mcp-server-webcrawl
Contents:
Installation
Setup Guides
Usage
mcp_server_webcrawl
mcp-server-webcrawl
Index
Index
_
|
A
|
B
|
C
|
D
|
F
|
G
|
I
|
K
|
M
|
O
|
P
|
R
|
S
|
T
|
U
|
V
|
W
_
__init__() (BaseCrawler method)
(BaseJsonApi method)
(BaseManager method)
(IndexedCrawler method)
(IndexedManager method)
(IndexState method)
(InterroBotCrawler method)
(InterroBotManager method)
(KatanaCrawler method)
(KatanaManager method)
(ResourceResult method)
(SiteOneCrawler method)
(SiteOneManager method)
(SiteResult method)
(SitesGroup method)
(SitesStat method)
(ThumbnailManager method)
(WarcCrawler method)
(WarcManager method)
(WgetCrawler method)
(WgetManager method)
A
append_error() (BaseJsonApi method)
AUDIO (ResourceResultType attribute)
B
BaseCrawler (class in mcp_server_webcrawl.crawlers.base.crawler)
BaseCrawlerTests (class in mcp_server_webcrawl.crawlers.base.tests)
BaseJsonApi (class in mcp_server_webcrawl.crawlers.base.api)
BaseJsonApiEncoder (class in mcp_server_webcrawl.crawlers.base.api)
BaseManager (class in mcp_server_webcrawl.crawlers.base.adapter)
C
COMPLETE (IndexStatus attribute)
CSS (ResourceResultType attribute)
D
datasrc (BaseCrawler property)
decruft_path() (BaseManager static method)
default() (BaseJsonApiEncoder method)
DOC (ResourceResultType attribute)
duration (IndexState property)
F
FAILED (IndexStatus attribute)
FEED (ResourceResultType attribute)
FONT (ResourceResultType attribute)
FRAME (ResourceResultType attribute)
from_isoformat_zulu() (in module mcp_server_webcrawl.utils)
G
get_basic_headers() (BaseManager static method)
get_connection() (IndexedManager method)
(InterroBotManager method)
get_crawler_tools() (in module mcp_server_webcrawl.utils.tools)
get_fixture_directory() (in module mcp_server_webcrawl.crawlers)
get_help_long_message() (in module mcp_server_webcrawl.utils.cli)
get_help_short_message() (in module mcp_server_webcrawl.utils.cli)
get_initialization_options() (BaseCrawler method)
get_logger() (in module mcp_server_webcrawl.utils.logger)
get_logger_configuration() (in module mcp_server_webcrawl.utils.logger)
get_resources() (in module mcp_server_webcrawl.crawlers.interrobot.adapter)
(in module mcp_server_webcrawl.crawlers.katana.adapter)
(in module mcp_server_webcrawl.crawlers.siteone.adapter)
(in module mcp_server_webcrawl.crawlers.warc.adapter)
(in module mcp_server_webcrawl.crawlers.wget.adapter)
get_resources_api() (BaseCrawler method)
get_resources_api_json() (BaseCrawler method)
get_resources_for_sites_group() (BaseManager method)
get_results() (BaseJsonApi method)
get_sites() (in module mcp_server_webcrawl.crawlers.interrobot.adapter)
(in module mcp_server_webcrawl.crawlers.katana.adapter)
(in module mcp_server_webcrawl.crawlers.siteone.adapter)
(in module mcp_server_webcrawl.crawlers.warc.adapter)
(in module mcp_server_webcrawl.crawlers.wget.adapter)
(SitesGroup method)
get_sites_api() (BaseCrawler method)
get_sites_api_json() (BaseCrawler method)
get_sites_for_directories() (IndexedManager method)
get_stats() (BaseManager method)
get_thumbnails() (BaseCrawler method)
(ThumbnailManager method)
I
IDLE (IndexStatus attribute)
IMAGE (ResourceResultType attribute)
increment_processed() (IndexState method)
IndexedCrawler (class in mcp_server_webcrawl.crawlers.base.indexed)
IndexedManager (class in mcp_server_webcrawl.crawlers.base.indexed)
INDEXING (IndexStatus attribute)
IndexState (class in mcp_server_webcrawl.crawlers.base.adapter)
IndexStatus (class in mcp_server_webcrawl.crawlers.base.adapter)
initialize_logger() (in module mcp_server_webcrawl.utils.logger)
initialize_mcp_server() (in module mcp_server_webcrawl.utils.server)
InterroBotCrawler (class in mcp_server_webcrawl.crawlers.interrobot.crawler)
InterroBotManager (class in mcp_server_webcrawl.crawlers.interrobot.adapter)
InterroBotTests (class in mcp_server_webcrawl.crawlers.interrobot.tests)
is_timeout() (IndexState method)
K
KatanaCrawler (class in mcp_server_webcrawl.crawlers.katana.crawler)
KatanaManager (class in mcp_server_webcrawl.crawlers.katana.adapter)
KatanaTests (class in mcp_server_webcrawl.crawlers.katana.tests)
M
mcp_call_tool() (BaseCrawler method)
mcp_list_prompts() (BaseCrawler method)
mcp_list_resources() (BaseCrawler method)
mcp_list_tools() (BaseCrawler method)
(IndexedCrawler method)
(InterroBotCrawler method)
mcp_server_webcrawl
module
mcp_server_webcrawl.crawlers
module
mcp_server_webcrawl.crawlers.base
module
mcp_server_webcrawl.crawlers.base.adapter
module
mcp_server_webcrawl.crawlers.base.api
module
mcp_server_webcrawl.crawlers.base.crawler
module
mcp_server_webcrawl.crawlers.base.indexed
module
mcp_server_webcrawl.crawlers.base.tests
module
mcp_server_webcrawl.crawlers.interrobot
module
mcp_server_webcrawl.crawlers.interrobot.adapter
module
mcp_server_webcrawl.crawlers.interrobot.crawler
module
mcp_server_webcrawl.crawlers.interrobot.tests
module
mcp_server_webcrawl.crawlers.katana
module
mcp_server_webcrawl.crawlers.katana.adapter
module
mcp_server_webcrawl.crawlers.katana.crawler
module
mcp_server_webcrawl.crawlers.katana.tests
module
mcp_server_webcrawl.crawlers.siteone
module
mcp_server_webcrawl.crawlers.siteone.adapter
module
mcp_server_webcrawl.crawlers.siteone.crawler
module
mcp_server_webcrawl.crawlers.siteone.tests
module
mcp_server_webcrawl.crawlers.warc
module
mcp_server_webcrawl.crawlers.warc.adapter
module
mcp_server_webcrawl.crawlers.warc.crawler
module
mcp_server_webcrawl.crawlers.warc.tests
module
mcp_server_webcrawl.crawlers.wget
module
mcp_server_webcrawl.crawlers.wget.adapter
module
mcp_server_webcrawl.crawlers.wget.crawler
module
mcp_server_webcrawl.crawlers.wget.tests
module
mcp_server_webcrawl.models
module
mcp_server_webcrawl.models.resources
module
mcp_server_webcrawl.models.sites
module
mcp_server_webcrawl.settings
module
mcp_server_webcrawl.settings_local
module
mcp_server_webcrawl.utils
module
mcp_server_webcrawl.utils.blobs
module
mcp_server_webcrawl.utils.cli
module
mcp_server_webcrawl.utils.logger
module
mcp_server_webcrawl.utils.server
module
mcp_server_webcrawl.utils.tools
module
module
mcp_server_webcrawl
mcp_server_webcrawl.crawlers
mcp_server_webcrawl.crawlers.base
mcp_server_webcrawl.crawlers.base.adapter
mcp_server_webcrawl.crawlers.base.api
mcp_server_webcrawl.crawlers.base.crawler
mcp_server_webcrawl.crawlers.base.indexed
mcp_server_webcrawl.crawlers.base.tests
mcp_server_webcrawl.crawlers.interrobot
mcp_server_webcrawl.crawlers.interrobot.adapter
mcp_server_webcrawl.crawlers.interrobot.crawler
mcp_server_webcrawl.crawlers.interrobot.tests
mcp_server_webcrawl.crawlers.katana
mcp_server_webcrawl.crawlers.katana.adapter
mcp_server_webcrawl.crawlers.katana.crawler
mcp_server_webcrawl.crawlers.katana.tests
mcp_server_webcrawl.crawlers.siteone
mcp_server_webcrawl.crawlers.siteone.adapter
mcp_server_webcrawl.crawlers.siteone.crawler
mcp_server_webcrawl.crawlers.siteone.tests
mcp_server_webcrawl.crawlers.warc
mcp_server_webcrawl.crawlers.warc.adapter
mcp_server_webcrawl.crawlers.warc.crawler
mcp_server_webcrawl.crawlers.warc.tests
mcp_server_webcrawl.crawlers.wget
mcp_server_webcrawl.crawlers.wget.adapter
mcp_server_webcrawl.crawlers.wget.crawler
mcp_server_webcrawl.crawlers.wget.tests
mcp_server_webcrawl.models
mcp_server_webcrawl.models.resources
mcp_server_webcrawl.models.sites
mcp_server_webcrawl.settings
mcp_server_webcrawl.settings_local
mcp_server_webcrawl.utils
mcp_server_webcrawl.utils.blobs
mcp_server_webcrawl.utils.cli
mcp_server_webcrawl.utils.logger
mcp_server_webcrawl.utils.server
mcp_server_webcrawl.utils.tools
O
OTHER (ResourceResultType attribute)
P
PAGE (ResourceResultType attribute)
PARTIAL (IndexStatus attribute)
PDF (ResourceResultType attribute)
processed (IndexState attribute)
R
read_file_contents() (BaseManager static method)
read_files() (BaseManager static method)
REMOTE (IndexStatus attribute)
ResourceResult (class in mcp_server_webcrawl.models.resources)
ResourceResultType (class in mcp_server_webcrawl.models.resources)
run_pragmar_content_tests() (BaseCrawlerTests method)
run_pragmar_image_tests() (BaseCrawlerTests method)
run_pragmar_report() (BaseCrawlerTests method)
run_pragmar_search_tests() (BaseCrawlerTests method)
run_pragmar_site_tests() (BaseCrawlerTests method)
run_pragmar_sort_tests() (BaseCrawlerTests method)
run_pragmar_tokenizer_tests() (BaseCrawlerTests method)
run_sites_resources_tests() (BaseCrawlerTests method)
S
SCRIPT (ResourceResultType attribute)
serve() (BaseCrawler method)
set_extra() (ResourceResult method)
set_results() (BaseJsonApi method)
set_status() (IndexState method)
setUp() (BaseCrawlerTests method)
(InterroBotTests method)
(KatanaTests method)
(SiteOneTests method)
(WarcTests method)
(WgetTests method)
SiteOneCrawler (class in mcp_server_webcrawl.crawlers.siteone.crawler)
SiteOneManager (class in mcp_server_webcrawl.crawlers.siteone.adapter)
SiteOneTests (class in mcp_server_webcrawl.crawlers.siteone.tests)
SiteResult (class in mcp_server_webcrawl.models.sites)
SitesGroup (class in mcp_server_webcrawl.crawlers.base.adapter)
SitesStat (class in mcp_server_webcrawl.crawlers.base.adapter)
status (IndexState attribute)
string_to_id() (BaseManager static method)
T
test_interrobot_advanced_site_features() (InterroBotTests method)
test_interrobot_content_parsing() (InterroBotTests method)
test_interrobot_images() (InterroBotTests method)
(KatanaTests method)
(SiteOneTests method)
test_interrobot_mcp_features() (InterroBotTests method)
test_interrobot_pulse() (InterroBotTests method)
test_interrobot_random_sort() (InterroBotTests method)
test_interrobot_resources() (InterroBotTests method)
test_interrobot_search() (InterroBotTests method)
test_interrobot_sites() (InterroBotTests method)
test_katana_content_parsing() (KatanaTests method)
test_katana_pulse() (KatanaTests method)
test_katana_random_sort() (KatanaTests method)
test_katana_resources() (KatanaTests method)
test_katana_search() (KatanaTests method)
test_katana_sites() (KatanaTests method)
test_pragmar_tokenizer() (KatanaTests method)
test_report() (InterroBotTests method)
(KatanaTests method)
(SiteOneTests method)
(WarcTests method)
(WgetTests method)
test_siteone_advanced_features() (SiteOneTests method)
test_siteone_content_parsing() (SiteOneTests method)
test_siteone_pulse() (SiteOneTests method)
test_siteone_random_sort() (SiteOneTests method)
test_siteone_resources() (SiteOneTests method)
test_siteone_search() (SiteOneTests method)
test_siteone_sites() (SiteOneTests method)
test_thumbnails_sync() (InterroBotTests method)
test_warc_content_parsing() (WarcTests method)
test_warc_pulse() (WarcTests method)
test_warc_random_sort() (WarcTests method)
test_warc_resources() (WarcTests method)
test_warc_search() (WarcTests method)
test_warc_sites() (WarcTests method)
test_wget_content_parsing() (WgetTests method)
test_wget_pulse() (WgetTests method)
test_wget_random_sort() (WgetTests method)
test_wget_resources() (WgetTests method)
test_wget_search() (WgetTests method)
test_wget_sites() (WgetTests method)
TEXT (ResourceResultType attribute)
ThumbnailManager (class in mcp_server_webcrawl.utils.blobs)
time_end (IndexState attribute)
time_start (IndexState attribute)
to_dict() (BaseJsonApi method)
(IndexState method)
(ResourceResult method)
(SiteResult method)
to_forcefield_dict() (ResourceResult method)
(SiteResult method)
to_int_map() (ResourceResultType class method)
to_isoformat_zulu() (in module mcp_server_webcrawl.utils)
to_json() (BaseJsonApi method)
total (BaseJsonApi property)
U
UNDEFINED (IndexStatus attribute)
(ResourceResultType attribute)
V
values() (ResourceResultType class method)
VIDEO (ResourceResultType attribute)
W
WarcCrawler (class in mcp_server_webcrawl.crawlers.warc.crawler)
WarcManager (class in mcp_server_webcrawl.crawlers.warc.adapter)
WarcTests (class in mcp_server_webcrawl.crawlers.warc.tests)
WgetCrawler (class in mcp_server_webcrawl.crawlers.wget.crawler)
WgetManager (class in mcp_server_webcrawl.crawlers.wget.adapter)
WgetTests (class in mcp_server_webcrawl.crawlers.wget.tests)