dirhunt package¶

Submodules¶

dirhunt.cli module¶

dirhunt.cli.random_spinner()[source]¶

dirhunt.cli.spinner(spinner_list)[source]¶

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)[source]¶

Bases: concurrent.futures.thread.ThreadPoolExecutor

add_domain(domain)[source]¶

add_init_urls(*urls)[source]¶: Add urls to queue.

add_message(body)[source]¶

add_url(crawler_url, force=False)[source]¶: Add url to queue

close(create_resume=False)[source]¶

create_report(to_file)[source]¶: Write to a file a report with current json() state. This file can be read to continue an analysis.

echo(body)[source]¶

erase()[source]¶

get_resume_file()[source]¶

in_domains(domain)[source]¶

json()[source]¶

options()[source]¶

property options_file¶

print_progress(finished=False)[source]¶

print_results(exclude=None, include=None)[source]¶

print_urls_info()[source]¶

restart()[source]¶

resume(path)[source]¶

urls_info = None¶

dirhunt.exceptions module¶

exception dirhunt.exceptions.DirHuntError(extra_body='')[source]¶

Bases: Exception

body = ''¶

exception dirhunt.exceptions.EmptyError(extra_body='')[source]¶: Bases: dirhunt.exceptions.DirHuntError

exception dirhunt.exceptions.IncompatibleVersionError(extra_body='')[source]¶: Bases: dirhunt.exceptions.DirHuntError

exception dirhunt.exceptions.RequestError(extra_body='')[source]¶: Bases: dirhunt.exceptions.DirHuntError

dirhunt.exceptions.catch(fn)[source]¶

dirhunt.exceptions.reraise_with_stack(func)[source]¶

dirhunt.management module¶

dirhunt.management.comma_separated(ctx, param, value)[source]¶

dirhunt.management.comma_separated_files(ctx, param, value)[source]¶

dirhunt.management.eprint(*args, **kwargs)[source]¶

dirhunt.management.flags_range(flags)[source]¶

dirhunt.management.key_value(ctx, param, values)[source]¶

dirhunt.management.latest_release(package)[source]¶

dirhunt.management.main()[source]¶

dirhunt.management.print_version(ctx, param, value)[source]¶

dirhunt.management.status_code_range(start, end)[source]¶

dirhunt.management.welcome()[source]¶

dirhunt.processors module¶

class dirhunt.processors.Error(crawler_url, error)[source]¶

Bases: dirhunt.processors.ProcessBase

classmethod is_applicable(request, text, crawler_url, soup)[source]¶

key_name = 'error'¶

name = 'Error'¶

process(text, soup=None)[source]¶

class dirhunt.processors.GenericProcessor(response, crawler_url)[source]¶

Bases: dirhunt.processors.ProcessBase

key_name = 'generic'¶

name = 'Generic'¶

process(text, soup=None)[source]¶

class dirhunt.processors.Message(error, level='ERROR')[source]¶

Bases: dirhunt.processors.Error

maybe_directory()[source]¶

class dirhunt.processors.ProcessBase(response, crawler_url)[source]¶

Bases: object

add_url(url, depth=3, **kwargs)[source]¶

property flags¶

index_file = None¶

classmethod is_applicable(request, text, crawler_url, soup)[source]¶

json()[source]¶

key_name = ''¶

maybe_directory()[source]¶

name = ''¶

process(text, soup=None)[source]¶

search_index_files()[source]¶

status_code = 0¶

url_line()[source]¶

class dirhunt.processors.ProcessBlankPageRequest(response, crawler_url)[source]¶

Bases: dirhunt.processors.ProcessHtmlRequest

classmethod is_applicable(response, text, crawler_url, soup)[source]¶

key_name = 'blank'¶

name = 'Blank page'¶

class dirhunt.processors.ProcessCssStyleSheet(response, crawler_url)[source]¶

Bases: dirhunt.processors.ProcessBase

classmethod is_applicable(response, text, crawler_url, soup)[source]¶

key_name = 'css'¶

name = 'CSS StyleSheet'¶

process(text, soup=None)[source]¶

class dirhunt.processors.ProcessHtmlRequest(response, crawler_url)[source]¶

Bases: dirhunt.processors.ProcessBase

analyze_asset(asset)[source]¶

assets(soup)[source]¶

classmethod is_applicable(response, text, crawler_url, soup)[source]¶

key_name = 'html'¶

links(soup)[source]¶

name = 'HTML document'¶

process(text, soup=None)[source]¶

class dirhunt.processors.ProcessIndexOfRequest(response, crawler_url)[source]¶

Bases: dirhunt.processors.ProcessHtmlRequest

files = None¶

property flags¶

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

interesting_ext_files()[source]¶

interesting_files()[source]¶

interesting_name_files()[source]¶

classmethod is_applicable(response, text, crawler_url, soup)[source]¶

key_name = 'index_of'¶

name = 'Index Of'¶

process(text, soup=None)[source]¶

classmethod repr_file(file)[source]¶

class dirhunt.processors.ProcessJavaScript(response, crawler_url)[source]¶

Bases: dirhunt.processors.ProcessBase

classmethod is_applicable(response, text, crawler_url, soup)[source]¶

key_name = 'js'¶

name = 'JavaScript'¶

process(text, soup=None)[source]¶

class dirhunt.processors.ProcessNotFound(response, crawler_url)[source]¶

Bases: dirhunt.processors.ProcessBase

property flags¶

classmethod is_applicable(request, text, crawler_url, soup)[source]¶

key_name = 'not_found'¶

name = 'Not Found'¶

process(text, soup=None)[source]¶

class dirhunt.processors.ProcessRedirect(response, crawler_url)[source]¶

Bases: dirhunt.processors.ProcessBase

classmethod is_applicable(request, text, crawler_url, soup)[source]¶

key_name = 'redirect'¶

name = 'Redirect'¶

process(text, soup=None)[source]¶

redirector = None¶

dirhunt.processors.get_processor(response, text, crawler_url, soup)[source]¶

dirhunt.url module¶

class dirhunt.url.Url(address)[source]¶

Bases: object

add_extra(data)[source]¶

breadcrumb()[source]¶

copy()[source]¶

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()[source]¶

is_valid()[source]¶

json()[source]¶

property name¶

property only_domain¶: Dominio sin el puerto

parent()[source]¶

property path¶

property port¶

property protocol¶

property protocol_domain¶

property query¶

set_children(children)[source]¶

property url¶

property urlparsed¶

dirhunt.url.full_url_address(address, url)[source]¶

:rtype :Url

dirhunt.utils module¶

dirhunt.utils.catch_keyboard_interrupt(fn, restart=None)[source]¶

dirhunt.utils.catch_keyboard_interrupt_choices(fn, choices, default_choice)[source]¶

dirhunt.utils.colored(text, *colors)[source]¶

dirhunt.utils.confirm_choices_close(choices, default_choice)[source]¶

dirhunt.utils.confirm_close()[source]¶

dirhunt.utils.flat_list(values)[source]¶

dirhunt.utils.force_url(url)[source]¶

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)[source]¶

dirhunt.utils.multiplier_arg(argument)[source]¶

dirhunt.utils.multiplier_args(arguments)[source]¶

dirhunt.utils.read_file_lines(file)[source]¶

dirhunt.utils.remove_ansi_escape(text)[source]¶

dirhunt.utils.value_is_file_path(value)[source]¶

dirhunt package¶

Submodules¶

dirhunt.cli module¶

dirhunt.crawler module¶

dirhunt.exceptions module¶

dirhunt.management module¶

dirhunt.processors module¶

dirhunt.url module¶

dirhunt.utils module¶

Module contents¶

Navigation

Related Topics