github.com/andybalholm/cascadia v1.3.1/go.mod h1:R4bJ1UQfqADjvDa4P6HZHLh/3OxWWEqc0Sk8XGwHqvA=
+github.com/antchfx/htmlquery v1.2.4 h1:qLteofCMe/KGovBI6SQgmou2QNyedFUW+pE+BpeZ494=
+github.com/antchfx/htmlquery v1.2.4/go.mod h1:2xO6iu3EVWs7R2JYqBbp8YzG50gj/ofqs5/0VZoDZLc=
+github.com/antchfx/xmlquery v1.3.9 h1:Y+zyMdiUZ4fasTQTkDb3DflOXP7+obcYEh80SISBmnQ=
+github.com/antchfx/xmlquery v1.3.9/go.mod h1:wojC/BxjEkjJt6dPiAqUzoXO5nIMWtxHS8PD8TmN4ks=
+github.com/antchfx/xpath v1.2.0 h1:mbwv7co+x0RwgeGAOHdrKy89GvHaGvxxBtPK0uF9Zr8=
+github.com/antchfx/xpath v1.2.0/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs=
 github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
 github.com/apolloconfig/agollo/v4 v4.0.9 h1:4YzFSOVTZjGU2ag0XxL0y311TAkEsqh9a5pBS8FOgaI=
 github.com/apolloconfig/agollo/v4 v4.0.9/go.mod h1:n/7qxpKOTbegygLmO5OKmFWCdy3T+S/zioBGlo457Dk=
@@ -149,6 +159,10 @@ github.com/go-sql-driver/mysql v1.6.0 h1:BCTh4TKNUYmOmMUcQ3IipzF5prigylS7XXjEkfC
 github.com/go-sql-driver/mysql v1.6.0/go.mod h1:DCzpHaOWr8IXmIStZouvnhqoel9Qv2LBy8hT2VhHyBg=
 github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
 github.com/go-task/slim-sprig v0.0.0-20210107165309-348f09dbbbc0/go.mod h1:fyg7847qk6SyHyPtNmDHnmrv/HOrqktSC+C9fM+CJOE=
+github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
+github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
+github.com/gocolly/colly v1.2.0 h1:qRz9YAn8FIH0qzgNUw+HT9UN7wm1oF9OBAilwEWpyrI=
+github.com/gocolly/colly v1.2.0/go.mod h1:Hof5T3ZswNVsOHYmba1u03W65HDWgpV5HifSuueE0EA=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/gogo/protobuf v1.1.1/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
@@ -307,6 +321,8 @@ github.com/jstemmer/go-junit-report v0.9.1/go.mod h1:Brl9GWCQeLvo8nXZwPNNblvFj/X
 github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
 github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
 github.com/julienschmidt/httprouter v1.3.0/go.mod h1:JR6WtHb+2LUe8TCKY3cZOxFyyO8IZAc4RVcycCCAKdM=
+github.com/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o=
+github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/klauspost/compress v1.13.6 h1:P76CopJELS0TiO2mebmnzgWaajssP/EszplttgQxcgc=
@@ -425,6 +441,8 @@ github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFR
 github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/ryanuber/columnize v0.0.0-20160712163229-9b3edd62028f/go.mod h1:sm1tb6uqfes/u+d4ooFouqFdy9/2g9QGwK3SQygK0Ts=
 github.com/sagikazarmark/crypt v0.1.0/go.mod h1:B/mN0msZuINBtQ1zZLEQcegFJJf9vnYIR88KRMEuODE=
+github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca h1:NugYot0LIVPxTvN8n+Kvkn6TrbMyxQiuvKdEwFdR9vI=
+github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca/go.mod h1:uugorj2VCxiV1x+LzaIdVa9b4S4qGAcH6cbhh4qVxOU=
 github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529/go.mod h1:DxrIzT+xaE7yg65j358z/aeFdxmN0P9QXhEzd20vsDc=
 github.com/shirou/gopsutil v3.21.10+incompatible h1:AL2kpVykjkqeN+MFe1WcwSBVUjGjvdU8/ubvCuXAjrU=
 github.com/shirou/gopsutil v3.21.10+incompatible/go.mod h1:5b4v6he4MtMOwMlS0TUMTu2PcXUg8+E1lC7eC3UO/RA=
@@ -463,6 +481,8 @@ github.com/stretchr/testify v1.7.0 h1:nwc3DEeHmmLAfoZucVR881uASk0Mfjw8xYJ99tb5Cc
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/subosito/gotenv v1.2.0 h1:Slr1R9HxAlEKefgq5jn9U+DnETlIUa6HfgEzj0g5d7s=
 github.com/subosito/gotenv v1.2.0/go.mod h1:N0PQaV/YGNqwC0u51sEeR/aUtSLEXKX9iv69rRypqCw=
+github.com/temoto/robotstxt v1.1.2 h1:W2pOjSJ6SWvldyEuiFXNxz3xZ8aiWX5LbfDiOFd7Fxg=
+github.com/temoto/robotstxt v1.1.2/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr3ujewlOo=
 github.com/tevid/gohamcrest v1.1.1 h1:ou+xSqlIw1xfGTg1uq1nif/htZ2S3EzRqLm2BP+tYU0=
 github.com/tevid/gohamcrest v1.1.1/go.mod h1:3UvtWlqm8j5JbwYZh80D/PVBt0mJ1eJiYgZMibh0H/k=
 github.com/tidwall/gjson v1.11.0 h1:C16pk7tQNiH6VlCrtIXL1w8GaOsi1X3W8KDkE1BuYd4=
@@ -598,6 +618,7 @@ golang.org/x/net v0.0.0-20200222125558-5a598a2470a0/go.mod h1:z5CRVTTTmAJ677TzLL
 golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200301022130-244492dfa37a/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200324143707-d3edc9973b7e/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
+golang.org/x/net v0.0.0-20200421231249-e086a090c8fd/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20200501053045-e0ff5e5a1de5/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20200506145744-7e3656a0809f/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20200513185701-a91f0712d120/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
@@ -605,6 +626,7 @@ golang.org/x/net v0.0.0-20200520004742-59133d7f0dd7/go.mod h1:qpuaurCH72eLCgpAm/
 golang.org/x/net v0.0.0-20200520182314-0ba52f642ac2/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20200625001655-4c5254603344/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
+golang.org/x/net v0.0.0-20200813134508-3edf25e44fcc/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/net v0.0.0-20201031054903-ff519b6c9102/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
@@ -618,8 +640,10 @@ golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96b
 golang.org/x/net v0.0.0-20210428140749-89ef3d95e781/go.mod h1:OJAsFXCWl8Ukc7SiCT/9KSuxbyM7479/AVlXFRxuMCk=
 golang.org/x/net v0.0.0-20210503060351-7fd8e65b6420/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20210726213435-c6fcb2dbf985/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/net v0.0.0-20210917221730-978cfadd31cf h1:R150MpwJIv1MpS0N/pc+NhTM8ajzvlmxlY5OYsrevXQ=
+golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20210917221730-978cfadd31cf/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20211216030914-fe4d6282115f h1:hEYJvxw1lSnWIl8X9ofsYMklzaDs90JI2az5YMd4fPM=
+golang.org/x/net v0.0.0-20211216030914-fe4d6282115f/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -828,6 +852,7 @@ google.golang.org/appengine v1.5.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7
 google.golang.org/appengine v1.6.1/go.mod h1:i06prIuMbXzDqacNJfV5OdTW448YApPu5ww/cMBSeb0=
 google.golang.org/appengine v1.6.5/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
 google.golang.org/appengine v1.6.6/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
+google.golang.org/appengine v1.6.7 h1:FZR1q0exgwxzPzp/aF+VccGrSfxfPpkBqjIIEq3ru6c=
 google.golang.org/appengine v1.6.7/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
 google.golang.org/genproto v0.0.0-20190307195333-5fe7a883aa19/go.mod h1:VzzqZJRnGkLBvHegQrXjBqPurQTc5/KpmUdxsrq26oE=
 google.golang.org/genproto v0.0.0-20190418145605-e7d98fc518a7/go.mod h1:VzzqZJRnGkLBvHegQrXjBqPurQTc5/KpmUdxsrq26oE=