hello-go/spider/common/common.go

package common

import (
	"golang.org/x/text/encoding/simplifiedchinese"
	"io"
	"math/rand"
	"regexp"
	"strings"
	"sync"
	"time"
)

/* -----------------------------------------------------全局常量定义-------------------------------------------------- */
var (
	PCUserAgentList = []string{
		"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1",
		"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
		"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36",
		"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
		"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36",
		"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
		"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
		"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
		"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
		"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
		"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0",
		"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 UBrowser/4.0.3214.0 Safari/537.36",
		"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.75 Safari/537.36",
		"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36",
		"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
		"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:65.0) Gecko/20100101 Firefox/65.0",
		"Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0",
		"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360SE",
		"Mozilla/5.0 (Windows NT 6.1; Win64; x64; Trident/7.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET4.0C; .NET4.0E; rv:11.0) like Gecko",
		"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36 OPR/60.0.3255.84",
		"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36 OPR/60.0.3255.83",
		"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4098.3 Safari/537.36",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3676.400 QQBrowser/10.4.3473.400",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.79 Safari/537.36 Maxthon/5.2.7.2500",
		"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.131 Safari/537.36",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 BIDUBrowser/8.7 Safari/537.36",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36 QIHU 360EE",
		"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36",
		"Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko",
		"Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:56.0)",
		"Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36 Request Payload",
		"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/604.3.5 (KHTML, like Gecko) Version/11.0.1 Safari/604.3.5",
		"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.89 Mobile Safari/537.36",
		"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:56.0) Gecko/20100101 Firefox/56.0",
		"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; rv:11.0) like Gecko",
		"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299",
		"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.74 Safari/537.36 Edg/79.0.309.43",
		"Mozilla/5.0 (compatible; WOW64; MSIE 10.0; Windows NT 6.2)",
		"Mozilla/5.0 (Windows NT 6.3; Trident/7.0; rv 11.0) like Gecko",
		"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2486.0 Safari/537.36Edge/13.10586",
		"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.94 Safari/537.36",
		"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36",
		"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Ubuntu/11.10 Chromium/27.0.1453.93 Chrome/27.0.1453.93 Safari/537.36",
		"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_6; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27",
		"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27",
	}
	CellUserAgentList = []string{
		"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
		"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
		"Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
		"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
		"Mozilla/5.0 (Linux; U; Android 2.2.1; zh-cn; HTC_Wildfire_A3333 Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
		"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
		"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
		"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
		"Mozilla/5.0 (Linux; U; Android 8.1.0; zh-cn; BLA-AL00 Build/HUAWEIBLA-AL00) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/57.0.2987.132 MQQBrowser/8.9 Mobile Safari/537.36",
		"Mozilla/5.0 (Linux; Android 8.1; PAR-AL00 Build/HUAWEIPAR-AL00; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/57.0.2987.132 MQQBrowser/6.2 TBS/044304 Mobile Safari/537.36 MicroMessenger/6.7.3.1360(0x26070333) NetType/WIFI Language/zh_CN Process/tools",
		"Mozilla/5.0 (Linux; Android 6.0.1; OPPO A57 Build/MMB29M; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/63.0.3239.83 Mobile Safari/537.36 T7/10.13 baiduboxapp/10.13.0.10 (Baidu; P1 6.0.1)",
		"Mozilla/5.0 (Linux; Android 8.1; EML-AL00 Build/HUAWEIEML-AL00; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/53.0.2785.143 Crosswalk/24.53.595.0 XWEB/358 MMWEBSDK/23 Mobile Safari/537.36 MicroMessenger/6.7.2.1340(0x2607023A) NetType/4G Language/zh_CN",
		"Mozilla/5.0 (Linux; Android 8.0; DUK-AL20 Build/HUAWEIDUK-AL20; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/57.0.2987.132 MQQBrowser/6.2 TBS/044353 Mobile Safari/537.36 MicroMessenger/6.7.3.1360(0x26070333) NetType/WIFI Language/zh_CN Process/tools",
		"Mozilla/5.0 (Linux; U; Android 8.1.0; zh-CN; EML-AL00 Build/HUAWEIEML-AL00) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/57.0.2987.108 UCBrowser/11.9.4.974 UWS/2.13.1.48 Mobile Safari/537.36 AliApp(DingTalk/4.5.11) com.alibaba.android.rimet/10487439 Channel/227200 language/zh-CN",
		"Mozilla/5.0 (Linux; U; Android 5.1.1; zh-CN; SM-J3109 Build/LMY47X) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/57.0.2987.108 UCBrowser/11.8.0.960 UWS/2.12.1.18 Mobile Safari/537.36 AliApp(TB/7.5.4) UCBS/2.11.1.1 WindVane/8.3.0 720X1280",
		"Mozilla/5.0 (iPhone 6s; CPU iPhone OS 11_4_1 like Mac OS X) AppleWebKit/604.3.5 (KHTML, like Gecko) Version/11.0 MQQBrowser/8.3.0 Mobile/15B87 Safari/604.1 MttCustomUA/2 QBWebViewType/1 WKType/1",
		"Mozilla/5.0 (iPhone; CPU iPhone OS 11_2 like Mac OS X) AppleWebKit/604.3.5 (KHTML, like Gecko) Version/11.0 MQQBrowser/8.8.2 Mobile/15B87 Safari/604.1 MttCustomUA/2 QBWebViewType/1 WKType/1",
		"Mozilla/5.0 (iPhone; CPU iPhone OS 11_4_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15G77 wxwork/2.5.8 MicroMessenger/6.3.22 Language/zh",
		"Mozilla/5.0 (iPhone; CPU iPhone OS 11_0_2 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Mobile/15A421 wxwork/2.5.8 MicroMessenger/6.3.22 Language/zh",
		"Mozilla/5.0 (iPhone; CPU iPhone OS 6_1_4 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) CriOS/27.0.1453.10 Mobile/10B350 Safari/8536.25",
		"Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19",
		"Mozilla/5.0 (iPhone; CPU iPhone OS 5_0 like Mac OS X) AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 Mobile/9A334 Safari/7534.48.3",
		"Mozilla/5.0 (iPhone; CPU iPhone OS 8_0_2 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/8.0 Mobile/12A366 Safari/600.1.4",
	}
)

/* -----------------------------------------------------全局变量定义-------------------------------------------------- */
var (
	gbkPattern, _ = regexp.Compile(`meta\s+http-equiv="Content-Type"\s+content="text/html;\s*charset=gbk"`)
	gbkDecoder    = simplifiedchinese.GBK.NewDecoder()
)

/* -----------------------------------------------------线程安全字典-------------------------------------------------- */
type ConcurrentMap struct {
	data   map[string]interface{}
	locker sync.RWMutex
}

func NewConcurrentMap() *ConcurrentMap {
	return &ConcurrentMap{
		data: make(map[string]interface{}),
	}
}

func (m *ConcurrentMap) Remove(k string) {
	k = strings.ToLower(strings.TrimSpace(k))
	if k == "" {
		return
	}

	m.locker.Lock()
	defer m.locker.Unlock()

	delete(m.data, k)
}

func (m *ConcurrentMap) Set(k string, v interface{}) {
	k = strings.ToLower(strings.TrimSpace(k))
	if k == "" {
		return
	}

	m.locker.Lock()
	defer m.locker.Unlock()

	m.data[k] = v
}

func (m *ConcurrentMap) Append(input map[string]interface{}) {
	if nil == input || len(input) == 0 {
		return
	}

	m.locker.Lock()
	defer m.locker.Unlock()

	for k, v := range input {
		k = strings.ToLower(strings.TrimSpace(k))
		m.data[k] = v
	}
}

func (m *ConcurrentMap) Len() int {
	m.locker.RLock()
	defer m.locker.RUnlock()

	if nil == m.data {
		return 0
	}
	return len(m.data)
}

func (m *ConcurrentMap) Keys() []string {
	m.locker.RLock()
	defer m.locker.RUnlock()

	if nil == m.data || len(m.data) == 0 {
		return nil
	}

	var keys []string
	for k := range m.data {
		keys = append(keys, k)
	}
	return keys
}

func (m *ConcurrentMap) Values() []interface{} {
	m.locker.RLock()
	defer m.locker.RUnlock()

	if nil == m.data || len(m.data) == 0 {
		return nil
	}

	var list []interface{}
	for _, v := range m.data {
		list = append(list, v)
	}
	return list
}

/* -----------------------------------------------------请求目标消息-------------------------------------------------- */
type Target struct {
	Key     string      // 消息发送到的队列名
	Method  string      // 请求http method
	URL     string      // 请求目标url
	Referer string      // 请求目标referer url
	IsCell  bool        // 是否移动端
	Data    io.Reader   // 请求参数
	Item    interface{} // 携带的待输出数据对象（请传递对象引用）
}

/* -------------------------------------------------------工具函数---------------------------------------------------- */
// 字符编码转换
func EncodeTrans(input []byte) []byte {
	if nil == input || len(input) == 0 {
		return input
	}

	if gbkPattern.Match(input) {
		output, _ := gbkDecoder.Bytes(input)
		return output
	} else {
		return input
	}
}

// 随机秒数
func RandSeconds() time.Duration {
	rand.Seed(time.Now().UnixNano())
	return time.Duration(rand.Intn(6)) * time.Second
}

// 随机获取User-Agent
func RandUserAgent(isCell bool) string {
	var list []string
	if isCell {
		list = CellUserAgentList
	} else {
		list = PCUserAgentList
	}

	rand.Seed(time.Now().UnixNano())
	idx := rand.Intn(len(list))
	return list[idx]
}