summaryrefslogtreecommitdiff
path: root/sift.go
blob: fdd01fd7aa201c10343407a7d66f474da3c4c5a4 (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
// Generate CSV from Google Books queries.
// authors, title, publishedDate, publisher, ISBN-13, ISBN-10, URL
package main

import (
	"bufio"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"io/fs"
	"log"
	"os"
	"strings"
)

func readFile(name string) []byte {
	in, err := os.Open(name)
	if err != nil {
		log.Fatal(err)
	}
	defer in.Close()
	body, err := io.ReadAll(in)
	if err != nil {
		log.Fatal(err)
	}

	return body
}

func write(writer *bufio.Writer, contents string) {
	_, err := writer.Write([]byte(contents))
	if err != nil {
		log.Fatal(err)
	}
}

/* Unnecessary complication.
Only one entry needs to be in memory at a time.
type Entry struct {
	authors: string
	title: string
	publishedDate: string
	isbn13: string
	isbn10: string
	url: string
}*/

func main() {
	// Read a list of file names, named after google books queries
	var fullTitle, authors, publishedDate, isbn13, isbn10, url string

	for _, title := range strings.Split(string(readFile("list")), "\n") {
		if (len(title) < 3) {
			continue
		}

		fmt.Println(title)

		// For each title, create csv file
		var out *os.File
		_, err := os.Stat(title + ".csv")
		if errors.Is(err, fs.ErrNotExist) {
			//log.Print(err)
			out, err = os.Create(title + ".csv")
			if err != nil {
				log.Fatal(err)
			}
		} else if err != nil {
			log.Fatal(err)
		} else {
			out, err = os.Open(title + ".csv")
			if err != nil {
				log.Fatal(err)
			}
		}
		defer out.Close()

		outWriter := bufio.NewWriter(out)
		//outWriter := bufio.NewWriter(os.Stdout)

		// Print CSV header
		write(outWriter, "Title, Authors, Published Date, ISBN-13, ISBN-10, URL\n")
		defer outWriter.Flush()

		// In each provided file, JSON results
		rawJson := readFile(title)
		var data interface{}
		// Parse the JSON into an associative array
		json.Unmarshal(rawJson, &data)
		// Get through the cruft
		m := data.(map[string]interface{})
		for _, subm := range m["items"].([]interface{}) {
			switch subm.(type) {
			case map[string]interface{}:
				m := subm.(map[string]interface{})
				m = m["volumeInfo"].(map[string]interface{})
				isbns := m["industryIdentifiers"].([]interface{})
				for _, v := range isbns {
					isbn := v.(map[string]interface{})
					isbnText := isbn["identifier"].(string)
					// ISBN-10 is sometimes 9 digits, ISBN-13 is always 13 digits
					if len(isbnText) == 13 {
						isbn13 = isbnText
					} else {
						isbn10 = isbnText
					}
				}

				if m["authors"] != nil {
					authorsMap := m["authors"].([]interface{})
					for i, author := range authorsMap {
						authorText := author.(string)
						if i > 0 {
							authors += " & "
							authors += authorText
						} else {
							authors = authorText
						}
					}
				}

				fullTitle = strings.Replace(m["title"].(string), ",", "", -1)
				if m["publishedDate"] != nil {
					publishedDate = m["publishedDate"].(string)
				}
				url = m["infoLink"].(string)
			default:
			}
			write(outWriter, fmt.Sprintf("%s,%s,%s,%s,%s,%s\n", fullTitle, authors, publishedDate, isbn13, isbn10, url))

		}
	}
}