Question

我试图从whoscored.com中提取匹配数据。当我在firefox上查看源代码时，我在第816行找到一个大json字符串，其中包含我想要的数据。我的目标是最终得到这个json。

在执行此操作时，我尝试下载https://www.whoscored.com/Matches/ID/Live的每个页面，其中ID是匹配的ID。我写了一个Go程序给GET请求每个ID到某一点：

package main

import (
    "fmt"
    "io/ioutil"
    "net/http"
    "os"
)

// http://www.whoscored.com/Matches/614052/Live is the match for
// Eveton vs Manchester
const match_address = "http://www.whoscored.com/Matches/"

// the max id we get
const max_id = 300
const num_workers = 10

// function that get the bytes of the match id from the website
func match_fetch(matchid int) {
    url := fmt.Sprintf("%s%d/Live", match_address, matchid)

    resp, err := http.Get(url)
    if err != nil {
        fmt.Println(err)
        return
    }

    // if we sucessfully got a response, store the
    // body in memory
    defer resp.Body.Close()
    body, err := ioutil.ReadAll(resp.Body)
    if err != nil {
        fmt.Println(err)
        return
    }

    // write the body to memory
    pwd, _ := os.Getwd()
    filepath := fmt.Sprintf("%s/match_data/%d", pwd, matchid)
    err = ioutil.WriteFile(filepath, body, 0644)
    if err != nil {
        fmt.Println(err)
        return
    }
}

// data type to send to the workers,
// last means this job is the last one
// matchid is the match id to be fetched
// a matchid of -1 means don't fetch a match
type job struct {
    last    bool
    matchid int
}

func create_worker(jobs chan job) {
    for {
        next_job := <-jobs
        if next_job.matchid != -1 {
            match_fetch(next_job.matchid)
        }
        if next_job.last {
            return
        }
    }
}

func main() {
    // do the eveton match as a reference
    match_fetch(614052)

    var joblist [num_workers]chan job
    var v int

    for i := 0; i < num_workers; i++ {
        job_chan := make(chan job)
        joblist[i] = job_chan
        go create_worker(job_chan)
    }
    for i := 0; i < max_id; i = i + num_workers {
        for index, c := range joblist {
            if i+index < max_id {
                v = i + index
            } else {
                v = -1
            }
            c <- job{false, v}
        }
    }
    for _, c := range joblist {
        c <- job{true, -1}
    }
}

代码似乎有用，因为它用html填充了一个名为match_data的目录。问题是这个html与我在浏览器中得到的完全不同！以下是我认为这样做的部分:(来自http://www.whoscored.com/Matches/614052/Live的GET请求的主体。

(function() { 

var z="";var b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for (var i=0;i<b.length;i+=2){z=z+parseInt(b.substring(i, i+2), 16)+",";}z = z.substring(0,z.length-1); eval(eval('String.fromCharCode('+z+')'));})();

我认为是这种情况的原因是页面中的javascript会将DOM提取并编辑到我在视图源上看到的内容。我怎样才能让golang运行javascript？有图书馆这样做吗？更好的是，我可以直接从服务器中获取JSON吗？

Answer 1

这可以通过https://godoc.org/github.com/sourcegraph/webloop#View.EvaluateJavaScript来完成阅读他们的主要示例https://github.com/sourcegraph/webloop

你需要的是一个无头浏览器＆＃34;总的来说。

Answer 2

通常，最好使用Web API与抓取。例如，whoscored自己使用OPTA，你应该能够直接访问。

http://www.jokecamp.com/blog/guide-to-football-and-soccer-data-and-apis/#opta

GET请求的输出与查看源不同

2 个答案: