1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
|
/* See COPYING file for copyright, license and warranty details. */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "util.c"
#define usage "getgbook " VERSION " - a google books downloader\n" \
"usage: getgbook [-i ip] [-p|-a] bookid\n" \
" -p print all available pages\n" \
" -a download all available pages\n" \
" -i appear from ip address\n" \
" otherwise, all pages in stdin will be downloaded\n"
#define URLMAX 1024
#define BOOKID_LEN 12
typedef struct {
int num;
char url[URLMAX];
char name[80];
} Page;
char extrahdr[1024] = "\0";
int gettotalpages(char *bookid)
{
char url[URLMAX];
char *buf, *c;
int total;
snprintf(url, URLMAX, "/books/feeds/volumes/%s", bookid);
bookid = malloc(sizeof(char *) * BOOKID_LEN);
if(!get("books.google.com", url, extrahdr, &buf))
return 0;
if((c = strstr(buf," pages</dc:format>")) == NULL)
return 0;
while(*c && *c != '>') c--;
sscanf(c+1, "%d ", &total);
return total;
}
Page *getpagedetail(char *bookid, char *pg)
{
char url[URLMAX];
char *buf, *c, *d, m[80], *p;
Page *page;
snprintf(url, URLMAX, "/books?id=%s&pg=%s&jscmd=click3", bookid, pg);
if(!get("books.google.com", url, extrahdr, &buf))
return NULL;
snprintf(m, 80, "\"pid\":\"%s\"", pg);
if((c = strstr(buf,m)) == NULL)
return NULL;
page = malloc(sizeof(Page));
strncpy(page->name, pg, 80);
page->url[0] = '\0';
page->num = 0;
if(strncmp(c+strlen(m)+1, "\"src\"", 5) != 0) {
free(buf); return page;
}
for(p=page->url, d=c+strlen(m)+8; *d && *d != '"'; d++, p++) {
if(!strncmp(d, "\\u0026", 6)) {
*p = '&';
d+=5;
} else
*p = *d;
}
*p = '\0';
for(; *d; d++) {
if(*d == '}') {
break;
}
if(!strncmp(d, "\"order\"", 7)) {
sscanf(d+8, "%d,", &(page->num));
break;
}
}
free(buf);
return page;
}
int main(int argc, char *argv[])
{
char *bookid, pg[16], buf[1024], n[80];
int totalpages, i;
Page *page;
if(argc < 2 || argc > 5 ||
(argv[1][0]=='-' && ((argv[1][1]!='p' && argv[1][1]!='a' && argv[1][1] != 'i') || argc < 3)))
die(usage);
if(argv[1][0] == '-' && argv[1][1] == 'i') {
snprintf(extrahdr, 1024, "X-Forwarded-For: %s\r\n", argv[2]);
argv+=2;
argc-=2;
}
bookid = argv[argc-1];
if(argv[1][0] == '-') {
/* note this isn't the best way, not least because it misses the
* non PA pages. best is to crawl around the json grabbing everything
* available, by starting on PP1, and filling in by going through
* all pages in totalpages. */
if(!(totalpages = gettotalpages(bookid)))
die("Book has no pages\n");
for(i=1; i<=totalpages; i++) {
snprintf(pg, 16, "%s%d", "PA", i);
if((page = getpagedetail(bookid, pg)) == NULL || page->url[0] == '\0') {
fprintf(stderr, "%s failed\n", pg);
free(page);
continue;
}
if(argv[1][1] == 'a') {
snprintf(n, 80, "%05d.png", page->num);
gettofile("books.google.com", page->url, extrahdr, n);
printf("Downloaded page %d\n", page->num);
} else
printf("%d\n", page->num);
free(page);
}
} else {
/* todo: find the page based on its order number, rather than using PA%d */
while(fgets(buf, 1024, stdin)) {
sscanf(buf, "%d", &i);
snprintf(pg, 16, "%s%d", "PA", i);
if((page = getpagedetail(bookid, pg)) == NULL || page->url[0] == '\0') {
fprintf(stderr, "%d failed\n", i);
free(page);
continue;
}
snprintf(n, 80, "%05d.png", page->num);
gettofile("books.google.com", page->url, extrahdr, n);
printf("Downloaded page %d\n", page->num);
free(page);
}
}
free(bookid);
return EXIT_SUCCESS;
}
|
