Functional parser printing plaintext to stdout.

2 files changed, 111 insertions, 0 deletions

diff --git a/main.go b/main.go
new file mode 100644
index 0000000..51f17e6
--- /dev/null
+++ b/main.go
@@ -0,0 +1,44 @@
+package main
+
+import (
+	"fmt"
+	"net/http"
+	"time"
+)
+
+type post struct {
+	Time    time.Time
+	Content string
+}
+
+func main() {
+	var groups []string
+	groups = append(groups, "")
+
+	for i := range groups {
+		url := "https://www.facebook.com/pg/" + groups[i] + "/posts/"
+
+		resp, err := http.Get(url)
+		if err != nil {
+			panic(err)
+		}
+		defer resp.Body.Close()
+
+		ps, err := parse(resp.Body)
+		if err != nil {
+			panic(err)
+		}
+
+		fmt.Println(url)
+		fmt.Printf("%s", present(ps))
+	}
+}
+
+func present(ps []post) (s string) {
+	for i := range ps {
+		s += ps[i].Time.String() + "\n"
+		s += ps[i].Content + "\n\n"
+	}
+
+	return
+}
diff --git a/parser.go b/parser.go
new file mode 100644
index 0000000..119c689
--- /dev/null
+++ b/parser.go
@@ -0,0 +1,67 @@
+package main
+
+import (
+	"io"
+	"strconv"
+	"strings"
+	"time"
+
+	"golang.org/x/net/html"
+)
+
+// parse takes an io.Reader which is supposed to be an entire web page (like http.Response.Body)
+// and returns the separate posts found inside.
+func parse(r io.Reader) (ps []post, err error) {
+	doc, err := html.Parse(r)
+	if err != nil {
+		return
+	}
+
+	var f func(*html.Node)
+	f = func(n *html.Node) {
+		if n.Type == html.ElementNode && n.Data == "div" {
+			for _, a := range n.Attr {
+				//if a.Key == "class" && strings.Contains(a.Val, "text_exposed_root") {
+				if a.Key == "class" && strings.Contains(a.Val, "userContentWrapper") {
+					var p post
+					parseNode(n, &p)
+					ps = append(ps, p)
+					break
+				}
+			}
+		}
+
+		// loop further down
+		for c := n.FirstChild; c != nil; c = c.NextSibling {
+			f(c)
+		}
+	}
+	f(doc)
+
+	return
+}
+
+func parseNode(n *html.Node, p *post) {
+	if n.Type == html.ElementNode {
+		if n.Data == "abbr" {
+			for _, attr := range n.Attr {
+				if attr.Key == "data-utime" {
+					unix, _ := strconv.ParseInt(attr.Val, 10, 64)
+					p.Time = time.Unix(unix, 0)
+					return
+				}
+			}
+		}
+	}
+
+	if n.Type == html.TextNode {
+		if n.Data != "..." {
+			p.Content += n.Data + "\n"
+		}
+	}
+
+	// loop deeper
+	for c := n.FirstChild; c != nil; c = c.NextSibling {
+		parseNode(c, p)
+	}
+}