browser.go 9.0 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158
  1. package backend
  2. import (
  3. "context"
  4. "encoding/json"
  5. "fmt"
  6. "io/ioutil"
  7. "math/rand"
  8. "net/http"
  9. "github.com/chromedp/cdproto/page"
  10. "github.com/chromedp/chromedp"
  11. )
  12. var (
  13. useragent = []string{
  14. "Chrome: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36",
  15. "Firefox: Mozilla/5.0 (Windows NT 6.3; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0",
  16. //"Safari: Mozilla/5.0 (iPhone; CPU iPhone OS 11_2_5 like Mac OS X) AppleWebKit/604.5.6 (KHTML, like Gecko) Version/11.0 Mobile/15D60 Safari/604.1",
  17. "MacOSX: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/602.2.14 (KHTML, like Gecko) Version/10.0.1 Safari/602.2.14",
  18. "Mozilla/5.0(Macintosh;U;IntelMacOSX10_6_8;en-us)AppleWebKit/534.50(KHTML,likeGecko)Version/5.1Safari/534.50",
  19. "Mozilla/5.0(Windows;U;WindowsNT6.1;en-us)AppleWebKit/534.50(KHTML,likeGecko)Version/5.1Safari/534.50",
  20. "Mozilla/5.0(Macintosh;IntelMacOSX10.6;rv:2.0.1)Gecko/20100101Firefox/4.0.1",
  21. "Mozilla/5.0(WindowsNT6.1;rv:2.0.1)Gecko/20100101Firefox/4.0.1",
  22. "Mozilla/5.0(Macintosh;IntelMacOSX10_7_0)AppleWebKit/535.11(KHTML,likeGecko)Chrome/17.0.963.56Safari/535.11",
  23. "Mozilla/4.0(compatible;MSIE7.0;WindowsNT5.1;Trident/4.0;SE2.XMetaSr1.0;SE2.XMetaSr1.0;.NETCLR2.0.50727;SE2.XMetaSr1.0)",
  24. "Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.70 Safari/537.36",
  25. "Chrome 9 Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36",
  26. "Safari Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.3 Safari/605.1.15",
  27. "Safari Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15",
  28. "Safari 11 Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/11.1.2 Safari/605.1.15 QQBrowserLite/1.3.0",
  29. "Chrome 9 Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36",
  30. "Chrome 59 Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36",
  31. "Chrome 9 Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36",
  32. "Safari 11 Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_1) AppleWebKit/604.3.5 (KHTML, like Gecko) Version/11.0.1 Safari/604.3.5",
  33. "Firefox 9 Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:93.0) Gecko/20100101 Firefox/93.0",
  34. "Safari Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/605.1.15",
  35. "Chrome 8 Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
  36. "Chrome Mozilla/5.0 (X11; U; U; Linux x86_64; zh-my) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36 Puffin/8.3.1.41624AP",
  37. "Opera 28 Mozilla/5.0 (Linux; BRAVIA 4K 2015 Build/LMY48E.S265) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36 OPR/28.0.1754.0",
  38. "Safari Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Safari/537.36 HeyTapBrowser/40.7.29.1",
  39. "Chrome 9 Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.58 Safari/537.36 Edg/93.0.961.33",
  40. "Chrome 9 Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) SamsungBrowser/15.0 Chrome/90.0.4430.210 Safari/537.36",
  41. "Chrome 9 Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36",
  42. "Chrome Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36",
  43. "Microsoft Edge Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/17.17134",
  44. "Chrome 8 Mozilla/5.0 (Windows NT 10.0; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36",
  45. "Chrome 8 Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36",
  46. "Chrome 9 Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36",
  47. "Chrome 8 Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36",
  48. "Chrome 9 Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
  49. "Chrome Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36",
  50. "Firefox 7 Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0",
  51. "Chrome 9 Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36",
  52. "Internet Explorer 11 Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; LCJB; rv:11.0) like Gecko",
  53. "Chrome 9 Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36",
  54. "Firefox 36 Mozilla/5.0 (Windows NT 6.3; rv:36.0) Gecko/20100101 Firefox/36.0",
  55. "Chrome Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3870.400 QQBrowser/10.8.4405.400",
  56. "Chrome 58 Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0",
  57. "Firefox 9 Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0",
  58. "Chrome 8 Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36",
  59. "Chrome 9 Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 Edg/94.0.992.38",
  60. }
  61. )
  62. func NewBrowser(headless bool, showImage bool, proxyServe bool) (
  63. context.Context, context.CancelFunc,
  64. context.Context, context.CancelFunc,
  65. context.Context, context.CancelFunc,
  66. ) {
  67. ctx, cancelFn := chromedp.NewContext(context.Background())
  68. chromeOptions := append(chromedp.DefaultExecAllocatorOptions[:],
  69. chromedp.NoDefaultBrowserCheck, //不检查默认浏览器
  70. chromedp.Flag("enable-automation", false), // 防止监测webdriver
  71. chromedp.Flag("disable-blink-features", "AutomationControlled"), //禁用 blink 特征
  72. chromedp.Flag("force-dev-mode-highlighting", true),
  73. chromedp.Flag("disable-extensions", false), //是否禁用扩展
  74. chromedp.Flag("headless", headless),
  75. chromedp.Flag("user-agent", useragent[rand.Intn(20)]), //搞到底还是要在这里设置useragent
  76. chromedp.Flag("disable-keep-alive", true),
  77. chromedp.Flag("disable-gpu", true),
  78. chromedp.Flag("no-sandbox", true),
  79. chromedp.Flag("disable-dev-shm-usage", false),
  80. chromedp.Flag("default-browser-check", false),
  81. chromedp.Flag("ignore-certificate-errors", false), //忽略错误 zj_zjsggzyjyzx_zbwjgs_gc
  82. chromedp.Flag("disable-web-security", true), //禁用网络安全标志
  83. chromedp.Flag("mute-audio", false),
  84. chromedp.Flag("accept-language", `zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7,zh-TW;q=0.6`),
  85. )
  86. if proxyServe {
  87. chromeOptions = append(chromeOptions,
  88. //chromedp.ProxyServer(fmt.Sprintf("socks5://%s", proxyServe)),
  89. chromedp.ProxyServer(GetProxyAddr()),
  90. )
  91. }
  92. if showImage {
  93. chromeOptions = append(chromeOptions,
  94. chromedp.Flag("blink-settings", "imagesEnabled=true"),
  95. )
  96. } else {
  97. chromeOptions = append(chromeOptions,
  98. chromedp.Flag("blink-settings", "imagesEnabled=false"),
  99. )
  100. }
  101. allocCtx, allocCancelFn := chromedp.NewExecAllocator(ctx, chromeOptions...)
  102. // 创建一个浏览器实例
  103. incCtx, incCancelFn := chromedp.NewContext(allocCtx,
  104. chromedp.WithLogf(nil))
  105. //
  106. chromedp.Run(ctx,
  107. chromedp.ActionFunc(func(cxt context.Context) error {
  108. _, err := page.AddScriptToEvaluateOnNewDocument("Object.defineProperty(navigator, 'webdriver', { get: () => false, });").Do(cxt)
  109. return err
  110. }),
  111. )
  112. return ctx, cancelFn, allocCtx, allocCancelFn, incCtx, incCancelFn
  113. }
  114. func GetProxyAddr() string {
  115. proxyAddr := "http://cc.spdata.jianyu360.com/crawl/proxy/socks5/fetch"
  116. roxyAuthor := "http://cc.spdata.jianyu360.com/crawl/proxy/socks5/fetch"
  117. //获取代理
  118. req, err := http.NewRequest(http.MethodGet, proxyAddr, nil)
  119. if err != nil {
  120. fmt.Println("get proxy request err:", err)
  121. return ""
  122. }
  123. //添加请求头
  124. req.Header.Add("Authorization", roxyAuthor)
  125. client := http.Client{}
  126. //发送请求
  127. resp, err := client.Do(req)
  128. if err != nil {
  129. fmt.Println("get proxy client err:", err)
  130. return ""
  131. }
  132. defer resp.Body.Close()
  133. bodyByte, err := ioutil.ReadAll(resp.Body)
  134. if err != nil {
  135. fmt.Println("get proxy read body err:", err)
  136. return ""
  137. }
  138. tmp := map[string]interface{}{}
  139. if json.Unmarshal(bodyByte, &tmp) != nil {
  140. return ""
  141. }
  142. if data, ok := tmp["data"].(map[string]interface{}); ok && len(data) > 0 {
  143. if httpProxy, ok := data["http"].(string); ok {
  144. return httpProxy
  145. } else if httpsProxy, ok := data["https"].(string); ok {
  146. return httpsProxy
  147. }
  148. }
  149. return ""
  150. }