10

[Golang] HTML Table to reStructuredText list-table via goquery

 3 years ago
source link: http://siongui.github.io/2016/04/14/go-html-table-to-rst-list-table-via-goquery/
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client

HTML table to reStructuredText list-table

goquery.go | repository | view raw 

package table2rst

import (
	"bufio"
	"fmt"
	"github.com/PuerkitoBio/goquery"
	"os"
	"strings"
)

func StringToLines(s string) []string {
	var lines []string

	scanner := bufio.NewScanner(strings.NewReader(s))
	for scanner.Scan() {
		lines = append(lines, scanner.Text())
	}

	if err := scanner.Err(); err != nil {
		fmt.Fprintln(os.Stderr, "reading standard input:", err)
	}

	return lines
}

func rstListTablePrefixOfEachLine(indexOfTd, indexOfLine int) string {
	if indexOfTd == 0 {
		if indexOfLine == 0 {
			return "   * - "
		} else {
			return "       "
		}
	} else {
		if indexOfLine == 0 {
			return "     - "
		} else {
			return "       "
		}
	}
}

func processTr(tr *goquery.Selection, fRstOutput *os.File) {
	tr.Find("td").Each(func(indexOfTd int, td *goquery.Selection) {
		lines := StringToLines(td.Text())
		for indexOfLine, line := range lines {
			line = strings.TrimSpace(line)
			fmt.Fprintf(fRstOutput, rstListTablePrefixOfEachLine(indexOfTd, indexOfLine))
			fmt.Fprintf(fRstOutput, line)
			fmt.Fprintf(fRstOutput, "\n")
		}
	})
}

func htmlTableToRst(url, outputFilePath string) {
	doc, err := goquery.NewDocument(url)
	if err != nil {
		panic(err)
	}

	fRstOutput, err := os.Create(outputFilePath)
	if err != nil {
		panic(err)
	}

	doc.Find("table").Each(func(_ int, table *goquery.Selection) {
		fmt.Fprintf(fRstOutput, ".. list-table:: \n\n")
		table.Find("tr").Each(func(_ int, tr *goquery.Selection) {
			processTr(tr, fRstOutput)
		})
		fmt.Fprintf(fRstOutput, "\n\n")
		fmt.Fprintf(fRstOutput, "|\n|\n\n")
	})
}

report

Recommend

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK