From 77d8181ef94411d944d08be2afd01d512449904a Mon Sep 17 00:00:00 2001
From: Squibid <me@zacharyscheiman.com>
Date: Sat, 23 Aug 2025 20:24:23 -0400
Subject: [PATCH] inital commit

---
 .gitignore |   1 +
 go.mod     |   6 +++
 go.sum     |   4 ++
 main.go    | 105 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 116 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 go.mod
 create mode 100644 go.sum
 create mode 100644 main.go

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..9be7342
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+*sites.db*
diff --git a/go.mod b/go.mod
new file mode 100644
index 0000000..cc1d5b8
--- /dev/null
+++ b/go.mod
@@ -0,0 +1,6 @@
+module squibid/scraper
+
+go 1.24.5
+
+require golang.org/x/net v0.43.0
+require github.com/mattn/go-sqlite3 v1.14.32 // indirect
diff --git a/go.sum b/go.sum
new file mode 100644
index 0000000..3dc33f3
--- /dev/null
+++ b/go.sum
@@ -0,0 +1,4 @@
+github.com/mattn/go-sqlite3 v1.14.32 h1:JD12Ag3oLy1zQA+BNn74xRgaBbdhbNIDYvQUEuuErjs=
+github.com/mattn/go-sqlite3 v1.14.32/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
+golang.org/x/net v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE=
+golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg=
diff --git a/main.go b/main.go
new file mode 100644
index 0000000..e2f8d31
--- /dev/null
+++ b/main.go
@@ -0,0 +1,105 @@
+package main
+
+import (
+	"database/sql"
+	"fmt"
+	"io"
+	"log"
+	"net/http"
+	"strings"
+
+	_ "github.com/mattn/go-sqlite3"
+	"golang.org/x/net/html"
+)
+
+var db *sql.DB
+
+func db_insert_url(url string, seen bool) {
+	db.Exec(`insert into urls values (?, ?)`, url, seen)
+}
+
+func deal_html(site string, reader io.Reader) {
+	doc, err := html.Parse(reader)
+	if err != nil {
+		fmt.Println("Error parsing HTML:", err)
+		return
+	}
+
+	var insert_url string
+	var walk func(n *html.Node)
+	walk = func(n *html.Node) {
+		if n.Type == html.ElementNode && n.Data == "a" {
+			for _, attr := range n.Attr {
+				if attr.Key == "href" && len(attr.Val) > 1 {
+					if attr.Val[:2] == "//" {
+						insert_url = "https:" + attr.Val
+					} else if attr.Val[:1] == "/" {
+						if site[len(site) - 1:] == "/" {
+							insert_url = site + attr.Val[1:]
+						} else {
+							insert_url = site + attr.Val
+						}
+					} else if len(attr.Val) > 4 && attr.Val[:4] == "http" {
+						insert_url = attr.Val
+					}
+					db_insert_url(insert_url, site == insert_url)
+				}
+			}
+		}
+		for c := n.FirstChild; c != nil; c = c.NextSibling {
+			walk(c)
+		}
+	}
+	walk(doc)
+}
+
+func main() {
+	var err any
+
+	site := "https://squi.bid/"
+	db, err = sql.Open("sqlite3", "./sites.db")
+	if err != nil {
+		log.Fatal(err)
+	}
+	defer db.Close()
+	db.Exec(`
+		create table if not exists
+		urls (url text not null primary key, indexed boolean not null);
+		`)
+
+	/* start fetching the sites */
+	for i := 0;; i++ {
+		if i > 0 {
+			rows, err := db.Query(`select url from urls where indexed is false`)
+			if err != nil {
+				return
+			}
+
+			for	rows.Next() {
+				var test string
+				rows.Scan(&test)
+				site = test
+				/* we can't just check if the site is the same because then when we're
+				 * checking squi.bid/example it won't register squi.bid as the same
+				 * domain, although maybe that's what we want.
+				 */
+				if !strings.Contains(test, site) {
+					break
+				}
+			}
+			rows.Close()
+		}
+
+		fmt.Println("fetching " + site)
+		resp, err := http.Get(site)
+		if err != nil {
+			fmt.Println("Error getting", site)
+			continue
+		}
+
+		deal_html(site, resp.Body)
+		db.Exec(`update urls set indexed = true where url == ?`, site)
+
+		resp.Body.Close()
+	}
+}