steve/go-extractor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: steve:main
Branches Tags
steve:main
steve:langchain
steve:eggwatch
steve:summary
..
compare: steve:langchain
Branches Tags
steve:main
steve:langchain
steve:eggwatch
steve:summary

No commits in common. "main" and "langchain" have entirely different histories.
main ... langchain

6 changed files with 14 additions and 175 deletions
Show Stats Expand all files Collapse all files

14
go.mod
View File

@ -3,19 +3,19 @@ module gitea.stevedudenhoeffer.com/steve/go-extractor
go 1.23.2
require (
github.com/go-shiori/go-readability v0.0.0-20250217085726-9f5bf5ca7612
github.com/playwright-community/playwright-go v0.5001.0
github.com/go-shiori/go-readability v0.0.0-20241012063810-92284fa8a71f
github.com/playwright-community/playwright-go v0.4802.0
github.com/urfave/cli/v3 v3.0.0-beta1
golang.org/x/text v0.23.0
golang.org/x/text v0.21.0
)
require (
github.com/andybalholm/cascadia v1.3.3 // indirect
github.com/andybalholm/cascadia v1.3.2 // indirect
github.com/araddon/dateparse v0.0.0-20210429162001-6b43995a97de // indirect
github.com/deckarep/golang-set/v2 v2.8.0 // indirect
github.com/go-jose/go-jose/v3 v3.0.4 // indirect
github.com/deckarep/golang-set/v2 v2.6.0 // indirect
github.com/go-jose/go-jose/v3 v3.0.3 // indirect
github.com/go-shiori/dom v0.0.0-20230515143342-73569d674e1c // indirect
github.com/go-stack/stack v1.8.1 // indirect
github.com/gogs/chardet v0.0.0-20211120154057-b7413eaefb8f // indirect
golang.org/x/net v0.37.0 // indirect
golang.org/x/net v0.32.0 // indirect
)

33
node.go
View File

@ -1,9 +1,6 @@
package extractor
import (
"fmt"
"strings"
"github.com/playwright-community/playwright-go"
)
@ -20,9 +17,6 @@ type Node interface {
SelectFirst(selector string) Node
ForEach(selector string, fn func(Node) error) error
SetHidden(val bool) error
SetAttribute(name, value string) error
}
type node struct {
@ -85,30 +79,3 @@ func (n node) ForEach(selector string, fn func(Node) error) error {
return nil
}
func (n node) SetHidden(val bool) error {
visible, err := n.locator.IsVisible()
if err != nil {
return fmt.Errorf("error checking visibility: %w", err)
}
if visible == !val {
return nil
}
// Set the hidden property
_, err = n.locator.Evaluate(fmt.Sprintf(`(element) => element.hidden = %t;`, val), nil)
if err != nil {
return fmt.Errorf("error setting hidden property: %w", err)
}
return nil
}
func escapeJavaScript(s string) string {
return strings.Replace(strings.Replace(s, "\\", "\\\\", -1), "'", "\\'", -1)
}
func (n node) SetAttribute(name, value string) error {
_, err := n.locator.Evaluate(fmt.Sprintf(`(element) => element.setAttribute('%s', '%s');`, escapeJavaScript(name), escapeJavaScript(value)), nil)
return err
}

35
playwright.go
View File

@ -36,10 +36,6 @@ const (
PlayWrightBrowserSelectionWebKit PlayWrightBrowserSelection = "webkit"
)
type Size struct {
Width int
Height int
}
type PlayWrightBrowserOptions struct {
UserAgent string // If empty, defaults to "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) Gecko/20100101 Firefox/133.0"
Browser PlayWrightBrowserSelection // If unset defaults to Firefox.
@ -50,9 +46,6 @@ type PlayWrightBrowserOptions struct {
CookieJar
ShowBrowser bool // If false, browser will be headless
Dimensions Size
DarkMode bool
}
func cookieToPlaywrightOptionalCookie(cookie Cookie) playwright.OptionalCookie {
@ -83,7 +76,6 @@ func NewPlayWrightBrowser(opts ...PlayWrightBrowserOptions) (Browser, error) {
UserAgent: "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) Gecko/20100101 Firefox/133.0",
Browser: PlayWrightBrowserSelectionFirefox,
Timeout: &thirtySeconds,
DarkMode: false,
}
for _, o := range opts {
@ -99,13 +91,6 @@ func NewPlayWrightBrowser(opts ...PlayWrightBrowserOptions) (Browser, error) {
if o.CookieJar != nil {
opt.CookieJar = o.CookieJar
}
if o.Dimensions.Width > 0 && o.Dimensions.Height > 0 {
opt.Dimensions = o.Dimensions
}
if o.DarkMode {
opt.DarkMode = true
}
opt.ShowBrowser = o.ShowBrowser
}
@ -148,26 +133,8 @@ func NewPlayWrightBrowser(opts ...PlayWrightBrowserOptions) (Browser, error) {
return nil, err
}
var viewport *playwright.Size
if opt.Dimensions.Width > 0 && opt.Dimensions.Height > 0 {
viewport = &playwright.Size{
Width: opt.Dimensions.Width,
Height: opt.Dimensions.Height,
}
}
var scheme *playwright.ColorScheme
if opt.DarkMode {
scheme = playwright.ColorSchemeDark
} else {
scheme = playwright.ColorSchemeNoPreference
}
c, err := browser.NewContext(playwright.BrowserNewContextOptions{
UserAgent: playwright.String(opt.UserAgent),
Viewport: viewport,
ColorScheme: scheme,
UserAgent: playwright.String(opt.UserAgent),
})
if err != nil {
return nil, err

24
sites/duckduckgo/cmd/duckduckgo/main.go
View File

@ -3,11 +3,11 @@ package main
import (
"context"
"fmt"
"github.com/urfave/cli/v3"
"io"
"os"
"strings"
"time"
"github.com/urfave/cli/v3"
"gitea.stevedudenhoeffer.com/steve/go-extractor/cmd/browser/pkg/browser"
"gitea.stevedudenhoeffer.com/steve/go-extractor/sites/duckduckgo"
@ -58,7 +58,6 @@ func deferClose(cl io.Closer) {
func main() {
var flags []cli.Flag
flags = append(flags, browser.Flags...)
flags = append(flags, Flags...)
cli := &cli.Command{
@ -82,24 +81,13 @@ func main() {
return fmt.Errorf("failed to create browser: %w", err)
}
search, err := c.OpenSearch(ctx, b, query)
res, err := c.Search(ctx, b, query)
if err != nil {
return fmt.Errorf("failed to open search: %w", err)
return fmt.Errorf("failed to search: %w", err)
}
defer deferClose(search)
res := search.GetResults()
fmt.Println("Results:", res)
err = search.LoadMore()
if err != nil {
return fmt.Errorf("failed to load more: %w", err)
}
time.Sleep(2 * time.Second)
res = search.GetResults()
fmt.Println("Results:", res)
fmt.Println(res)
return nil
},

15
sites/duckduckgo/duckduckgo.go
View File

@ -77,21 +77,6 @@ func deferClose(cl io.Closer) {
}
}
func (c Config) OpenSearch(ctx context.Context, b extractor.Browser, query string) (SearchPage, error) {
u := c.ToSearchURL(query)
slog.Info("searching", "url", u, "query", query, "config", c, "browser", b)
doc, err := b.Open(ctx, u.String(), extractor.OpenPageOptions{})
if err != nil {
if doc != nil {
_ = doc.Close()
}
return nil, fmt.Errorf("failed to open url: %w", err)
}
return searchPage{doc}, nil
}
func (c Config) Search(ctx context.Context, b extractor.Browser, query string) ([]Result, error) {
u := c.ToSearchURL(query)

68
sites/duckduckgo/page.go
View File

@ -1,68 +0,0 @@
package duckduckgo
import (
"fmt"
"gitea.stevedudenhoeffer.com/steve/go-extractor"
"io"
"log/slog"
)
type SearchPage interface {
io.Closer
GetResults() []Result
LoadMore() error
}
type searchPage struct {
doc extractor.Document
}
func (s searchPage) GetResults() []Result {
var res []Result
var err error
err = s.doc.ForEach(`article[id^="r1-"]`, func(n extractor.Node) error {
var r Result
links := n.Select(`a[href][target="_self"]`)
if len(links) == 0 {
return nil
}
r.URL, err = links[0].Attr(`href`)
if err != nil {
return fmt.Errorf("failed to get link: %w", err)
}
titles := n.Select("h2")
if len(titles) != 0 {
r.Title, _ = titles[0].Text()
}
descriptions := n.Select("span > span")
if len(descriptions) != 0 {
r.Description, _ = descriptions[0].Text()
}
res = append(res, r)
return nil
})
return res
}
func (s searchPage) LoadMore() error {
return s.doc.ForEach(`button#more-results`, func(n extractor.Node) error {
slog.Info("clicking load more", "node", n)
return n.Click()
})
}
func (s searchPage) Close() error {
return s.doc.Close()
}