feat: 有/无序列表的支持，请求公众号url的支持

format/format.go

@@ -14,7 +14,7 @@ func Format(article parse.Article) string {
 	result += metaMdStr
 	var tagsMdStr string = formatTags(article.Tags)
 	result += tagsMdStr
-	var content string = formatContent(article.Content)
+	var content string = formatContent(article.Content, 0)
 	result += content
 	return result
 }
@@ -36,7 +36,7 @@ func formatTags(tags string) string {
 	return tags + "  \n" // TODO
 }
 
-func formatContent(pieces []parse.Piece) string {
+func formatContent(pieces []parse.Piece, depth int) string {
 	var contentMdStr string
 	for _, piece := range pieces {
 		var pieceMdStr string
@@ -62,7 +62,9 @@ func formatContent(pieces []parse.Piece) string {
 			pieceMdStr = formatCodeBlock(piece)
 		case parse.BLOCK_QUOTES:
 		case parse.O_LIST:
+			pieceMdStr = formatList(piece, depth)
 		case parse.U_LIST:
+			pieceMdStr = formatList(piece, depth)
 		case parse.HR:
 		case parse.BR:
 			pieceMdStr = "  \n"
@@ -72,6 +74,21 @@ func formatContent(pieces []parse.Piece) string {
 	return contentMdStr
 }
 
+func formatList(li parse.Piece, depth int) string {
+	var listMdString string
+	var prefix string
+	for j := 0; j < depth; j++ {
+		prefix += "    "
+	}
+	if li.Type == parse.U_LIST {
+		prefix += "- "
+	} else if li.Type == parse.O_LIST {
+		prefix += strconv.Itoa(1) + ". " // 写死成1也大丈夫，markdown会自动累加序号
+	}
+	listMdString += prefix + formatContent(li.Val.([]parse.Piece), depth+1) + "  \n"
+	return listMdString
+}
+
 func formatCodeBlock(piece parse.Piece) string {
 	var codeMdStr string
 	codeMdStr += "```\n"

main.go

@@ -3,5 +3,6 @@ package main
 import "github.com/fengxxc/wechatmp2markdown/test"
 
 func main() {
-	test.Test1()
+	// test.Test1()
+	test.Test2()
 }

parse/parse.go

@@ -17,28 +17,33 @@ import (
 func parseSection(s *goquery.Selection) []Piece {
 	var piece []Piece
 	s.Children().Each(func(i int, s *goquery.Selection) {
-		var p Piece
+		var p []Piece
 		attr := make(map[string]string)
 		if s.Is("span") {
-			p = Piece{NORMAL_TEXT, s.Text(), nil}
+			// p = Piece{NORMAL_TEXT, s.Text(), nil}
+			p = append(p, Piece{NORMAL_TEXT, s.Text(), nil})
 		} else if s.Is("a") {
 			attr["href"], _ = s.Attr("href")
-			p = Piece{LINK, removeBrAndBlank(s.Text()), attr}
+			// p = Piece{LINK, removeBrAndBlank(s.Text()), attr}
+			p = append(p, Piece{LINK, removeBrAndBlank(s.Text()), attr})
 		} else if s.Is("img") {
 			attr["src"], _ = s.Attr("data-src")
 			attr["alt"], _ = s.Attr("alt")
 			attr["title"], _ = s.Attr("title")
-			p = Piece{IMAGE, "", attr}
+			// p = Piece{IMAGE, "", attr}
+			p = append(p, Piece{IMAGE, "", attr})
 		} else if s.Is("ol") {
-			// TODO
+			p = append(p, parseOl(s)...)
 		} else if s.Is("ul") {
-			// TODO
+			p = append(p, parseUl(s)...)
+		} else if s.Is("section") {
+			p = append(p, parseSection(s)...)
 		} else {
-			p = Piece{NORMAL_TEXT, s.Text(), nil}
+			// p = Piece{NORMAL_TEXT, s.Text(), nil}
 			// TODO
 		}
 		// fmt.Printf("%+v\n", t)
-		piece = append(piece, p)
+		piece = append(piece, p...)
 	})
 	return piece
 }
@@ -73,6 +78,24 @@ func parsePre(s *goquery.Selection) []Piece {
 	return []Piece{p}
 }
 
+func parseUl(s *goquery.Selection) []Piece {
+	var list []Piece
+	s.Find("li").Each(func(i int, s *goquery.Selection) {
+		li := Piece{U_LIST, parseSection(s), nil}
+		list = append(list, li)
+	})
+	return list
+}
+
+func parseOl(s *goquery.Selection) []Piece {
+	var list []Piece
+	s.Find("li").Each(func(i int, s *goquery.Selection) {
+		li := Piece{O_LIST, parseSection(s), nil}
+		list = append(list, li)
+	})
+	return list
+}
+
 func ParseFromReader(r io.Reader) Article {
 	var article Article
 	doc, err := goquery.NewDocumentFromReader(r)
@@ -107,18 +130,15 @@ func ParseFromReader(r io.Reader) Article {
 		// var paragraph Paragraph
 		if s.Is("pre") || s.Is("section.code-snippet__fix") {
 			// 代码块
-			// paragraph = parsePre(s)
 			pieces = append(pieces, parsePre(s)...)
 		} else if s.Is("p") || s.Is("section") {
-			// paragraph = parseSection(s)
 			pieces = append(pieces, parseSection(s)...)
 		} else if s.Is("h1") || s.Is("h2") || s.Is("h3") || s.Is("h4") || s.Is("h5") || s.Is("h6") {
-			// paragraph = parseHeader(s)
 			pieces = append(pieces, parseHeader(s)...)
 		} else if s.Is("ol") {
-			// TODO
+			pieces = append(pieces, parseOl(s)...)
 		} else if s.Is("ul") {
-			// TODO
+			pieces = append(pieces, parseUl(s)...)
 		}
 		// sections = append(sections, paragraph)
 		pieces = append(pieces, Piece{BR, nil, nil})

test/test2.go

@@ -0,0 +1,20 @@
+package test
+
+import (
+	"encoding/json"
+	"io/ioutil"
+
+	"github.com/fengxxc/wechatmp2markdown/format"
+	"github.com/fengxxc/wechatmp2markdown/parse"
+)
+
+func Test2() {
+	var articleStruct parse.Article = parse.ParseFromURL("https://mp.weixin.qq.com/s?__biz=MzIzOTU0NTQ0MA==&mid=2247506315&idx=1&sn=1546be4ecece176f669da4eed7076ee2&chksm=e92ae484de5d6d92d93cd68b927fa91e2935a75c9aafc02f294237653ca8a342e8982cabbc1d&cur_album_id=1391790902901014528&scene=189#wechat_redirect")
+
+	byteArry, _ := json.MarshalIndent(articleStruct, "", "  ")
+	// fmt.Println(string(byteArry))
+	ioutil.WriteFile("./test/test2_target.json", byteArry, 0644)
+
+	var mdString string = format.Format((articleStruct))
+	ioutil.WriteFile("./test/test2_target.md", []byte(mdString), 0644)
+}