Retry properly with specific pages

2 files changed, 15 insertions, 8 deletions

diff --git a/TODO b/TODO
index efb6f83..43cb56a 100644
--- a/TODO
+++ b/TODO
@@ -1,7 +1,11 @@
+Note: looks like google allows around 3 page requests per cookie session, and about 40 per ip per [some time period]. If I knew the time period, and once stdin retry is working, could make a script that gets all it can, gets a list of failures, waits, then tries failures, etc. Note these would also have to stop at some point; some pages just aren't available
+
 make sure i'm checking all lib calls that could fail
 
 make sure all arrays are used within bounds
 
+strace to check paths taken are sensible
+
 use defined constants rather than e.g. 1024
 
 getgbooktxt (different program as it gets from html pages, which getgbook doesn't any more)
diff --git a/getgbook.c b/getgbook.c
index c87b1c1..f947a82 100644
--- a/getgbook.c
+++ b/getgbook.c
@@ -124,16 +124,19 @@ int main(int argc, char *argv[])
 	} else {
 		while(fgets(buf, 1024, stdin)) {
 			sscanf(buf, "%15s", pg);
-			get("books.google.com", "/", NULL, cookie, &tmp);
-			if(!(page = getpagedetail(bookid, pg, cookie)) || !page->url[0]) {
-				fprintf(stderr, "%s failed\n", pg);
+			for(retry = 0; retry < 5; retry++) {
+				get("books.google.com", "/", NULL, cookie, &tmp);
+				if((page = getpagedetail(bookid, pg, cookie)) && page->url[0]) {
+					snprintf(n, 80, "%05d.png", page->num);
+					gettofile("books.google.com", page->url, cookie, NULL, n);
+					printf("Downloaded page %d\n", page->num);
+					free(page);
+					break;
+				}
 				if(page) free(page);
-				continue;
 			}
-			snprintf(n, 80, "%05d.png", page->num);
-			gettofile("books.google.com", page->url, cookie, NULL, n);
-			printf("Downloaded page %d\n", page->num);
-			free(page);
+			if(retry == 5)
+				fprintf(stderr, "%s failed\n", pg);
 		}
 	}