小编典典

从Golang中的字节数组解压缩gzip

go

我有一堆来自某些Web请求的文件,有些文件是gzip压缩的,我需要将它们解压缩并将其打印为字符串。这是我第一次尝试使用golang,尝试了一些在网上找到的示例,但无法正常使用。

这是我尝试的最后一个测试:

package main

import (
    "bytes"
    "compress/gzip"
    "fmt"
    "io/ioutil"
)

func main() {
    content := []byte{72,84,84,80,47,49,46,49,32,50,48,48,32,79,75,13,10,84,114,97,110,115,102,101,114,45,69,110,99,111,100,105,110,103,58,32,99,104,117,110,107,101,100,13,10,67,111,110,110,101,99,116,105,111,110,58,32,75,101,101,112,45,65,108,105,118,101,13,10,67,111,110,116,101,110,116,45,69,110,99,111,100,105,110,103,58,32,103,122,105,112,13,10,67,111,110,116,101,110,116,45,84,121,112,101,58,32,116,101,120,116,47,104,116,109,108,13,10,68,97,116,101,58,32,83,117,110,44,32,49,52,32,65,112,114,32,50,48,49,57,32,48,53,58,49,50,58,50,51,32,71,77,84,13,10,75,101,101,112,45,65,108,105,118,101,58,32,116,105,109,101,111,117,116,61,53,44,32,109,97,120,61,49,48,48,13,10,83,101,114,118,101,114,58,32,65,112,97,99,104,101,47,50,46,52,46,49,48,32,40,68,101,98,105,97,110,41,13,10,86,97,114,121,58,32,65,99,99,101,112,116,45,69,110,99,111,100,105,110,103,13,10,13,10,54,98,100,13,10,31,139,8,0,0,0,0,0,0,3,236,89,235,111,218,72,16,255,156,254,21,83,127,1,36,108,243,200,163,215,0,82,66,104,19,53,205,85,133,94,85,157,78,104,177,7,188,141,189,246,237,174,33,180,234,255,126,179,182,73,8,143,132,180,167,83,117,106,68,204,122,119,231,249,155,89,123,134,103,123,173,231,103,191,119,7,159,222,245,32,208,81,216,121,214,202,191,0,90,1,50,223,12,104,168,185,14,177,211,239,95,2,116,121,18,160,132,126,202,53,42,250,74,146,88,106,244,225,116,14,159,226,84,194,169,140,103,10,101,203,205,105,114,250,231,182,221,138,80,51,16,44,194,182,53,229,56,51,100,22,120,177,208,40,116,219,154,113,95,7,109,31,167,220,67,59,187,169,2,23,92,115,22,218,202,99,33,182,235,78,205,234,216,118,193,241,135,185,85,33,98,55,60,74,163,197,132,117,167,43,156,198,177,86,90,178,4,110,5,134,92,92,67,32,113,220,182,60,165,220,209,98,135,19,113,225,208,140,5,18,195,182,165,244,60,68,21,32,146,58,17,250,156,209,148,39,17,133,181,204,39,219,202,73,93,171,96,25,104,157,168,151,174,235,121,142,239,41,244,156,84,112,59,96,66,196,83,148,142,143,46,143,38,238,152,77,29,34,178,64,207,19,178,155,71,108,130,238,141,157,241,201,16,115,23,144,181,70,177,63,47,4,250,124,10,220,39,159,144,178,214,210,156,23,50,165,200,24,242,25,227,2,101,177,182,186,158,144,16,219,240,189,183,99,111,121,11,33,190,180,68,139,247,86,85,194,68,157,160,107,5,245,44,130,150,3,8,206,8,70,30,42,136,199,43,209,67,155,91,46,113,121,152,111,131,216,178,220,133,165,133,11,103,179,153,179,193,131,165,78,139,124,8,74,122,237,146,113,230,89,183,143,158,125,25,79,226,161,23,205,175,157,68,76,104,139,203,54,136,93,153,89,189,189,211,169,68,218,151,54,59,169,148,187,161,212,25,4,92,193,12,71,42,203,159,9,159,210,117,30,167,20,158,227,88,70,76,243,88,0,125,116,128,96,188,229,229,222,82,121,186,205,141,143,70,185,143,104,46,203,61,5,68,8,100,113,42,185,152,192,249,96,240,174,111,50,65,160,103,152,41,103,69,223,117,173,72,229,189,189,91,115,216,74,72,234,25,215,154,92,232,197,145,171,2,38,209,90,32,80,172,216,217,172,61,74,181,54,1,237,51,205,236,84,134,59,4,181,23,160,119,93,80,104,188,161,196,237,154,25,136,83,189,226,128,45,166,59,5,177,226,95,40,33,66,38,39,88,204,4,76,5,154,77,140,150,161,202,121,88,157,193,140,242,210,96,76,246,82,48,81,98,242,68,119,158,143,83,145,185,170,236,87,85,149,251,149,175,83,38,225,179,170,142,63,171,182,239,76,80,247,66,140,232,92,81,167,243,1,155,92,209,161,83,86,149,63,107,127,29,243,113,249,249,242,134,211,249,133,95,38,6,149,175,25,37,229,61,211,88,172,17,201,241,103,229,80,38,114,223,12,76,32,90,174,155,132,76,27,224,157,101,55,211,137,69,76,149,243,89,89,199,164,132,147,144,127,133,190,138,125,116,184,32,251,245,41,18,13,150,115,29,43,199,223,190,149,253,216,75,141,152,170,149,91,101,85,111,225,153,17,155,202,113,203,45,204,93,10,132,173,113,221,26,73,183,211,74,22,81,18,82,250,151,204,33,82,34,103,14,77,164,150,58,219,158,3,163,251,207,1,40,199,146,142,142,124,33,161,192,162,177,240,176,242,178,229,38,157,181,212,217,16,154,45,58,101,99,49,233,244,19,244,200,134,252,38,87,117,117,247,254,221,238,123,135,140,65,236,17,210,37,65,111,112,14,125,138,167,71,40,14,239,40,206,48,119,45,133,208,42,209,26,233,54,51,203,94,173,218,24,85,182,26,214,235,158,157,247,108,186,246,79,236,147,94,191,222,120,97,191,238,190,181,251,231,39,141,131,195,173,54,209,54,56,229,122,171,5,198,86,188,241,40,39,39,248,18,214,142,82,20,206,140,95,243,196,60,199,156,88,78,92,115,231,246,194,208,24,235,13,233,196,153,226,240,140,143,199,28,237,115,12,195,136,137,18,104,147,133,186,93,26,142,66,38,174,115,205,77,206,85,129,128,151,243,204,77,59,203,58,241,167,140,194,197,31,246,110,105,135,125,205,132,207,164,191,46,138,28,147,75,122,123,210,221,89,4,185,208,38,31,174,115,91,248,150,117,156,239,66,243,232,49,52,223,223,97,249,11,199,159,22,199,102,109,71,28,73,200,34,39,155,47,246,183,98,73,219,126,97,185,3,150,228,195,141,88,102,190,253,78,44,235,251,79,192,146,100,253,2,241,7,65,172,111,132,176,254,125,0,214,106,213,223,252,237,0,254,4,105,72,42,12,203,44,156,196,146,235,32,170,172,27,79,27,126,118,200,254,245,188,35,216,154,7,59,193,246,159,103,220,255,1,175,157,83,108,219,59,253,56,149,84,108,201,226,189,254,85,126,183,92,143,238,246,174,222,44,117,62,208,11,191,125,50,161,50,228,229,102,156,94,148,58,111,227,47,60,12,153,123,224,212,160,252,145,11,159,202,4,184,26,64,189,230,212,142,129,38,14,247,143,225,230,112,191,2,39,73,18,226,71,28,189,225,218,61,104,30,57,205,67,40,191,57,31,188,189,172,66,200,175,17,94,83,169,24,87,160,27,200,56,66,247,168,233,212,104,203,139,166,83,175,53,161,207,198,76,242,130,236,73,17,75,102,188,203,202,20,83,179,80,1,234,14,46,251,64,245,170,202,161,223,102,22,237,154,214,157,198,83,69,237,138,51,210,3,65,14,77,33,51,188,16,62,247,50,92,54,0,127,117,97,112,191,7,222,118,157,183,213,229,79,53,194,148,233,74,51,42,220,233,193,101,42,85,208,60,194,135,156,69,181,189,113,107,78,20,143,239,23,247,62,247,65,196,26,20,10,31,88,198,11,166,44,76,113,67,56,155,81,214,81,185,107,120,64,170,168,32,45,240,0,170,129,3,216,242,186,13,44,19,80,188,92,195,53,157,32,166,149,114,151,234,206,35,153,35,25,57,228,61,155,237,150,32,141,82,231,143,71,227,168,233,52,225,73,254,111,44,74,113,245,16,210,181,198,168,74,151,35,186,52,107,116,169,239,211,163,148,142,229,39,203,234,221,104,20,198,134,135,196,213,232,175,74,255,7,230,194,204,101,100,46,126,117,60,174,213,105,84,111,60,89,238,123,140,98,42,229,7,255,81,96,61,91,52,71,158,45,53,249,76,23,53,73,85,96,45,247,8,139,225,222,237,142,113,76,138,222,245,74,31,237,181,46,226,202,138,82,211,63,241,232,220,225,218,202,163,154,180,54,45,108,160,97,34,227,41,247,243,62,138,233,141,173,245,233,182,244,61,173,181,67,226,172,219,239,117,179,99,66,162,66,38,189,0,38,50,78,19,96,122,51,215,213,182,221,58,203,75,228,35,193,191,192,7,193,179,163,82,207,225,188,32,200,158,67,134,111,65,99,229,52,171,141,239,45,218,187,60,74,72,75,149,70,142,249,93,194,234,92,208,61,23,89,19,47,239,82,193,69,134,50,4,108,138,148,208,115,58,9,162,172,89,7,148,202,127,167,168,178,38,40,208,163,132,41,204,126,33,96,222,138,157,15,136,31,179,32,44,36,247,153,162,183,11,120,69,51,121,155,56,185,133,120,61,26,104,144,183,224,41,142,242,31,84,246,254,1,0,0,255,255,3,0,8,20,73,242,107,25,0,0,13,10,48,13,10,13,10}
    buf := bytes.NewBuffer(content)
    reader, err := gzip.NewReader(buf)
    if err != nil {
        panic(err)
    }
    defer reader.Close()


    s, err := ioutil.ReadAll(reader)
    if err != nil {
        panic(err)
    }

    fmt.Println("decompressed:\t", string(s))
}

但它显示了错误:panic:,gzip: invalid header与其他一些示例相同。

如何解压缩字节数组的内容?


阅读 1028

收藏
2020-07-02

共1个答案

小编典典

content := []byte{72,84,84,80,47,49,46,49,32,50,48,48,32,79,75, ...

这根本不是gzip数据。正确的gzip数据以魔术序列开头0x1f 0x8b,即[]byte{31,139,...}。就此而言,它正确地抱怨
gzip:invalid header

因此,让我们仔细看看该字节序列实际上是什么。当将其打印为字符串时,它给出:

HTTP/1.1 200 OK
Transfer-Encoding: chunked
Connection: Keep-Alive
Content-Encoding: gzip
Content-Type: text/html
Date: Sun, 14 Apr 2019 05:12:23 GMT
Keep-Alive: timeout=5, max=100
Server: Apache/2.4.10 (Debian)
Vary: Accept-Encoding

6bd
... binary data ..
0

因此,这是HTTP响应,其中首先使用gzip压缩主体,然后使用分块传输编码对主体进行编码。要提取数据,您需要首先删除HTTP标头,然后从分块的传输编码中解码,然后可以获取结果并使用gzip解压缩。

2020-07-02