From be77fe85042dfcc4a943c4c979ba7b990d6a124f Mon Sep 17 00:00:00 2001 From: Nick White Date: Sun, 21 Aug 2011 17:00:00 +0100 Subject: Tighten sscanf usage, add TODOs --- TODO | 24 ++++++++---------------- getgbook.c | 10 ++++++---- 2 files changed, 14 insertions(+), 20 deletions(-) diff --git a/TODO b/TODO index 8a1deb7..4703148 100644 --- a/TODO +++ b/TODO @@ -8,6 +8,10 @@ use "" rather than "\0" in headermax # other todos +use wide string functions when dealing with stuff returned over http; it's known utf8 + +bug in get(): if the \r\n\r\n after http headers is cut off between recv buffers + use HTTP/1.1 with "Connection: close" header try supporting 3xx in get, if it can be done in a few lines @@ -25,23 +29,11 @@ have websummary.sh print the date of release, e.g. ## getgbook +mkdir of bookid and save pages in there + Google will give you up to 5 cookies which get useful pages in immediate succession. It will stop serving new pages to the ip, even with a fresh cookie. So the cookie is certainly not everything. If one does something too naughty, all requests from the ip to books.google.com are blocked with a 403 'automated requests' error for 24 hours. What causes this ip block is less clear. It certainly isn't after just trying lots of pages with 5 cookies. It seems to be after requesting 100 new cookies in a certain time period - 100 in 5 minutes seemed to do it, as did 100 in ~15 minutes. -So, if no more than 5 useable cookies can be gotten, and many more than this cause an ip block, a strategy could be to not bother getting more than 5 cookies, and bail once the 5th starts failing. of course, this doesn't address getting more pages, and moreover it doesn't address knowing which pages are available. - -all pages available (includes page code & order (even when not available from main click3 part) (& title sometimes, & height), though not url): curl 'http://books.google.com/books?id=h3DSQ0L10o8C&printsec=frontcover' | sed -e '/OC_Run\(/!d' -e 's/.*_OC_Run\({"page"://g' -e 's/}].*//g' - -TODO, THEN: - at start (if in -p or -a mode), fill a Page struct (don't hold url in struct any more) - in -a, go through Page struct, if file exists, skip, otherwise get the url for the page (don't bother about re-getting order etc). this means that getgfailed and getgmissing can go away - in -p, just go through Page struct and print each entry - when 5 cookies have been exhausted, quit, saying no more cookies available for now (and recommending a time period to retry) - have -a be default, and stdin be - - - so, usage should be - getgbook [-] bookid - if - is given, read page codes from stdin - otherwise, just download everything (skipping already - downloaded pages) +NOTE!!: the method of getting all pages from book page does miss some; they aren't all listed +* these pages can often be requested, though diff --git a/getgbook.c b/getgbook.c index 5f1e381..62faf46 100644 --- a/getgbook.c +++ b/getgbook.c @@ -23,7 +23,7 @@ typedef struct { int getpagelist(char *bookid, Page **pages) { - char url[URLMAX]; + char url[URLMAX], m[STRMAX]; char *buf; char *s; int i; @@ -43,7 +43,8 @@ int getpagelist(char *bookid, Page **pages) if(*s == ']') break; if(!strncmp(s, "\"pid\"", 5)) { - sscanf(s+6, "\"%[^\"]\",", p->name); + snprintf(m, STRMAX, "\"%%%d[^\"]\"", STRMAX-1); + sscanf(s+6, m, p->name); for(;*s; s++) { if(*s == '}') break; @@ -58,7 +59,7 @@ int getpagelist(char *bookid, Page **pages) } int getpageurls(char *bookid, Page **pages, int totalpages, char *pagecode, char *cookie) { - char url[URLMAX], code[STRMAX]; + char url[URLMAX], code[STRMAX], m[STRMAX]; char *c, *d, *p, *buf = NULL; int i; @@ -69,7 +70,8 @@ int getpageurls(char *bookid, Page **pages, int totalpages, char *pagecode, char c = buf; while(*c && (c = strstr(c, "\"pid\":"))) { - if(!sscanf(c, "\"pid\":\"%[^\"]\"", code)) + snprintf(m, STRMAX, "\"pid\":\"%%%d[^\"]\"", STRMAX-1); + if(!sscanf(c, m, code)) break; for(; *c; c++) { if(*c == '}') { -- cgit v1.2.3