main.go

package main

import (
	"fmt"
	"io"
	"net/http"
	"net/url"
	"os"
	"strings"
	"time"

	"github.com/tidwall/gjson"
)

func main() {
	docID := ""
	fmt.Println("输入doc_id(形如 https://docs.qq.com/pdf/DYW5nb09QUFVTaVVw 中的 DYW5nb09QUFVTaVVw): ")
	fmt.Printf("> ")
	fmt.Scanf("%s", &docID)

	if docID == "" {
		panic("无效的doc_id!")
	}

	metaUrl := fmt.Sprintf("https://docs.qq.com/dop-api/pdf/data/get?id=%s", docID)
	fmt.Printf("downloading doc=%s\n", docID)

	req, err := http.NewRequest("GET", metaUrl, nil)
	if err != nil {
		panic(err)
	}
	req.Header.Add("referer", fmt.Sprintf("https://docs.qq.com/pdf/%s", docID))
	req.Header.Add("user-agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36")

	rsp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer rsp.Body.Close()

	bytes, err := io.ReadAll(rsp.Body)
	if err != nil {
		panic(err)
	}

	pdfUrl := gjson.GetBytes(bytes, "data.collab_client_vars.pdfData.url").String()

	fmt.Printf("pdf data url=%v\n", pdfUrl)

	if pdfUrl == "" {
		panic("无效的doc_id!")
	}

	uri, err := url.Parse(pdfUrl)
	if err != nil {
		panic(err)
	}

	tmp := uri.Query().Get("response-content-disposition")

	filename := ""
	for _, v := range strings.Split(tmp, ";") {
		if strings.HasPrefix(v, "filename=") {
			v = strings.TrimPrefix(v, "filename=")
			v = v[1 : len(v)-1]
			filename = v
		}
	}

	fmt.Printf("writing file=%v\n", filename)

	pdfRsp, err := http.Get(pdfUrl)
	if err != nil {
		panic(err)
	}
	defer pdfRsp.Body.Close()

	pdfBytes, err := io.ReadAll(pdfRsp.Body)
	if err != nil {
		panic(err)
	}

	if err := os.WriteFile(filename, pdfBytes, 0644); err != nil {
		panic(err)
	}

	fmt.Println("download success")

	time.Sleep(time.Second * 3)
}