84 lines
2.5 KiB
Python
84 lines
2.5 KiB
Python
import click
|
|
import json
|
|
from browser_cli.client import send_command, BrowserNotConnected
|
|
from rich.console import Console
|
|
from rich.table import Table
|
|
|
|
console = Console()
|
|
|
|
|
|
def _handle(command, args=None):
|
|
try:
|
|
return send_command(command, args or {})
|
|
except BrowserNotConnected as e:
|
|
console.print(f"[red]Error:[/red] {e}")
|
|
raise SystemExit(1)
|
|
except RuntimeError as e:
|
|
console.print(f"[red]Browser error:[/red] {e}")
|
|
raise SystemExit(1)
|
|
|
|
|
|
@click.group("extract")
|
|
def extract_group():
|
|
"""Extract content from the active tab."""
|
|
|
|
|
|
@extract_group.command("links")
|
|
def extract_links():
|
|
"""Extract all links from the active tab."""
|
|
links = _handle("extract.links")
|
|
if not links:
|
|
console.print("[yellow]No links found[/yellow]")
|
|
return
|
|
table = Table(show_header=True, header_style="bold cyan")
|
|
table.add_column("Text", width=40)
|
|
table.add_column("URL")
|
|
for lnk in links:
|
|
table.add_row((lnk.get("text") or "")[:60], lnk.get("href") or "")
|
|
console.print(table)
|
|
|
|
|
|
@extract_group.command("images")
|
|
def extract_images():
|
|
"""Extract all images from the active tab."""
|
|
images = _handle("extract.images")
|
|
if not images:
|
|
console.print("[yellow]No images found[/yellow]")
|
|
return
|
|
table = Table(show_header=True, header_style="bold cyan")
|
|
table.add_column("Alt", width=30)
|
|
table.add_column("Src")
|
|
for img in images:
|
|
table.add_row((img.get("alt") or "")[:40], img.get("src") or "")
|
|
console.print(table)
|
|
|
|
|
|
@extract_group.command("text")
|
|
def extract_text():
|
|
"""Extract all visible text from the active tab."""
|
|
text = _handle("extract.text")
|
|
console.print(text or "")
|
|
|
|
|
|
@extract_group.command("json")
|
|
@click.argument("selector")
|
|
def extract_json(selector):
|
|
"""Parse and pretty-print JSON content inside SELECTOR."""
|
|
data = _handle("extract.json", {"selector": selector})
|
|
console.print_json(json.dumps(data))
|
|
|
|
|
|
@extract_group.command("html")
|
|
def extract_html():
|
|
"""Print the full HTML of the active tab to stdout."""
|
|
html = _handle("extract.html")
|
|
click.echo(html or "")
|
|
|
|
|
|
@extract_group.command("markdown")
|
|
@click.option("--selector", help="Extract only the DOM subtree matching this CSS selector.")
|
|
def extract_markdown(selector):
|
|
"""Extract the page's main content as Markdown."""
|
|
markdown = _handle("extract.markdown", {"selector": selector})
|
|
click.echo(markdown or "", nl=not (markdown or "").endswith("\n"))
|