├── README.md
└── download.go


/README.md:
--------------------------------------------------------------------------------
 1 | ## Install
 2 | 
 3 | ```
 4 | go get github.com/dearplain/douding
 5 | ```
 6 | 
 7 | ## Usage
 8 | 
 9 | example
10 | ```
11 | douding http://www.docin.com/p-931453357.html
12 | douding https://wenku.baidu.com/view/bb52fecf561252d381eb6e65.html
13 | ```
14 | 
15 | ## Online
16 | 
17 | [在线看douding文档](http://dearplain.github.io)
18 | 


--------------------------------------------------------------------------------
/download.go:
--------------------------------------------------------------------------------
  1 | package main
  2 | 
  3 | import (
  4 | 	"bytes"
  5 | 	"fmt"
  6 | 	"io"
  7 | 	"io/ioutil"
  8 | 	"log"
  9 | 	"net/http"
 10 | 	"os"
 11 | 	"regexp"
 12 | 	"strings"
 13 | )
 14 | 
 15 | type Jpgs struct {
 16 | 	Zoom string
 17 | 	Page int
 18 | }
 19 | 
 20 | func main() {
 21 | 	if len(os.Args) <= 1 {
 22 | 		fmt.Println("error: no url specified!")
 23 | 		return
 24 | 	}
 25 | 	if strings.Contains(os.Args[1], "www.docin.com") {
 26 | 		downDouding(os.Args[1])
 27 | 	} else if strings.Contains(os.Args[1], "wenku.baidu.com") {
 28 | 		downWenkuPPT(os.Args[1])
 29 | 	}
 30 | }
 31 | 
 32 | func downWenkuPPT(url string) {
 33 | 
 34 | 	regID := regexp.MustCompile("view/(.*).html")
 35 | 	urls := regID.FindAllStringSubmatch(url, -1)
 36 | 
 37 | 	docID := urls[0][1]
 38 | 	getUrl := "https://wenku.baidu.com/browse/getbcsurl?doc_id=" + docID + "&pn=1&rn=99999&type=ppt"
 39 | 
 40 | 	body, _ := downloadBuf(getUrl)
 41 | 
 42 | 	regPages := regexp.MustCompile(`{"zoom":"(.*?)","page"`)
 43 | 	pages := regPages.FindAllStringSubmatch(string(body), -1)
 44 | 
 45 | 	os.Mkdir(docID, 0700)
 46 | 	for i, p := range pages {
 47 | 		p[1] = strings.Replace(p[1], "\\", "", -1)
 48 | 		fmt.Println("downloading:", p[1])
 49 | 		body, _ := downloadBuf(p[1])
 50 | 		ioutil.WriteFile(docID+"/img"+fmt.Sprint(i)+".jpg", body, 0644)
 51 | 	}
 52 | 	fmt.Println("download complete! total:", len(pages))
 53 | }
 54 | 
 55 | func downDouding(url string) {
 56 | 	re := regexp.MustCompile("p-([0-9]*)")
 57 | 	ss := re.FindStringSubmatch(url)
 58 | 
 59 | 	id := ss[1]
 60 | 	os.MkdirAll(id, 0700)
 61 | 	for page := 1; ; page++ {
 62 | 		buf, err := downloadBuf("http://211.147.220.164/index.jsp?file=" + id +
 63 | 			"&width=800&pageno=" + fmt.Sprintf("%d", page))
 64 | 		if err != nil {
 65 | 			fmt.Println(err)
 66 | 			break
 67 | 		}
 68 | 		if len(buf) < 1024 {
 69 | 			fmt.Println("download complete!")
 70 | 			break
 71 | 		}
 72 | 		err = ioutil.WriteFile(id+"/"+fmt.Sprintf("%04d.jpg", page), buf, 0644)
 73 | 		if err != nil {
 74 | 			fmt.Println(err)
 75 | 			break
 76 | 		}
 77 | 	}
 78 | }
 79 | 
 80 | func downloadBuf(url string) ([]byte, error) {
 81 | 	var buffer bytes.Buffer
 82 | 	if err := download(&buffer, url); err != nil {
 83 | 		fmt.Println(err)
 84 | 		return nil, err
 85 | 	}
 86 | 	return buffer.Bytes(), nil
 87 | }
 88 | 
 89 | func download(w io.Writer, url string) error {
 90 | 	resp, err := http.Get(url)
 91 | 	if err != nil {
 92 | 		return err
 93 | 	}
 94 | 	defer resp.Body.Close()
 95 | 
 96 | 	_, err = io.Copy(w, resp.Body)
 97 | 	return err
 98 | }
 99 | 
100 | func downloadA(url string) []byte {
101 | 	client := &http.Client{}
102 | 
103 | 	req, err := http.NewRequest("GET", url, nil)
104 | 	if err != nil {
105 | 		log.Fatalln(err)
106 | 	}
107 | 
108 | 	req.Header.Set("User-Agent", "Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1")
109 | 
110 | 	resp, err := client.Do(req)
111 | 	if err != nil {
112 | 		log.Fatalln(err)
113 | 	}
114 | 
115 | 	defer resp.Body.Close()
116 | 	body, err := ioutil.ReadAll(resp.Body)
117 | 	if err != nil {
118 | 		log.Fatalln(err)
119 | 	}
120 | 
121 | 	return body
122 | }
123 | 


--------------------------------------------------------------------------------