voidarc/omnisearch
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

those who commit

Browse Source
This commit is contained in:
frosty
2026-03-10 02:32:51 -04:00
parent 24cec7a350
commit a11bf8bb6c
19 changed files with 1537 additions and 1284 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
src/Config.c
View File

@@ -24,7 +24,8 @@ int load_config(const char *filename, Config *config) {
char *end = strchr(line, ']');
if (end) {
*end = '\0';
snprintf(section, sizeof(section), "%.*s", (int)(sizeof(section) - 1), line + 1);
snprintf(section, sizeof(section), "%.*s", (int)(sizeof(section) - 1),
line + 1);
section[sizeof(section) - 1] = '\0';
}
continue;
@@ -36,8 +37,10 @@ int load_config(const char *filename, Config *config) {
char *key = line;
char *value = delimiter + 1;
while (*key == ' ' || *key == '\t') key++;
while (*value == ' ' || *value == '\t') value++;
while (*key == ' ' || *key == '\t')
key++;
while (*value == ' ' || *value == '\t')
value++;
char *key_end = key + strlen(key) - 1;
while (key_end > key && (*key_end == ' ' || *key_end == '\t')) {
@@ -46,12 +49,14 @@ int load_config(const char *filename, Config *config) {
}
char *value_end = value + strlen(value) - 1;
while (value_end > value && (*value_end == ' ' || *value_end == '\t' || *value_end == '"' || *value_end == '\'')) {
while (value_end > value && (*value_end == ' ' || *value_end == '\t' ||
*value_end == '"' || *value_end == '\'')) {
*value_end = '\0';
value_end--;
}
while (*value == '"' || *value == '\'') value++;
while (*value == '"' || *value == '\'')
value++;
if (strcmp(section, "server") == 0) {
if (strcmp(key, "host") == 0) {
@@ -65,7 +70,8 @@ int load_config(const char *filename, Config *config) {
strncpy(config->proxy, value, sizeof(config->proxy) - 1);
config->proxy[sizeof(config->proxy) - 1] = '\0';
} else if (strcmp(key, "list_file") == 0) {
strncpy(config->proxy_list_file, value, sizeof(config->proxy_list_file) - 1);
strncpy(config->proxy_list_file, value,
sizeof(config->proxy_list_file) - 1);
config->proxy_list_file[sizeof(config->proxy_list_file) - 1] = '\0';
} else if (strcmp(key, "max_retries") == 0) {
config->max_proxy_retries = atoi(value);
@@ -80,4 +86,4 @@ int load_config(const char *filename, Config *config) {
fclose(file);
return 0;
}
}

2
src/Config.h
View File

@@ -13,4 +13,4 @@ typedef struct {
int load_config(const char *filename, Config *config);
#endif
#endif

41
src/Infobox/Calculator.c
View File

@@ -1,9 +1,9 @@
#include "Calculator.h"
#include <ctype.h>
#include <math.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include <ctype.h>
static char logic_log[4096];
@@ -15,7 +15,8 @@ typedef struct {
static double parse_expression(Parser *p);
static void skip_ws(Parser *p) {
while (p->buffer[p->pos] == ' ') p->pos++;
while (p->buffer[p->pos] == ' ')
p->pos++;
}
static double parse_factor(Parser *p) {
@@ -27,7 +28,8 @@ static double parse_factor(Parser *p) {
if (p->buffer[p->pos] == '(') {
p->pos++;
double res = parse_expression(p);
if (p->buffer[p->pos] == ')') p->pos++;
if (p->buffer[p->pos] == ')')
p->pos++;
return res;
}
char *endptr;
@@ -50,7 +52,7 @@ static double parse_term(Parser *p) {
char step[256];
snprintf(step, sizeof(step), "<div>%g %c %g = <b>%g</b></div>", old, op,
right, left);
right, left);
strncat(logic_log, step, sizeof(logic_log) - strlen(logic_log) - 1);
} else
break;
@@ -72,7 +74,7 @@ static double parse_expression(Parser *p) {
char step[256];
snprintf(step, sizeof(step), "<div>%g %c %g = <b>%g</b></div>", old, op,
right, left);
right, left);
strncat(logic_log, step, sizeof(logic_log) - strlen(logic_log) - 1);
} else
break;
@@ -82,33 +84,34 @@ static double parse_expression(Parser *p) {
double evaluate(const char *expr) {
logic_log[0] = '\0';
if (!expr || strlen(expr) == 0) return 0.0;
if (!expr || strlen(expr) == 0)
return 0.0;
Parser p = {expr, 0};
return parse_expression(&p);
}
InfoBox fetch_calc_data(char *math_input) {
InfoBox info = {NULL, NULL, NULL, NULL};
if (!math_input) return info;
if (!math_input)
return info;
double result = evaluate(math_input);
char html_output[5120];
snprintf(html_output, sizeof(html_output),
"<div class='calc-container' style='line-height: 1.6;'>"
"%s"
"<div style='margin-top: 8px; border-top: 1px solid #eee; "
"padding-top: 8px; font-size: 1.2em;'>"
"<b>%g</b>"
"</div>"
"</div>",
strlen(logic_log) > 0 ? logic_log : "<div>Constant value</div>",
result);
"<div class='calc-container' style='line-height: 1.6;'>"
"%s"
"<div style='margin-top: 8px; border-top: 1px solid #eee; "
"padding-top: 8px; font-size: 1.2em;'>"
"<b>%g</b>"
"</div>"
"</div>",
strlen(logic_log) > 0 ? logic_log : "<div>Constant value</div>",
result);
info.title = strdup("Calculation");
info.extract = strdup(html_output);
info.thumbnail_url =
strdup("/static/calculation.svg");
info.thumbnail_url = strdup("/static/calculation.svg");
info.url = strdup("#");
return info;

197
src/Infobox/Dictionary.c
View File

@@ -1,6 +1,7 @@
#include "Dictionary.h"
#include "../Proxy/Proxy.h"
#include "../Scraping/Scraping.h"
#include <ctype.h>
#include <curl/curl.h>
#include <libxml/HTMLparser.h>
#include <libxml/xpath.h>
@@ -8,42 +9,60 @@
#include <stdlib.h>
#include <string.h>
#include <strings.h>
#include <ctype.h>
static const char *PREFIXES[] = {
"what is the definition of ", "what's the definition of ",
"what is the meaning of ", "what's the meaning of ",
"what does the word ", "definition of ", "meaning of ", "def of ",
"define ", "definition ", "define:", "def ", "def:",
"what does ", "what is ", "what's ", "whats ",
"meaning ", "dictionary ", "dict ", NULL
};
static const char *PREFIXES[] = {"what is the definition of ",
"what's the definition of ",
"what is the meaning of ",
"what's the meaning of ",
"what does the word ",
"definition of ",
"meaning of ",
"def of ",
"define ",
"definition ",
"define:",
"def ",
"def:",
"what does ",
"what is ",
"what's ",
"whats ",
"meaning ",
"dictionary ",
"dict ",
NULL};
static const char *SUFFIXES[] = {
" definition", " def", " meaning", " mean", " means",
" dictionary", " dict", " define", " defined",
" definition?", " def?", " meaning?", " mean?", " means?",
" in english", " in english?", NULL
};
" definition", " def", " meaning", " mean", " means",
" dictionary", " dict", " define", " defined", " definition?",
" def?", " meaning?", " mean?", " means?", " in english",
" in english?", NULL};
static const char *SKIP_WORDS[] = {"of ", "the ", "a ", "an ", NULL};
static const char *strcasestr_impl(const char *haystack, const char *needle) {
if (!haystack || !needle || !*needle) return haystack;
if (!haystack || !needle || !*needle)
return haystack;
size_t len = strlen(needle);
for (const char *h = haystack; *h; h++) {
if (strncasecmp(h, needle, len) == 0) return h;
if (strncasecmp(h, needle, len) == 0)
return h;
}
return NULL;
}
struct MemStruct { char *memory; size_t size; };
struct MemStruct {
char *memory;
size_t size;
};
static size_t WriteCallback(void *contents, size_t size, size_t nmemb, void *userp) {
static size_t WriteCallback(void *contents, size_t size, size_t nmemb,
void *userp) {
size_t realsize = size * nmemb;
struct MemStruct *mem = (struct MemStruct *)userp;
char *ptr = realloc(mem->memory, mem->size + realsize + 1);
if (!ptr) return 0;
if (!ptr)
return 0;
mem->memory = ptr;
memcpy(&(mem->memory[mem->size]), contents, realsize);
mem->size += realsize;
@@ -53,40 +72,57 @@ static size_t WriteCallback(void *contents, size_t size, size_t nmemb, void *use
static char *xpath_text(xmlDocPtr doc, const char *xpath) {
xmlXPathContextPtr ctx = xmlXPathNewContext(doc);
if (!ctx) return NULL;
if (!ctx)
return NULL;
xmlXPathObjectPtr obj = xmlXPathEvalExpression((const xmlChar *)xpath, ctx);
xmlXPathFreeContext(ctx);
if (!obj || !obj->nodesetval || obj->nodesetval->nodeNr == 0) {
if (obj) xmlXPathFreeObject(obj);
if (obj)
xmlXPathFreeObject(obj);
return NULL;
}
xmlChar *content = xmlNodeGetContent(obj->nodesetval->nodeTab[0]);
char *result = content ? strdup((char *)content) : NULL;
if (content) xmlFree(content);
if (content)
xmlFree(content);
xmlXPathFreeObject(obj);
return result;
}
static char *build_html(const char *word, const char *pron, const char *pos,
const char *def, const char *ex) {
static char *build_html(const char *word, const char *pron, const char *pos,
const char *def, const char *ex) {
char html[4096];
int n = snprintf(html, sizeof(html), "<div class='dict-container' style='line-height: 1.6;'>");
if (word) n += snprintf(html + n, sizeof(html) - n,
"<div style='font-size: 1.3em; font-weight: bold; margin-bottom: 4px;'>%s</div>", word);
if (pron) n += snprintf(html + n, sizeof(html) - n,
"<div style='color: #666; margin-bottom: 8px;'>/%s/</div>", pron);
if (pos) n += snprintf(html + n, sizeof(html) - n,
"<div style='font-style: italic; color: #888; margin-bottom: 8px;'>%s</div>", pos);
if (def) n += snprintf(html + n, sizeof(html) - n,
"<div style='margin-bottom: 8px;'>%s</div>", def);
if (ex) n += snprintf(html + n, sizeof(html) - n,
"<div style='color: #555; font-style: italic; margin-top: 8px;'>\"%s\"</div>", ex);
int n = snprintf(html, sizeof(html),
"<div class='dict-container' style='line-height: 1.6;'>");
if (word)
n += snprintf(html + n, sizeof(html) - n,
"<div style='font-size: 1.3em; font-weight: bold; "
"margin-bottom: 4px;'>%s</div>",
word);
if (pron)
n += snprintf(html + n, sizeof(html) - n,
"<div style='color: #666; margin-bottom: 8px;'>/%s/</div>",
pron);
if (pos)
n += snprintf(html + n, sizeof(html) - n,
"<div style='font-style: italic; color: #888; margin-bottom: "
"8px;'>%s</div>",
pos);
if (def)
n += snprintf(html + n, sizeof(html) - n,
"<div style='margin-bottom: 8px;'>%s</div>", def);
if (ex)
n += snprintf(html + n, sizeof(html) - n,
"<div style='color: #555; font-style: italic; margin-top: "
"8px;'>\"%s\"</div>",
ex);
snprintf(html + n, sizeof(html) - n, "</div>");
return strdup(html);
}
static char *extract_word(const char *query) {
if (!query) return NULL;
if (!query)
return NULL;
const char *start = query;
@@ -98,9 +134,11 @@ static char *extract_word(const char *query) {
}
}
while (*start == ' ') start++;
while (*start == ' ')
start++;
char *word = strdup(start);
if (!word) return NULL;
if (!word)
return NULL;
int changed = 1;
while (changed) {
@@ -130,29 +168,37 @@ static char *extract_word(const char *query) {
}
size_t len = strlen(word);
while (len > 0 && (word[len-1] == ' ' || word[len-1] == '?' ||
word[len-1] == '!' || word[len-1] == '.')) {
while (len > 0 && (word[len - 1] == ' ' || word[len - 1] == '?' ||
word[len - 1] == '!' || word[len - 1] == '.')) {
word[--len] = '\0';
}
if (len == 0) { free(word); return NULL; }
if (len == 0) {
free(word);
return NULL;
}
for (size_t i = 0; i < len; i++) word[i] = tolower((unsigned char)word[i]);
for (size_t i = 0; i < len; i++)
word[i] = tolower((unsigned char)word[i]);
char *space = strchr(word, ' ');
if (space) *space = '\0';
if (space)
*space = '\0';
return word;
}
int is_dictionary_query(const char *query) {
if (!query) return 0;
if (!query)
return 0;
for (int i = 0; PREFIXES[i]; i++) {
size_t len = strlen(PREFIXES[i]);
if (strncasecmp(query, PREFIXES[i], len) == 0) {
const char *after = query + len;
while (*after == ' ') after++;
if (*after != '\0') return 1;
while (*after == ' ')
after++;
if (*after != '\0')
return 1;
}
}
@@ -160,23 +206,29 @@ int is_dictionary_query(const char *query) {
const char *pos = strcasestr_impl(query, SUFFIXES[i]);
if (pos) {
const char *after = pos + strlen(SUFFIXES[i]);
while (*after == ' ' || *after == '?' || *after == '!' || *after == '.') after++;
if (*after == '\0' && pos > query && (pos - query) < 100) return 1;
while (*after == ' ' || *after == '?' || *after == '!' || *after == '.')
after++;
if (*after == '\0' && pos > query && (pos - query) < 100)
return 1;
}
}
if (strncasecmp(query, "what is ", 8) == 0 ||
strncasecmp(query, "what's ", 7) == 0 ||
strncasecmp(query, "whats ", 6) == 0) {
const char *word = query + (strncasecmp(query, "what is ", 8) == 0 ? 8 :
strncasecmp(query, "what's ", 7) == 0 ? 7 : 6);
const char *articles[] = {"the ", "your ", "my ", "his ", "her ", "their ",
"our ", "this ", "that ", "these ", "those ", "a ", "an ", NULL};
if (strncasecmp(query, "what is ", 8) == 0 ||
strncasecmp(query, "what's ", 7) == 0 ||
strncasecmp(query, "whats ", 6) == 0) {
const char *word = query + (strncasecmp(query, "what is ", 8) == 0 ? 8
: strncasecmp(query, "what's ", 7) == 0 ? 7
: 6);
const char *articles[] = {"the ", "your ", "my ", "his ", "her ",
"their ", "our ", "this ", "that ", "these ",
"those ", "a ", "an ", NULL};
for (int i = 0; articles[i]; i++) {
if (strncasecmp(word, articles[i], strlen(articles[i])) == 0) return 0;
if (strncasecmp(word, articles[i], strlen(articles[i])) == 0)
return 0;
}
const char *space = strchr(word, ' ');
if (!space || *(space + 1) == '\0' || *(space + 1) == '?') return 1;
if (!space || *(space + 1) == '\0' || *(space + 1) == '?')
return 1;
}
return 0;
@@ -184,10 +236,14 @@ int is_dictionary_query(const char *query) {
char *construct_dictionary_url(const char *query) {
char *word = extract_word(query);
if (!word) return NULL;
if (!word)
return NULL;
CURL *curl = curl_easy_init();
if (!curl) { free(word); return NULL; }
if (!curl) {
free(word);
return NULL;
}
char *escaped = curl_easy_escape(curl, word, 0);
const char *base = "https://dictionary.cambridge.org/dictionary/english/";
@@ -207,10 +263,14 @@ InfoBox fetch_dictionary_data(const char *query) {
InfoBox info = {NULL, NULL, NULL, NULL};
char *url = construct_dictionary_url(query);
if (!url) return info;
if (!url)
return info;
CURL *curl = curl_easy_init();
if (!curl) { free(url); return info; }
if (!curl) {
free(url);
return info;
}
struct MemStruct chunk = {malloc(1), 0};
curl_easy_setopt(curl, CURLOPT_URL, url);
@@ -222,10 +282,13 @@ InfoBox fetch_dictionary_data(const char *query) {
if (curl_easy_perform(curl) == CURLE_OK && chunk.size > 0) {
htmlDocPtr doc = htmlReadMemory(chunk.memory, chunk.size, url, NULL,
HTML_PARSE_RECOVER | HTML_PARSE_NOERROR | HTML_PARSE_NOWARNING);
HTML_PARSE_RECOVER | HTML_PARSE_NOERROR |
HTML_PARSE_NOWARNING);
if (doc) {
char *word = xpath_text(doc, "//span[@class='hw dhw']");
char *pron = xpath_text(doc, "//span[@class='us dpron-i']//span[@class='ipa dipa lpr-2 lpl-1']");
char *pron = xpath_text(
doc,
"//span[@class='us dpron-i']//span[@class='ipa dipa lpr-2 lpl-1']");
char *pos = xpath_text(doc, "//span[@class='pos dpos']");
char *def = xpath_text(doc, "(//div[@class='def ddef_d db'])[1]");
char *ex = xpath_text(doc, "(//span[@class='eg deg'])[1]");
@@ -237,7 +300,11 @@ InfoBox fetch_dictionary_data(const char *query) {
info.url = strdup(url);
}
free(word); free(pron); free(pos); free(def); free(ex);
free(word);
free(pron);
free(pos);
free(def);
free(ex);
xmlFreeDoc(doc);
}
}
@@ -246,4 +313,4 @@ InfoBox fetch_dictionary_data(const char *query) {
free(chunk.memory);
free(url);
return info;
}
}

2
src/Infobox/Dictionary.h
View File

@@ -7,4 +7,4 @@ InfoBox fetch_dictionary_data(const char *word);
char *construct_dictionary_url(const char *word);
int is_dictionary_query(const char *query);
#endif
#endif

633
src/Infobox/UnitConversion.c
View File

@@ -23,49 +23,73 @@ typedef struct {
} UnitDef;
static const UnitDef UNITS[] = {
{"metre", {"m", "metres", "meter", "meters"}, UNIT_LENGTH, 1.0},
{"kilometre", {"km", "kilometres", "kilometer", "kilometers"}, UNIT_LENGTH, 1000.0},
{"centimetre", {"cm", "centimetres", "centimeter", "centimeters"}, UNIT_LENGTH, 0.01},
{"millimetre", {"mm", "millimetres", "millimeter", "millimeters"}, UNIT_LENGTH, 0.001},
{"mile", {"mi", "miles"}, UNIT_LENGTH, 1609.344},
{"yard", {"yd", "yards"}, UNIT_LENGTH, 0.9144},
{"foot", {"ft", "feet", "'"}, UNIT_LENGTH, 0.3048},
{"inch", {"in", "inches", "\""}, UNIT_LENGTH, 0.0254},
{"metre", {"m", "metres", "meter", "meters"}, UNIT_LENGTH, 1.0},
{"kilometre",
{"km", "kilometres", "kilometer", "kilometers"},
UNIT_LENGTH,
1000.0},
{"centimetre",
{"cm", "centimetres", "centimeter", "centimeters"},
UNIT_LENGTH,
0.01},
{"millimetre",
{"mm", "millimetres", "millimeter", "millimeters"},
UNIT_LENGTH,
0.001},
{"mile", {"mi", "miles"}, UNIT_LENGTH, 1609.344},
{"yard", {"yd", "yards"}, UNIT_LENGTH, 0.9144},
{"foot", {"ft", "feet", "'"}, UNIT_LENGTH, 0.3048},
{"inch", {"in", "inches", "\""}, UNIT_LENGTH, 0.0254},
{"kilogram", {"kg", "kilograms", "kilo", "kilos"}, UNIT_WEIGHT, 1.0},
{"gram", {"g", "grams"}, UNIT_WEIGHT, 0.001},
{"milligram", {"mg", "milligrams"}, UNIT_WEIGHT, 0.000001},
{"pound", {"lb", "lbs", "pounds"}, UNIT_WEIGHT, 0.453592},
{"ounce", {"oz", "ounces"}, UNIT_WEIGHT, 0.0283495},
{"tonne", {"tonnes", "tons", "ton"}, UNIT_WEIGHT, 1000.0},
{"stone", {"st", "stones"}, UNIT_WEIGHT, 6.35029},
{"kilogram", {"kg", "kilograms", "kilo", "kilos"}, UNIT_WEIGHT, 1.0},
{"gram", {"g", "grams"}, UNIT_WEIGHT, 0.001},
{"milligram", {"mg", "milligrams"}, UNIT_WEIGHT, 0.000001},
{"pound", {"lb", "lbs", "pounds"}, UNIT_WEIGHT, 0.453592},
{"ounce", {"oz", "ounces"}, UNIT_WEIGHT, 0.0283495},
{"tonne", {"tonnes", "tons", "ton"}, UNIT_WEIGHT, 1000.0},
{"stone", {"st", "stones"}, UNIT_WEIGHT, 6.35029},
{"celsius", {"c", "°c", "degrees celsius", "degrees c"}, UNIT_TEMP, 1.0},
{"fahrenheit", {"f", "°f", "degrees fahrenheit", "degrees f"}, UNIT_TEMP, 1.0},
{"kelvin", {"k", "degrees kelvin", "degrees k"}, UNIT_TEMP, 1.0},
{"celsius", {"c", "°c", "degrees celsius", "degrees c"}, UNIT_TEMP, 1.0},
{"fahrenheit",
{"f", "°f", "degrees fahrenheit", "degrees f"},
UNIT_TEMP,
1.0},
{"kelvin", {"k", "degrees kelvin", "degrees k"}, UNIT_TEMP, 1.0},
{"litre", {"l", "litres", "liter", "liters"}, UNIT_VOLUME, 1.0},
{"millilitre", {"ml", "millilitres", "milliliter", "milliliters"}, UNIT_VOLUME, 0.001},
{"gallon", {"gal", "gallons"}, UNIT_VOLUME, 3.78541},
{"quart", {"qt", "quarts"}, UNIT_VOLUME, 0.946353},
{"pint", {"pt", "pints"}, UNIT_VOLUME, 0.473176},
{"cup", {"cups"}, UNIT_VOLUME, 0.236588},
{"fluid ounce", {"fl oz", "fluid ounces"}, UNIT_VOLUME, 0.0295735},
{"litre", {"l", "litres", "liter", "liters"}, UNIT_VOLUME, 1.0},
{"millilitre",
{"ml", "millilitres", "milliliter", "milliliters"},
UNIT_VOLUME,
0.001},
{"gallon", {"gal", "gallons"}, UNIT_VOLUME, 3.78541},
{"quart", {"qt", "quarts"}, UNIT_VOLUME, 0.946353},
{"pint", {"pt", "pints"}, UNIT_VOLUME, 0.473176},
{"cup", {"cups"}, UNIT_VOLUME, 0.236588},
{"fluid ounce", {"fl oz", "fluid ounces"}, UNIT_VOLUME, 0.0295735},
{"square metre", {"sqm", "sq m", "m2", "square metres"}, UNIT_AREA, 1.0},
{"square foot", {"sqft", "sq ft", "ft2", "square feet"}, UNIT_AREA, 0.092903},
{"square kilometre", {"sqkm", "sq km", "km2", "square kilometres"}, UNIT_AREA, 1000000.0},
{"square mile", {"sqmi", "sq mi", "mi2", "square miles"}, UNIT_AREA, 2589988.0},
{"acre", {"acres"}, UNIT_AREA, 4046.86},
{"hectare", {"ha", "hectares"}, UNIT_AREA, 10000.0},
{"square metre", {"sqm", "sq m", "m2", "square metres"}, UNIT_AREA, 1.0},
{"square foot",
{"sqft", "sq ft", "ft2", "square feet"},
UNIT_AREA,
0.092903},
{"square kilometre",
{"sqkm", "sq km", "km2", "square kilometres"},
UNIT_AREA,
1000000.0},
{"square mile",
{"sqmi", "sq mi", "mi2", "square miles"},
UNIT_AREA,
2589988.0},
{"acre", {"acres"}, UNIT_AREA, 4046.86},
{"hectare", {"ha", "hectares"}, UNIT_AREA, 10000.0},
{"second", {"sec", "seconds", "s"}, UNIT_TIME, 1.0},
{"minute", {"min", "minutes"}, UNIT_TIME, 60.0},
{"hour", {"hr", "hours", "h"}, UNIT_TIME, 3600.0},
{"day", {"days", "d"}, UNIT_TIME, 86400.0},
{"week", {"weeks", "wk"}, UNIT_TIME, 604800.0},
{"month", {"months", "mo"}, UNIT_TIME, 2629746.0},
{"year", {"years", "yr"}, UNIT_TIME, 31556952.0},
{"second", {"sec", "seconds", "s"}, UNIT_TIME, 1.0},
{"minute", {"min", "minutes"}, UNIT_TIME, 60.0},
{"hour", {"hr", "hours", "h"}, UNIT_TIME, 3600.0},
{"day", {"days", "d"}, UNIT_TIME, 86400.0},
{"week", {"weeks", "wk"}, UNIT_TIME, 604800.0},
{"month", {"months", "mo"}, UNIT_TIME, 2629746.0},
{"year", {"years", "yr"}, UNIT_TIME, 31556952.0},
};
static const int UNIT_COUNT = sizeof(UNITS) / sizeof(UNITS[0]);
@@ -75,70 +99,73 @@ static int is_whitespace(char c) {
}
static const UnitDef *find_unit(const char *str) {
if (!str || !*str) return NULL;
if (!str || !*str)
return NULL;
size_t len = strlen(str);
char normalized[64] = {0};
size_t j = 0;
for (size_t i = 0; i < len && j < 63; i++) {
if ((unsigned char)str[i] == 0xC2 && (unsigned char)str[i+1] == 0xB0) {
i++;
continue;
}
if (str[i] == '^' && i + 1 < len && str[i + 1] == '2') {
normalized[j++] = '2';
i++;
continue;
}
normalized[j++] = tolower((unsigned char)str[i]);
if ((unsigned char)str[i] == 0xC2 && (unsigned char)str[i + 1] == 0xB0) {
i++;
continue;
}
if (str[i] == '^' && i + 1 < len && str[i + 1] == '2') {
normalized[j++] = '2';
i++;
continue;
}
normalized[j++] = tolower((unsigned char)str[i]);
}
normalized[j] = '\0';
for (int i = 0; i < UNIT_COUNT; i++) {
if (strcmp(normalized, UNITS[i].name) == 0) return &UNITS[i];
for (int k = 0; k < 4 && UNITS[i].alias[k]; k++) {
if (strcmp(normalized, UNITS[i].alias[k]) == 0) return &UNITS[i];
}
if (strcmp(normalized, UNITS[i].name) == 0)
return &UNITS[i];
for (int k = 0; k < 4 && UNITS[i].alias[k]; k++) {
if (strcmp(normalized, UNITS[i].alias[k]) == 0)
return &UNITS[i];
}
}
return NULL;
}
int is_unit_conv_query(const char *query) {
if (!query) return 0;
if (!query)
return 0;
const char *patterns[] = {
" to ", " in ", " into ",
" = ", " equals ", " equal ",
" convert ", " conversion ",
" -> ", " → ",
NULL
};
const char *patterns[] = {" to ", " in ", " into ", " = ",
" equals ", " equal ", " convert ", " conversion ",
" -> ", " → ", NULL};
int has_pattern = 0;
for (int i = 0; patterns[i]; i++) {
if (strstr(query, patterns[i])) {
has_pattern = 1;
break;
}
if (strstr(query, patterns[i])) {
has_pattern = 1;
break;
}
}
if (!has_pattern) {
const char *last_space = strrchr(query, ' ');
if (last_space) {
const UnitDef *u = find_unit(last_space + 1);
if (u) {
const char *before = query;
while (*before && is_whitespace(*before)) before++;
const char *num_end = before;
while (*num_end &&
(isdigit(*num_end) || *num_end == '.' || *num_end == '-' ||
*num_end == '+' || *num_end == '/' || *num_end == '\'' || *num_end == '"')) {
num_end++;
const char *last_space = strrchr(query, ' ');
if (last_space) {
const UnitDef *u = find_unit(last_space + 1);
if (u) {
const char *before = query;
while (*before && is_whitespace(*before))
before++;
const char *num_end = before;
while (*num_end &&
(isdigit(*num_end) || *num_end == '.' || *num_end == '-' ||
*num_end == '+' || *num_end == '/' || *num_end == '\'' ||
*num_end == '"')) {
num_end++;
}
if (num_end > before)
has_pattern = 1;
}
}
if (num_end > before) has_pattern = 1;
}
}
}
return has_pattern;
@@ -146,65 +173,68 @@ int is_unit_conv_query(const char *query) {
static double parse_value(const char **ptr) {
const char *p = *ptr;
while (*p && is_whitespace(*p)) p++;
while (*p && is_whitespace(*p))
p++;
double value = 0.0;
int has_num = 0;
if (*p == '-' || *p == '+') p++;
if (*p == '-' || *p == '+')
p++;
while (*p >= '0' && *p <= '9') {
value = value * 10 + (*p - '0');
has_num = 1;
p++;
}
if (*p == '.') {
p++;
double frac = 0.1;
while (*p >= '0' && *p <= '9') {
value += (*p - '0') * frac;
frac *= 0.1;
value = value * 10 + (*p - '0');
has_num = 1;
p++;
}
}
if (*p == '/' && has_num) {
p++;
double denom = 0.0;
int has_denom = 0;
while (*p >= '0' && *p <= '9') {
denom = denom * 10 + (*p - '0');
has_denom = 1;
p++;
}
if (has_denom && denom > 0) {
value = value / denom;
}
}
while (*p == '\'' || *p == '"') {
double extra = 0.0;
p++;
while (*p >= '0' && *p <= '9') {
extra = extra * 10 + (*p - '0');
p++;
}
if (*p == '.') {
p++;
double frac = 0.1;
while (*p >= '0' && *p <= '9') {
extra += (*p - '0') * frac;
frac *= 0.1;
p++;
value += (*p - '0') * frac;
frac *= 0.1;
has_num = 1;
p++;
}
}
if (*p == '\'' || *p == '"') p++;
value += extra * (p[-1] == '\'' ? 0.3048 : 0.0254);
if (*p == '/' && has_num) {
p++;
double denom = 0.0;
int has_denom = 0;
while (*p >= '0' && *p <= '9') {
denom = denom * 10 + (*p - '0');
has_denom = 1;
p++;
}
if (has_denom && denom > 0) {
value = value / denom;
}
}
while (*p == '\'' || *p == '"') {
double extra = 0.0;
p++;
while (*p >= '0' && *p <= '9') {
extra = extra * 10 + (*p - '0');
p++;
}
if (*p == '.') {
p++;
double frac = 0.1;
while (*p >= '0' && *p <= '9') {
extra += (*p - '0') * frac;
frac *= 0.1;
p++;
}
}
if (*p == '\'' || *p == '"')
p++;
value += extra * (p[-1] == '\'' ? 0.3048 : 0.0254);
}
if (!has_num) {
*ptr = p;
return 0.0;
*ptr = p;
return 0.0;
}
*ptr = p;
@@ -212,10 +242,13 @@ static double parse_value(const char **ptr) {
}
static int is_separator(char c) {
return is_whitespace(c) || c == ',' || c == '.' || c == '(' || c == ')' || c == '\0';
return is_whitespace(c) || c == ',' || c == '.' || c == '(' || c == ')' ||
c == '\0';
}
static int parse_conversion_query(const char *query, double *value, const UnitDef **from_unit, const UnitDef **to_unit) {
static int parse_conversion_query(const char *query, double *value,
const UnitDef **from_unit,
const UnitDef **to_unit) {
*value = 0;
*from_unit = NULL;
*to_unit = NULL;
@@ -223,127 +256,151 @@ static int parse_conversion_query(const char *query, double *value, const UnitDe
const char *value_end = query;
*value = parse_value(&value_end);
if (value_end == query) return 0;
if (value_end == query)
return 0;
const char *p = value_end;
while (*p && is_whitespace(*p)) p++;
while (*p && is_whitespace(*p))
p++;
size_t remaining = strlen(p);
if (remaining < 2) return 0;
if (remaining < 2)
return 0;
const char *to_keywords[] = {" to ", " in ", " into ", " -> ", " → ", " = ", NULL};
const char *to_keywords[] = {" to ", " in ", " into ", " -> ",
" → ", " = ", NULL};
const char *to_pos = NULL;
size_t keyword_len = 0;
for (int i = 0; to_keywords[i]; i++) {
const char *found = strstr(p, to_keywords[i]);
if (found) {
to_pos = found + strlen(to_keywords[i]);
keyword_len = strlen(to_keywords[i]);
break;
}
const char *found = strstr(p, to_keywords[i]);
if (found) {
to_pos = found + strlen(to_keywords[i]);
keyword_len = strlen(to_keywords[i]);
break;
}
}
if (!to_pos) {
const char *last_space = strrchr(p, ' ');
if (last_space && last_space > p) {
char from_part[64] = {0};
size_t len = last_space - p;
if (len < 63) {
strncpy(from_part, p, len);
*from_unit = find_unit(from_part);
if (*from_unit) {
*to_unit = find_unit(last_space + 1);
return *to_unit ? 1 : 0;
const char *last_space = strrchr(p, ' ');
if (last_space && last_space > p) {
char from_part[64] = {0};
size_t len = last_space - p;
if (len < 63) {
strncpy(from_part, p, len);
*from_unit = find_unit(from_part);
if (*from_unit) {
*to_unit = find_unit(last_space + 1);
return *to_unit ? 1 : 0;
}
}
}
}
}
return 0;
return 0;
}
char from_part[64] = {0};
size_t from_len = to_pos - p - keyword_len;
if (from_len > 63) from_len = 63;
if (from_len > 63)
from_len = 63;
strncpy(from_part, p, from_len);
char *end_from = from_part + from_len;
while (end_from > from_part && is_whitespace(end_from[-1])) end_from--;
while (end_from > from_part && is_whitespace(end_from[-1]))
end_from--;
*end_from = '\0';
*from_unit = find_unit(from_part);
if (!*from_unit) {
char *end = from_part + strlen(from_part);
while (end > from_part) {
while (end > from_part && is_whitespace(end[-1])) end--;
if (end <= from_part) break;
char *start = end;
while (start > from_part && !is_whitespace(start[-1])) start--;
size_t word_len = end - start;
memmove(from_part + word_len + 1, from_part, start - from_part);
from_part[word_len] = ' ';
from_part[word_len + 1] = '\0';
*from_unit = find_unit(from_part);
if (*from_unit) break;
end = start;
}
char *end = from_part + strlen(from_part);
while (end > from_part) {
while (end > from_part && is_whitespace(end[-1]))
end--;
if (end <= from_part)
break;
char *start = end;
while (start > from_part && !is_whitespace(start[-1]))
start--;
size_t word_len = end - start;
memmove(from_part + word_len + 1, from_part, start - from_part);
from_part[word_len] = ' ';
from_part[word_len + 1] = '\0';
*from_unit = find_unit(from_part);
if (*from_unit)
break;
end = start;
}
}
if (!*from_unit) return 0;
if (!*from_unit)
return 0;
while (*to_pos && is_whitespace(*to_pos)) to_pos++;
while (*to_pos && is_whitespace(*to_pos))
to_pos++;
if (!*to_pos) return 0;
if (!*to_pos)
return 0;
char to_part[64] = {0};
size_t to_len = 0;
const char *tp = to_pos;
while (*tp && !is_separator(*tp) && to_len < 63) {
to_part[to_len++] = *tp++;
to_part[to_len++] = *tp++;
}
to_part[to_len] = '\0';
*to_unit = find_unit(to_part);
if (!*to_unit) {
const char *try_ptr = to_pos;
while (*try_ptr && is_whitespace(*try_ptr)) try_ptr++;
char try_buf[64] = {0};
size_t try_len = 0;
while (*try_ptr && try_len < 63) {
try_buf[try_len++] = *try_ptr++;
}
while (try_len > 0) {
*to_unit = find_unit(try_buf);
if (*to_unit) {
strcpy(to_part, try_buf);
break;
const char *try_ptr = to_pos;
while (*try_ptr && is_whitespace(*try_ptr))
try_ptr++;
char try_buf[64] = {0};
size_t try_len = 0;
while (*try_ptr && try_len < 63) {
try_buf[try_len++] = *try_ptr++;
}
while (try_len > 0) {
*to_unit = find_unit(try_buf);
if (*to_unit) {
strcpy(to_part, try_buf);
break;
}
char *last_space = strrchr(try_buf, ' ');
if (!last_space)
break;
*last_space = '\0';
try_len = strlen(try_buf);
}
char *last_space = strrchr(try_buf, ' ');
if (!last_space) break;
*last_space = '\0';
try_len = strlen(try_buf);
}
}
return *to_unit ? 1 : 0;
}
static double convert_temp(double value, const UnitDef *from, const UnitDef *to) {
static double convert_temp(double value, const UnitDef *from,
const UnitDef *to) {
double celsius = 0;
if (strcmp(from->name, "celsius") == 0) celsius = value;
else if (strcmp(from->name, "fahrenheit") == 0) celsius = (value - 32) * 5.0 / 9.0;
else if (strcmp(from->name, "kelvin") == 0) celsius = value - 273.15;
if (strcmp(from->name, "celsius") == 0)
celsius = value;
else if (strcmp(from->name, "fahrenheit") == 0)
celsius = (value - 32) * 5.0 / 9.0;
else if (strcmp(from->name, "kelvin") == 0)
celsius = value - 273.15;
if (strcmp(to->name, "celsius") == 0) return celsius;
else if (strcmp(to->name, "fahrenheit") == 0) return celsius * 9.0 / 5.0 + 32;
else if (strcmp(to->name, "kelvin") == 0) return celsius + 273.15;
if (strcmp(to->name, "celsius") == 0)
return celsius;
else if (strcmp(to->name, "fahrenheit") == 0)
return celsius * 9.0 / 5.0 + 32;
else if (strcmp(to->name, "kelvin") == 0)
return celsius + 273.15;
return 0;
}
static double convert_value(double value, const UnitDef *from, const UnitDef *to) {
if (from->type != to->type) return 0;
static double convert_value(double value, const UnitDef *from,
const UnitDef *to) {
if (from->type != to->type)
return 0;
if (from->type == UNIT_TEMP) {
return convert_temp(value, from, to);
return convert_temp(value, from, to);
}
double base_value = value * from->to_base;
@@ -351,112 +408,124 @@ static double convert_value(double value, const UnitDef *from, const UnitDef *to
}
static void format_number(double val, char *buf, size_t bufsize) {
if (bufsize == 0) return;
if (bufsize == 0)
return;
if (val == 0) {
snprintf(buf, bufsize, "0");
return;
snprintf(buf, bufsize, "0");
return;
}
if (fabs(val) < 0.01 && fabs(val) > 0) {
snprintf(buf, bufsize, "%.2g", val);
snprintf(buf, bufsize, "%.2g", val);
} else if (fabs(val) < 1) {
snprintf(buf, bufsize, "%.2f", val);
char *p = buf + strlen(buf) - 1;
while (p > buf && *p == '0') *p-- = '\0';
if (*p == '.') *p = '\0';
snprintf(buf, bufsize, "%.2f", val);
char *p = buf + strlen(buf) - 1;
while (p > buf && *p == '0')
*p-- = '\0';
if (*p == '.')
*p = '\0';
} else if (fmod(val + 0.0001, 1.0) < 0.0002) {
snprintf(buf, bufsize, "%.0f", val);
snprintf(buf, bufsize, "%.0f", val);
} else {
snprintf(buf, bufsize, "%.2f", val);
char *p = buf + strlen(buf) - 1;
while (p > buf && *p == '0') *p-- = '\0';
if (*p == '.') *p = '\0';
snprintf(buf, bufsize, "%.2f", val);
char *p = buf + strlen(buf) - 1;
while (p > buf && *p == '0')
*p-- = '\0';
if (*p == '.')
*p = '\0';
}
}
static const char *pluralize(const char *unit, double value, char *buf, size_t bufsize) {
static const char *pluralize(const char *unit, double value, char *buf,
size_t bufsize) {
int is_one = (fabs(value - 1.0) < 0.0001 || fabs(value + 1.0) < 0.0001);
size_t len = strlen(unit);
if (len == 0 || bufsize == 0) return unit;
if (len == 0 || bufsize == 0)
return unit;
strncpy(buf, unit, bufsize - 1);
buf[bufsize - 1] = '\0';
if (strcmp(unit, "foot") == 0 || strcmp(unit, "square foot") == 0) {
if (is_one) strcpy(buf, unit);
else strcpy(buf, strcmp(unit, "square foot") == 0 ? "square feet" : "feet");
return buf;
if (is_one)
strcpy(buf, unit);
else
strcpy(buf, strcmp(unit, "square foot") == 0 ? "square feet" : "feet");
return buf;
}
if (strcmp(unit, "inch") == 0 || strcmp(unit, "square inch") == 0) {
if (is_one) strcpy(buf, unit);
else strcpy(buf, strcmp(unit, "square inch") == 0 ? "square inches" : "inches");
return buf;
if (is_one)
strcpy(buf, unit);
else
strcpy(buf,
strcmp(unit, "square inch") == 0 ? "square inches" : "inches");
return buf;
}
if (strcmp(unit, "stone") == 0) {
if (is_one) strcpy(buf, "stone");
else strcpy(buf, "stones");
return buf;
if (is_one)
strcpy(buf, "stone");
else
strcpy(buf, "stones");
return buf;
}
if (strcmp(unit, "celsius") == 0 ||
strcmp(unit, "fahrenheit") == 0 ||
strcmp(unit, "kelvin") == 0) {
strcpy(buf, unit);
return buf;
if (strcmp(unit, "celsius") == 0 || strcmp(unit, "fahrenheit") == 0 ||
strcmp(unit, "kelvin") == 0) {
strcpy(buf, unit);
return buf;
}
if (unit[len-1] == 's' ||
unit[len-1] == 'x' ||
unit[len-1] == 'z' ||
(len >= 2 && unit[len-2] == 'c' && unit[len-1] == 'h') ||
(len >= 2 && unit[len-2] == 's' && unit[len-1] == 'h')) {
if (!is_one) {
buf[len] = 'e';
buf[len+1] = '\0';
}
} else if (unit[len-1] == 'y' && len >= 2 &&
!(unit[len-2] == 'a' || unit[len-2] == 'e' ||
unit[len-2] == 'i' || unit[len-2] == 'o' ||
unit[len-2] == 'u')) {
if (is_one) {
buf[len-1] = '\0';
if (unit[len - 1] == 's' || unit[len - 1] == 'x' || unit[len - 1] == 'z' ||
(len >= 2 && unit[len - 2] == 'c' && unit[len - 1] == 'h') ||
(len >= 2 && unit[len - 2] == 's' && unit[len - 1] == 'h')) {
if (!is_one) {
buf[len] = 'e';
buf[len + 1] = '\0';
}
} else if (unit[len - 1] == 'y' && len >= 2 &&
!(unit[len - 2] == 'a' || unit[len - 2] == 'e' ||
unit[len - 2] == 'i' || unit[len - 2] == 'o' ||
unit[len - 2] == 'u')) {
if (is_one) {
buf[len - 1] = '\0';
} else {
buf[len] = 's';
buf[len + 1] = '\0';
}
} else if (len >= 2 && unit[len - 2] == 'f' && unit[len - 1] == 'e') {
if (is_one) {
buf[len - 2] = '\0';
} else {
buf[len - 1] = 's';
buf[len] = '\0';
}
} else if (unit[len - 1] == 'f' && len >= 1) {
if (is_one) {
buf[len - 1] = '\0';
} else {
buf[len - 1] = 'v';
buf[len] = 'e';
buf[len + 1] = 's';
buf[len + 2] = '\0';
}
} else if (unit[len - 1] == 'e' && len >= 2 && unit[len - 2] == 'f') {
if (is_one) {
buf[len - 2] = '\0';
} else {
buf[len - 1] = 's';
buf[len] = '\0';
}
} else {
buf[len] = 's';
buf[len+1] = '\0';
}
} else if (len >= 2 && unit[len-2] == 'f' && unit[len-1] == 'e') {
if (is_one) {
buf[len-2] = '\0';
} else {
buf[len-1] = 's';
buf[len] = '\0';
}
} else if (unit[len-1] == 'f' && len >= 1) {
if (is_one) {
buf[len-1] = '\0';
} else {
buf[len-1] = 'v';
buf[len] = 'e';
buf[len+1] = 's';
buf[len+2] = '\0';
}
} else if (unit[len-1] == 'e' && len >= 2 && unit[len-2] == 'f') {
if (is_one) {
buf[len-2] = '\0';
} else {
buf[len-1] = 's';
buf[len] = '\0';
}
} else {
if (!is_one) {
buf[len] = 's';
buf[len+1] = '\0';
}
if (!is_one) {
buf[len] = 's';
buf[len + 1] = '\0';
}
}
return buf;
}
static char *build_html(double value, const UnitDef *from, double result, const UnitDef *to) {
static char *build_html(double value, const UnitDef *from, double result,
const UnitDef *to) {
static char html[4096];
char val_buf[64], res_buf[64], from_name_buf[64], to_name_buf[64];
format_number(value, val_buf, sizeof(val_buf));
@@ -466,30 +535,34 @@ static char *build_html(double value, const UnitDef *from, double result, const
pluralize(to->name, result, to_name_buf, sizeof(to_name_buf));
int n = snprintf(html, sizeof(html),
"<div class='unit-conv-container' style='line-height: 1.6;'>"
"<div style='font-size: 1.3em; margin-bottom: 8px;'>"
"<b>%s %s</b> = <b>%s %s</b>"
"</div>",
val_buf, from_name_buf,
res_buf, to_name_buf);
"<div class='unit-conv-container' style='line-height: 1.6;'>"
"<div style='font-size: 1.3em; margin-bottom: 8px;'>"
"<b>%s %s</b> = <b>%s %s</b>"
"</div>",
val_buf, from_name_buf, res_buf, to_name_buf);
snprintf(html + n, sizeof(html) - n, "</div>");
return html;
}
InfoBox fetch_unit_conv_data(const char *query) {
InfoBox info = {NULL, NULL, NULL, NULL};
if (!query) return info;
if (!query)
return info;
double value = 0;
const UnitDef *from = NULL;
const UnitDef *to = NULL;
if (!parse_conversion_query(query, &value, &from, &to)) return info;
if (!from || !to) return info;
if (from->type != to->type) return info;
if (!parse_conversion_query(query, &value, &from, &to))
return info;
if (!from || !to)
return info;
if (from->type != to->type)
return info;
double result = convert_value(value, from, to);
if (result == 0 && value != 0 && from->type != UNIT_TEMP) return info;
if (result == 0 && value != 0 && from->type != UNIT_TEMP)
return info;
info.title = strdup("Unit Conversion");
info.extract = strdup(build_html(value, from, result, to));

149
src/Infobox/Wikipedia.c
View File

@@ -14,41 +14,43 @@ struct WikiMemoryStruct {
};
static void shorten_summary(char **extract_ptr, int max_chars) {
if (!extract_ptr || !*extract_ptr) return;
if (!extract_ptr || !*extract_ptr)
return;
char *text = *extract_ptr;
int len = strlen(text);
if (len <= max_chars) return;
if (len <= max_chars)
return;
int end_pos = max_chars;
for (int i = max_chars; i > (max_chars / 2); i--) {
if (text[i] == '.' || text[i] == '!' || text[i] == '?') {
end_pos = i + 1;
break;
}
if (text[i] == '.' || text[i] == '!' || text[i] == '?') {
end_pos = i + 1;
break;
}
}
char *new_text = (char *)malloc(end_pos + 4);
if (new_text) {
strncpy(new_text, text, end_pos);
new_text[end_pos] = '\0';
strcat(new_text, "...");
free(*extract_ptr);
*extract_ptr = new_text;
strncpy(new_text, text, end_pos);
new_text[end_pos] = '\0';
strcat(new_text, "...");
free(*extract_ptr);
*extract_ptr = new_text;
}
}
static size_t WikiWriteMemoryCallback(void *contents, size_t size, size_t nmemb,
void *userp) {
void *userp) {
size_t realsize = size * nmemb;
struct WikiMemoryStruct *mem = (struct WikiMemoryStruct *)userp;
char *ptr = realloc(mem->memory, mem->size + realsize + 1);
if (ptr == NULL) {
fprintf(stderr, "Not enough memory (realloc returned NULL)\n");
return 0;
fprintf(stderr, "Not enough memory (realloc returned NULL)\n");
return 0;
}
mem->memory = ptr;
@@ -63,48 +65,49 @@ static void extract_wiki_info(xmlNode *node, InfoBox *info) {
xmlNode *cur_node = NULL;
for (cur_node = node; cur_node; cur_node = cur_node->next) {
if (cur_node->type == XML_ELEMENT_NODE) {
if (strcmp((const char *)cur_node->name, "page") == 0) {
xmlChar *title = xmlGetProp(cur_node, (const xmlChar *)"title");
if (title) {
info->title = strdup((const char *)title);
if (cur_node->type == XML_ELEMENT_NODE) {
if (strcmp((const char *)cur_node->name, "page") == 0) {
xmlChar *title = xmlGetProp(cur_node, (const xmlChar *)"title");
if (title) {
info->title = strdup((const char *)title);
const char *base_article_url = "https://en.wikipedia.org/wiki/";
char *formatted_title = strdup((const char *)title);
for (int i = 0; formatted_title[i]; i++) {
if (formatted_title[i] == ' ') formatted_title[i] = '_';
const char *base_article_url = "https://en.wikipedia.org/wiki/";
char *formatted_title = strdup((const char *)title);
for (int i = 0; formatted_title[i]; i++) {
if (formatted_title[i] == ' ')
formatted_title[i] = '_';
}
info->url =
malloc(strlen(base_article_url) + strlen(formatted_title) + 1);
if (info->url) {
strcpy(info->url, base_article_url);
strcat(info->url, formatted_title);
}
free(formatted_title);
xmlFree(title);
}
}
info->url =
malloc(strlen(base_article_url) + strlen(formatted_title) + 1);
if (info->url) {
strcpy(info->url, base_article_url);
strcat(info->url, formatted_title);
if (strcmp((const char *)cur_node->name, "thumbnail") == 0) {
xmlChar *source = xmlGetProp(cur_node, (const xmlChar *)"source");
if (source) {
info->thumbnail_url = strdup((const char *)source);
xmlFree(source);
}
}
free(formatted_title);
xmlFree(title);
}
}
if (strcmp((const char *)cur_node->name, "thumbnail") == 0) {
xmlChar *source = xmlGetProp(cur_node, (const xmlChar *)"source");
if (source) {
info->thumbnail_url = strdup((const char *)source);
xmlFree(source);
}
}
if (strcmp((const char *)cur_node->name, "extract") == 0) {
xmlChar *content = xmlNodeGetContent(cur_node);
if (content) {
info->extract = strdup((const char *)content);
if (strcmp((const char *)cur_node->name, "extract") == 0) {
xmlChar *content = xmlNodeGetContent(cur_node);
if (content) {
info->extract = strdup((const char *)content);
shorten_summary(&(info->extract), 300);
xmlFree(content);
shorten_summary(&(info->extract), 300);
xmlFree(content);
}
}
}
}
}
extract_wiki_info(cur_node->children, info);
extract_wiki_info(cur_node->children, info);
}
}
@@ -120,27 +123,27 @@ InfoBox fetch_wiki_data(char *api_url) {
curl_handle = curl_easy_init();
if (curl_handle) {
curl_easy_setopt(curl_handle, CURLOPT_URL, api_url);
curl_easy_setopt(curl_handle, CURLOPT_WRITEFUNCTION,
WikiWriteMemoryCallback);
curl_easy_setopt(curl_handle, CURLOPT_WRITEDATA, (void *)&chunk);
curl_easy_setopt(curl_handle, CURLOPT_USERAGENT, "libcurl-agent/1.0");
apply_proxy_settings(curl_handle);
curl_easy_setopt(curl_handle, CURLOPT_URL, api_url);
curl_easy_setopt(curl_handle, CURLOPT_WRITEFUNCTION,
WikiWriteMemoryCallback);
curl_easy_setopt(curl_handle, CURLOPT_WRITEDATA, (void *)&chunk);
curl_easy_setopt(curl_handle, CURLOPT_USERAGENT, "libcurl-agent/1.0");
apply_proxy_settings(curl_handle);
res = curl_easy_perform(curl_handle);
res = curl_easy_perform(curl_handle);
if (res == CURLE_OK) {
xmlDocPtr doc =
xmlReadMemory(chunk.memory, chunk.size, "noname.xml", NULL, 0);
if (doc != NULL) {
xmlNode *root_element = xmlDocGetRootElement(doc);
extract_wiki_info(root_element, &info);
xmlFreeDoc(doc);
if (res == CURLE_OK) {
xmlDocPtr doc =
xmlReadMemory(chunk.memory, chunk.size, "noname.xml", NULL, 0);
if (doc != NULL) {
xmlNode *root_element = xmlDocGetRootElement(doc);
extract_wiki_info(root_element, &info);
xmlFreeDoc(doc);
}
}
}
curl_easy_cleanup(curl_handle);
free(chunk.memory);
curl_easy_cleanup(curl_handle);
free(chunk.memory);
}
return info;
@@ -148,18 +151,18 @@ InfoBox fetch_wiki_data(char *api_url) {
char *construct_wiki_url(const char *search_term) {
CURL *curl = curl_easy_init();
if (!curl) return NULL;
if (!curl)
return NULL;
char *escaped_term = curl_easy_escape(curl, search_term, 0);
const char *base =
"https://en.wikipedia.org/w/"
"api.php?action=query&prop=extracts|pageimages&exintro&"
"explaintext&pithumbsize=400&format=xml&origin=*&titles=";
const char *base = "https://en.wikipedia.org/w/"
"api.php?action=query&prop=extracts|pageimages&exintro&"
"explaintext&pithumbsize=400&format=xml&origin=*&titles=";
char *full_url = malloc(strlen(base) + strlen(escaped_term) + 1);
if (full_url) {
strcpy(full_url, base);
strcat(full_url, escaped_term);
strcpy(full_url, base);
strcat(full_url, escaped_term);
}
curl_free(escaped_term);

53
src/Main.c
View File

@@ -7,15 +7,16 @@
#include "Config.h"
#include "Proxy/Proxy.h"
#include "Scraping/Scraping.h"
#include "Routes/Home.h"
#include "Routes/Images.h"
#include "Routes/ImageProxy.h"
#include "Routes/Images.h"
#include "Routes/Search.h"
#include "Scraping/Scraping.h"
int handle_opensearch(UrlParams *params) {
(void)params;
serve_static_file_with_mime("opensearch.xml", "application/opensearchdescription+xml");
serve_static_file_with_mime("opensearch.xml",
"application/opensearchdescription+xml");
return 0;
}
@@ -30,33 +31,35 @@ int main() {
curl_global_init(CURL_GLOBAL_DEFAULT);
Config config = {
.host = "0.0.0.0",
.port = 5000,
.proxy = "",
.proxy_list_file = "",
.max_proxy_retries = 3,
.randomize_username = 0,
.randomize_password = 0
};
Config config = {.host = "0.0.0.0",
.port = 5000,
.proxy = "",
.proxy_list_file = "",
.max_proxy_retries = 3,
.randomize_username = 0,
.randomize_password = 0};
if (load_config("config.ini", &config) != 0) {
fprintf(stderr, "Warning: Could not load config file, using defaults\n");
fprintf(stderr, "Warning: Could not load config file, using defaults\n");
}
if (config.proxy_list_file[0] != '\0') {
if (load_proxy_list(config.proxy_list_file) < 0) {
fprintf(stderr, "Warning: Failed to load proxy list, continuing without proxies\n");
}
if (load_proxy_list(config.proxy_list_file) < 0) {
fprintf(
stderr,
"Warning: Failed to load proxy list, continuing without proxies\n");
}
}
max_proxy_retries = config.max_proxy_retries;
set_proxy_config(config.proxy, config.randomize_username, config.randomize_password);
set_proxy_config(config.proxy, config.randomize_username,
config.randomize_password);
if (proxy_url[0] != '\0') {
fprintf(stderr, "Using proxy: %s\n", proxy_url);
fprintf(stderr, "Using proxy: %s\n", proxy_url);
} else if (proxy_count > 0) {
fprintf(stderr, "Using %d proxies from %s\n", proxy_count, config.proxy_list_file);
fprintf(stderr, "Using %d proxies from %s\n", proxy_count,
config.proxy_list_file);
}
set_handler("/", home_handler);
@@ -70,14 +73,14 @@ int main() {
int result = beaker_run(config.host, config.port);
if (result != 0) {
fprintf(stderr, "Error: Beaker server failed to start.\n");
curl_global_cleanup();
xmlCleanupParser();
return EXIT_FAILURE;
fprintf(stderr, "Error: Beaker server failed to start.\n");
curl_global_cleanup();
xmlCleanupParser();
return EXIT_FAILURE;
}
curl_global_cleanup();
xmlCleanupParser();
free_proxy_list();
return EXIT_SUCCESS;
}
}

278
src/Proxy/Proxy.c
View File

@@ -1,9 +1,9 @@
#include "Proxy.h"
#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include <pthread.h>
Proxy *proxy_list = NULL;
int proxy_count = 0;
@@ -13,76 +13,85 @@ int randomize_password = 0;
char proxy_url[512] = {0};
static pthread_mutex_t proxy_mutex = PTHREAD_MUTEX_INITIALIZER;
static const char RAND_CHARS[] = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789";
static const char RAND_CHARS[] =
"abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789";
static void generate_random_string(char *buf, size_t len) {
for (size_t i = 0; i < len - 1; i++) {
buf[i] = RAND_CHARS[rand() % (sizeof(RAND_CHARS) - 1)];
buf[i] = RAND_CHARS[rand() % (sizeof(RAND_CHARS) - 1)];
}
buf[len - 1] = '\0';
}
void set_proxy_config(const char *proxy_str, int rand_user, int rand_pass) {
if (proxy_str && proxy_str[0]) {
strncpy(proxy_url, proxy_str, sizeof(proxy_url) - 1);
proxy_url[sizeof(proxy_url) - 1] = '\0';
strncpy(proxy_url, proxy_str, sizeof(proxy_url) - 1);
proxy_url[sizeof(proxy_url) - 1] = '\0';
}
randomize_username = rand_user;
randomize_password = rand_pass;
}
static Proxy parse_proxy_line(const char *line) {
Proxy proxy = {.type = PROXY_SOCKS5, .port = 0, .username[0] = '\0', .password[0] = '\0', .failures = 0};
Proxy proxy = {.type = PROXY_SOCKS5,
.port = 0,
.username[0] = '\0',
.password[0] = '\0',
.failures = 0};
const char *host_start = NULL;
const char *port_start = NULL;
size_t len = strlen(line);
if (len == 0) return proxy;
if (len == 0)
return proxy;
if (strncmp(line, "http://", 7) == 0) {
proxy.type = PROXY_HTTP;
host_start = line + 7;
proxy.type = PROXY_HTTP;
host_start = line + 7;
} else if (strncmp(line, "socks5://", 9) == 0) {
proxy.type = PROXY_SOCKS5;
host_start = line + 9;
proxy.type = PROXY_SOCKS5;
host_start = line + 9;
} else if (strncmp(line, "socks4://", 9) == 0) {
proxy.type = PROXY_SOCKS4;
host_start = line + 9;
proxy.type = PROXY_SOCKS4;
host_start = line + 9;
} else {
host_start = line;
host_start = line;
}
const char *at = strchr(host_start, '@');
if (at) {
char cred_buf[128];
size_t cred_len = at - host_start;
if (cred_len >= sizeof(cred_buf)) cred_len = sizeof(cred_buf) - 1;
strncpy(cred_buf, host_start, cred_len);
cred_buf[cred_len] = '\0';
char *colon = strchr(cred_buf, ':');
if (colon) {
size_t user_len = colon - cred_buf;
if (user_len >= sizeof(proxy.username)) user_len = sizeof(proxy.username) - 1;
strncpy(proxy.username, cred_buf, user_len);
proxy.username[user_len] = '\0';
strncpy(proxy.password, colon + 1, sizeof(proxy.password) - 1);
proxy.password[sizeof(proxy.password) - 1] = '\0';
}
host_start = at + 1;
char cred_buf[128];
size_t cred_len = at - host_start;
if (cred_len >= sizeof(cred_buf))
cred_len = sizeof(cred_buf) - 1;
strncpy(cred_buf, host_start, cred_len);
cred_buf[cred_len] = '\0';
char *colon = strchr(cred_buf, ':');
if (colon) {
size_t user_len = colon - cred_buf;
if (user_len >= sizeof(proxy.username))
user_len = sizeof(proxy.username) - 1;
strncpy(proxy.username, cred_buf, user_len);
proxy.username[user_len] = '\0';
strncpy(proxy.password, colon + 1, sizeof(proxy.password) - 1);
proxy.password[sizeof(proxy.password) - 1] = '\0';
}
host_start = at + 1;
}
port_start = strchr(host_start, ':');
if (port_start) {
char host_buf[256];
size_t host_len = port_start - host_start;
if (host_len >= sizeof(host_buf)) host_len = sizeof(host_buf) - 1;
strncpy(host_buf, host_start, host_len);
host_buf[host_len] = '\0';
snprintf(proxy.host, sizeof(proxy.host), "%.*s", (int)host_len, host_buf);
proxy.port = atoi(port_start + 1);
char host_buf[256];
size_t host_len = port_start - host_start;
if (host_len >= sizeof(host_buf))
host_len = sizeof(host_buf) - 1;
strncpy(host_buf, host_start, host_len);
host_buf[host_len] = '\0';
snprintf(proxy.host, sizeof(proxy.host), "%.*s", (int)host_len, host_buf);
proxy.port = atoi(port_start + 1);
} else {
snprintf(proxy.host, sizeof(proxy.host), "%s", host_start);
snprintf(proxy.host, sizeof(proxy.host), "%s", host_start);
}
return proxy;
@@ -90,71 +99,73 @@ static Proxy parse_proxy_line(const char *line) {
int load_proxy_list(const char *filename) {
if (!filename || filename[0] == '\0') {
return 0;
return 0;
}
pthread_mutex_lock(&proxy_mutex);
if (proxy_list) {
free(proxy_list);
proxy_list = NULL;
free(proxy_list);
proxy_list = NULL;
}
proxy_count = 0;
FILE *file = fopen(filename, "r");
if (!file) {
pthread_mutex_unlock(&proxy_mutex);
fprintf(stderr, "[WARN] Could not open proxy list file: %s\n", filename);
return -1;
pthread_mutex_unlock(&proxy_mutex);
fprintf(stderr, "[WARN] Could not open proxy list file: %s\n", filename);
return -1;
}
int capacity = 16;
proxy_list = (Proxy *)malloc(capacity * sizeof(Proxy));
if (!proxy_list) {
fclose(file);
return -1;
fclose(file);
return -1;
}
proxy_count = 0;
char line[512];
while (fgets(line, sizeof(line), file)) {
line[strcspn(line, "\r\n")] = 0;
line[strcspn(line, "\r\n")] = 0;
if (line[0] == '\0' || line[0] == '#') {
continue;
}
char *p = line;
while (*p == ' ' || *p == '\t') p++;
char *end = p + strlen(p) - 1;
while (end > p && (*end == ' ' || *end == '\t')) {
*end = '\0';
end--;
}
if (p[0] == '\0') continue;
Proxy proxy = parse_proxy_line(p);
if (proxy.port == 0) {
continue;
}
if (proxy_count >= capacity) {
capacity *= 2;
Proxy *new_list = (Proxy *)realloc(proxy_list, capacity * sizeof(Proxy));
if (!new_list) {
free(proxy_list);
proxy_list = NULL;
proxy_count = 0;
fclose(file);
pthread_mutex_unlock(&proxy_mutex);
return -1;
if (line[0] == '\0' || line[0] == '#') {
continue;
}
proxy_list = new_list;
}
proxy_list[proxy_count++] = proxy;
char *p = line;
while (*p == ' ' || *p == '\t')
p++;
char *end = p + strlen(p) - 1;
while (end > p && (*end == ' ' || *end == '\t')) {
*end = '\0';
end--;
}
if (p[0] == '\0')
continue;
Proxy proxy = parse_proxy_line(p);
if (proxy.port == 0) {
continue;
}
if (proxy_count >= capacity) {
capacity *= 2;
Proxy *new_list = (Proxy *)realloc(proxy_list, capacity * sizeof(Proxy));
if (!new_list) {
free(proxy_list);
proxy_list = NULL;
proxy_count = 0;
fclose(file);
pthread_mutex_unlock(&proxy_mutex);
return -1;
}
proxy_list = new_list;
}
proxy_list[proxy_count++] = proxy;
}
fclose(file);
@@ -166,8 +177,8 @@ int load_proxy_list(const char *filename) {
void free_proxy_list(void) {
pthread_mutex_lock(&proxy_mutex);
if (proxy_list) {
free(proxy_list);
proxy_list = NULL;
free(proxy_list);
proxy_list = NULL;
}
proxy_count = 0;
pthread_mutex_unlock(&proxy_mutex);
@@ -176,8 +187,8 @@ void free_proxy_list(void) {
Proxy *get_random_proxy(void) {
pthread_mutex_lock(&proxy_mutex);
if (proxy_count == 0) {
pthread_mutex_unlock(&proxy_mutex);
return NULL;
pthread_mutex_unlock(&proxy_mutex);
return NULL;
}
int start = rand() % proxy_count;
@@ -185,19 +196,19 @@ Proxy *get_random_proxy(void) {
Proxy *selected = NULL;
while (checked < proxy_count) {
int idx = (start + checked) % proxy_count;
if (proxy_list[idx].failures < max_proxy_retries) {
selected = &proxy_list[idx];
break;
}
checked++;
int idx = (start + checked) % proxy_count;
if (proxy_list[idx].failures < max_proxy_retries) {
selected = &proxy_list[idx];
break;
}
checked++;
}
if (!selected) {
for (int i = 0; i < proxy_count; i++) {
proxy_list[i].failures = 0;
}
selected = &proxy_list[rand() % proxy_count];
for (int i = 0; i < proxy_count; i++) {
proxy_list[i].failures = 0;
}
selected = &proxy_list[rand() % proxy_count];
}
pthread_mutex_unlock(&proxy_mutex);
@@ -205,7 +216,8 @@ Proxy *get_random_proxy(void) {
}
void record_proxy_failure(Proxy *proxy) {
if (!proxy) return;
if (!proxy)
return;
pthread_mutex_lock(&proxy_mutex);
proxy->failures++;
pthread_mutex_unlock(&proxy_mutex);
@@ -213,45 +225,49 @@ void record_proxy_failure(Proxy *proxy) {
void apply_proxy_settings(CURL *curl) {
if (proxy_url[0] != '\0') {
curl_easy_setopt(curl, CURLOPT_PROXY, proxy_url);
if (strncmp(proxy_url, "socks5://", 9) == 0) {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5);
} else if (strncmp(proxy_url, "socks4://", 9) == 0) {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS4A);
} else {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_HTTP);
}
if (randomize_username || randomize_password) {
char userpwd[256];
char username[32] = {0};
char password[32] = {0};
if (randomize_username) generate_random_string(username, sizeof(username));
if (randomize_password) generate_random_string(password, sizeof(password));
snprintf(userpwd, sizeof(userpwd), "%s:%s", username, password);
curl_easy_setopt(curl, CURLOPT_PROXYUSERPWD, userpwd);
}
} else if (proxy_count > 0) {
Proxy *proxy = get_random_proxy();
if (proxy) {
char proxy_url_buf[512];
snprintf(proxy_url_buf, sizeof(proxy_url_buf), "%s:%d", proxy->host, proxy->port);
curl_easy_setopt(curl, CURLOPT_PROXY, proxy_url_buf);
if (proxy->type == PROXY_HTTP) {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_HTTP);
} else if (proxy->type == PROXY_SOCKS4) {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS4A);
curl_easy_setopt(curl, CURLOPT_PROXY, proxy_url);
if (strncmp(proxy_url, "socks5://", 9) == 0) {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5);
} else if (strncmp(proxy_url, "socks4://", 9) == 0) {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS4A);
} else {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5);
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_HTTP);
}
if (proxy->username[0] != '\0' || proxy->password[0] != '\0') {
char userpwd[128];
snprintf(userpwd, sizeof(userpwd), "%s:%s", proxy->username, proxy->password);
curl_easy_setopt(curl, CURLOPT_PROXYUSERPWD, userpwd);
if (randomize_username || randomize_password) {
char userpwd[256];
char username[32] = {0};
char password[32] = {0};
if (randomize_username)
generate_random_string(username, sizeof(username));
if (randomize_password)
generate_random_string(password, sizeof(password));
snprintf(userpwd, sizeof(userpwd), "%s:%s", username, password);
curl_easy_setopt(curl, CURLOPT_PROXYUSERPWD, userpwd);
}
} else if (proxy_count > 0) {
Proxy *proxy = get_random_proxy();
if (proxy) {
char proxy_url_buf[512];
snprintf(proxy_url_buf, sizeof(proxy_url_buf), "%s:%d", proxy->host,
proxy->port);
curl_easy_setopt(curl, CURLOPT_PROXY, proxy_url_buf);
if (proxy->type == PROXY_HTTP) {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_HTTP);
} else if (proxy->type == PROXY_SOCKS4) {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS4A);
} else {
curl_easy_setopt(curl, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5);
}
if (proxy->username[0] != '\0' || proxy->password[0] != '\0') {
char userpwd[128];
snprintf(userpwd, sizeof(userpwd), "%s:%s", proxy->username,
proxy->password);
curl_easy_setopt(curl, CURLOPT_PROXYUSERPWD, userpwd);
}
}
}
}
}

90
src/Routes/ImageProxy.c
View File

@@ -16,9 +16,9 @@ typedef struct {
static int is_allowed_domain(const char *url) {
const char *protocol = strstr(url, "://");
if (!protocol) {
protocol = url;
protocol = url;
} else {
protocol += 3;
protocol += 3;
}
const char *path = strchr(protocol, '/');
@@ -26,49 +26,46 @@ static int is_allowed_domain(const char *url) {
char host[256] = {0};
if (host_len >= sizeof(host)) {
host_len = sizeof(host) - 1;
host_len = sizeof(host) - 1;
}
strncpy(host, protocol, host_len);
const char *allowed_domains[] = {
"mm.bing.net",
"th.bing.com",
NULL
};
const char *allowed_domains[] = {"mm.bing.net", "th.bing.com", NULL};
for (int i = 0; allowed_domains[i] != NULL; i++) {
size_t domain_len = strlen(allowed_domains[i]);
size_t host_str_len = strlen(host);
size_t domain_len = strlen(allowed_domains[i]);
size_t host_str_len = strlen(host);
if (host_str_len >= domain_len) {
const char *suffix = host + host_str_len - domain_len;
if (strcmp(suffix, allowed_domains[i]) == 0) {
return 1;
if (host_str_len >= domain_len) {
const char *suffix = host + host_str_len - domain_len;
if (strcmp(suffix, allowed_domains[i]) == 0) {
return 1;
}
}
}
}
return 0;
}
static size_t write_callback(void *contents, size_t size, size_t nmemb,
void *userp) {
void *userp) {
size_t realsize = size * nmemb;
MemoryBuffer *buf = (MemoryBuffer *)userp;
if (buf->size + realsize > MAX_IMAGE_SIZE) {
return 0;
return 0;
}
if (buf->size + realsize > buf->capacity) {
size_t new_capacity = buf->capacity * 2;
if (new_capacity < buf->size + realsize) {
new_capacity = buf->size + realsize;
}
char *new_data = realloc(buf->data, new_capacity);
if (!new_data) return 0;
buf->data = new_data;
buf->capacity = new_capacity;
size_t new_capacity = buf->capacity * 2;
if (new_capacity < buf->size + realsize) {
new_capacity = buf->size + realsize;
}
char *new_data = realloc(buf->data, new_capacity);
if (!new_data)
return 0;
buf->data = new_data;
buf->capacity = new_capacity;
}
memcpy(buf->data + buf->size, contents, realsize);
@@ -79,38 +76,34 @@ static size_t write_callback(void *contents, size_t size, size_t nmemb,
int image_proxy_handler(UrlParams *params) {
const char *url = NULL;
for (int i = 0; i < params->count; i++) {
if (strcmp(params->params[i].key, "url") == 0) {
url = params->params[i].value;
break;
}
if (strcmp(params->params[i].key, "url") == 0) {
url = params->params[i].value;
break;
}
}
if (!url || strlen(url) == 0) {
send_response("Missing 'url' parameter");
return 0;
send_response("Missing 'url' parameter");
return 0;
}
if (!is_allowed_domain(url)) {
send_response("Domain not allowed");
return 0;
send_response("Domain not allowed");
return 0;
}
CURL *curl = curl_easy_init();
if (!curl) {
send_response("Failed to initialize curl");
return 0;
send_response("Failed to initialize curl");
return 0;
}
MemoryBuffer buf = {
.data = malloc(8192),
.size = 0,
.capacity = 8192
};
MemoryBuffer buf = {.data = malloc(8192), .size = 0, .capacity = 8192};
if (!buf.data) {
curl_easy_cleanup(curl);
send_response("Memory allocation failed");
return 0;
curl_easy_cleanup(curl);
send_response("Memory allocation failed");
return 0;
}
curl_easy_setopt(curl, CURLOPT_URL, url);
@@ -130,18 +123,19 @@ int image_proxy_handler(UrlParams *params) {
char content_type[64] = {0};
if (content_type_ptr) {
strncpy(content_type, content_type_ptr, sizeof(content_type) - 1);
strncpy(content_type, content_type_ptr, sizeof(content_type) - 1);
}
curl_easy_cleanup(curl);
if (res != CURLE_OK || response_code != 200) {
free(buf.data);
send_response("Failed to fetch image");
return 0;
free(buf.data);
send_response("Failed to fetch image");
return 0;
}
const char *mime_type = strlen(content_type) > 0 ? content_type : "image/jpeg";
const char *mime_type =
strlen(content_type) > 0 ? content_type : "image/jpeg";
serve_data(buf.data, buf.size, mime_type);
free(buf.data);

343
src/Routes/Images.c
View File

@@ -1,7 +1,7 @@
#include "Images.h"
#include "../Utility/Unescape.h"
#include "../Proxy/Proxy.h"
#include "../Scraping/Scraping.h"
#include "../Utility/Unescape.h"
#include <curl/curl.h>
#include <libxml/HTMLparser.h>
@@ -17,12 +17,12 @@ struct MemoryBlock {
};
static size_t ImageWriteCallback(void *data, size_t size, size_t nmemb,
void *userp) {
void *userp) {
size_t realsize = size * nmemb;
struct MemoryBlock *mem = (struct MemoryBlock *)userp;
char *ptr = (char *)realloc(mem->response, mem->size + realsize + 1);
if (ptr == NULL) {
return 0;
return 0;
}
mem->response = ptr;
memcpy(&(mem->response[mem->size]), data, realsize);
@@ -35,30 +35,30 @@ static char *fetch_images_html(const char *url) {
CURL *curl_handle;
struct MemoryBlock chunk = {.response = malloc(1), .size = 0};
if (!chunk.response) {
return NULL;
return NULL;
}
curl_handle = curl_easy_init();
if (!curl_handle) {
free(chunk.response);
return NULL;
free(chunk.response);
return NULL;
}
curl_easy_setopt(curl_handle, CURLOPT_URL, url);
curl_easy_setopt(curl_handle, CURLOPT_WRITEFUNCTION, ImageWriteCallback);
curl_easy_setopt(curl_handle, CURLOPT_WRITEDATA, (void *)&chunk);
curl_easy_setopt(
curl_handle, CURLOPT_USERAGENT,
"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko");
curl_handle, CURLOPT_USERAGENT,
"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko");
curl_easy_setopt(curl_handle, CURLOPT_FOLLOWLOCATION, 1L);
curl_easy_setopt(curl_handle, CURLOPT_TIMEOUT, 10L);
apply_proxy_settings(curl_handle);
CURLcode res = curl_easy_perform(curl_handle);
if (res != CURLE_OK) {
free(chunk.response);
curl_easy_cleanup(curl_handle);
return NULL;
free(chunk.response);
curl_easy_cleanup(curl_handle);
return NULL;
}
curl_easy_cleanup(curl_handle);
@@ -71,15 +71,16 @@ int images_handler(UrlParams *params) {
int page = 1;
if (params) {
for (int i = 0; i < params->count; i++) {
if (strcmp(params->params[i].key, "q") == 0) {
raw_query = params->params[i].value;
} else if (strcmp(params->params[i].key, "p") == 0) {
int parsed = atoi(params->params[i].value);
if (parsed > 1) page = parsed;
for (int i = 0; i < params->count; i++) {
if (strcmp(params->params[i].key, "q") == 0) {
raw_query = params->params[i].value;
} else if (strcmp(params->params[i].key, "p") == 0) {
int parsed = atoi(params->params[i].value);
if (parsed > 1)
page = parsed;
}
}
}
}
context_set(&ctx, "query", raw_query);
@@ -87,7 +88,7 @@ int images_handler(UrlParams *params) {
snprintf(page_str, sizeof(page_str), "%d", page);
snprintf(prev_str, sizeof(prev_str), "%d", page > 1 ? page - 1 : 0);
snprintf(next_str, sizeof(next_str), "%d", page + 1);
context_set(&ctx, "page", page_str);
context_set(&ctx, "page", page_str);
context_set(&ctx, "prev_page", prev_str);
context_set(&ctx, "next_page", next_str);
@@ -95,207 +96,239 @@ int images_handler(UrlParams *params) {
context_set(&ctx, "query", display_query);
if (!raw_query || strlen(raw_query) == 0) {
send_response("<h1>No query provided</h1>");
if (display_query) free(display_query);
free_context(&ctx);
return -1;
send_response("<h1>No query provided</h1>");
if (display_query)
free(display_query);
free_context(&ctx);
return -1;
}
CURL *tmp = curl_easy_init();
if (!tmp) {
send_response("<h1>Error initializing curl</h1>");
if (display_query) free(display_query);
free_context(&ctx);
return -1;
send_response("<h1>Error initializing curl</h1>");
if (display_query)
free(display_query);
free_context(&ctx);
return -1;
}
char *encoded_query = curl_easy_escape(tmp, raw_query, 0);
curl_easy_cleanup(tmp);
if (!encoded_query) {
send_response("<h1>Error encoding query</h1>");
if (display_query) free(display_query);
free_context(&ctx);
return -1;
send_response("<h1>Error encoding query</h1>");
if (display_query)
free(display_query);
free_context(&ctx);
return -1;
}
char url[1024];
int first = (page - 1) * 32 + 1;
snprintf(url, sizeof(url),
"https://www.bing.com/images/search?q=%s&first=%d", encoded_query, first);
snprintf(url, sizeof(url), "https://www.bing.com/images/search?q=%s&first=%d",
encoded_query, first);
char *html = fetch_images_html(url);
if (!html) {
send_response("<h1>Error fetching images</h1>");
free(encoded_query);
free(display_query);
free_context(&ctx);
return -1;
send_response("<h1>Error fetching images</h1>");
free(encoded_query);
free(display_query);
free_context(&ctx);
return -1;
}
htmlDocPtr doc = htmlReadMemory(html, (int)strlen(html), NULL, NULL,
HTML_PARSE_RECOVER | HTML_PARSE_NOERROR);
HTML_PARSE_RECOVER | HTML_PARSE_NOERROR);
if (!doc) {
free(html);
free(encoded_query);
free(display_query);
free_context(&ctx);
return -1;
free(html);
free(encoded_query);
free(display_query);
free_context(&ctx);
return -1;
}
xmlXPathContextPtr xpathCtx = xmlXPathNewContext(doc);
if (!xpathCtx) {
xmlFreeDoc(doc);
free(html);
free(encoded_query);
free(display_query);
free_context(&ctx);
return -1;
xmlFreeDoc(doc);
free(html);
free(encoded_query);
free(display_query);
free_context(&ctx);
return -1;
}
xmlXPathObjectPtr xpathObj =
xmlXPathEvalExpression((const xmlChar *)"//div[@class='item']", xpathCtx);
xmlXPathEvalExpression((const xmlChar *)"//div[@class='item']", xpathCtx);
int image_count = 0;
char ***image_matrix = NULL;
int *inner_counts = NULL;
if (xpathObj && xpathObj->nodesetval) {
int nodes = xpathObj->nodesetval->nodeNr;
int nodes = xpathObj->nodesetval->nodeNr;
int max_images = (nodes < 32) ? nodes : 32;
image_matrix = malloc(sizeof(char **) * max_images);
inner_counts = malloc(sizeof(int) * max_images);
int max_images = (nodes < 32) ? nodes : 32;
image_matrix = malloc(sizeof(char **) * max_images);
inner_counts = malloc(sizeof(int) * max_images);
for (int i = 0; i < nodes; i++) {
if (image_count >= 32) break;
for (int i = 0; i < nodes; i++) {
if (image_count >= 32)
break;
xmlNodePtr node = xpathObj->nodesetval->nodeTab[i];
xmlNodePtr img_node = NULL;
xmlNodePtr tit_node = NULL;
xmlNodePtr des_node = NULL;
xmlNodePtr thumb_link = NULL;
xmlNodePtr node = xpathObj->nodesetval->nodeTab[i];
xmlNodePtr img_node = NULL;
xmlNodePtr tit_node = NULL;
xmlNodePtr des_node = NULL;
xmlNodePtr thumb_link = NULL;
for (xmlNodePtr child = node->children; child; child = child->next) {
if (child->type != XML_ELEMENT_NODE) continue;
for (xmlNodePtr child = node->children; child; child = child->next) {
if (child->type != XML_ELEMENT_NODE)
continue;
if (xmlStrcmp(child->name, (const xmlChar *)"a") == 0) {
xmlChar *class = xmlGetProp(child, (const xmlChar *)"class");
if (class) {
if (xmlStrstr(class, (const xmlChar *)"thumb") != NULL) {
thumb_link = child;
for (xmlNodePtr thumb_child = child->children; thumb_child; thumb_child = thumb_child->next) {
if (xmlStrcmp(thumb_child->name, (const xmlChar *)"div") == 0) {
xmlChar *div_class = xmlGetProp(thumb_child, (const xmlChar *)"class");
if (div_class && xmlStrcmp(div_class, (const xmlChar *)"cico") == 0) {
for (xmlNodePtr cico_child = thumb_child->children; cico_child; cico_child = cico_child->next) {
if (xmlStrcmp(cico_child->name, (const xmlChar *)"img") == 0) {
img_node = cico_child;
break;
if (xmlStrcmp(child->name, (const xmlChar *)"a") == 0) {
xmlChar *class = xmlGetProp(child, (const xmlChar *)"class");
if (class) {
if (xmlStrstr(class, (const xmlChar *)"thumb") != NULL) {
thumb_link = child;
for (xmlNodePtr thumb_child = child->children; thumb_child;
thumb_child = thumb_child->next) {
if (xmlStrcmp(thumb_child->name, (const xmlChar *)"div") == 0) {
xmlChar *div_class =
xmlGetProp(thumb_child, (const xmlChar *)"class");
if (div_class &&
xmlStrcmp(div_class, (const xmlChar *)"cico") == 0) {
for (xmlNodePtr cico_child = thumb_child->children;
cico_child; cico_child = cico_child->next) {
if (xmlStrcmp(cico_child->name, (const xmlChar *)"img") ==
0) {
img_node = cico_child;
break;
}
}
}
if (div_class)
xmlFree(div_class);
}
}
} else if (xmlStrstr(class, (const xmlChar *)"tit") != NULL) {
tit_node = child;
}
xmlFree(class);
}
} else if (xmlStrcmp(child->name, (const xmlChar *)"div") == 0) {
xmlChar *class = xmlGetProp(child, (const xmlChar *)"class");
if (class && xmlStrcmp(class, (const xmlChar *)"meta") == 0) {
for (xmlNodePtr meta_child = child->children; meta_child;
meta_child = meta_child->next) {
if (xmlStrcmp(meta_child->name, (const xmlChar *)"div") == 0) {
xmlChar *div_class =
xmlGetProp(meta_child, (const xmlChar *)"class");
if (div_class) {
if (xmlStrcmp(div_class, (const xmlChar *)"des") == 0) {
des_node = meta_child;
}
xmlFree(div_class);
}
} else if (xmlStrcmp(meta_child->name, (const xmlChar *)"a") ==
0) {
xmlChar *a_class =
xmlGetProp(meta_child, (const xmlChar *)"class");
if (a_class &&
xmlStrstr(a_class, (const xmlChar *)"tit") != NULL) {
tit_node = meta_child;
}
if (a_class)
xmlFree(a_class);
}
}
}
if (class)
xmlFree(class);
}
}
xmlChar *iurl =
img_node ? xmlGetProp(img_node, (const xmlChar *)"src") : NULL;
xmlChar *full_url =
thumb_link ? xmlGetProp(thumb_link, (const xmlChar *)"href") : NULL;
xmlChar *title = des_node
? xmlNodeGetContent(des_node)
: (tit_node ? xmlNodeGetContent(tit_node) : NULL);
xmlChar *rurl =
tit_node ? xmlGetProp(tit_node, (const xmlChar *)"href") : NULL;
if (iurl && strlen((char *)iurl) > 0) {
char *proxy_url = NULL;
CURL *esc_curl = curl_easy_init();
if (esc_curl) {
char *encoded = curl_easy_escape(esc_curl, (char *)iurl, 0);
if (encoded) {
size_t proxy_len = strlen("/proxy?url=") + strlen(encoded) + 1;
proxy_url = malloc(proxy_len);
if (proxy_url) {
snprintf(proxy_url, proxy_len, "/proxy?url=%s", encoded);
}
curl_free(encoded);
}
if (div_class) xmlFree(div_class);
curl_easy_cleanup(esc_curl);
}
}
} else if (xmlStrstr(class, (const xmlChar *)"tit") != NULL) {
tit_node = child;
}
xmlFree(class);
}
} else if (xmlStrcmp(child->name, (const xmlChar *)"div") == 0) {
xmlChar *class = xmlGetProp(child, (const xmlChar *)"class");
if (class && xmlStrcmp(class, (const xmlChar *)"meta") == 0) {
for (xmlNodePtr meta_child = child->children; meta_child; meta_child = meta_child->next) {
if (xmlStrcmp(meta_child->name, (const xmlChar *)"div") == 0) {
xmlChar *div_class = xmlGetProp(meta_child, (const xmlChar *)"class");
if (div_class) {
if (xmlStrcmp(div_class, (const xmlChar *)"des") == 0) {
des_node = meta_child;
}
xmlFree(div_class);
}
} else if (xmlStrcmp(meta_child->name, (const xmlChar *)"a") == 0) {
xmlChar *a_class = xmlGetProp(meta_child, (const xmlChar *)"class");
if (a_class && xmlStrstr(a_class, (const xmlChar *)"tit") != NULL) {
tit_node = meta_child;
}
if (a_class) xmlFree(a_class);
}
}
}
if (class) xmlFree(class);
}
}
xmlChar *iurl = img_node ? xmlGetProp(img_node, (const xmlChar *)"src") : NULL;
xmlChar *full_url = thumb_link ? xmlGetProp(thumb_link, (const xmlChar *)"href") : NULL;
xmlChar *title = des_node ? xmlNodeGetContent(des_node) : (tit_node ? xmlNodeGetContent(tit_node) : NULL);
xmlChar *rurl = tit_node ? xmlGetProp(tit_node, (const xmlChar *)"href") : NULL;
if (iurl && strlen((char *)iurl) > 0) {
char *proxy_url = NULL;
CURL *esc_curl = curl_easy_init();
if (esc_curl) {
char *encoded = curl_easy_escape(esc_curl, (char *)iurl, 0);
if (encoded) {
size_t proxy_len = strlen("/proxy?url=") + strlen(encoded) + 1;
proxy_url = malloc(proxy_len);
if (proxy_url) {
snprintf(proxy_url, proxy_len, "/proxy?url=%s", encoded);
image_matrix[image_count] = malloc(sizeof(char *) * 4);
image_matrix[image_count][0] =
proxy_url ? strdup(proxy_url) : strdup((char *)iurl);
image_matrix[image_count][1] = strdup(title ? (char *)title : "Image");
image_matrix[image_count][2] = strdup(rurl ? (char *)rurl : "#");
image_matrix[image_count][3] =
strdup(full_url ? (char *)full_url : "#");
inner_counts[image_count] = 4;
image_count++;
}
curl_free(encoded);
}
curl_easy_cleanup(esc_curl);
}
image_matrix[image_count] = malloc(sizeof(char *) * 4);
image_matrix[image_count][0] = proxy_url ? strdup(proxy_url) : strdup((char *)iurl);
image_matrix[image_count][1] = strdup(title ? (char *)title : "Image");
image_matrix[image_count][2] = strdup(rurl ? (char *)rurl : "#");
image_matrix[image_count][3] = strdup(full_url ? (char *)full_url : "#");
inner_counts[image_count] = 4;
image_count++;
if (iurl)
xmlFree(iurl);
if (title)
xmlFree(title);
if (rurl)
xmlFree(rurl);
if (full_url)
xmlFree(full_url);
}
if (iurl) xmlFree(iurl);
if (title) xmlFree(title);
if (rurl) xmlFree(rurl);
if (full_url) xmlFree(full_url);
}
}
context_set_array_of_arrays(&ctx, "images", image_matrix, image_count,
inner_counts);
inner_counts);
char *rendered = render_template("images.html", &ctx);
if (rendered) {
send_response(rendered);
free(rendered);
send_response(rendered);
free(rendered);
} else {
send_response("<h1>Error rendering image results</h1>");
send_response("<h1>Error rendering image results</h1>");
}
if (image_matrix) {
for (int i = 0; i < image_count; i++) {
for (int j = 0; j < 4; j++) {
free(image_matrix[i][j]);
for (int i = 0; i < image_count; i++) {
for (int j = 0; j < 4; j++) {
free(image_matrix[i][j]);
}
free(image_matrix[i]);
}
free(image_matrix[i]);
}
free(image_matrix);
free(image_matrix);
}
if (inner_counts) {
free(inner_counts);
free(inner_counts);
}
if (xpathObj) xmlXPathFreeObject(xpathObj);
if (xpathCtx) xmlXPathFreeContext(xpathCtx);
if (doc) xmlFreeDoc(doc);
if (xpathObj)
xmlXPathFreeObject(xpathObj);
if (xpathCtx)
xmlXPathFreeContext(xpathCtx);
if (doc)
xmlFreeDoc(doc);
free(html);
curl_free(encoded_query);
free(display_query);
free_context(&ctx);
return 0;
}
}

367
src/Routes/Search.c
View File

@@ -1,8 +1,8 @@
#include "Search.h"
#include "../Infobox/Wikipedia.h"
#include "../Infobox/Calculator.h"
#include "../Infobox/Dictionary.h"
#include "../Infobox/UnitConversion.h"
#include "../Infobox/Wikipedia.h"
#include "../Scraping/Scraping.h"
#include "../Utility/Display.h"
#include "../Utility/Unescape.h"
@@ -23,62 +23,66 @@ static void *wiki_thread_func(void *arg) {
InfoBoxThreadData *data = (InfoBoxThreadData *)arg;
char *dynamic_url = construct_wiki_url(data->query);
if (dynamic_url) {
data->result = fetch_wiki_data(dynamic_url);
data->success =
(data->result.title != NULL && data->result.extract != NULL &&
strlen(data->result.extract) > 10);
free(dynamic_url);
data->result = fetch_wiki_data(dynamic_url);
data->success =
(data->result.title != NULL && data->result.extract != NULL &&
strlen(data->result.extract) > 10);
free(dynamic_url);
} else {
data->success = 0;
data->success = 0;
}
return NULL;
}
static int is_calculator_query(const char *query) {
if (!query) return 0;
if (!query)
return 0;
int has_digit = 0;
int has_math_operator = 0;
for (const char *p = query; *p; p++) {
if (isdigit(*p) || *p == '.') {
has_digit = 1;
}
if (*p == '+' || *p == '-' || *p == '*' || *p == '/' || *p == '^') {
has_math_operator = 1;
}
if (isdigit(*p) || *p == '.') {
has_digit = 1;
}
if (*p == '+' || *p == '-' || *p == '*' || *p == '/' || *p == '^') {
has_math_operator = 1;
}
}
if (!has_digit || !has_math_operator) return 0;
if (!has_digit || !has_math_operator)
return 0;
int len = strlen(query);
for (int i = 0; i < len; i++) {
char c = query[i];
if (c == '+' || c == '-' || c == '*' || c == '/' || c == '^') {
int has_num_before = 0;
int has_num_after = 0;
char c = query[i];
if (c == '+' || c == '-' || c == '*' || c == '/' || c == '^') {
int has_num_before = 0;
int has_num_after = 0;
for (int j = i - 1; j >= 0; j--) {
if (isdigit(query[j]) || query[j] == '.') {
has_num_before = 1;
break;
}
if (query[j] != ' ') break;
}
for (int j = i - 1; j >= 0; j--) {
if (isdigit(query[j]) || query[j] == '.') {
has_num_before = 1;
break;
}
if (query[j] != ' ')
break;
}
for (int j = i + 1; j < len; j++) {
if (isdigit(query[j]) || query[j] == '.') {
has_num_after = 1;
break;
}
if (query[j] != ' ') break;
}
for (int j = i + 1; j < len; j++) {
if (isdigit(query[j]) || query[j] == '.') {
has_num_after = 1;
break;
}
if (query[j] != ' ')
break;
}
if (has_num_before || has_num_after) {
return 1;
if (has_num_before || has_num_after) {
return 1;
}
}
}
}
return 0;
}
@@ -87,11 +91,11 @@ static void *calc_thread_func(void *arg) {
InfoBoxThreadData *data = (InfoBoxThreadData *)arg;
if (is_calculator_query(data->query)) {
data->result = fetch_calc_data((char *)data->query);
data->success =
(data->result.title != NULL && data->result.extract != NULL);
data->result = fetch_calc_data((char *)data->query);
data->success =
(data->result.title != NULL && data->result.extract != NULL);
} else {
data->success = 0;
data->success = 0;
}
return NULL;
@@ -101,11 +105,11 @@ static void *dict_thread_func(void *arg) {
InfoBoxThreadData *data = (InfoBoxThreadData *)arg;
if (is_dictionary_query(data->query)) {
data->result = fetch_dictionary_data(data->query);
data->success =
(data->result.title != NULL && data->result.extract != NULL);
data->result = fetch_dictionary_data(data->query);
data->success =
(data->result.title != NULL && data->result.extract != NULL);
} else {
data->success = 0;
data->success = 0;
}
return NULL;
@@ -115,27 +119,30 @@ static void *unit_thread_func(void *arg) {
InfoBoxThreadData *data = (InfoBoxThreadData *)arg;
if (is_unit_conv_query(data->query)) {
data->result = fetch_unit_conv_data(data->query);
data->success =
(data->result.title != NULL && data->result.extract != NULL);
data->result = fetch_unit_conv_data(data->query);
data->success =
(data->result.title != NULL && data->result.extract != NULL);
} else {
data->success = 0;
data->success = 0;
}
return NULL;
}
static int add_infobox_to_collection(InfoBox *infobox, char ****collection,
int **inner_counts, int current_count) {
int **inner_counts, int current_count) {
*collection =
(char ***)realloc(*collection, sizeof(char **) * (current_count + 1));
(char ***)realloc(*collection, sizeof(char **) * (current_count + 1));
*inner_counts =
(int *)realloc(*inner_counts, sizeof(int) * (current_count + 1));
(int *)realloc(*inner_counts, sizeof(int) * (current_count + 1));
(*collection)[current_count] = (char **)malloc(sizeof(char *) * 4);
(*collection)[current_count][0] = infobox->title ? strdup(infobox->title) : NULL;
(*collection)[current_count][1] = infobox->thumbnail_url ? strdup(infobox->thumbnail_url) : NULL;
(*collection)[current_count][2] = infobox->extract ? strdup(infobox->extract) : NULL;
(*collection)[current_count][0] =
infobox->title ? strdup(infobox->title) : NULL;
(*collection)[current_count][1] =
infobox->thumbnail_url ? strdup(infobox->thumbnail_url) : NULL;
(*collection)[current_count][2] =
infobox->extract ? strdup(infobox->extract) : NULL;
(*collection)[current_count][3] = infobox->url ? strdup(infobox->url) : NULL;
(*inner_counts)[current_count] = 4;
@@ -148,15 +155,16 @@ int results_handler(UrlParams *params) {
int page = 1;
if (params) {
for (int i = 0; i < params->count; i++) {
if (strcmp(params->params[i].key, "q") == 0) {
raw_query = params->params[i].value;
} else if (strcmp(params->params[i].key, "p") == 0) {
int parsed = atoi(params->params[i].value);
if (parsed > 1) page = parsed;
for (int i = 0; i < params->count; i++) {
if (strcmp(params->params[i].key, "q") == 0) {
raw_query = params->params[i].value;
} else if (strcmp(params->params[i].key, "p") == 0) {
int parsed = atoi(params->params[i].value);
if (parsed > 1)
page = parsed;
}
}
}
}
context_set(&ctx, "query", raw_query);
@@ -164,14 +172,14 @@ int results_handler(UrlParams *params) {
snprintf(page_str, sizeof(page_str), "%d", page);
snprintf(prev_str, sizeof(prev_str), "%d", page > 1 ? page - 1 : 0);
snprintf(next_str, sizeof(next_str), "%d", page + 1);
context_set(&ctx, "page", page_str);
context_set(&ctx, "page", page_str);
context_set(&ctx, "prev_page", prev_str);
context_set(&ctx, "next_page", next_str);
if (!raw_query || strlen(raw_query) == 0) {
send_response("<h1>No query provided</h1>");
free_context(&ctx);
return -1;
send_response("<h1>No query provided</h1>");
free_context(&ctx);
return -1;
}
pthread_t wiki_tid, calc_tid, dict_tid, unit_tid;
@@ -181,36 +189,36 @@ int results_handler(UrlParams *params) {
InfoBoxThreadData unit_data = {.query = raw_query, .success = 0};
if (page == 1) {
pthread_create(&wiki_tid, NULL, wiki_thread_func, &wiki_data);
pthread_create(&calc_tid, NULL, calc_thread_func, &calc_data);
pthread_create(&dict_tid, NULL, dict_thread_func, &dict_data);
pthread_create(&unit_tid, NULL, unit_thread_func, &unit_data);
pthread_create(&wiki_tid, NULL, wiki_thread_func, &wiki_data);
pthread_create(&calc_tid, NULL, calc_thread_func, &calc_data);
pthread_create(&dict_tid, NULL, dict_thread_func, &dict_data);
pthread_create(&unit_tid, NULL, unit_thread_func, &unit_data);
}
ScrapeJob jobs[ENGINE_COUNT];
SearchResult *all_results[ENGINE_COUNT];
for (int i = 0; i < ENGINE_COUNT; i++) {
all_results[i] = NULL;
jobs[i].engine = &ENGINE_REGISTRY[i];
jobs[i].query = raw_query;
jobs[i].out_results = &all_results[i];
jobs[i].max_results = 10;
jobs[i].results_count = 0;
jobs[i].page = page;
jobs[i].handle = NULL;
jobs[i].response.memory = NULL;
jobs[i].response.size = 0;
jobs[i].response.capacity = 0;
all_results[i] = NULL;
jobs[i].engine = &ENGINE_REGISTRY[i];
jobs[i].query = raw_query;
jobs[i].out_results = &all_results[i];
jobs[i].max_results = 10;
jobs[i].results_count = 0;
jobs[i].page = page;
jobs[i].handle = NULL;
jobs[i].response.memory = NULL;
jobs[i].response.size = 0;
jobs[i].response.capacity = 0;
}
scrape_engines_parallel(jobs, ENGINE_COUNT);
if (page == 1) {
pthread_join(wiki_tid, NULL);
pthread_join(calc_tid, NULL);
pthread_join(dict_tid, NULL);
pthread_join(unit_tid, NULL);
pthread_join(wiki_tid, NULL);
pthread_join(calc_tid, NULL);
pthread_join(dict_tid, NULL);
pthread_join(unit_tid, NULL);
}
char ***infobox_matrix = NULL;
@@ -218,120 +226,135 @@ int results_handler(UrlParams *params) {
int infobox_count = 0;
if (page == 1) {
if (dict_data.success) {
infobox_count = add_infobox_to_collection(&dict_data.result, &infobox_matrix,
&infobox_inner_counts, infobox_count);
}
if (dict_data.success) {
infobox_count =
add_infobox_to_collection(&dict_data.result, &infobox_matrix,
&infobox_inner_counts, infobox_count);
}
if (calc_data.success) {
infobox_count = add_infobox_to_collection(&calc_data.result, &infobox_matrix,
&infobox_inner_counts, infobox_count);
}
if (calc_data.success) {
infobox_count =
add_infobox_to_collection(&calc_data.result, &infobox_matrix,
&infobox_inner_counts, infobox_count);
}
if (unit_data.success) {
infobox_count = add_infobox_to_collection(&unit_data.result, &infobox_matrix,
&infobox_inner_counts, infobox_count);
}
if (unit_data.success) {
infobox_count =
add_infobox_to_collection(&unit_data.result, &infobox_matrix,
&infobox_inner_counts, infobox_count);
}
if (wiki_data.success) {
infobox_count = add_infobox_to_collection(&wiki_data.result, &infobox_matrix,
&infobox_inner_counts, infobox_count);
}
if (wiki_data.success) {
infobox_count =
add_infobox_to_collection(&wiki_data.result, &infobox_matrix,
&infobox_inner_counts, infobox_count);
}
}
if (infobox_count > 0) {
context_set_array_of_arrays(&ctx, "infoboxes", infobox_matrix,
infobox_count, infobox_inner_counts);
for (int i = 0; i < infobox_count; i++) {
for (int j = 0; j < 4; j++) free(infobox_matrix[i][j]);
free(infobox_matrix[i]);
}
free(infobox_matrix);
free(infobox_inner_counts);
context_set_array_of_arrays(&ctx, "infoboxes", infobox_matrix,
infobox_count, infobox_inner_counts);
for (int i = 0; i < infobox_count; i++) {
for (int j = 0; j < 4; j++)
free(infobox_matrix[i][j]);
free(infobox_matrix[i]);
}
free(infobox_matrix);
free(infobox_inner_counts);
}
int total_results = 0;
for (int i = 0; i < ENGINE_COUNT; i++) {
total_results += jobs[i].results_count;
total_results += jobs[i].results_count;
}
if (total_results > 0) {
char ***results_matrix = (char ***)malloc(sizeof(char **) * total_results);
int *results_inner_counts = (int *)malloc(sizeof(int) * total_results);
char **seen_urls = (char **)malloc(sizeof(char *) * total_results);
int unique_count = 0;
char ***results_matrix = (char ***)malloc(sizeof(char **) * total_results);
int *results_inner_counts = (int *)malloc(sizeof(int) * total_results);
char **seen_urls = (char **)malloc(sizeof(char *) * total_results);
int unique_count = 0;
for (int i = 0; i < ENGINE_COUNT; i++) {
for (int j = 0; j < jobs[i].results_count; j++) {
char *display_url = all_results[i][j].url;
for (int i = 0; i < ENGINE_COUNT; i++) {
for (int j = 0; j < jobs[i].results_count; j++) {
char *display_url = all_results[i][j].url;
int is_duplicate = 0;
for (int k = 0; k < unique_count; k++) {
if (strcmp(seen_urls[k], display_url) == 0) {
is_duplicate = 1;
break;
int is_duplicate = 0;
for (int k = 0; k < unique_count; k++) {
if (strcmp(seen_urls[k], display_url) == 0) {
is_duplicate = 1;
break;
}
}
if (is_duplicate) {
free(all_results[i][j].url);
free(all_results[i][j].title);
free(all_results[i][j].snippet);
continue;
}
seen_urls[unique_count] = strdup(display_url);
results_matrix[unique_count] = (char **)malloc(sizeof(char *) * 4);
char *pretty_url = pretty_display_url(display_url);
results_matrix[unique_count][0] = strdup(display_url);
results_matrix[unique_count][1] = strdup(pretty_url);
results_matrix[unique_count][2] = all_results[i][j].title
? strdup(all_results[i][j].title)
: strdup("Untitled");
results_matrix[unique_count][3] =
all_results[i][j].snippet ? strdup(all_results[i][j].snippet)
: strdup("");
results_inner_counts[unique_count] = 4;
free(pretty_url);
free(all_results[i][j].url);
free(all_results[i][j].title);
free(all_results[i][j].snippet);
unique_count++;
}
free(all_results[i]);
}
if (is_duplicate) {
free(all_results[i][j].url);
free(all_results[i][j].title);
free(all_results[i][j].snippet);
continue;
context_set_array_of_arrays(&ctx, "results", results_matrix, unique_count,
results_inner_counts);
char *html = render_template("results.html", &ctx);
if (html) {
send_response(html);
free(html);
}
seen_urls[unique_count] = strdup(display_url);
results_matrix[unique_count] = (char **)malloc(sizeof(char *) * 4);
char *pretty_url = pretty_display_url(display_url);
results_matrix[unique_count][0] = strdup(display_url);
results_matrix[unique_count][1] = strdup(pretty_url);
results_matrix[unique_count][2] = all_results[i][j].title ? strdup(all_results[i][j].title) : strdup("Untitled");
results_matrix[unique_count][3] = all_results[i][j].snippet ? strdup(all_results[i][j].snippet) : strdup("");
results_inner_counts[unique_count] = 4;
free(pretty_url);
free(all_results[i][j].url);
free(all_results[i][j].title);
free(all_results[i][j].snippet);
unique_count++;
for (int i = 0; i < unique_count; i++) {
for (int j = 0; j < 4; j++)
free(results_matrix[i][j]);
free(results_matrix[i]);
free(seen_urls[i]);
}
free(all_results[i]);
}
context_set_array_of_arrays(&ctx, "results", results_matrix, unique_count, results_inner_counts);
char *html = render_template("results.html", &ctx);
if (html) {
send_response(html);
free(html);
}
for (int i = 0; i < unique_count; i++) {
for (int j = 0; j < 4; j++) free(results_matrix[i][j]);
free(results_matrix[i]);
free(seen_urls[i]);
}
free(seen_urls);
free(results_matrix);
free(results_inner_counts);
free(seen_urls);
free(results_matrix);
free(results_inner_counts);
} else {
char *html = render_template("results.html", &ctx);
if (html) {
send_response(html);
free(html);
}
char *html = render_template("results.html", &ctx);
if (html) {
send_response(html);
free(html);
}
}
if (page == 1) {
if (wiki_data.success) free_infobox(&wiki_data.result);
if (calc_data.success) free_infobox(&calc_data.result);
if (dict_data.success) free_infobox(&dict_data.result);
if (unit_data.success) free_infobox(&unit_data.result);
if (wiki_data.success)
free_infobox(&wiki_data.result);
if (calc_data.success)
free_infobox(&calc_data.result);
if (dict_data.success)
free_infobox(&dict_data.result);
if (unit_data.success)
free_infobox(&unit_data.result);
}
free_context(&ctx);
return 0;
}
}

599
src/Scraping/Scraping.c
View File

@@ -11,21 +11,22 @@
#include <unistd.h>
static size_t WriteMemoryCallback(void *contents, size_t size, size_t nmemb,
void *userp) {
void *userp) {
size_t realsize = size * nmemb;
MemoryBuffer *mem = (MemoryBuffer *)userp;
if (mem->size + realsize + 1 > mem->capacity) {
size_t new_cap = mem->capacity == 0 ? 16384 : mem->capacity * 2;
while (new_cap < mem->size + realsize + 1) new_cap *= 2;
size_t new_cap = mem->capacity == 0 ? 16384 : mem->capacity * 2;
while (new_cap < mem->size + realsize + 1)
new_cap *= 2;
char *ptr = (char *)realloc(mem->memory, new_cap);
if (!ptr) {
return 0;
}
mem->memory = ptr;
mem->capacity = new_cap;
char *ptr = (char *)realloc(mem->memory, new_cap);
if (!ptr) {
return 0;
}
mem->memory = ptr;
mem->capacity = new_cap;
}
memcpy(&(mem->memory[mem->size]), contents, realsize);
@@ -37,37 +38,39 @@ static size_t WriteMemoryCallback(void *contents, size_t size, size_t nmemb,
static const char *get_random_user_agent() {
static const char *agents[] = {
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, "
"like Gecko) Chrome/120.0.0.0 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like "
"Gecko) "
"Chrome/120.0.0.0` Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 "
"Firefox/121.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 "
"(KHTML, like Gecko) Version/17.2 Safari/605.1.15"};
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, "
"like Gecko) Chrome/120.0.0.0 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like "
"Gecko) "
"Chrome/120.0.0.0` Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 "
"Firefox/121.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 "
"(KHTML, like Gecko) Version/17.2 Safari/605.1.15"};
return agents[rand() % 5];
}
static int parse_ddg_lite(const char *engine_name, xmlDocPtr doc,
SearchResult **out_results, int max_results) {
SearchResult **out_results, int max_results) {
(void)engine_name;
int found_count = 0;
xmlXPathContextPtr xpathCtx = xmlXPathNewContext(doc);
if (!xpathCtx) {
return 0;
return 0;
}
const char *link_xpath = "//tr[not(contains(@class, 'result-sponsored'))]//a[@class='result-link']";
const char *link_xpath = "//tr[not(contains(@class, "
"'result-sponsored'))]//a[@class='result-link']";
xmlXPathObjectPtr xpathObj =
xmlXPathEvalExpression((xmlChar *)link_xpath, xpathCtx);
xmlXPathEvalExpression((xmlChar *)link_xpath, xpathCtx);
if (!xpathObj || !xpathObj->nodesetval || xpathObj->nodesetval->nodeNr == 0) {
if (xpathObj) xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
if (xpathObj)
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
}
int num_links = xpathObj->nodesetval->nodeNr;
@@ -75,49 +78,54 @@ static int parse_ddg_lite(const char *engine_name, xmlDocPtr doc,
int actual_alloc = (num_links < max_results) ? num_links : max_results;
*out_results = (SearchResult *)calloc(actual_alloc, sizeof(SearchResult));
if (!*out_results) {
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
}
for (int i = 0; i < num_links && found_count < max_results; i++) {
xmlNodePtr linkNode = xpathObj->nodesetval->nodeTab[i];
char *title = (char *)xmlNodeGetContent(linkNode);
char *url = (char *)xmlGetProp(linkNode, (xmlChar *)"href");
char *snippet_text = NULL;
xmlNodePtr linkNode = xpathObj->nodesetval->nodeTab[i];
char *title = (char *)xmlNodeGetContent(linkNode);
char *url = (char *)xmlGetProp(linkNode, (xmlChar *)"href");
char *snippet_text = NULL;
xmlNodePtr current = linkNode->parent;
while (current && xmlStrcasecmp(current->name, (const xmlChar *)"tr") != 0)
current = current->parent;
xmlNodePtr current = linkNode->parent;
while (current && xmlStrcasecmp(current->name, (const xmlChar *)"tr") != 0)
current = current->parent;
if (current && current->next) {
xmlNodePtr snippetRow = current->next;
while (snippetRow &&
xmlStrcasecmp(snippetRow->name, (const xmlChar *)"tr") != 0)
snippetRow = snippetRow->next;
if (snippetRow) {
if (current && current->next) {
xmlNodePtr snippetRow = current->next;
while (snippetRow &&
xmlStrcasecmp(snippetRow->name, (const xmlChar *)"tr") != 0)
snippetRow = snippetRow->next;
if (snippetRow) {
xpathCtx->node = snippetRow;
xmlXPathObjectPtr sObj = xmlXPathEvalExpression(
(xmlChar *)".//td[@class='result-snippet']", xpathCtx);
if (sObj && sObj->nodesetval && sObj->nodesetval->nodeNr > 0) {
snippet_text = (char *)xmlNodeGetContent(sObj->nodesetval->nodeTab[0]);
xpathCtx->node = snippetRow;
xmlXPathObjectPtr sObj = xmlXPathEvalExpression(
(xmlChar *)".//td[@class='result-snippet']", xpathCtx);
if (sObj && sObj->nodesetval && sObj->nodesetval->nodeNr > 0) {
snippet_text =
(char *)xmlNodeGetContent(sObj->nodesetval->nodeTab[0]);
}
if (sObj)
xmlXPathFreeObject(sObj);
xpathCtx->node = NULL;
}
}
if (sObj) xmlXPathFreeObject(sObj);
xpathCtx->node = NULL;
}
}
(*out_results)[found_count].url = unescape_search_url(url);
(*out_results)[found_count].title = strdup(title ? title : "No Title");
(*out_results)[found_count].snippet =
strdup(snippet_text ? snippet_text : "");
(*out_results)[found_count].url = unescape_search_url(url);
(*out_results)[found_count].title = strdup(title ? title : "No Title");
(*out_results)[found_count].snippet = strdup(snippet_text ? snippet_text : "");
found_count++;
found_count++;
if (title) xmlFree(title);
if (url) xmlFree(url);
if (snippet_text) xmlFree(snippet_text);
if (title)
xmlFree(title);
if (url)
xmlFree(url);
if (snippet_text)
xmlFree(snippet_text);
}
xmlXPathFreeObject(xpathObj);
@@ -126,22 +134,23 @@ static int parse_ddg_lite(const char *engine_name, xmlDocPtr doc,
}
static int parse_startpage(const char *engine_name, xmlDocPtr doc,
SearchResult **out_results, int max_results) {
SearchResult **out_results, int max_results) {
(void)engine_name;
int found_count = 0;
xmlXPathContextPtr xpathCtx = xmlXPathNewContext(doc);
if (!xpathCtx) {
return 0;
return 0;
}
const char *container_xpath = "//div[contains(@class, 'result')]";
xmlXPathObjectPtr xpathObj =
xmlXPathEvalExpression((xmlChar *)container_xpath, xpathCtx);
xmlXPathEvalExpression((xmlChar *)container_xpath, xpathCtx);
if (!xpathObj || !xpathObj->nodesetval || xpathObj->nodesetval->nodeNr == 0) {
if (xpathObj) xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
if (xpathObj)
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
}
int num_results = xpathObj->nodesetval->nodeNr;
@@ -149,55 +158,61 @@ static int parse_startpage(const char *engine_name, xmlDocPtr doc,
int actual_alloc = (num_results < max_results) ? num_results : max_results;
*out_results = (SearchResult *)calloc(actual_alloc, sizeof(SearchResult));
if (!*out_results) {
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
}
for (int i = 0; i < num_results && found_count < max_results; i++) {
xmlNodePtr resultNode = xpathObj->nodesetval->nodeTab[i];
xpathCtx->node = resultNode;
xmlNodePtr resultNode = xpathObj->nodesetval->nodeTab[i];
xpathCtx->node = resultNode;
xmlXPathObjectPtr linkObj = xmlXPathEvalExpression(
(xmlChar *)".//a[contains(@class, 'result-link')]", xpathCtx);
char *url =
(linkObj && linkObj->nodesetval && linkObj->nodesetval->nodeNr > 0)
? (char *)xmlGetProp(linkObj->nodesetval->nodeTab[0],
(xmlChar *)"href")
: NULL;
xmlXPathObjectPtr linkObj = xmlXPathEvalExpression(
(xmlChar *)".//a[contains(@class, 'result-link')]", xpathCtx);
char *url =
(linkObj && linkObj->nodesetval && linkObj->nodesetval->nodeNr > 0)
? (char *)xmlGetProp(linkObj->nodesetval->nodeTab[0],
(xmlChar *)"href")
: NULL;
xmlXPathObjectPtr titleObj = xmlXPathEvalExpression(
(xmlChar *)".//h2[contains(@class, 'wgl-title')]", xpathCtx);
char *title =
(titleObj && titleObj->nodesetval && titleObj->nodesetval->nodeNr > 0)
? (char *)xmlNodeGetContent(titleObj->nodesetval->nodeTab[0])
: NULL;
xmlXPathObjectPtr titleObj = xmlXPathEvalExpression(
(xmlChar *)".//h2[contains(@class, 'wgl-title')]", xpathCtx);
char *title =
(titleObj && titleObj->nodesetval && titleObj->nodesetval->nodeNr > 0)
? (char *)xmlNodeGetContent(titleObj->nodesetval->nodeTab[0])
: NULL;
xmlXPathObjectPtr snippetObj = xmlXPathEvalExpression(
(xmlChar *)".//p[contains(@class, 'description')]", xpathCtx);
char *snippet_text =
(snippetObj && snippetObj->nodesetval &&
snippetObj->nodesetval->nodeNr > 0)
? (char *)xmlNodeGetContent(snippetObj->nodesetval->nodeTab[0])
: NULL;
xmlXPathObjectPtr snippetObj = xmlXPathEvalExpression(
(xmlChar *)".//p[contains(@class, 'description')]", xpathCtx);
char *snippet_text =
(snippetObj && snippetObj->nodesetval &&
snippetObj->nodesetval->nodeNr > 0)
? (char *)xmlNodeGetContent(snippetObj->nodesetval->nodeTab[0])
: NULL;
if (url && title) {
(*out_results)[found_count].url = strdup(url);
(*out_results)[found_count].title = strdup(title);
(*out_results)[found_count].snippet =
strdup(snippet_text ? snippet_text : "");
found_count++;
if (url && title) {
(*out_results)[found_count].url = strdup(url);
(*out_results)[found_count].title = strdup(title);
(*out_results)[found_count].snippet =
strdup(snippet_text ? snippet_text : "");
found_count++;
}
if (title)
xmlFree(title);
if (url)
xmlFree(url);
if (snippet_text)
xmlFree(snippet_text);
if (linkObj)
xmlXPathFreeObject(linkObj);
if (titleObj)
xmlXPathFreeObject(titleObj);
if (snippetObj)
xmlXPathFreeObject(snippetObj);
}
if (title) xmlFree(title);
if (url) xmlFree(url);
if (snippet_text) xmlFree(snippet_text);
if (linkObj) xmlXPathFreeObject(linkObj);
if (titleObj) xmlXPathFreeObject(titleObj);
if (snippetObj) xmlXPathFreeObject(snippetObj);
}
xpathCtx->node = NULL;
xpathCtx->node = NULL;
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
@@ -205,22 +220,23 @@ static int parse_startpage(const char *engine_name, xmlDocPtr doc,
}
static int parse_yahoo(const char *engine_name, xmlDocPtr doc,
SearchResult **out_results, int max_results) {
SearchResult **out_results, int max_results) {
(void)engine_name;
int found_count = 0;
xmlXPathContextPtr xpathCtx = xmlXPathNewContext(doc);
if (!xpathCtx) {
return 0;
return 0;
}
const char *container_xpath = "//div[contains(@class, 'algo-sr')]";
xmlXPathObjectPtr xpathObj =
xmlXPathEvalExpression((xmlChar *)container_xpath, xpathCtx);
xmlXPathEvalExpression((xmlChar *)container_xpath, xpathCtx);
if (!xpathObj || !xpathObj->nodesetval || xpathObj->nodesetval->nodeNr == 0) {
if (xpathObj) xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
if (xpathObj)
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
}
int num_results = xpathObj->nodesetval->nodeNr;
@@ -228,53 +244,59 @@ static int parse_yahoo(const char *engine_name, xmlDocPtr doc,
int actual_alloc = (num_results < max_results) ? num_results : max_results;
*out_results = (SearchResult *)calloc(actual_alloc, sizeof(SearchResult));
if (!*out_results) {
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
xmlXPathFreeObject(xpathObj);
xmlXPathFreeContext(xpathCtx);
return 0;
}
for (int i = 0; i < num_results && found_count < max_results; i++) {
xmlNodePtr resultNode = xpathObj->nodesetval->nodeTab[i];
xpathCtx->node = resultNode;
xmlNodePtr resultNode = xpathObj->nodesetval->nodeTab[i];
xpathCtx->node = resultNode;
xmlXPathObjectPtr linkObj = xmlXPathEvalExpression(
(xmlChar *)".//div[contains(@class, 'compTitle')]//a[@target='_blank']",
xpathCtx);
char *url =
(linkObj && linkObj->nodesetval && linkObj->nodesetval->nodeNr > 0)
? (char *)xmlGetProp(linkObj->nodesetval->nodeTab[0],
(xmlChar *)"href")
: NULL;
xmlXPathObjectPtr linkObj = xmlXPathEvalExpression(
(xmlChar *)".//div[contains(@class, 'compTitle')]//a[@target='_blank']",
xpathCtx);
char *url =
(linkObj && linkObj->nodesetval && linkObj->nodesetval->nodeNr > 0)
? (char *)xmlGetProp(linkObj->nodesetval->nodeTab[0],
(xmlChar *)"href")
: NULL;
xmlXPathObjectPtr titleObj = xmlXPathEvalExpression(
(xmlChar *)".//h3[contains(@class, 'title')]", xpathCtx);
char *title =
(titleObj && titleObj->nodesetval && titleObj->nodesetval->nodeNr > 0)
? (char *)xmlNodeGetContent(titleObj->nodesetval->nodeTab[0])
: NULL;
xmlXPathObjectPtr titleObj = xmlXPathEvalExpression(
(xmlChar *)".//h3[contains(@class, 'title')]", xpathCtx);
char *title =
(titleObj && titleObj->nodesetval && titleObj->nodesetval->nodeNr > 0)
? (char *)xmlNodeGetContent(titleObj->nodesetval->nodeTab[0])
: NULL;
xmlXPathObjectPtr snippetObj = xmlXPathEvalExpression(
(xmlChar *)".//div[contains(@class, 'compText')]//p", xpathCtx);
char *snippet_text =
(snippetObj && snippetObj->nodesetval &&
snippetObj->nodesetval->nodeNr > 0)
? (char *)xmlNodeGetContent(snippetObj->nodesetval->nodeTab[0])
: NULL;
xmlXPathObjectPtr snippetObj = xmlXPathEvalExpression(
(xmlChar *)".//div[contains(@class, 'compText')]//p", xpathCtx);
char *snippet_text =
(snippetObj && snippetObj->nodesetval &&
snippetObj->nodesetval->nodeNr > 0)
? (char *)xmlNodeGetContent(snippetObj->nodesetval->nodeTab[0])
: NULL;
if (url && title) {
(*out_results)[found_count].url = unescape_search_url(url);
(*out_results)[found_count].title = strdup(title);
(*out_results)[found_count].snippet =
strdup(snippet_text ? snippet_text : "");
found_count++;
}
if (url && title) {
(*out_results)[found_count].url = unescape_search_url(url);
(*out_results)[found_count].title = strdup(title);
(*out_results)[found_count].snippet =
strdup(snippet_text ? snippet_text : "");
found_count++;
}
if (title) xmlFree(title);
if (url) xmlFree(url);
if (snippet_text) xmlFree(snippet_text);
if (linkObj) xmlXPathFreeObject(linkObj);
if (titleObj) xmlXPathFreeObject(titleObj);
if (snippetObj) xmlXPathFreeObject(snippetObj);
if (title)
xmlFree(title);
if (url)
xmlFree(url);
if (snippet_text)
xmlFree(snippet_text);
if (linkObj)
xmlXPathFreeObject(linkObj);
if (titleObj)
xmlXPathFreeObject(titleObj);
if (snippetObj)
xmlXPathFreeObject(snippetObj);
}
xpathCtx->node = NULL;
@@ -284,36 +306,36 @@ static int parse_yahoo(const char *engine_name, xmlDocPtr doc,
}
const SearchEngine ENGINE_REGISTRY[] = {
{.name = "DuckDuckGo Lite",
.base_url = "https://lite.duckduckgo.com/lite/?q=",
.host_header = "lite.duckduckgo.com",
.referer = "https://lite.duckduckgo.com/",
.page_param = "s",
.page_multiplier = 30,
.page_base = 0,
.parser = parse_ddg_lite},
{.name = "Startpage",
.base_url = "https://www.startpage.com/sp/search?q=",
.host_header = "www.startpage.com",
.referer = "https://www.startpage.com/",
.page_param = "page",
.page_multiplier = 1,
.page_base = 1,
.parser = parse_startpage},
{.name = "Yahoo",
.base_url = "https://search.yahoo.com/search?p=",
.host_header = "search.yahoo.com",
.referer = "https://search.yahoo.com/",
.page_param = "b",
.page_multiplier = 10,
.page_base = 1,
.parser = parse_yahoo}};
{.name = "DuckDuckGo Lite",
.base_url = "https://lite.duckduckgo.com/lite/?q=",
.host_header = "lite.duckduckgo.com",
.referer = "https://lite.duckduckgo.com/",
.page_param = "s",
.page_multiplier = 30,
.page_base = 0,
.parser = parse_ddg_lite},
{.name = "Startpage",
.base_url = "https://www.startpage.com/sp/search?q=",
.host_header = "www.startpage.com",
.referer = "https://www.startpage.com/",
.page_param = "page",
.page_multiplier = 1,
.page_base = 1,
.parser = parse_startpage},
{.name = "Yahoo",
.base_url = "https://search.yahoo.com/search?p=",
.host_header = "search.yahoo.com",
.referer = "https://search.yahoo.com/",
.page_param = "b",
.page_multiplier = 10,
.page_base = 1,
.parser = parse_yahoo}};
const int ENGINE_COUNT = sizeof(ENGINE_REGISTRY) / sizeof(SearchEngine);
static void configure_curl_handle(CURL *curl, const char *full_url,
MemoryBuffer *chunk,
struct curl_slist *headers) {
static void configure_curl_handle(CURL *curl, const char *full_url,
MemoryBuffer *chunk,
struct curl_slist *headers) {
curl_easy_setopt(curl, CURLOPT_URL, full_url);
curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, WriteMemoryCallback);
@@ -340,152 +362,153 @@ int scrape_engines_parallel(ScrapeJob *jobs, int num_jobs) {
retry:
CURLM *multi_handle = curl_multi_init();
if (!multi_handle) {
return -1;
return -1;
}
for (int i = 0; i < num_jobs; i++) {
ScrapeJob *job = &jobs[i];
ScrapeJob *job = &jobs[i];
if (job->handle) {
curl_easy_cleanup(job->handle);
job->handle = NULL;
}
if (job->response.memory) {
free(job->response.memory);
if (job->handle) {
curl_easy_cleanup(job->handle);
job->handle = NULL;
}
if (job->response.memory) {
free(job->response.memory);
}
job->handle = curl_easy_init();
if (!job->handle) {
continue;
}
job->response.memory = (char *)malloc(16384);
job->response.size = 0;
job->response.capacity = 16384;
char full_url[1024];
char *encoded_query = curl_easy_escape(job->handle, job->query, 0);
if (!encoded_query) {
curl_easy_cleanup(job->handle);
job->handle = NULL;
continue;
}
int page = (job->page < 1) ? 1 : job->page;
int page_value =
(page - 1) * job->engine->page_multiplier + job->engine->page_base;
snprintf(full_url, sizeof(full_url), "%s%s&%s=%d", job->engine->base_url,
encoded_query, job->engine->page_param, page_value);
curl_free(encoded_query);
struct curl_slist *headers = NULL;
char host_buf[256], ref_buf[256];
snprintf(host_buf, sizeof(host_buf), "Host: %s", job->engine->host_header);
snprintf(ref_buf, sizeof(ref_buf), "Referer: %s", job->engine->referer);
headers = curl_slist_append(headers, host_buf);
headers = curl_slist_append(headers, ref_buf);
headers = curl_slist_append(
headers,
"Accept: "
"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");
headers = curl_slist_append(headers, "Accept-Language: en-US,en;q=0.5");
headers = curl_slist_append(headers, "DNT: 1");
configure_curl_handle(job->handle, full_url, &job->response, headers);
curl_easy_setopt(job->handle, CURLOPT_PRIVATE, headers);
curl_multi_add_handle(multi_handle, job->handle);
}
job->handle = curl_easy_init();
if (!job->handle) {
continue;
}
job->response.memory = (char *)malloc(16384);
job->response.size = 0;
job->response.capacity = 16384;
char full_url[1024];
char *encoded_query = curl_easy_escape(job->handle, job->query, 0);
if (!encoded_query) {
curl_easy_cleanup(job->handle);
job->handle = NULL;
continue;
}
int page = (job->page < 1) ? 1 : job->page;
int page_value = (page - 1) * job->engine->page_multiplier + job->engine->page_base;
snprintf(full_url, sizeof(full_url), "%s%s&%s=%d",
job->engine->base_url,
encoded_query,
job->engine->page_param,
page_value);
curl_free(encoded_query);
struct curl_slist *headers = NULL;
char host_buf[256], ref_buf[256];
snprintf(host_buf, sizeof(host_buf), "Host: %s", job->engine->host_header);
snprintf(ref_buf, sizeof(ref_buf), "Referer: %s", job->engine->referer);
headers = curl_slist_append(headers, host_buf);
headers = curl_slist_append(headers, ref_buf);
headers = curl_slist_append(headers, "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");
headers = curl_slist_append(headers, "Accept-Language: en-US,en;q=0.5");
headers = curl_slist_append(headers, "DNT: 1");
configure_curl_handle(job->handle, full_url, &job->response, headers);
curl_easy_setopt(job->handle, CURLOPT_PRIVATE, headers);
curl_multi_add_handle(multi_handle, job->handle);
}
usleep(100000 + (rand() % 100000));
usleep(100000 + (rand() % 100000));
int still_running = 0;
curl_multi_perform(multi_handle, &still_running);
do {
int numfds = 0;
CURLMcode mc = curl_multi_wait(multi_handle, NULL, 0, 1000, &numfds);
int numfds = 0;
CURLMcode mc = curl_multi_wait(multi_handle, NULL, 0, 1000, &numfds);
if (mc != CURLM_OK) {
break;
}
if (mc != CURLM_OK) {
break;
}
curl_multi_perform(multi_handle, &still_running);
curl_multi_perform(multi_handle, &still_running);
} while (still_running);
CURLMsg *msg;
int msgs_left;
while ((msg = curl_multi_info_read(multi_handle, &msgs_left))) {
if (msg->msg == CURLMSG_DONE) {
CURL *handle = msg->easy_handle;
if (msg->msg == CURLMSG_DONE) {
CURL *handle = msg->easy_handle;
for (int i = 0; i < num_jobs; i++) {
if (jobs[i].handle && jobs[i].handle == handle) {
ScrapeJob *job = &jobs[i];
for (int i = 0; i < num_jobs; i++) {
if (jobs[i].handle && jobs[i].handle == handle) {
ScrapeJob *job = &jobs[i];
long response_code;
curl_easy_getinfo(handle, CURLINFO_RESPONSE_CODE, &response_code);
long response_code;
curl_easy_getinfo(handle, CURLINFO_RESPONSE_CODE, &response_code);
if (msg->data.result == CURLE_OK && job->response.size > 0) {
xmlDocPtr doc = htmlReadMemory(
job->response.memory, job->response.size, NULL, NULL,
HTML_PARSE_RECOVER | HTML_PARSE_NOERROR | HTML_PARSE_NOWARNING);
if (msg->data.result == CURLE_OK && job->response.size > 0) {
xmlDocPtr doc = htmlReadMemory(
job->response.memory, job->response.size, NULL, NULL,
HTML_PARSE_RECOVER | HTML_PARSE_NOERROR | HTML_PARSE_NOWARNING);
if (doc) {
job->results_count = job->engine->parser(
job->engine->name, doc, job->out_results, job->max_results);
xmlFreeDoc(doc);
if (doc) {
job->results_count = job->engine->parser(
job->engine->name, doc, job->out_results, job->max_results);
xmlFreeDoc(doc);
}
} else {
job->results_count = 0;
}
struct curl_slist *headers;
curl_easy_getinfo(handle, CURLINFO_PRIVATE, &headers);
if (headers)
curl_slist_free_all(headers);
free(job->response.memory);
job->response.memory = NULL;
curl_multi_remove_handle(multi_handle, handle);
if (handle)
curl_easy_cleanup(handle);
job->handle = NULL;
break;
}
}
} else {
job->results_count = 0;
}
struct curl_slist *headers;
curl_easy_getinfo(handle, CURLINFO_PRIVATE, &headers);
if (headers) curl_slist_free_all(headers);
free(job->response.memory);
job->response.memory = NULL;
curl_multi_remove_handle(multi_handle, handle);
if (handle) curl_easy_cleanup(handle);
job->handle = NULL;
break;
}
}
}
}
curl_multi_cleanup(multi_handle);
if (retries < max_proxy_retries && proxy_count > 0) {
int any_failed = 0;
for (int i = 0; i < num_jobs; i++) {
if (jobs[i].results_count == 0 && jobs[i].response.size == 0) {
any_failed = 1;
break;
int any_failed = 0;
for (int i = 0; i < num_jobs; i++) {
if (jobs[i].results_count == 0 && jobs[i].response.size == 0) {
any_failed = 1;
break;
}
}
if (any_failed) {
retries++;
goto retry;
}
}
if (any_failed) {
retries++;
goto retry;
}
}
return 0;
}
int scrape_engine(const SearchEngine *engine, const char *query,
SearchResult **out_results, int max_results) {
ScrapeJob job = {
.engine = engine,
.query = (char *)query,
.out_results = out_results,
.max_results = max_results,
.results_count = 0,
.page = 1
};
SearchResult **out_results, int max_results) {
ScrapeJob job = {.engine = engine,
.query = (char *)query,
.out_results = out_results,
.max_results = max_results,
.results_count = 0,
.page = 1};
scrape_engines_parallel(&job, 1);
return job.results_count;
}
}

12
src/Scraping/Scraping.h
View File

@@ -1,8 +1,8 @@
#ifndef SCRAPING_H
#define SCRAPING_H
#include <libxml/HTMLparser.h>
#include <curl/curl.h>
#include <libxml/HTMLparser.h>
typedef struct {
char *url;
@@ -11,7 +11,7 @@ typedef struct {
} SearchResult;
typedef int (*ParserFunc)(const char *engine_name, xmlDocPtr doc,
SearchResult **out_results, int max_results);
SearchResult **out_results, int max_results);
typedef struct {
const char *name;
@@ -20,8 +20,8 @@ typedef struct {
const char *referer;
const char *page_param;
int page_multiplier;
int page_base;
int page_multiplier;
int page_base;
ParserFunc parser;
} SearchEngine;
@@ -36,7 +36,7 @@ typedef struct {
char *query;
SearchResult **out_results;
int max_results;
int page;
int page;
CURL *handle;
MemoryBuffer response;
int results_count;
@@ -46,7 +46,7 @@ extern const SearchEngine ENGINE_REGISTRY[];
extern const int ENGINE_COUNT;
int scrape_engine(const SearchEngine *engine, const char *query,
SearchResult **out_results, int max_results);
SearchResult **out_results, int max_results);
int scrape_engines_parallel(ScrapeJob *jobs, int num_jobs);

6
src/Utility/Display.c
View File

@@ -5,7 +5,8 @@
#include <strings.h>
char *pretty_display_url(const char *input) {
if (!input) return NULL;
if (!input)
return NULL;
const char *start = input;
@@ -28,7 +29,8 @@ char *pretty_display_url(const char *input) {
}
char *output = (char *)malloc(strlen(temp) * 3 + 1);
if (!output) return NULL;
if (!output)
return NULL;
size_t j = 0;
for (size_t i = 0; temp[i] != '\0'; i++) {

15
src/Utility/Unescape.c
View File

@@ -4,7 +4,8 @@
#include <string.h>
char *unescape_search_url(const char *input) {
if (!input) return NULL;
if (!input)
return NULL;
const char *key = NULL;
const char *start = NULL;
@@ -14,7 +15,8 @@ char *unescape_search_url(const char *input) {
if (strstr(input, "uddg=")) {
key = "uddg=";
start = strstr(input, key);
if (!start) return NULL;
if (!start)
return NULL;
start += strlen(key);
end = strchr(start, '&');
len = end ? (size_t)(end - start) : strlen(start);
@@ -23,7 +25,8 @@ char *unescape_search_url(const char *input) {
else if (strstr(input, "RU=")) {
key = "RU=";
start = strstr(input, key);
if (!start) return strdup(input);
if (!start)
return strdup(input);
start += strlen(key);
end = strchr(start, '/');
len = end ? (size_t)(end - start) : strlen(start);
@@ -34,7 +37,8 @@ char *unescape_search_url(const char *input) {
}
char *output = (char *)malloc(len * 3 + 1);
if (!output) return NULL;
if (!output)
return NULL;
size_t i = 0, j = 0;
while (i < len) {
@@ -60,7 +64,8 @@ char *unescape_search_url(const char *input) {
}
char *url_decode_query(const char *src) {
if (!src) return NULL;
if (!src)
return NULL;
char *res = strdup(src);
char *p = res;
while (*src) {

1
src/Utility/Unescape.h
View File

@@ -7,4 +7,3 @@ char *unescape_search_url(const char *input);
char *url_decode_query(const char *src);
#endif

9
src/Utility/Utility.c
View File

@@ -1,8 +1,11 @@
#include "Utility.h"
int hex_to_int(char c) {
if (c >= '0' && c <= '9') return c - '0';
if (c >= 'a' && c <= 'f') return c - 'a' + 10;
if (c >= 'A' && c <= 'F') return c - 'A' + 10;
if (c >= '0' && c <= '9')
return c - '0';
if (c >= 'a' && c <= 'f')
return c - 'a' + 10;
if (c >= 'A' && c <= 'F')
return c - 'A' + 10;
return -1;
}