-
-
Save tejasri-v/bd150250c5c31d37f6392740040f52be to your computer and use it in GitHub Desktop.
Lab6-Part2
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Part 2: Web page downloader | |
--------------------------- | |
There is a very useful program called "wget". It's a command line | |
tool that you can use to download a web page like this: | |
wget http://www.gnu.org/software/make/manual/make.html | |
which will download the make manual page, make.html, and save it in | |
the current directory. wget can do much more (downloading a whole web | |
site, for example); see man wget for more info. | |
Your job is to write a limited version of wget, which we will call | |
http-client.c, that can download a single file. You use it like this: | |
./http-client www.gnu.org 80 /software/make/manual/make.html | |
So you give the components of the URL separately in the command line: | |
the host, the port number, and the file path. The program will | |
download the given file and save it in the current directory. So | |
in the case above, it should produce make.html in the current | |
directory. It should overwrite an existing file. | |
Hints: | |
- The program should open a socket connection to the host and port | |
number specified in the command line, and then request the given | |
file using HTTP 1.0 protocol. (See | |
http://www.jmarshall.com/easy/http/ for HTTP 1.0 protocol.) An HTTP | |
GET request looks like this: | |
GET /path/file.html HTTP/1.0 | |
[zero or more headers ...] | |
[a blank line] | |
- Include the following header in your request: | |
Host: the.host.name.you.are.connecting.to:<port_number> | |
Some web sites require it. | |
- Use "\r\n" rather than "\n" as newline when you send your request. | |
It's required by the HTTP protocol. | |
- Then the program reads the response from the web server which looks | |
like this: | |
HTTP/1.0 200 OK | |
Date: Fri, 31 Dec 1999 23:59:59 GMT | |
Content-Type: text/html | |
Content-Length: 1354 | |
<html> | |
<body> | |
<h1>Happy New Millennium!</h1> | |
(more file contents) | |
. | |
. | |
. | |
</body> | |
</html> | |
Just like in part 1, you can use fdopen() to wrap the socket with a | |
FILE*, which will make reading the lines much easier. | |
- The "200" in the 1st line indicates that the request was successful. | |
If it's not 200, the program should print the 1st line and exit. | |
- After the 1st line, a bunch of headers will come, then comes a blank | |
line, and then the actual file content starts. Your program should | |
skip over all headers and just receive the file content. | |
- Note that the program should be able to download any type of file, not | |
just HTML files. | |
- The server will terminate the socket connection when it's done | |
sending the file. | |
- You will need to pick out the file name part of a file path | |
(make.html from /software/make/manual/make.html for example). Check | |
out strrchr(). | |
- You will need to convert a host name into an IP address. Here is one way | |
to convert a host name into an IP address in dotted-quad notation: | |
struct hostent *he; | |
char *serverName = argv[1]; | |
// get server ip from server name | |
if ((he = gethostbyname(serverName)) == NULL) { | |
die("gethostbyname failed"); | |
} | |
char *serverIP = inet_ntoa(*(struct in_addr *)he->h_addr); | |
The man pages of the functions will tell you which header files need to be | |
included. | |
-- | |
Good luck! |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <ctype.h> | |
#include <stdio.h> | |
#include <stdlib.h> | |
#include <string.h> | |
#include <assert.h> | |
#include <unistd.h> | |
#include <sys/wait.h> | |
#include <sys/stat.h> | |
#include <arpa/inet.h> | |
#include <sys/types.h> | |
#include <sys/socket.h> | |
#include <netdb.h> | |
#include <arpa/inet.h> | |
static void die(const char *s) { perror(s); exit(1); } | |
int main(int argc, char **argv) | |
{ | |
if (argc != 4){ | |
fprintf(stderr, "usage: %s <host> <port> <file-path>\n", argv[0]); | |
exit(1); | |
} | |
struct hostent *he; | |
char *serverName = argv[1]; | |
if ((he = gethostbyname(serverName)) == NULL) | |
die("gethostbyname failed"); | |
char *serverIP = inet_ntoa(*(struct in_addr *)he->h_addr); | |
unsigned short port = atoi(argv[2]); | |
int sock; | |
if ((sock = socket(AF_INET, SOCK_STREAM, 0)) < 0) | |
die("socket failed"); | |
struct sockaddr_in servaddr; | |
memset(&servaddr, 0, sizeof(servaddr)); | |
servaddr.sin_family = AF_INET; | |
servaddr.sin_addr.s_addr = inet_addr(serverIP); | |
servaddr.sin_port = htons(port); | |
if (connect(sock, (struct sockaddr *) &servaddr, sizeof(servaddr)) < 0) | |
die("connect failed"); | |
char buf[1000]; | |
snprintf(buf, 1000, "GET %s HTTP/1.0\r\n", argv[3]); | |
size_t len = strlen(buf); | |
if(send(sock, buf, len, 0) != len) | |
die("send failed"); | |
snprintf(buf, 1000, "Host: %s:%s\r\n", argv[1], argv[2]); | |
len = strlen(buf); | |
if(send(sock, buf, len, 0) != len) | |
die("send failed"); | |
snprintf(buf, 1000, "\r\n"); | |
len = strlen(buf); | |
if(send(sock, buf, len, 0) != len) | |
die("send failed"); //not sure that this is the right way to print everything ->is it cheating to send three times | |
FILE *response = fdopen(sock, "r"); | |
char a[1000]; | |
fgets(a, 1000, response); | |
// printf("%s", a); | |
if(a[9] == '2' && a[10] == '0' && a[11] == '0'){ | |
while(a[strlen(a)-1] == '\n' && a[strlen(a)-2] == '\r' && strlen(a) > 2){ | |
fgets(a, 1000, response); | |
} | |
// fgets(a, 1000, response); | |
// if(strlen(a) != 2) | |
// printf("not past the header"); | |
// fgets(a, 1000, response); | |
// printf("%s", a); | |
FILE *fp; | |
char *name; | |
name = strrchr(argv[3], '/'); | |
fp = fopen(name+1, "w"); | |
if(fp == NULL) | |
die("fopen failed"); | |
char b[1000]; | |
while(fread(b, 1, 1, response) == 1){ | |
fwrite(b, 1, 1, fp); | |
} | |
} | |
else{ | |
printf("%s", a); | |
exit(1); | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CC = gcc | |
CXX = g++ | |
CFLAGS = -g -Wall $(INCLUDES) | |
CXXFLAGS = -g -Wall $(INCLUDES) | |
.PHONY: default | |
default: http-client | |
.PHONY: clean | |
clean: | |
rm -f *.o *~ a.out core http-client | |
.PHONY: all | |
all: clean default |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment