RugMunchMedia/pryscraper
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(pry): kill cli recursion, delete parser.tmp, fix broken completions, correct hallucinated docs

Browse source
This commit is contained in:
Crypto Rug Munch 2026-07-06 18:26:03 +07:00
parent 68f1690ede
commit c6194ca444
5 changed files with 93 additions and 73 deletions
Download patch file Download diff file Expand all files Collapse all files

110
cli.py
View file

@ -11,7 +11,6 @@ Usage:
pry transform <data> Convert data format
pry run [pry.yml] Execute jobs from pry.yml
pry serve Start the API server
pry completions Install shell autocomplete
pry proxy ... Manage proxy providers and signup
"""
@ -231,28 +230,68 @@ def cmd_serve(host="0.0.0.0", port=8005): # nosec B104
os.execvp("uvicorn", ["uvicorn", "api:app", "--host", host, "--port", str(port)])
def _print_usage() -> None:
"""Print the standard Pry usage block (no exit)."""
print(f"{BOLD}Pry v{VERSION}{NC} — Pry open any website. {CYAN}pry.dev{NC}")
print()
print(f" {BOLD}Usage:{NC}")
print(f" {CYAN}pry open <url>{NC} Scrape a URL")
print(f" {CYAN}pry watch <url>{NC} Monitor for changes")
print(f" {CYAN}pry crawl <url>{NC} Crawl a site")
print(f" {CYAN}pry batch <file>{NC} Batch scrape from a file")
print(f" {CYAN}pry parse <url>{NC} Parse a document")
print(f" {CYAN}pry ss <url>{NC} Take a screenshot")
print(f" {CYAN}pry run [pry.yml]{NC} Execute job file")
print(f" {CYAN}pry migrate{NC} Run database migrations")
print(f" {CYAN}pry serve{NC} Start the server")
print(f" {CYAN}pry completions{NC} Install autocomplete")
print(f" {CYAN}pry proxy ...{NC} Manage proxy providers and signup")
print()
print(f" {BOLD}Examples:{NC}")
print(" pry open https://example.com")
print(" pry open https://store.com --json --schema product.json")
print(" pry watch https://site.com --webhook slack://...")
print(" pry crawl https://docs.com --max-pages 20 -o data.json")
print(' pry batch urls.txt --template \'{"price":".price"}\'')
print(" pry run")
print(" pry serve")
print(" pry proxy list")
print(" pry proxy signup brightdata")
print()
print(f" {BOLD}Settings:{NC}")
print(" PRY_URL=http://localhost:8005 (default)")
def cmd_completions(shell="bash"):
"""Install shell autocomplete."""
script = {
"bash": 'eval "$(_PRY_COMPLETE=bash_source pry)"',
"zsh": 'eval "$(_PRY_COMPLETE=zsh_source pry)"',
"fish": 'eval "$(_PRY_COMPLETE=fish_source pry)"',
}.get(shell, "")
if shell == "bash":
rc = os.path.expanduser("~/.bashrc")
elif shell == "zsh":
rc = os.path.expanduser("~/.zshrc")
elif shell == "fish":
rc = os.path.expanduser("~/.config/fish/config.fish")
else:
"""Print shell-autocomplete installation instructions.
Pry does not currently ship a `_PRY_COMPLETE` env-var handler, so we do
not silently write a broken eval line into the user's shell rc file.
Print copy/paste instructions instead.
"""
if shell not in ("bash", "zsh", "fish"):
print(f"{YELLOW}Unknown shell: {shell}. Supported: bash, zsh, fish{NC}")
return
dirname = os.path.dirname(rc)
os.makedirs(dirname, exist_ok=True)
with open(rc, "a") as f:
f.write(f"\n# Pry autocomplete\n{script}\n")
print(f"{GREEN}✓{NC} Autocomplete installed for {shell}")
print(f" Restart your shell or run: source {rc}")
print(f"{BOLD}Pry shell autocomplete ({shell}){NC}")
print()
if shell == "bash":
print(" Add the following line to your ~/.bashrc:")
print(f" {CYAN}eval \"$(register-python-argcomplete pry)\"{NC}")
print()
print(" install dependency: pip install argcomplete")
elif shell == "zsh":
print(" Add the following line to your ~/.zshrc:")
print(f" {CYAN}eval \"$(register-python-argcomplete --shell zsh pry)\"{NC}")
print()
print(" install dependency: pip install argcomplete")
else:
print(" Add the following line to ~/.config/fish/config.fish:")
print(f" {CYAN}register-python-argcomplete --shell fish pry | source{NC}")
print()
print(" install dependency: pip install argcomplete")
print()
print(f"{YELLOW}Note:{NC} Pry does not yet wire `_PRY_COMPLETE` itself; once it")
print(" does, this command will switch to a one-shot installer.")
def main():
@ -260,34 +299,7 @@ def main():
cli.main(standalone_mode=False)
return
if len(sys.argv) < 2:
print(f"{BOLD}Pry v{VERSION}{NC} — Pry open any website. {CYAN}pry.dev{NC}")
print()
print(f" {BOLD}Usage:{NC}")
print(f" {CYAN}pry open <url>{NC} Scrape a URL")
print(f" {CYAN}pry watch <url>{NC} Monitor for changes")
print(f" {CYAN}pry crawl <url>{NC} Crawl a site")
print(f" {CYAN}pry batch <file>{NC} Batch scrape from a file")
print(f" {CYAN}pry parse <url>{NC} Parse a document")
print(f" {CYAN}pry ss <url>{NC} Take a screenshot")
print(f" {CYAN}pry run [pry.yml]{NC} Execute job file")
print(f" {CYAN}pry migrate{NC} Run database migrations")
print(f" {CYAN}pry serve{NC} Start the server")
print(f" {CYAN}pry completions{NC} Install autocomplete")
print(f" {CYAN}pry proxy ...{NC} Manage proxy providers and signup")
print()
print(f" {BOLD}Examples:{NC}")
print(" pry open https://example.com")
print(" pry open https://store.com --json --schema product.json")
print(" pry watch https://site.com --webhook slack://...")
print(" pry crawl https://docs.com --max-pages 20 -o data.json")
print(' pry batch urls.txt --template \'{"price":".price"}\'')
print(" pry run")
print(" pry serve")
print(" pry proxy list")
print(" pry proxy signup brightdata")
print()
print(f" {BOLD}Settings:{NC}")
print(" PRY_URL=http://localhost:8005 (default)")
_print_usage()
return
cmd = sys.argv[1]
@ -350,7 +362,7 @@ def main():
print(f"Pry v{VERSION}")
elif cmd in ("-h", "--help", "help"):
main()
_print_usage()
elif cmd == "proxy":
if click is None: