File: http_fetcher.c

package info (click to toggle)
s3d 0.2.2-10
  • links: PTS, VCS
  • area: main
  • in suites: jessie, jessie-kfreebsd
  • size: 6,544 kB
  • ctags: 5,243
  • sloc: ansic: 20,861; python: 488; perl: 98; makefile: 39; sh: 29
file content (638 lines) | stat: -rw-r--r-- 15,461 bytes parent folder | download | duplicates (3)
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
/* http_fetcher.c - HTTP handling functions
 *
 * Copyright (C) 2001  Lyle Hanson <lhanson@cs.nmu.edu>
 *
 * This file is part of s3dosm, a gps card application for s3d.
 * See http://s3d.berlios.de/ for more updates.
 *
 * s3dosm is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * s3dosm is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with s3dosm; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 *
 *
 * Changes:
 *  Simon Wunderlich <sw@simonwunderlich.de>
 *  + added http_setAuth() to support basic http-authentication and some minor fixes
 */

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <netdb.h>
#include <unistd.h>
#include <netinet/in.h>
#include <errno.h>
#include <sys/types.h>
#include <sys/time.h>
#include "http_fetcher.h"

/* Globals */
static int timeout = DEFAULT_READ_TIMEOUT;
static char *userAgent = NULL;
static char *referer = NULL;
static char *auth = NULL;
static int hideUserAgent = 0;
static int hideReferer = 1;
static int errorSource = 0;
static int http_errno = 0;
static int errorInt = 0;   /* When the error message has a %d in it,
          * this variable is inserted */
static int freeOldAgent = 0; /* Indicates previous malloc's */
static int freeOldReferer = 0; /* Indicated previous malloc's */


/*
 * Actually downloads the page, registering a hit (donation)
 * If the fileBuf passed in is NULL, the url is downloaded and then
 * freed; otherwise the necessary space is allocated for fileBuf.
 * Returns size of download on success, -1 on error is set,
 */
int http_fetch(const char *url_tmp, char **fileBuf)
{
	fd_set rfds;
	struct timeval tv;
	char requestBuf[REQUEST_BUF_SIZE];
	char headerBuf[HEADER_BUF_SIZE];
	char *url, *pageBuf, *host, *charIndex;
	int sock, bytesRead = 0, contentLength = -1;
	int ret = -1, i, selectRet;


	if (url_tmp == NULL) {
		errorSource = FETCHER_ERROR;
		http_errno = HF_NULLURL;
		return -1;
	}

	/* Copy the url passed in into a buffer we can work with, change, etc. */
	url = (char*)malloc(strlen(url_tmp) + 1);
	if (url == NULL) {
		errorSource = ERRNO;
		return -1;
	}
	strncpy(url, url_tmp, strlen(url_tmp) + 1);

	/* Seek to the file path portion of the url */
	charIndex = strstr(url, "://");
	if (charIndex != NULL) {
		/* url contains a protocol field */
		charIndex += strlen("://");
		host = charIndex;
		charIndex = strchr(charIndex, '/');
	} else {
		host = (char *)url;
		charIndex = strchr(url, '/');
	}

	/* Compose a request string */
	if (charIndex == NULL)
		/* The url has no '/' in it, assume the user is making a root-level
		 * request */
		sprintf(requestBuf, "GET / %s\r\n", HTTP_VERSION);
	else
		sprintf(requestBuf, "GET %s %s\r\n", charIndex, HTTP_VERSION);
	/* Null out the end of the hostname if need be */
	if (charIndex != NULL)
		*charIndex = 0;

	strcat(requestBuf, "Host: ");
	strcat(requestBuf, host);
	strcat(requestBuf, "\r\n");


	if (!hideReferer && referer != NULL) { /* NO default referer */
		strcat(requestBuf, "Referer: ");
		strcat(requestBuf, referer);
		strcat(requestBuf, "\r\n");
	}

	if (!hideUserAgent && userAgent == NULL) {
		strcat(requestBuf, "User-Agent: ");
		strcat(requestBuf, DEFAULT_USER_AGENT);
		strcat(requestBuf, "/");
		strcat(requestBuf, HTTP_FETCHER_VERSION);
		strcat(requestBuf, "\r\n");
	} else if (!hideUserAgent) {
		strcat(requestBuf, "User-Agent: ");
		strcat(requestBuf, userAgent);
		strcat(requestBuf, "\r\n");
	}
	if (auth != NULL) {
		strcat(requestBuf, "Authorization: Basic ");
		strcat(requestBuf, auth);
		strcat(requestBuf, "\r\n");
	}
	strcat(requestBuf, "\r\n");

	printf("[HTTP] creating connection ...\n");
	sock = makeSocket(host);   /* errorSource set within makeSocket */
	if (sock == -1) {
		free(url);
		return -1;
	}
	printf("[HTTP] sending request \n");
	if (write(sock, requestBuf, strlen(requestBuf)) == -1) {
		close(sock);
		free(url);
		errorSource = ERRNO;
		return -1;
	}

	printf("[HTTP] receiving header\n");
	/* Grab enough of the response to get the metadata */
	ret = _http_read_header(sock, headerBuf); /* errorSource set within */
	if (ret < 0) {
		close(sock);
		free(url);
		return -1;
	}
	printf("[HTTP] receiving content\n");

	/* Get the return code */
	charIndex = strstr(headerBuf, "HTTP/");
	if (charIndex == NULL) {
		close(sock);
		free(url);
		errorSource = FETCHER_ERROR;
		http_errno = HF_FRETURNCODE;
		return -1;
	}
	while (*charIndex != ' ')
		charIndex++;
	charIndex++;

	ret = sscanf(charIndex, "%i", &i);
	if (ret != 1) {
		close(sock);
		free(url);
		errorSource = FETCHER_ERROR;
		http_errno = HF_CRETURNCODE;
		return -1;
	}
	if (i < 200 || i > 299) {
		close(sock);
		free(url);
		errorInt = i; /* Status code, to be inserted in error string */
		errorSource = FETCHER_ERROR;
		http_errno = HF_STATUSCODE;
		return -1;
	}

	/*
	 * Parse out about how big the data segment is.
	 * Note that under current HTTP standards (1.1 and prior), the
	 * Content-Length field is not guaranteed to be accurate or even present.
	 * I just use it here so I can allocate a ballpark amount of memory.
	 *
	 * Note that some servers use different capitalization
	 */
	charIndex = strstr(headerBuf, "Content-Length:");
	if (charIndex == NULL)
		charIndex = strstr(headerBuf, "Content-length:");

	if (charIndex != NULL) {
		ret = sscanf(charIndex + strlen("content-length: "), "%i",
		             &contentLength);
		if (ret < 1) {
			close(sock);
			free(url);
			errorSource = FETCHER_ERROR;
			http_errno = HF_CONTENTLEN;
			return -1;
		}
	}

	/* Allocate enough memory to hold the page */
	if (contentLength == -1)
		contentLength = DEFAULT_PAGE_BUF_SIZE;

	pageBuf = (char *)malloc(contentLength + 1);
	if (pageBuf == NULL) {
		close(sock);
		free(url);
		errorSource = ERRNO;
		return -1;
	}

	/* Begin reading the body of the file */
	while (ret > 0) {
		FD_ZERO(&rfds);
		FD_SET(sock, &rfds);
		tv.tv_sec = timeout;
		tv.tv_usec = 0;

		if (timeout >= 0)
			selectRet = select(sock + 1, &rfds, NULL, NULL, &tv);
		else  /* No timeout, can block indefinately */
			selectRet = select(sock + 1, &rfds, NULL, NULL, NULL);

		if (selectRet == 0 && timeout < 0) {
			errorSource = FETCHER_ERROR;
			http_errno = HF_DATATIMEOUT;
			errorInt = timeout;
			close(sock);
			free(url);
			free(pageBuf);
			return -1;
		} else if (selectRet == -1) {
			close(sock);
			free(url);
			free(pageBuf);
			errorSource = ERRNO;
			return -1;
		}

		ret = read(sock, pageBuf + bytesRead, contentLength);
		if (ret == -1) {
			close(sock);
			free(url);
			free(pageBuf);
			errorSource = ERRNO;
			return -1;
		}

		bytesRead += ret;

		if (ret > 0) {
			/* To be tolerant of inaccurate Content-Length fields, we'll
			 * allocate another read-sized chunk to make sure we have
			 * enough room.
			 */
			pageBuf = (char *)realloc(pageBuf, bytesRead + contentLength);
			if (pageBuf == NULL) {
				close(sock);
				free(url);
				free(pageBuf);
				errorSource = ERRNO;
				return -1;
			}
		}
		printf("[HTTP] read %d bytes\n", ret);
	}

	/*
	 * The download buffer is too large.  Trim off the safety padding.
	 */
	pageBuf = (char *)realloc(pageBuf, bytesRead);
	/* pageBuf shouldn't be null, since we're _shrinking_ the buffer,
	 * and if it DID fail, we could go on with the too-large buffer,
	 * but something would DEFINATELY be wrong, so we'll just give
	 * an error message */
	if (pageBuf == NULL) {
		close(sock);
		free(url);
		free(pageBuf);
		errorSource = ERRNO;
		return -1;
	}

	if (fileBuf == NULL) /* They just wanted us to "hit" the url */
		free(pageBuf);
	else
		*fileBuf = pageBuf;

	close(sock);
	free(url);
	return bytesRead;
}



/*
 * Changes the User Agent.  Returns 0 on success, -1 on error.
 */
int http_setUserAgent(const char *newAgent)
{
	char *tmp;

	if (newAgent == NULL) {
		if (freeOldAgent) free(userAgent);
		userAgent = NULL;
		hideUserAgent = 1;
	} else {
		tmp = (char *)malloc(strlen(newAgent));
		if (tmp == NULL) {
			errorSource = ERRNO;
			return -1;
		}
		if (freeOldAgent) free(userAgent);
		userAgent = tmp;
		strcpy(userAgent, newAgent);
		freeOldAgent = 1;
		hideUserAgent = 0;
	}

	return 0;
}



/*
 * Changes the Referer.  Returns 0 on success, -1 on error
 */
int http_setReferer(const char *newReferer)
{
	char *tmp;

	if (newReferer == NULL) {
		if (freeOldReferer) free(referer);
		referer = NULL;
		hideReferer = 1;
	} else {
		tmp = (char *)malloc(strlen(newReferer));
		if (tmp == NULL) {
			errorSource = ERRNO;
			return -1;
		}
		if (freeOldReferer) free(referer);
		referer = tmp;
		strcpy(referer, newReferer);
		freeOldReferer = 1;
		hideReferer = 0;
	}

	return 0;
}
int http_setAuth(const char *user, const char *pass)
{
	unsigned char plain[1024];
	char ec64[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
	char *b64;
	int i, j, c, len;
	char o = 0;
	/* base64 encode user and pass */
	if ((user == NULL) || (pass == NULL)) { /* bad input or request to clean up */
		if (auth != NULL) free(auth); /* free old auth */
		auth = NULL;
		return -1;
	}

	snprintf((char *)plain, 1024, "%s:%s", user, pass);
	len = strlen((char *)plain);
	b64 = (char*)malloc(len * 4 + 1);
	i = j = c = 0;
	while (i < len || c != 0) {
		switch (c) {
		case 0:
			o = ec64[ plain[i] >> 2 ];
			i++;
			break;
		case 1:
			o = ec64[((plain[i-1] & 0x3) << 4) | (plain[i] >> 4)];
			i++;
			break;
		case 2:
			o = (i >= len) ? '=' : ec64[((plain[i-1] & 0xf) << 2) | (plain[i] >> 6)];
			break;
		case 3:
			o = (i >= len) ? '=' : ec64[ plain[i] & 0x3f];
			i++;
			break;
		}
		b64[j] = o;
		c = (c + 1) % 4;
		j++;
	}
	b64[j] = 0;
	if (auth != NULL) free(auth); /* free old auth */
	auth = b64;
	return 0;


}




/*
 * Changes the amount of time that HTTP Fetcher will wait for data
 * before timing out on reads
 */
void http_setTimeout(int seconds)
{
	timeout = seconds;
}



/*
 * Puts the filename portion of the url into 'filename'.
 * Returns:
 * 0 on success
 * 1 when url contains no end filename (i.e., 'www.foo.com/'),
 *  and **filename should not be assumed to be valid
 * -1 on error
 */
int http_parseFilename(const char *url, char **filename)
{
	char *ptr;

	if (url == NULL) {
		errorSource = FETCHER_ERROR;
		http_errno = HF_NULLURL;
		return -1;
	}

	ptr = (char *)rindex(url, '/');
	if (ptr == NULL)
		/* Root level request, apparently */
		return 1;

	ptr++;
	if (*ptr == '\0') return 1;

	*filename = (char *)malloc(strlen(ptr));
	if (*filename == NULL) {
		errorSource = ERRNO;
		return -1;
	}
	strcpy(*filename, ptr);

	return 0;
}



/* Depending on the source of error, calls either perror() or prints
 * an HTTP Fetcher error message to stdout */
void http_perror(const char *string)
{
	if (errorSource == ERRNO)
		perror(string);
	else if (errorSource == H_ERRNO)
		herror(string);
	else if (errorSource == FETCHER_ERROR) {
		char *stringIndex;

		if (strstr(http_errlist[http_errno], "%d") == NULL) {
			fputs(string, stderr);
			fputs(": ", stderr);
			fputs(http_errlist[http_errno], stderr);
			fputs("\n", stderr);
		} else {
			/* The error string has a %d in it, we need to insert errorInt */
			stringIndex = (char *)http_errlist[http_errno];
			while (*stringIndex != '%') {  /* Print up to the %d */
				fputc(*stringIndex, stderr);
				stringIndex++;
			}
			fprintf(stderr, "%d", errorInt); /* Print the number */
			stringIndex += 2;     /* Skip past the %d */
			while (*stringIndex != 0) {  /* Print up to the end NULL */
				fputc(*stringIndex, stderr);
				stringIndex++;
			}
			fputs("\n", stderr);
		}
	}
}



/*
 * Returns a pointer to the current error description message. The
 * message pointed to is only good until the next call to http_strerror(),
 * so if you need to hold on to the message for a while you should make
 * a copy of it
 */
const char *http_strerror(void)
{
	if (errorSource == ERRNO)
		return strerror(errno);
	else if (errorSource == H_ERRNO)
		return hstrerror(h_errno);
	else if (errorSource == FETCHER_ERROR) {
		if (strstr(http_errlist[http_errno], "%d") == NULL)
			return http_errlist[http_errno];
		else {
			/* The error string has a %d in it, we need to insert errorInt.
			 * convertedError[128] has been declared for that purpose */
			char *stringIndex, *originalError;

			originalError = (char *)http_errlist[http_errno];
			convertedError[0] = 0;  /* Start off with NULL */
			stringIndex = strstr(originalError, "%d");
			strncat(convertedError, originalError,  /* Copy up to %d */
			        abs(stringIndex - originalError));
			sprintf(&convertedError[strlen(convertedError)], "%d", errorInt);
			stringIndex += 2;  /* Skip past the %d */
			strcat(convertedError, stringIndex);

			return convertedError;
		}
	}

	return http_errlist[HF_METAERROR]; /* Should NEVER happen */
}


/*
 * Reads the metadata of an HTTP response.
 * Perhaps a little inefficient, as it reads 1 byte at a time, but
 * I don't think it's that much of a loss (most headers aren't HUGE).
 * Returns:
 * # of bytes read on success, or
 * -1 on error
 */
int _http_read_header(int sock, char *headerPtr)
{
	fd_set rfds;
	struct timeval tv;
	int bytesRead = 0, newlines = 0, ret, selectRet;

	while (newlines != 2 && bytesRead != HEADER_BUF_SIZE) {
		FD_ZERO(&rfds);
		FD_SET(sock, &rfds);
		tv.tv_sec = timeout;
		tv.tv_usec = 0;

		if (timeout >= 0)
			selectRet = select(sock + 1, &rfds, NULL, NULL, &tv);
		else  /* No timeout, can block indefinately */
			selectRet = select(sock + 1, &rfds, NULL, NULL, NULL);

		if (selectRet == 0 && timeout < 0) {
			errorSource = FETCHER_ERROR;
			http_errno = HF_HEADTIMEOUT;
			errorInt = timeout;
			return -1;
		} else if (selectRet == -1) {
			errorSource = ERRNO;
			return -1;
		}

		ret = read(sock, headerPtr, 1);
		if (ret == -1) {
			errorSource = ERRNO;
			return -1;
		}
		bytesRead++;

		if (*headerPtr == '\r') {  /* Ignore CR */
			/* Basically do nothing special, just don't set newlines
			 * to 0 */
			headerPtr++;
			continue;
		} else if (*headerPtr == '\n')  /* LF is the separator */
			newlines++;
		else
			newlines = 0;

		headerPtr++;
	}

	headerPtr -= 3;  /* Snip the trailing LF's */
	*headerPtr = '\0';
	return bytesRead;
}



/*
 * Opens a TCP socket and returns the descriptor
 * Returns:
 * socket descriptor, or
 * -1 on error
 */
int makeSocket(const char *host)
{
	int sock;          /* Socket descriptor */
	struct sockaddr_in sa;       /* Socket address */
	struct hostent *hp;        /* Host entity */
	int ret;

	hp = gethostbyname(host);
	if (hp == NULL) {
		errorSource = H_ERRNO;
		return -1;
	}

	/* Copy host address from hostent to (server) socket address */
	memcpy((char *)&sa.sin_addr, (char *)hp->h_addr, hp->h_length);
	sa.sin_family = hp->h_addrtype;  /* Set service sin_family to PF_INET */
	sa.sin_port = htons(PORT_NUMBER); /* Put portnum into sockaddr */

	sock = socket(hp->h_addrtype, SOCK_STREAM, 0);
	if (sock == -1) {
		errorSource = ERRNO;
		return -1;
	}

	ret = connect(sock, (struct sockaddr *) & sa, sizeof(sa));
	if (ret == -1) {
		errorSource = ERRNO;
		return -1;
	}

	return sock;
}