dirhunt package

Submodules

dirhunt.cli module

dirhunt.cli.random_spinner()

dirhunt.cli.spinner(spinner_list)

dirhunt.crawler module

class dirhunt.crawler.Crawler(max_workers=None, interesting_extensions=None, interesting_files=None, std=None, progress_enabled=True, timeout=10, depth=3, not_follow_subdomains=False, exclude_sources=(), not_allow_redirects=False, proxies=None, delay=0, limit=1000, to_file=None, user_agent=None, cookies=None, headers=None)

Bases: ThreadPoolExecutor

add_domain(domain)

add_init_urls(*urls)

Add urls to queue.

add_message(body)

add_url(crawler_url, force=False, lock=True)

Add url to queue

close(create_resume=False)

create_report(to_file)

Write to a file a report with current json() state. This file can be read to continue an analysis.

echo(body)

erase()

get_resume_file()

in_domains(domain)

json()

options()

property options_file

print_progress(finished=False)

print_results(exclude=None, include=None)

print_urls_info()

restart()

resume(path)

urls_info = None

dirhunt.exceptions module

exception dirhunt.exceptions.DirHuntError(extra_body='')

Bases: Exception

body = ''

exception dirhunt.exceptions.EmptyError(extra_body='')

Bases: DirHuntError

exception dirhunt.exceptions.IncompatibleVersionError(extra_body='')

Bases: DirHuntError

exception dirhunt.exceptions.RequestError(extra_body='')

Bases: DirHuntError

dirhunt.exceptions.catch(fn)

dirhunt.exceptions.reraise_with_stack(func)

dirhunt.management module

dirhunt.management.comma_separated(ctx, param, value)

dirhunt.management.comma_separated_files(ctx, param, value)

dirhunt.management.eprint(*args, **kwargs)

dirhunt.management.flags_range(flags)

dirhunt.management.key_value(ctx, param, values)

dirhunt.management.latest_release(package)

dirhunt.management.main()

dirhunt.management.print_version(ctx, param, value)

dirhunt.management.status_code_range(start, end)

dirhunt.management.welcome()

dirhunt.processors module

class dirhunt.processors.Error(crawler_url, error)

Bases: ProcessBase

classmethod is_applicable(request, text, crawler_url, soup)

key_name = 'error'

name = 'Error'

process(text, soup=None)

class dirhunt.processors.GenericProcessor(response, crawler_url)

Bases: ProcessBase

key_name = 'generic'

name = 'Generic'

process(text, soup=None)

class dirhunt.processors.Message(error, level='ERROR')

Bases: Error

maybe_directory()

class dirhunt.processors.ProcessBase(response, crawler_url)

Bases: object

add_url(url, depth=3, **kwargs)

property flags

index_file = None

classmethod is_applicable(request, text, crawler_url, soup)

json()

key_name = ''

maybe_directory()

name = ''

process(text, soup=None)

search_index_files()

status_code = 0

url_line()

class dirhunt.processors.ProcessBlankPageRequest(response, crawler_url)

Bases: ProcessHtmlRequest

classmethod is_applicable(response, text, crawler_url, soup)

key_name = 'blank'

name = 'Blank page'

class dirhunt.processors.ProcessCssStyleSheet(response, crawler_url)

Bases: ProcessBase

classmethod is_applicable(response, text, crawler_url, soup)

key_name = 'css'

name = 'CSS StyleSheet'

process(text, soup=None)

class dirhunt.processors.ProcessHtmlRequest(response, crawler_url)

Bases: ProcessBase

analyze_asset(asset)

assets(soup)

classmethod is_applicable(response, text, crawler_url, soup)

key_name = 'html'

links(soup)

name = 'HTML document'

process(text, soup=None)

class dirhunt.processors.ProcessIndexOfRequest(response, crawler_url)

Bases: ProcessHtmlRequest

files = None

property flags

index_titles = ('index of', 'directory listing for')

interesting_ext_files()

interesting_files()

interesting_name_files()

classmethod is_applicable(response, text, crawler_url, soup)

key_name = 'index_of'

name = 'Index Of'

process(text, soup=None)

classmethod repr_file(file)

class dirhunt.processors.ProcessJavaScript(response, crawler_url)

Bases: ProcessBase

classmethod is_applicable(response, text, crawler_url, soup)

key_name = 'js'

name = 'JavaScript'

process(text, soup=None)

class dirhunt.processors.ProcessNotFound(response, crawler_url)

Bases: ProcessBase

property flags

classmethod is_applicable(request, text, crawler_url, soup)

key_name = 'not_found'

name = 'Not Found'

process(text, soup=None)

class dirhunt.processors.ProcessRedirect(response, crawler_url)

Bases: ProcessBase

classmethod is_applicable(request, text, crawler_url, soup)

key_name = 'redirect'

name = 'Redirect'

process(text, soup=None)

redirector = None

dirhunt.processors.get_processor(response, text, crawler_url, soup)

dirhunt.url module

class dirhunt.url.Url(address)

Bases: object

add_extra(data)

breadcrumb()

copy()

property directories

property directory_path

property domain

property domain_port

Dominio con el puerto si lo hay

property fragment

property full_path

property is_absolute

Si es sólo un path o una dirección entera

is_ip()

is_valid()

json()

property name

property only_domain

Dominio sin el puerto

parent()

property path

property port

property protocol

property protocol_domain

property query

set_children(children)

property url

property urlparsed

dirhunt.url.full_url_address(address, url)

:rtype :Url

dirhunt.utils module

dirhunt.utils.catch_keyboard_interrupt(fn, restart=None)

dirhunt.utils.catch_keyboard_interrupt_choices(fn, choices, default_choice)

dirhunt.utils.colored(text, *colors)

dirhunt.utils.confirm_choices_close(choices, default_choice)

dirhunt.utils.confirm_close()

dirhunt.utils.flat_list(values)

dirhunt.utils.force_url(url)

Transform domain.com to http://domain.com

Try the most common protocols until you get an answer. Check the destination url in case the server is redirecting the response to invalidate it.

dirhunt.utils.lrange(start, end)

dirhunt.utils.multiplier_arg(argument)

dirhunt.utils.multiplier_args(arguments)

dirhunt.utils.read_file_lines(file)

dirhunt.utils.remove_ansi_escape(text)

dirhunt.utils.value_is_file_path(value)

Module contents