summaryrefslogtreecommitdiff
path: root/src/utils.c
blob: 8b3e6915de46762fb4c0acdd370f61468e35d0a7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdbool.h>
#include "utils.h"
#include "../libs/curl.h"
#include "../libs/string.h"

int tokenCount(char *string, char *delimiter)
{
	int totalCount = 0;

	if (string != NULL && delimiter != NULL)
	{
		char *auxString = (char *)calloc(strlen(string) + 1, sizeof(char));
		strcpy(auxString, string);

		char *token = strtok(auxString, delimiter);

		while (token != NULL)
		{
			totalCount++;
			token = strtok(NULL, delimiter);
		}

		free(auxString);
	}

	return totalCount;
}

char **tokenizer(char *string, char *delimiter)
{
	char **tokens = NULL;

	if (string != NULL && delimiter != NULL)
	{
		char *auxString = (char *)calloc(strlen(string) + 1, sizeof(char));
		strcpy(auxString, string);

		tokens = (char **)calloc(tokenCount(auxString, delimiter), sizeof(char *));
		char *tempToken = strtok(auxString, delimiter);

		for (int i = 0; tempToken != NULL; i++)
		{
			tokens[i] = (char *)calloc(strlen(tempToken) + 1, sizeof(char));
			strcpy(tokens[i], tempToken);
			tempToken = strtok(NULL, delimiter);
		}

		free(auxString);
	}
	else
	{
		tokens = (char **)calloc(1, sizeof(char));
	}

	return tokens;
}

void freeTokens(char **tokens, int size)
{
	if ( size > 0 )
	{
		for ( int i = 0; i < size; i++ )
		{
			free(tokens[i]);
		}
	}
	free(tokens);
}

char *queryNormalizer(char *query)
{
	char *norm = NULL;
	if (query != NULL && strlen(query) > 0)
	{
		// Declaring Initial Query Size
		int querySize = strlen(query);

		// Calculating Normalized Query Size Allocation
		for (int i = 0; i < strlen(query); i++)
		{
			if (query[i] == '+' || query[i] == '#' || query[i] == '&')
			{
				querySize += 2;
			}
		}

		// Allocating Memory
		norm = (char *)calloc(querySize + 1, sizeof(char));

		// Creating New Normalized Query
		for (int i = 0, added = 0; i < strlen(query); i++)
		{
			switch (query[i])
			{
				case '+':
					/* fall through */
				case '#':
					/* fall through */
				case '&':
					for (int j = 0; j < 3; j++)
					{
						switch (j)
						{
							case 0:
								norm[i + j + added] = '%';
								break;
							case 1:
								norm[i + j + added] = '2';
								break;
							case 2:
								switch (query[i])
								{
									case '+':
										norm[i + j + added] = 'B';
										break;
									case '#':
										norm[i + j + added] = '3';
										break;
									case '&':
										norm[i + j + added] = '6';
								}
						}
					}
					added += 2;
					break;
				case ' ':
					norm[i + added] = '+';
					break;
				default:
					norm[i + added] = query[i];
			}
		}
	}
	return norm;
}

char* extractQueryJSON(char *youtubeurl)
{
	char *json = NULL;

	if (youtubeurl != NULL && strlen(youtubeurl) > 0)
	{
		char *htmlPage = downloadPage(youtubeurl);
		if ( htmlPage != NULL && strlen(htmlPage) > 0 )
		{
			// Setting Up Vars
			char jsonVar[] = "ytInitialData", needlessHTML[] = ";</script><script", **tokens = tokenizer(htmlPage, " ");
			int numberOfTokens = tokenCount(htmlPage, " ");
			json = (char *)calloc(1, sizeof(char));

			// Extracting JSON String
			for (int i = 0, j = 1; i < numberOfTokens && strstr(tokens[j-1], needlessHTML) == NULL; i++)
			{
				if ( strcmp(tokens[i], jsonVar) == 0 )
				{
					for ( j = i + 2; strstr(tokens[j-1], needlessHTML) == NULL; j++ )
					{
						json = realloc(json, (strlen(json) + strlen(tokens[j]) + 2));
						strcat(json, tokens[j]);
						strcat(json, " ");
					}
				}
			}

			json[strlen(json) - strlen(needlessHTML)] = '\0';
			freeTokens(tokens, numberOfTokens);
		}
		free(htmlPage);
	}
	return json;
}