steve
c3be14095a
Playwright's bundled Chromium has a distinct build fingerprint (build ID, uniform WebGL/codec lists, HeadlessChrome residue) that anti-bot services increasingly flag. Driving a system-installed Google Chrome via Playwright's channel option sheds that signal and aligns sec-ch-ua with UA more cleanly. Changes: - Add BrowserOptions.Channel string field (chrome, chrome-beta, chromium, msedge; empty = default). - When stealth+headless+Chromium and Channel is empty, default to "chrome" (was "chromium"). Explicit Channel values always win, so callers can opt back to "chromium" or pick another channel. - Merge Channel in mergeOptions. - Expose --channel/--ch flag on cmd/browser for A/B fingerprint testing. Callers must have the chosen browser installed on the host (e.g. `playwright install chrome`). Firefox and WebKit paths are untouched. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
97 lines
2.2 KiB
Go
97 lines
2.2 KiB
Go
package browser
|
|
|
|
import (
|
|
"context"
|
|
"time"
|
|
|
|
"github.com/urfave/cli/v3"
|
|
|
|
"gitea.stevedudenhoeffer.com/steve/go-extractor"
|
|
)
|
|
|
|
type BrowserFlags []cli.Flag
|
|
|
|
var Flags = BrowserFlags{
|
|
&cli.StringFlag{
|
|
Name: "user-agent",
|
|
Aliases: []string{"ua"},
|
|
Usage: "User-Agent to use for requests",
|
|
DefaultText: extractor.DefaultUserAgent,
|
|
},
|
|
&cli.StringFlag{
|
|
Name: "timeout",
|
|
Aliases: []string{"t"},
|
|
Usage: "Timeout for requests",
|
|
DefaultText: "30s",
|
|
},
|
|
&cli.StringFlag{
|
|
Name: "browser",
|
|
Aliases: []string{"b"},
|
|
Usage: "Browser to use, one of: chromium, firefox, webkit",
|
|
DefaultText: "firefox",
|
|
},
|
|
&cli.StringFlag{
|
|
Name: "cookies-file",
|
|
Aliases: []string{"c"},
|
|
Usage: "cookies.txt file to load cookies from",
|
|
DefaultText: "",
|
|
},
|
|
&cli.BoolFlag{
|
|
Name: "visible",
|
|
Usage: "If set, the browser will be visible, if not set, the browser will be headless",
|
|
DefaultText: "false",
|
|
},
|
|
&cli.BoolFlag{
|
|
Name: "no-stealth",
|
|
Usage: "Disable stealth mode (anti-bot-detection evasions are enabled by default)",
|
|
DefaultText: "false",
|
|
},
|
|
&cli.StringFlag{
|
|
Name: "channel",
|
|
Usage: "Chromium channel to launch (chrome, chrome-beta, chromium, msedge). Only applies when --browser=chromium. Empty = stealth default (chrome).",
|
|
Aliases: []string{"ch"},
|
|
},
|
|
}
|
|
|
|
func FromCommand(ctx context.Context, cmd *cli.Command) (extractor.Browser, error) {
|
|
var opts extractor.BrowserOptions
|
|
|
|
if ua := cmd.String("user-agent"); ua != "" {
|
|
opts.UserAgent = ua
|
|
}
|
|
|
|
if to := cmd.String("timeout"); to != "" {
|
|
d, err := time.ParseDuration(to)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
opts.Timeout = &d
|
|
}
|
|
|
|
if b := cmd.String("browser"); b != "" {
|
|
opts.Browser = extractor.BrowserSelection(b)
|
|
}
|
|
|
|
if cf := cmd.String("cookies-file"); cf != "" {
|
|
cookies, err := extractor.LoadCookiesFile(cf)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
opts.CookieJar = cookies
|
|
}
|
|
|
|
if cmd.IsSet("visible") {
|
|
opts.ShowBrowser = extractor.Bool(cmd.Bool("visible"))
|
|
}
|
|
|
|
if cmd.IsSet("no-stealth") && cmd.Bool("no-stealth") {
|
|
opts.Stealth = extractor.Bool(false)
|
|
}
|
|
|
|
if ch := cmd.String("channel"); ch != "" {
|
|
opts.Channel = ch
|
|
}
|
|
|
|
return extractor.NewBrowser(ctx, opts)
|
|
}
|