内网环境图片解锁小插件

背景说明:

前面有个博客提到：

https://bbs.huaweicloud.com/blogs/1736e75674b111eab759fa163e330718

这几天就把这个想法实现了一下,

测试的目标帖子是:https://zhuanlan.zhihu.com/p/49468787,

由于zhuanlan.zhihu.com也不在白名单，所以访问其快照地址

https://webcache.googleusercontent.com/search?q=cache:8zRJ_LpHVaAJ:https://zhuanlan.zhihu.com/p/49468787+&cd=1&hl=en&ct=clnk&gl=sg

然后可以发现形如"*://*.zhimg.com/*"的图片域也是无法访问的,

• 开启插件和转发服务前
  

• 开启插件和转发服务后

chrome浏览器插件部分

• background.js

chrome.webRequest.onBeforeRequest.addListener(
	function(details) {
		return {
			redirectUrl: "http://127.0.0.1:8099/search?q=" + details.url + "&tbm=isch"
		};
	}, {
		urls: [
			"*://*.zhimg.com/*",
		],
		types: ["main_frame", "sub_frame", "stylesheet", "script", "image", "object", "xmlhttprequest", "other"]
	}, ["blocking"]
);

• content.js

'use strict';

(function() {
  var tags = document.getElementsByTagName('noscript');

  for (var i = tags.length-1; i >=0 ; i--) {
    if (tags[i].firstChild) {
      var newDiv = document.createElement('div');
      newDiv.innerHTML = tags[i].innerHTML;
      tags[i].parentNode.removeChild(tags[i].nextSibling);
      tags[i].parentNode.replaceChild(newDiv, tags[i]);
    }
  }
})();

• manifest.json

  ...
  "background": {
    "scripts": [
      "background.js"
    ]
  },
  "content_scripts": [{
    "matches": ["*://webcache.googleusercontent.com/*"],
    "js": ["content.js"],
    "run_at": "document_end"
 }],
  "permissions": [
    "<all_urls>",
    "webRequest",
    "webNavigation",
    "webRequestBlocking",
    "browsingData"
  ]
  ...

请求转发部分

package main
import (
	"fmt"
	"github.com/gorilla/mux"
	"io"
	"io/ioutil"
	"log"
	"net/http"
	"os"
	"regexp"
	"strings"
)
func get_google_img(res http.ResponseWriter,query string)  {
	url1 := "https://www.google.com/search?q=" + query + "&tbm=isch"
	os.Setenv("HTTP_PROXY", "http://uid:pass@proxy.domain.com:port")
	resq, err := http.NewRequest("GET", url1, nil)
	resq.Header.Set("user-agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36")
	client := &http.Client{}
	resp, err := client.Do(resq)
	if err != nil {
		log.Fatalln(err)
	}
	defer resp.Body.Close()
	if resp.StatusCode != 200 {
		log.Fatalf("status code error: %d %s", resp.StatusCode, resp.Status)
	}
	body,err := ioutil.ReadAll(resp.Body)
	if err !=nil {
		log.Fatalln(err)
	}
	r := regexp.MustCompile("(https://encrypted-tbn0.gstatic.com/[^\"]+)")
	matches := r.FindAllStringSubmatch(string(body), -1)
	decoded := strings.ReplaceAll(matches[0][1],"\\u003d","=")
	decoded = strings.ReplaceAll(decoded,"\\u0026","&")
	resq, err = http.NewRequest("GET", decoded, nil)
	reqImg, err := client.Do(resq)
	if err != nil {
		log.Fatalln(err)
	}
	if reqImg.StatusCode != 200 {
		log.Fatalf("status code error: %d %s", reqImg.StatusCode, reqImg.Status)
	}
	res.Header().Set("Content-Length", fmt.Sprint(reqImg.ContentLength))
	res.Header().Set("Content-Type", reqImg.Header.Get("Content-Type"))
	if _, err = io.Copy(res, reqImg.Body); err != nil {
		log.Fatalln(err)
	}
	reqImg.Body.Close()
}
func main() {
	gmux := mux.NewRouter().StrictSlash(true)
	gmux.HandleFunc("/search", func(w http.ResponseWriter, r *http.Request) {
		w.Header().Set("Access-Control-Allow-Origin", "*")                                                                                                                                 
		w.Header().Add("Access-Control-Allow-Headers", "X-Requested-With, Content-Type,Origin, Authorization, Accept, Client-Security-Token, Accept-Encoding, X-Auth-Token, content-type") 
		w.Header().Set("content-type", "application/json")                                                                                                                                 
		w.Header().Add("Access-Control-Allow-Methods", "GET, POST, PUT, PATCH, POST, DELETE, OPTIONS")
		q := r.URL.Query().Get("q")
		get_google_img(w,q)
	}).Methods("GET")
	//go func() {
		http.ListenAndServe(":8099", gmux)
	//}()
}

小结

原来考虑采用chrome.webRequest.replaceStringOccurred,那样适用范围会大些不用一个个适配,但是这个阶段redirectUrl已经不管用了,所以就改成现在的实现;

此外chrome.webRequest.onBeforeRequest的回调也不方便返回异步,所以在background中fetch的方案也有问题;

直接在content.js中fetch需要插件处理跨域问题,综合来说现在的方案 写法还是要简单的多;

----只在内网有些用，外网几本没大用.