finished more crawlers

Forums/Initialization/forumsList.txt

@@ -1 +1 @@
-AbyssForum
+CryptBB

Forums/Initialization/forums_mining.py

@@ -106,6 +106,9 @@ if __name__ == '__main__':
         elif forum == "Altenens":
             crawlerAltenensForum()
 
+
+
+
     print("Scraping process completed successfully!")
 
 

Forums/Initialization/geckodriver.log

@@ -5432,3 +5432,286 @@ unwatchForTargets()@TargetList.jsm:37
 destructor()@TargetList.jsm:109
 stop()@CDP.jsm:104
 close()@RemoteAgent.jsm:138
+1687455077757	geckodriver	INFO	Listening on 127.0.0.1:51921
+1687455083576	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51922" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileiMnt9Y"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687455084579	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51922/devtools/browser/50fc5309-4448-4643-b620-1944f94d9ab0
+1687455087004	Marionette	INFO	Listening on port 51927
+1687455087586	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1687455216600	Marionette	INFO	Stopped listening on port 51927
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PageThumbs.jsm, line 709: AbortError: IOUtils.profileBeforeChange getter: IOUtils: profileBeforeChange phase has already finished
+
+###!!! [Child][MessageChannel] Error: (msgtype=0x59000C,name=PHttpChannel::Msg___delete__) Channel closing: too late to send/recv, messages will be lost
+
+
+###!!! [Child][MessageChannel] Error: (msgtype=0x690023,name=PNecko::Msg_RemoveRequestContext) Channel closing: too late to send/recv, messages will be lost
+
+1687455216907	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1687455226201	geckodriver	INFO	Listening on 127.0.0.1:51997
+1687455228295	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51998" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileexb7nL"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687455228607	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51998/devtools/browser/888a7285-4a85-4e1a-8fbe-55e6a2adbf66
+1687455229445	Marionette	INFO	Listening on port 52003
+1687455229702	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://fonts.googleapis.com/css?family=Nunito:300,300i,400,400i,500,500i,600,600i,700,700i without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/341e4a57816af3ba440d891ca87450ff_framework.css.263e0b2a021157e94abb049d32a231b2.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/05e81b71abe4f22d6eb8d1a929494829_responsive.css.2b22c143d0e5ca765c62096277bba194.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/20446cf2d164adcc029377cb04d43d17_flags.css.758a08424164d23f112b6ec2481369a2.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/5e53142098efe430fe4640eabd79b3c6_menuicons.css.a918687a524788f5b223ba01803d2eab.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/79bfb05544daeca4ec6d8979c07ae88e_button.css.aa1bb91a1e01bc96d9b98955b914d67b.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/72f83c71d84327caf917932c957d1930_tthumb.css.3c2c897b5cd04a111e36f36918bec493.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/24bd4821c74747f952801a16eb6c868a_main.css.b1810b27e513fa774b6890ab866909df.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/13136374e1b49ed2a6386fef2a59fb0c_skins.css.72d5c72729ec031009e6afe8feb39e0a.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/90eb5adf50a8c640f633d47fd7eb1778_core.css.e526a33eaadabb033be3513cebde0838.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/5a0da001ccc2200dc5625c3f3934497d_core_responsive.css.d69517154f8e6fde7b033562b64c824f.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/62e269ced0fdab7e30e026f1d30ae516_forums.css.4050a065985ae566d2046d5e66d93755.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/76e62c573090645fb99a15a363d8620e_forums_responsive.css.788fdb90de5b90f1bad497cfcdaf3343.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/258adbb6e4f3e83cd3b355f84e3fa002_custom.css.eadf39a11fb30964439d233cba16e549.css?v=026d4e282a without a browsingContextID set
+console.error: (new TypeError("container.editor is undefined", "resource://devtools/client/inspector/markup/markup.js", 1619))
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.error: (new TypeError("currentNode is null", "resource://devtools/client/inspector/shared/style-change-tracker.js", 66))
+TypeError: currentNode is null: canMutationImpactCurrentStyles@resource://devtools/client/inspector/shared/style-change-tracker.js:66:20
+onMutations@resource://devtools/client/inspector/shared/style-change-tracker.js:84:41
+_emit@resource://devtools/shared/event-emitter.js:226:34
+emit@resource://devtools/shared/event-emitter.js:172:18
+emit@resource://devtools/shared/event-emitter.js:324:18
+getMutations@resource://devtools/client/fronts/walker.js:311:10
+
+1687455743435	Marionette	INFO	Stopped listening on port 52003
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\Helium\AppData\Local\Temp\rust_mozprofileexb7nL\thumbnails) because it does not exist
+1687455743784	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1687455784593	geckodriver	INFO	Listening on 127.0.0.1:52087
+1687455788326	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "52088" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileR6GZWe"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687455788927	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:52088/devtools/browser/e0042277-a371-4056-af3d-85ce0875f158
+1687455790458	Marionette	INFO	Listening on port 52093
+1687455791011	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+SourceActor threw an exception: [Exception... "Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/44357726-27b9-4d16-b4e7-4e6f59447a8b'"  nsresult: "0x805303f4 (<unknown>)"  location: "JS frame :: resource://devtools/shared/DevToolsUtils.js :: mainThreadFetch/< :: line 670"  data: yes]
+Stack: mainThreadFetch/<@resource://devtools/shared/DevToolsUtils.js:670:15
+mainThreadFetch@resource://devtools/shared/DevToolsUtils.js:516:10
+_fetchURLContents@resource://devtools/server/actors/utils/sources-manager.js:442:22
+urlContents@resource://devtools/server/actors/utils/sources-manager.js:406:17
+_resurrectSource@resource://devtools/server/actors/thread.js:2142:35
+addAllSources@resource://devtools/server/actors/thread.js:1509:14
+watch@resource://devtools/server/actors/resources/sources.js:52:17
+watchResources@resource://devtools/server/actors/resources/index.js:239:19
+_watchTargetResources@resource://devtools/server/actors/targets/target-actor-mixin.js:156:24
+addWatcherDataEntry@resource://devtools/server/actors/targets/target-actor-mixin.js:47:20
+_addWatcherDataEntry@resource://devtools/server/connectors/js-window-actor/DevToolsFrameChild.jsm:483:24
+receiveMessage@resource://devtools/server/connectors/js-window-actor/DevToolsFrameChild.jsm:425:21
+Line: 670, column: 0
+console.error: ({})
+SourceActor threw an exception: [Exception... "Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/d0bda8df-b93e-42d3-a860-8f679aef9868'"  nsresult: "0x805303f4 (<unknown>)"  location: "JS frame :: resource://devtools/shared/DevToolsUtils.js :: mainThreadFetch/< :: line 670"  data: yes]
+Stack: mainThreadFetch/<@resource://devtools/shared/DevToolsUtils.js:670:15
+mainThreadFetch@resource://devtools/shared/DevToolsUtils.js:516:10
+_fetchURLContents@resource://devtools/server/actors/utils/sources-manager.js:442:22
+urlContents@resource://devtools/server/actors/utils/sources-manager.js:406:17
+_resurrectSource@resource://devtools/server/actors/thread.js:2142:35
+addAllSources@resource://devtools/server/actors/thread.js:1509:14
+watch@resource://devtools/server/actors/resources/sources.js:52:17
+watchResources@resource://devtools/server/actors/resources/index.js:239:19
+_watchTargetResources@resource://devtools/server/actors/targets/target-actor-mixin.js:156:24
+addWatcherDataEntry@resource://devtools/server/actors/targets/target-actor-mixin.js:47:20
+_addWatcherDataEntry@resource://devtools/server/connectors/js-window-actor/DevToolsFrameChild.jsm:483:24
+receiveMessage@resource://devtools/server/connectors/js-window-actor/DevToolsFrameChild.jsm:425:21
+Line: 670, column: 0
+console.error: ({})
+JavaScript error: resource://devtools/shared/DevToolsUtils.js, line 670: Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/44357726-27b9-4d16-b4e7-4e6f59447a8b'
+JavaScript error: resource://devtools/shared/DevToolsUtils.js, line 670: Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/d0bda8df-b93e-42d3-a860-8f679aef9868'
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://fonts.googleapis.com/css?family=Nunito:300,300i,400,400i,500,500i,600,600i,700,700i without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/341e4a57816af3ba440d891ca87450ff_framework.css.263e0b2a021157e94abb049d32a231b2.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/05e81b71abe4f22d6eb8d1a929494829_responsive.css.2b22c143d0e5ca765c62096277bba194.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/20446cf2d164adcc029377cb04d43d17_flags.css.758a08424164d23f112b6ec2481369a2.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/5e53142098efe430fe4640eabd79b3c6_menuicons.css.a918687a524788f5b223ba01803d2eab.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/79bfb05544daeca4ec6d8979c07ae88e_button.css.aa1bb91a1e01bc96d9b98955b914d67b.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/72f83c71d84327caf917932c957d1930_tthumb.css.3c2c897b5cd04a111e36f36918bec493.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/24bd4821c74747f952801a16eb6c868a_main.css.b1810b27e513fa774b6890ab866909df.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/13136374e1b49ed2a6386fef2a59fb0c_skins.css.72d5c72729ec031009e6afe8feb39e0a.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/90eb5adf50a8c640f633d47fd7eb1778_core.css.e526a33eaadabb033be3513cebde0838.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/5a0da001ccc2200dc5625c3f3934497d_core_responsive.css.d69517154f8e6fde7b033562b64c824f.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/62e269ced0fdab7e30e026f1d30ae516_forums.css.4050a065985ae566d2046d5e66d93755.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/76e62c573090645fb99a15a363d8620e_forums_responsive.css.788fdb90de5b90f1bad497cfcdaf3343.css?v=026d4e282a without a browsingContextID set
+JavaScript error: resource://devtools/server/actors/network-monitor/network-event-actor.js, line 109: Error: Got a request https://crackingall.com/uploads/css_built_5/258adbb6e4f3e83cd3b355f84e3fa002_custom.css.eadf39a11fb30964439d233cba16e549.css?v=026d4e282a without a browsingContextID set
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.error: "Error writing request: getGrids"
+console.error: "Error writing request: getGrids"
+console.warn: "Resource  of root-node was not found."
+JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\Helium\AppData\Local\Temp\rust_mozprofileR6GZWe\thumbnails) because it does not exist
+1687456242405	Marionette	INFO	Stopped listening on port 52093
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\Helium\AppData\Local\Temp\rust_mozprofileR6GZWe\thumbnails) because it does not exist
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+1687456242603	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1687456258163	geckodriver	INFO	Listening on 127.0.0.1:52192
+1687456260149	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "52193" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileQo9Zp0"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687456260474	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:52193/devtools/browser/d308bc8a-df10-4763-824a-6f23a5c493b7
+1687456261290	Marionette	INFO	Listening on port 52198
+1687456261497	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+JavaScript error: undefined, line 0: Error: Invalid tab ID: 1
+JavaScript error: undefined, line 0: Error: Invalid tab ID: 1
+JavaScript error: undefined, line 0: Error: Invalid tab ID: 1
+JavaScript error: undefined, line 0: Error: Invalid tab ID: 1
+1687456791586	Marionette	INFO	Stopped listening on port 52198
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PageThumbs.jsm, line 709: AbortError: IOUtils.profileBeforeChange getter: IOUtils: profileBeforeChange phase has already finished
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+1687456791708	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1687467349686	geckodriver	INFO	Listening on 127.0.0.1:51629
+1687467357094	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51630" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofilePDgGsl"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687467359136	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51630/devtools/browser/85f253a2-0be5-4d19-a5ad-367d7a91bfb6
+1687467364474	Marionette	INFO	Listening on port 51635
+1687467365127	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+
+###!!! [Child][MessageChannel] Error: (msgtype=0x59000C,name=PHttpChannel::Msg___delete__) Channel closing: too late to send/recv, messages will be lost
+
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+1687467402685	Marionette	INFO	Stopped listening on port 51635
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\Helium\AppData\Local\Temp\rust_mozprofilePDgGsl\thumbnails) because it does not exist
+[Parent 4292, IPC I/O Parent] WARNING: file /var/tmp/build/firefox-b6010b1466c9/ipc/chromium/src/base/process_util_win.cc:167
+1687467404034	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138

MarketPlaces/AnonymousMarketplace/crawler_selenium.py

@@ -0,0 +1,298 @@
+__author__ = 'Helium'
+
+'''
+AnonymousMarketplace Forum Crawler (Selenium)
+'''
+
+from selenium import webdriver
+from selenium.common.exceptions import NoSuchElementException
+from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
+from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
+from selenium.webdriver.firefox.service import Service
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.AnonymousMarketplace.parser import anonymous_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/'
+
+
+# Opens Tor Browser, crawls the website, then parses, then closes tor
+#acts like the main method for the crawler, another function at the end of this code calls this function later
+def startCrawling():
+    opentor()
+    # mktName = getMKTName()
+    driver = getAccess()
+
+    if driver != 'down':
+        try:
+            login(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closetor(driver)
+
+    # new_parse(forumName, baseURL, False)
+
+
+# Opens Tor Browser
+#prompts for ENTER input to continue
+def opentor():
+    global pid
+    print("Connecting Tor...")
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'AnonymousMarketplace'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+def closetor(driver):
+    # global pid
+    # os.system("taskkill /pid " + str(pro.pid))
+    # os.system("taskkill /t /f /im tor.exe")
+    print('Closing Tor...')
+    driver.close()
+    time.sleep(3)
+    return
+
+
+# Creates FireFox 'driver' and configure its 'Profile'
+# to use Tor proxy and socket
+def createFFDriver():
+    ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))
+
+    ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path'))
+    ff_prof.set_preference("places.history.enabled", False)
+    ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True)
+    ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
+    ff_prof.set_preference("signon.rememberSignons", False)
+    ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
+    ff_prof.set_preference("network.dns.disablePrefetch", True)
+    ff_prof.set_preference("network.http.sendRefererHeader", 0)
+    ff_prof.set_preference("permissions.default.image", 2)
+    ff_prof.set_preference("browser.download.folderList", 2)
+    ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
+    ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
+    ff_prof.set_preference('network.proxy.type', 1)
+    ff_prof.set_preference("network.proxy.socks_version", 5)
+    ff_prof.set_preference('network.proxy.socks', '127.0.0.1')
+    ff_prof.set_preference('network.proxy.socks_port', 9150)
+    ff_prof.set_preference('network.proxy.socks_remote_dns', True)
+    ff_prof.set_preference("javascript.enabled", False)
+    ff_prof.update_preferences()
+
+    service = Service(config.get('TOR', 'geckodriver_path'))
+
+    driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
+
+    return driver
+
+
+#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down'
+#return: return the selenium driver or string 'down'
+def getAccess():
+    url = getFixedURL()
+    driver = createFFDriver()
+    try:
+        driver.get(url)
+        return driver
+    except:
+        driver.close()
+        return 'down'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.ID, "woocommerce_product_categories-2")))
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+def savePage(page, url):
+    cleanPage = cleanHTML(page)
+    filePath = getFullPathName(url)
+    os.makedirs(os.path.dirname(filePath), exist_ok=True)
+    open(filePath, 'wb').write(cleanPage.encode('utf-8'))
+    return
+
+
+# Gets the full path of the page to be saved along with its appropriate file name
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import CURRENT_DATE
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\AnonymousMarketplace\HTML_Pages\\' + CURRENT_DATE + r'\\Description\\' + fileName + '.html'
+    else:
+        fullPath = r'..\AnonymousMarketplace\HTML_Pages\\' + CURRENT_DATE + r'\\Listing\\' + fileName + '.html'
+    return fullPath
+
+
+# Creates the file name from passed URL, gives distinct name if can't be made unique after cleaned
+#@param: raw url as crawler crawls through every site
+def getNameFromURL(url):
+    global counter
+    name = ''.join(e for e in url if e.isalnum())
+    if (name == ''):
+        name = str(counter)
+        counter = counter + 1
+    return name
+
+
+# returns list of urls, here is where you can list the different urls of interest, the crawler runs through this list
+#in this example, there are a couple of categories some threads fall under such as
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # carding
+    links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/carding/')
+    # # hacked paypal
+    # links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/hacked-paypal-accounts/')
+    # # hacking services
+    # links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/hacking-services/')
+
+    return links
+
+
+# gets links of interest to crawl through, iterates through list, where each link is clicked and crawled through
+#topic and description pages are crawled through here, where both types of pages are saved
+#@param: selenium driver
+def crawlForum(driver):
+    print("Crawling the AnonymousMarketplace market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 0
+    while i < len(linksToCrawl):
+        link = linksToCrawl[i]
+        print('Crawling :', link)
+        try:
+            try:
+                driver.get(link)
+            except:
+                driver.refresh()
+            html = driver.page_source
+            savePage(html, link)
+
+            has_next_page = True
+            while has_next_page:
+                list = productPages(html)
+                for item in list:
+                    itemURL = urlparse.urljoin(baseURL, str(item))
+                    try:
+                        driver.get(itemURL)
+                    except:
+                        driver.refresh()
+                    savePage(driver.page_source, item)
+                    driver.back()
+
+                    # comment out
+                    break
+
+                # comment out
+                if count == 1:
+                    count = 0
+                    break
+
+                try:
+                    link = ""
+                    if link == "":
+                        raise NoSuchElementException
+                    try:
+                        driver.get(link)
+                    except:
+                        driver.refresh()
+                    html = driver.page_source
+                    savePage(html, link)
+                    count += 1
+
+                except NoSuchElementException:
+                    has_next_page = False
+
+        except Exception as e:
+            print(link, e)
+        i += 1
+
+    # finalTime = time.time()
+    # print finalTime - initialTime
+
+    input("Crawling AnonymousMarketplace forum done sucessfully. Press ENTER to continue\n")
+
+
+# Returns 'True' if the link is a description link
+#@param: url of any url crawled
+#return: true if is a description page, false if not
+def isDescriptionLink(url):
+    if 'product/' in url:
+        return True
+    return False
+
+
+# Returns True if the link is a listingPage link
+#@param: url of any url crawled
+#return: true if is a Listing page, false if not
+def isListingLink(url):
+    if 'product-' in url:
+        return True
+    return False
+
+
+# calling the parser to define the links, the html is the url of a link from the list of interested link list
+#@param: link from interested link list ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return anonymous_links_parser(soup)
+
+
+# Drop links that "signout"
+# def isSignOut(url):
+#     #absURL = urlparse.urljoin(url.base_url, url.url)
+#     if 'signout' in url.lower() or 'logout' in url.lower():
+#         return True
+#
+#     return False
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/AnonymousMarketplace/parser.py

@@ -0,0 +1,291 @@
+__author__ = 'DarkWeb'
+
+# Here, we are importing the auxiliary functions to clean or convert data
+from MarketPlaces.Utilities.utilities import *
+
+# Here, we are importing BeautifulSoup to search through the HTML tree
+from bs4 import BeautifulSoup
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    lastSeen = "-1"                     # 2 Product_LastViewDate
+    rules = "-1"                        # 3 NOT USED ...
+    CVE = "-1"                          # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = "-1"                           # 5 Product_MS_Classification (Microsoft Security)
+    review = "-1"                       # 6 Product_Number_Of_Reviews
+    category = "-1"                     # 7 Product_Category
+    shipFrom = "-1"                     # 8 Product_ShippedFrom
+    shipTo = "-1"                       # 9 Product_ShippedTo
+    left = "-1"                         # 10 Product_QuantityLeft
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # Searching for CVE and MS categories
+    cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+    if cve:
+        CVE = " "
+        for idx in cve:
+            CVE += (idx)
+            CVE += "  "
+            CVE = CVE.replace(',', ' ')
+            CVE = CVE.replace('\n', '')
+    ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
+    if ms:
+        MS = " "
+        for im in ms:
+            MS += (im)
+            MS += " "
+            MS = MS.replace(',', ' ')
+            MS = MS.replace('\n', '')
+
+    # Populating the final variable (this should be a list with all fields scraped)
+    row = (name, describe, lastSeen, rules, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor,
+       sold, addDate, available, endDate, BTC, USD, rating, success, EURO)
+
+    # Sending the results
+    return row
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+        if not cve:
+            cveValue="-1"
+        else:
+            cee = " "
+            for idx in cve:
+                cee += (idx)
+                cee += "  "
+                cee = cee.replace(',', ' ')
+                cee = cee.replace('\n', '')
+            cveValue=cee
+        CVE.append(cveValue)
+        
+        ms = a.findAll(text=re.compile('MS\d{2}-\d{3}'))
+        if not ms:
+            MSValue="-1"
+        else:
+            me = " "
+            for im in ms:
+                me += (im)
+                me += " "
+                me = me.replace(',', ' ')
+                me = me.replace('\n', '')
+            MSValue=me
+        MS.append(MSValue)
+
+    # Populate the final variable (this should be a list with all fields scraped)
+    return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen,
+                     BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def anonymous_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.find('ul', {"class": "products columns-4"}).findAll('li')
+
+    for a in listing:
+        bae = a.find('a', {"class": "woocommerce-LoopProduct-link woocommerce-loop-product__link"}, href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href

MarketPlaces/CypherMarketplace/crawler_selenium.py

@@ -0,0 +1,312 @@
+__author__ = 'Helium'
+
+'''
+CypherMarketplace Forum Crawler (Selenium)
+'''
+
+from selenium import webdriver
+from selenium.common.exceptions import NoSuchElementException
+from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
+from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
+from selenium.webdriver.firefox.service import Service
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.CypherMarketplace.parser import cyphermarketplace_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://6c5qa2ke2esh6ake6u6yoxjungz2czbbl7hqxl75v5k37frtzhxuk7ad.onion/'
+
+
+# Opens Tor Browser, crawls the website, then parses, then closes tor
+#acts like the main method for the crawler, another function at the end of this code calls this function later
+def startCrawling():
+    opentor()
+    # mktName = getMKTName()
+    driver = getAccess()
+
+    if driver != 'down':
+        try:
+            login(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closetor(driver)
+
+    # new_parse(forumName, baseURL, False)
+
+
+# Opens Tor Browser
+#prompts for ENTER input to continue
+def opentor():
+    global pid
+    print("Connecting Tor...")
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'CypherMarketplace'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://6c5qa2ke2esh6ake6u6yoxjungz2czbbl7hqxl75v5k37frtzhxuk7ad.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+def closetor(driver):
+    # global pid
+    # os.system("taskkill /pid " + str(pro.pid))
+    # os.system("taskkill /t /f /im tor.exe")
+    print('Closing Tor...')
+    driver.close()
+    time.sleep(3)
+    return
+
+
+# Creates FireFox 'driver' and configure its 'Profile'
+# to use Tor proxy and socket
+def createFFDriver():
+    ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))
+
+    ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path'))
+    ff_prof.set_preference("places.history.enabled", False)
+    ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True)
+    ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
+    ff_prof.set_preference("signon.rememberSignons", False)
+    ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
+    ff_prof.set_preference("network.dns.disablePrefetch", True)
+    ff_prof.set_preference("network.http.sendRefererHeader", 0)
+    ff_prof.set_preference("permissions.default.image", 2)
+    ff_prof.set_preference("browser.download.folderList", 2)
+    ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
+    ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
+    ff_prof.set_preference('network.proxy.type', 1)
+    ff_prof.set_preference("network.proxy.socks_version", 5)
+    ff_prof.set_preference('network.proxy.socks', '127.0.0.1')
+    ff_prof.set_preference('network.proxy.socks_port', 9150)
+    ff_prof.set_preference('network.proxy.socks_remote_dns', True)
+    ff_prof.set_preference("javascript.enabled", False)
+    ff_prof.update_preferences()
+
+    service = Service(config.get('TOR', 'geckodriver_path'))
+
+    driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
+
+    return driver
+
+
+#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down'
+#return: return the selenium driver or string 'down'
+def getAccess():
+    url = getFixedURL()
+    driver = createFFDriver()
+    try:
+        driver.get(url)
+        return driver
+    except:
+        driver.close()
+        return 'down'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div/div[1]/div/div[1]/div[1]/ul")))
+
+    # entering username and password into input boxes
+    usernameBox = driver.find_element(by=By.XPATH, value='/html/body/div/div[2]/div/form/table/tbody/tr[2]/td[2]/input')
+    # Username here
+    usernameBox.send_keys('beachyoga278')  # sends string to the username box
+    passwordBox = driver.find_element(by=By.XPATH, value='/html/body/div/div[2]/div/form/table/tbody/tr[3]/td[2]/input')
+    # Password here
+    passwordBox.send_keys('sunfish278')  # sends string to passwordBox
+
+    input("Press ENTER when CAPTCHA is completed\n")
+
+    # wait for listing page show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[2]/div/div/div[1]/div/div/div[1]/div[2]/ul/li[8]/a")))
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+def savePage(page, url):
+    cleanPage = cleanHTML(page)
+    filePath = getFullPathName(url)
+    os.makedirs(os.path.dirname(filePath), exist_ok=True)
+    open(filePath, 'wb').write(cleanPage.encode('utf-8'))
+    return
+
+
+# Gets the full path of the page to be saved along with its appropriate file name
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import CURRENT_DATE
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\CypherMarketplace\HTML_Pages\\' + CURRENT_DATE + r'\\Description\\' + fileName + '.html'
+    else:
+        fullPath = r'..\CypherMarketplace\HTML_Pages\\' + CURRENT_DATE + r'\\Listing\\' + fileName + '.html'
+    return fullPath
+
+
+# Creates the file name from passed URL, gives distinct name if can't be made unique after cleaned
+#@param: raw url as crawler crawls through every site
+def getNameFromURL(url):
+    global counter
+    name = ''.join(e for e in url if e.isalnum())
+    if (name == ''):
+        name = str(counter)
+        counter = counter + 1
+    return name
+
+
+# returns list of urls, here is where you can list the different urls of interest, the crawler runs through this list
+#in this example, there are a couple of categories some threads fall under such as
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # software
+    links.append('http://6c5qa2ke2esh6ake6u6yoxjungz2czbbl7hqxl75v5k37frtzhxuk7ad.onion/category/040ca140-3cfc-11ea-9364-87edd8c0a63f')
+    # # guides
+    # links.append('http://6c5qa2ke2esh6ake6u6yoxjungz2czbbl7hqxl75v5k37frtzhxuk7ad.onion/category/35a35d10-3cfb-11ea-9b14-65b8930c1372')
+
+    return links
+
+
+# gets links of interest to crawl through, iterates through list, where each link is clicked and crawled through
+#topic and description pages are crawled through here, where both types of pages are saved
+#@param: selenium driver
+def crawlForum(driver):
+    print("Crawling the CypherMarketplace market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 0
+    while i < len(linksToCrawl):
+        link = linksToCrawl[i]
+        print('Crawling :', link)
+        try:
+            try:
+                driver.get(link)
+            except:
+                driver.refresh()
+            html = driver.page_source
+            savePage(html, link)
+
+            has_next_page = True
+            while has_next_page:
+                list = productPages(html)
+                for item in list:
+                    itemURL = urlparse.urljoin(baseURL, str(item))
+                    try:
+                        driver.get(itemURL)
+                    except:
+                        driver.refresh()
+                    savePage(driver.page_source, item)
+                    driver.back()
+
+                    # comment out
+                    break
+
+                # comment out
+                if count == 1:
+                    count = 0
+                    break
+
+                try:
+                    temp = driver.find_element(by=By.XPATH, value=
+                        '/html/body/div[2]/div/div/div[2]/div/nav/ul')
+                    link = temp.find_element(by=By.TAG_NAME, value='page-link').get_attribute('href')
+                    if link == "":
+                        raise NoSuchElementException
+                    try:
+                        driver.get(link)
+                    except:
+                        driver.refresh()
+                    html = driver.page_source
+                    savePage(html, link)
+                    count += 1
+
+                except NoSuchElementException:
+                    has_next_page = False
+
+        except Exception as e:
+            print(link, e)
+        i += 1
+
+    # finalTime = time.time()
+    # print finalTime - initialTime
+
+    input("Crawling CypherMarketplace forum done sucessfully. Press ENTER to continue\n")
+
+
+# Returns 'True' if the link is a description link
+#@param: url of any url crawled
+#return: true if is a description page, false if not
+def isDescriptionLink(url):
+    if 'product' in url:
+        return True
+    return False
+
+
+# Returns True if the link is a listingPage link
+#@param: url of any url crawled
+#return: true if is a Listing page, false if not
+def isListingLink(url):
+    if 'category' in url:
+        return True
+    return False
+
+
+# calling the parser to define the links, the html is the url of a link from the list of interested link list
+#@param: link from interested link list ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return cyphermarketplace_links_parser(soup)
+
+
+# Drop links that "signout"
+# def isSignOut(url):
+#     #absURL = urlparse.urljoin(url.base_url, url.url)
+#     if 'signout' in url.lower() or 'logout' in url.lower():
+#         return True
+#
+#     return False
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/CypherMarketplace/parser.py

@@ -0,0 +1,291 @@
+__author__ = 'DarkWeb'
+
+# Here, we are importing the auxiliary functions to clean or convert data
+from MarketPlaces.Utilities.utilities import *
+
+# Here, we are importing BeautifulSoup to search through the HTML tree
+from bs4 import BeautifulSoup
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    lastSeen = "-1"                     # 2 Product_LastViewDate
+    rules = "-1"                        # 3 NOT USED ...
+    CVE = "-1"                          # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = "-1"                           # 5 Product_MS_Classification (Microsoft Security)
+    review = "-1"                       # 6 Product_Number_Of_Reviews
+    category = "-1"                     # 7 Product_Category
+    shipFrom = "-1"                     # 8 Product_ShippedFrom
+    shipTo = "-1"                       # 9 Product_ShippedTo
+    left = "-1"                         # 10 Product_QuantityLeft
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # Searching for CVE and MS categories
+    cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+    if cve:
+        CVE = " "
+        for idx in cve:
+            CVE += (idx)
+            CVE += "  "
+            CVE = CVE.replace(',', ' ')
+            CVE = CVE.replace('\n', '')
+    ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
+    if ms:
+        MS = " "
+        for im in ms:
+            MS += (im)
+            MS += " "
+            MS = MS.replace(',', ' ')
+            MS = MS.replace('\n', '')
+
+    # Populating the final variable (this should be a list with all fields scraped)
+    row = (name, describe, lastSeen, rules, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor,
+       sold, addDate, available, endDate, BTC, USD, rating, success, EURO)
+
+    # Sending the results
+    return row
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+        if not cve:
+            cveValue="-1"
+        else:
+            cee = " "
+            for idx in cve:
+                cee += (idx)
+                cee += "  "
+                cee = cee.replace(',', ' ')
+                cee = cee.replace('\n', '')
+            cveValue=cee
+        CVE.append(cveValue)
+        
+        ms = a.findAll(text=re.compile('MS\d{2}-\d{3}'))
+        if not ms:
+            MSValue="-1"
+        else:
+            me = " "
+            for im in ms:
+                me += (im)
+                me += " "
+                me = me.replace(',', ' ')
+                me = me.replace('\n', '')
+            MSValue=me
+        MS.append(MSValue)
+
+    # Populate the final variable (this should be a list with all fields scraped)
+    return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen,
+                     BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def cyphermarketplace_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.findAll('div', {"class": "card-body"})
+
+    for a in listing:
+        bae = a.find('a', {"class": "text-info"}, href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href

MarketPlaces/DarkTor/crawler_selenium.py

@@ -0,0 +1,298 @@
+__author__ = 'Helium'
+
+'''
+DarkTor Forum Crawler (Selenium)
+'''
+
+from selenium import webdriver
+from selenium.common.exceptions import NoSuchElementException
+from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
+from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
+from selenium.webdriver.firefox.service import Service
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.DarkTor.parser import darktor_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://zuauw53dukqdmll5p3fld26ns2gepcyfmbofobjczdni6ecmkoitnfid.onion/'
+
+
+# Opens Tor Browser, crawls the website, then parses, then closes tor
+#acts like the main method for the crawler, another function at the end of this code calls this function later
+def startCrawling():
+    opentor()
+    # mktName = getMKTName()
+    driver = getAccess()
+
+    if driver != 'down':
+        try:
+            login(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closetor(driver)
+
+    # new_parse(forumName, baseURL, False)
+
+
+# Opens Tor Browser
+#prompts for ENTER input to continue
+def opentor():
+    global pid
+    print("Connecting Tor...")
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'DarkTor'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://zuauw53dukqdmll5p3fld26ns2gepcyfmbofobjczdni6ecmkoitnfid.onion//'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+def closetor(driver):
+    # global pid
+    # os.system("taskkill /pid " + str(pro.pid))
+    # os.system("taskkill /t /f /im tor.exe")
+    print('Closing Tor...')
+    driver.close()
+    time.sleep(3)
+    return
+
+
+# Creates FireFox 'driver' and configure its 'Profile'
+# to use Tor proxy and socket
+def createFFDriver():
+    ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))
+
+    ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path'))
+    ff_prof.set_preference("places.history.enabled", False)
+    ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True)
+    ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
+    ff_prof.set_preference("signon.rememberSignons", False)
+    ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
+    ff_prof.set_preference("network.dns.disablePrefetch", True)
+    ff_prof.set_preference("network.http.sendRefererHeader", 0)
+    ff_prof.set_preference("permissions.default.image", 2)
+    ff_prof.set_preference("browser.download.folderList", 2)
+    ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
+    ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
+    ff_prof.set_preference('network.proxy.type', 1)
+    ff_prof.set_preference("network.proxy.socks_version", 5)
+    ff_prof.set_preference('network.proxy.socks', '127.0.0.1')
+    ff_prof.set_preference('network.proxy.socks_port', 9150)
+    ff_prof.set_preference('network.proxy.socks_remote_dns', True)
+    ff_prof.set_preference("javascript.enabled", False)
+    ff_prof.update_preferences()
+
+    service = Service(config.get('TOR', 'geckodriver_path'))
+
+    driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
+
+    return driver
+
+
+#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down'
+#return: return the selenium driver or string 'down'
+def getAccess():
+    url = getFixedURL()
+    driver = createFFDriver()
+    try:
+        driver.get(url)
+        return driver
+    except:
+        driver.close()
+        return 'down'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[1]/div/div/div[2]/main/div/div/section[5]/div/div[1]/div")))
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+def savePage(page, url):
+    cleanPage = cleanHTML(page)
+    filePath = getFullPathName(url)
+    os.makedirs(os.path.dirname(filePath), exist_ok=True)
+    open(filePath, 'wb').write(cleanPage.encode('utf-8'))
+    return
+
+
+# Gets the full path of the page to be saved along with its appropriate file name
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import CURRENT_DATE
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\DarkTor\HTML_Pages\\' + CURRENT_DATE + r'\\Description\\' + fileName + '.html'
+    else:
+        fullPath = r'..\DarkTor\HTML_Pages\\' + CURRENT_DATE + r'\\Listing\\' + fileName + '.html'
+    return fullPath
+
+
+# Creates the file name from passed URL, gives distinct name if can't be made unique after cleaned
+#@param: raw url as crawler crawls through every site
+def getNameFromURL(url):
+    global counter
+    name = ''.join(e for e in url if e.isalnum())
+    if (name == ''):
+        name = str(counter)
+        counter = counter + 1
+    return name
+
+
+# returns list of urls, here is where you can list the different urls of interest, the crawler runs through this list
+#in this example, there are a couple of categories some threads fall under such as
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # Hacking
+    links.append('http://zuauw53dukqdmll5p3fld26ns2gepcyfmbofobjczdni6ecmkoitnfid.onion/product-category/hacking-services/')
+    # Carding
+    links.append('http://zuauw53dukqdmll5p3fld26ns2gepcyfmbofobjczdni6ecmkoitnfid.onion/product-category/carding/')
+    # hacked paypals
+    links.append('http://zuauw53dukqdmll5p3fld26ns2gepcyfmbofobjczdni6ecmkoitnfid.onion/product-category/hacked-paypal-accounts/')
+
+    return links
+
+
+# gets links of interest to crawl through, iterates through list, where each link is clicked and crawled through
+#topic and description pages are crawled through here, where both types of pages are saved
+#@param: selenium driver
+def crawlForum(driver):
+    print("Crawling the DarkTor market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 0
+    while i < len(linksToCrawl):
+        link = linksToCrawl[i]
+        print('Crawling :', link)
+        try:
+            try:
+                driver.get(link)
+            except:
+                driver.refresh()
+            html = driver.page_source
+            savePage(html, link)
+
+            has_next_page = True
+            while has_next_page:
+                list = productPages(html)
+                for item in list:
+                    itemURL = urlparse.urljoin(baseURL, str(item))
+                    try:
+                        driver.get(itemURL)
+                    except:
+                        driver.refresh()
+                    savePage(driver.page_source, item)
+                    driver.back()
+
+                    # comment out
+                    break
+
+                # comment out
+                if count == 1:
+                    count = 0
+                    break
+
+                try:
+                    link = ""
+                    if link == "":
+                        raise NoSuchElementException
+                    try:
+                        driver.get(link)
+                    except:
+                        driver.refresh()
+                    html = driver.page_source
+                    savePage(html, link)
+                    count += 1
+
+                except NoSuchElementException:
+                    has_next_page = False
+
+        except Exception as e:
+            print(link, e)
+        i += 1
+
+    # finalTime = time.time()
+    # print finalTime - initialTime
+
+    input("Crawling DarkTor forum done sucessfully. Press ENTER to continue\n")
+
+
+# Returns 'True' if the link is a description link
+#@param: url of any url crawled
+#return: true if is a description page, false if not
+def isDescriptionLink(url):
+    if 'product/' in url:
+        return True
+    return False
+
+
+# Returns True if the link is a listingPage link
+#@param: url of any url crawled
+#return: true if is a Listing page, false if not
+def isListingLink(url):
+    if 'product-' in url:
+        return True
+    return False
+
+
+# calling the parser to define the links, the html is the url of a link from the list of interested link list
+#@param: link from interested link list ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return darktor_links_parser(soup)
+
+
+# Drop links that "signout"
+# def isSignOut(url):
+#     #absURL = urlparse.urljoin(url.base_url, url.url)
+#     if 'signout' in url.lower() or 'logout' in url.lower():
+#         return True
+#
+#     return False
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/DarkTor/parser.py

@@ -0,0 +1,291 @@
+__author__ = 'DarkWeb'
+
+# Here, we are importing the auxiliary functions to clean or convert data
+from MarketPlaces.Utilities.utilities import *
+
+# Here, we are importing BeautifulSoup to search through the HTML tree
+from bs4 import BeautifulSoup
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    lastSeen = "-1"                     # 2 Product_LastViewDate
+    rules = "-1"                        # 3 NOT USED ...
+    CVE = "-1"                          # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = "-1"                           # 5 Product_MS_Classification (Microsoft Security)
+    review = "-1"                       # 6 Product_Number_Of_Reviews
+    category = "-1"                     # 7 Product_Category
+    shipFrom = "-1"                     # 8 Product_ShippedFrom
+    shipTo = "-1"                       # 9 Product_ShippedTo
+    left = "-1"                         # 10 Product_QuantityLeft
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # Searching for CVE and MS categories
+    cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+    if cve:
+        CVE = " "
+        for idx in cve:
+            CVE += (idx)
+            CVE += "  "
+            CVE = CVE.replace(',', ' ')
+            CVE = CVE.replace('\n', '')
+    ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
+    if ms:
+        MS = " "
+        for im in ms:
+            MS += (im)
+            MS += " "
+            MS = MS.replace(',', ' ')
+            MS = MS.replace('\n', '')
+
+    # Populating the final variable (this should be a list with all fields scraped)
+    row = (name, describe, lastSeen, rules, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor,
+       sold, addDate, available, endDate, BTC, USD, rating, success, EURO)
+
+    # Sending the results
+    return row
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+        if not cve:
+            cveValue="-1"
+        else:
+            cee = " "
+            for idx in cve:
+                cee += (idx)
+                cee += "  "
+                cee = cee.replace(',', ' ')
+                cee = cee.replace('\n', '')
+            cveValue=cee
+        CVE.append(cveValue)
+        
+        ms = a.findAll(text=re.compile('MS\d{2}-\d{3}'))
+        if not ms:
+            MSValue="-1"
+        else:
+            me = " "
+            for im in ms:
+                me += (im)
+                me += " "
+                me = me.replace(',', ' ')
+                me = me.replace('\n', '')
+            MSValue=me
+        MS.append(MSValue)
+
+    # Populate the final variable (this should be a list with all fields scraped)
+    return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen,
+                     BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def darktor_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.findAll('div', {"class": "product-block"})
+
+    for a in listing:
+        bae = a.find('a', {"class": "woocommerce-LoopProduct-link woocommerce-loop-product__link"}, href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href

MarketPlaces/DigitalThriftShop/crawler_selenium.py

@@ -0,0 +1,303 @@
+__author__ = 'Helium'
+
+'''
+DigitalThriftShop Forum Crawler (Selenium)
+'''
+
+from selenium import webdriver
+from selenium.common.exceptions import NoSuchElementException
+from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
+from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
+from selenium.webdriver.firefox.service import Service
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.DigitalThriftShop.parser import digitalthriftshop_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://kw4zlnfhxje7top26u57iosg55i7dzuljjcyswo2clgc3mdliviswwyd.onion/'
+
+
+# Opens Tor Browser, crawls the website, then parses, then closes tor
+#acts like the main method for the crawler, another function at the end of this code calls this function later
+def startCrawling():
+    opentor()
+    # mktName = getMKTName()
+    driver = getAccess()
+
+    if driver != 'down':
+        try:
+            login(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closetor(driver)
+
+    # new_parse(forumName, baseURL, False)
+
+
+# Opens Tor Browser
+#prompts for ENTER input to continue
+def opentor():
+    global pid
+    print("Connecting Tor...")
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'DigitalThriftShop'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://kw4zlnfhxje7top26u57iosg55i7dzuljjcyswo2clgc3mdliviswwyd.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+def closetor(driver):
+    # global pid
+    # os.system("taskkill /pid " + str(pro.pid))
+    # os.system("taskkill /t /f /im tor.exe")
+    print('Closing Tor...')
+    driver.close()
+    time.sleep(3)
+    return
+
+
+# Creates FireFox 'driver' and configure its 'Profile'
+# to use Tor proxy and socket
+def createFFDriver():
+    ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))
+
+    ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path'))
+    ff_prof.set_preference("places.history.enabled", False)
+    ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True)
+    ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
+    ff_prof.set_preference("signon.rememberSignons", False)
+    ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
+    ff_prof.set_preference("network.dns.disablePrefetch", True)
+    ff_prof.set_preference("network.http.sendRefererHeader", 0)
+    ff_prof.set_preference("permissions.default.image", 2)
+    ff_prof.set_preference("browser.download.folderList", 2)
+    ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
+    ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
+    ff_prof.set_preference('network.proxy.type', 1)
+    ff_prof.set_preference("network.proxy.socks_version", 5)
+    ff_prof.set_preference('network.proxy.socks', '127.0.0.1')
+    ff_prof.set_preference('network.proxy.socks_port', 9150)
+    ff_prof.set_preference('network.proxy.socks_remote_dns', True)
+    ff_prof.set_preference("javascript.enabled", False)
+    ff_prof.update_preferences()
+
+    service = Service(config.get('TOR', 'geckodriver_path'))
+
+    driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
+
+    return driver
+
+
+#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down'
+#return: return the selenium driver or string 'down'
+def getAccess():
+    url = getFixedURL()
+    driver = createFFDriver()
+    try:
+        driver.get(url)
+        return driver
+    except:
+        driver.close()
+        return 'down'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.ID, "woocommerce_product_categories-2")))
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+def savePage(page, url):
+    cleanPage = cleanHTML(page)
+    filePath = getFullPathName(url)
+    os.makedirs(os.path.dirname(filePath), exist_ok=True)
+    open(filePath, 'wb').write(cleanPage.encode('utf-8'))
+    return
+
+
+# Gets the full path of the page to be saved along with its appropriate file name
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import CURRENT_DATE
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\DigitalThriftShop\HTML_Pages\\' + CURRENT_DATE + r'\\Description\\' + fileName + '.html'
+    else:
+        fullPath = r'..\DigitalThriftShop\HTML_Pages\\' + CURRENT_DATE + r'\\Listing\\' + fileName + '.html'
+    return fullPath
+
+
+# Creates the file name from passed URL, gives distinct name if can't be made unique after cleaned
+#@param: raw url as crawler crawls through every site
+def getNameFromURL(url):
+    global counter
+    name = ''.join(e for e in url if e.isalnum())
+    if (name == ''):
+        name = str(counter)
+        counter = counter + 1
+    return name
+
+
+# returns list of urls, here is where you can list the different urls of interest, the crawler runs through this list
+#in this example, there are a couple of categories some threads fall under such as
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # Bot nets
+    links.append('http://kw4zlnfhxje7top26u57iosg55i7dzuljjcyswo2clgc3mdliviswwyd.onion/product-category/botnets/')
+    # # data leak
+    # links.append('http://kw4zlnfhxje7top26u57iosg55i7dzuljjcyswo2clgc3mdliviswwyd.onion/product-category/dataleak/')
+    # databases
+    links.append('http://kw4zlnfhxje7top26u57iosg55i7dzuljjcyswo2clgc3mdliviswwyd.onion/product-category/databases/')
+    # # ransomware
+    # links.append('http://kw4zlnfhxje7top26u57iosg55i7dzuljjcyswo2clgc3mdliviswwyd.onion/product-category/ransomware/')
+    # # rats
+    # links.append('http://kw4zlnfhxje7top26u57iosg55i7dzuljjcyswo2clgc3mdliviswwyd.onion/product-category/rats/')
+
+    return links
+
+
+# gets links of interest to crawl through, iterates through list, where each link is clicked and crawled through
+#topic and description pages are crawled through here, where both types of pages are saved
+#@param: selenium driver
+def crawlForum(driver):
+    print("Crawling the DigitalThriftShop market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 0
+    while i < len(linksToCrawl):
+        link = linksToCrawl[i]
+        print('Crawling :', link)
+        try:
+            try:
+                driver.get(link)
+            except:
+                driver.refresh()
+            html = driver.page_source
+            savePage(html, link)
+
+            has_next_page = True
+            while has_next_page:
+                list = productPages(html)
+                for item in list:
+                    itemURL = urlparse.urljoin(baseURL, str(item))
+                    try:
+                        driver.get(itemURL)
+                    except:
+                        driver.refresh()
+                    savePage(driver.page_source, item)
+                    driver.back()
+
+                    # comment out
+                    break
+
+                # comment out
+                if count == 1:
+                    count = 0
+                    break
+
+                try:
+                    link = driver.find_element(by=By.XPATH, value=
+                        '/html/body/div[1]/div[2]/div/div[2]/main/div[1]/nav/ul/li[5]/a').get_attribute('href')
+                    if link == "":
+                        raise NoSuchElementException
+                    try:
+                        driver.get(link)
+                    except:
+                        driver.refresh()
+                    html = driver.page_source
+                    savePage(html, link)
+                    count += 1
+
+                except NoSuchElementException:
+                    has_next_page = False
+
+        except Exception as e:
+            print(link, e)
+        i += 1
+
+    # finalTime = time.time()
+    # print finalTime - initialTime
+
+    input("Crawling DigitalThriftShop forum done sucessfully. Press ENTER to continue\n")
+
+
+# Returns 'True' if the link is a description link
+#@param: url of any url crawled
+#return: true if is a description page, false if not
+def isDescriptionLink(url):
+    if 'product/' in url:
+        return True
+    return False
+
+
+# Returns True if the link is a listingPage link
+#@param: url of any url crawled
+#return: true if is a Listing page, false if not
+def isListingLink(url):
+    if 'product-' in url:
+        return True
+    return False
+
+
+# calling the parser to define the links, the html is the url of a link from the list of interested link list
+#@param: link from interested link list ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return digitalthriftshop_links_parser(soup)
+
+
+# Drop links that "signout"
+# def isSignOut(url):
+#     #absURL = urlparse.urljoin(url.base_url, url.url)
+#     if 'signout' in url.lower() or 'logout' in url.lower():
+#         return True
+#
+#     return False
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/DigitalThriftShop/parser.py

@@ -0,0 +1,291 @@
+__author__ = 'DarkWeb'
+
+# Here, we are importing the auxiliary functions to clean or convert data
+from MarketPlaces.Utilities.utilities import *
+
+# Here, we are importing BeautifulSoup to search through the HTML tree
+from bs4 import BeautifulSoup
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    lastSeen = "-1"                     # 2 Product_LastViewDate
+    rules = "-1"                        # 3 NOT USED ...
+    CVE = "-1"                          # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = "-1"                           # 5 Product_MS_Classification (Microsoft Security)
+    review = "-1"                       # 6 Product_Number_Of_Reviews
+    category = "-1"                     # 7 Product_Category
+    shipFrom = "-1"                     # 8 Product_ShippedFrom
+    shipTo = "-1"                       # 9 Product_ShippedTo
+    left = "-1"                         # 10 Product_QuantityLeft
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # Searching for CVE and MS categories
+    cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+    if cve:
+        CVE = " "
+        for idx in cve:
+            CVE += (idx)
+            CVE += "  "
+            CVE = CVE.replace(',', ' ')
+            CVE = CVE.replace('\n', '')
+    ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
+    if ms:
+        MS = " "
+        for im in ms:
+            MS += (im)
+            MS += " "
+            MS = MS.replace(',', ' ')
+            MS = MS.replace('\n', '')
+
+    # Populating the final variable (this should be a list with all fields scraped)
+    row = (name, describe, lastSeen, rules, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor,
+       sold, addDate, available, endDate, BTC, USD, rating, success, EURO)
+
+    # Sending the results
+    return row
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+        if not cve:
+            cveValue="-1"
+        else:
+            cee = " "
+            for idx in cve:
+                cee += (idx)
+                cee += "  "
+                cee = cee.replace(',', ' ')
+                cee = cee.replace('\n', '')
+            cveValue=cee
+        CVE.append(cveValue)
+        
+        ms = a.findAll(text=re.compile('MS\d{2}-\d{3}'))
+        if not ms:
+            MSValue="-1"
+        else:
+            me = " "
+            for im in ms:
+                me += (im)
+                me += " "
+                me = me.replace(',', ' ')
+                me = me.replace('\n', '')
+            MSValue=me
+        MS.append(MSValue)
+
+    # Populate the final variable (this should be a list with all fields scraped)
+    return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen,
+                     BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def digitalthriftshop_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.find('ul', {"class": "products columns-5"}).findAll('li')
+
+    for a in listing:
+        bae = a.find('a', href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href

MarketPlaces/Initialization/geckodriver.log

@@ -8604,8 +8604,8 @@ DevTools listening on ws://localhost:56159/devtools/browser/da664e77-92c9-4160-8
 1687385553572	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
 JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
 JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
-1687385720138	geckodriver	INFO	Listening on 127.0.0.1:56246
-1687385723484	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "56247" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileuCc0P6"
+JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\Helium\AppData\Local\Temp\rust_mozprofileR8jT8Z\thumbnails) because it does not exist
+-debugging-port" "56247" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileuCc0P6"
 console.log: "TorSettings: loadFromPrefs()"
 console.log: "TorConnect: init()"
 console.log: "TorConnect: Entering Initial state"
@@ -8641,3 +8641,271 @@ unwatchForTargets()@TargetList.jsm:37
 destructor()@TargetList.jsm:109
 stop()@CDP.jsm:104
 close()@RemoteAgent.jsm:138
+1687449887317	geckodriver	INFO	Listening on 127.0.0.1:51004
+1687449890873	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51005" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileKCABtF"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687449891534	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51005/devtools/browser/6d865809-fbc7-4760-bc49-9b9aab0e2bf7
+1687449893058	Marionette	INFO	Listening on port 51014
+1687449893582	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+SourceActor threw an exception: [Exception... "Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/9d56152f-51c2-42be-9fbd-fe4e215c085c'"  nsresult: "0x805303f4 (<unknown>)"  location: "JS frame :: resource://devtools/shared/DevToolsUtils.js :: mainThreadFetch/< :: line 670"  data: yes]
+Stack: mainThreadFetch/<@resource://devtools/shared/DevToolsUtils.js:670:15
+mainThreadFetch@resource://devtools/shared/DevToolsUtils.js:516:10
+_fetchURLContents@resource://devtools/server/actors/utils/sources-manager.js:442:22
+urlContents@resource://devtools/server/actors/utils/sources-manager.js:406:17
+_resurrectSource@resource://devtools/server/actors/thread.js:2142:35
+addAllSources@resource://devtools/server/actors/thread.js:1509:14
+watch@resource://devtools/server/actors/resources/sources.js:52:17
+watchResources@resource://devtools/server/actors/resources/index.js:239:19
+_watchTargetResources@resource://devtools/server/actors/targets/target-actor-mixin.js:156:24
+addWatcherDataEntry@resource://devtools/server/actors/targets/target-actor-mixin.js:47:20
+_addWatcherDataEntry@resource://devtools/server/connectors/js-window-actor/DevToolsFrameChild.jsm:483:24
+receiveMessage@resource://devtools/server/connectors/js-window-actor/DevToolsFrameChild.jsm:425:21
+Line: 670, column: 0
+console.error: ({})
+SourceActor threw an exception: [Exception... "Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/861a57ef-0b59-4882-b8a4-f722933956f0'"  nsresult: "0x805303f4 (<unknown>)"  location: "JS frame :: resource://devtools/shared/DevToolsUtils.js :: mainThreadFetch/< :: line 670"  data: yes]
+Stack: mainThreadFetch/<@resource://devtools/shared/DevToolsUtils.js:670:15
+mainThreadFetch@resource://devtools/shared/DevToolsUtils.js:516:10
+_fetchURLContents@resource://devtools/server/actors/utils/sources-manager.js:442:22
+urlContents@resource://devtools/server/actors/utils/sources-manager.js:406:17
+_resurrectSource@resource://devtools/server/actors/thread.js:2142:35
+addAllSources@resource://devtools/server/actors/thread.js:1509:14
+watch@resource://devtools/server/actors/resources/sources.js:52:17
+watchResources@resource://devtools/server/actors/resources/index.js:239:19
+_watchTargetResources@resource://devtools/server/actors/targets/target-actor-mixin.js:156:24
+addWatcherDataEntry@resource://devtools/server/actors/targets/target-actor-mixin.js:47:20
+_addWatcherDataEntry@resource://devtools/server/connectors/js-window-actor/DevToolsFrameChild.jsm:483:24
+receiveMessage@resource://devtools/server/connectors/js-window-actor/DevToolsFrameChild.jsm:425:21
+Line: 670, column: 0
+console.error: ({})
+JavaScript error: resource://devtools/shared/DevToolsUtils.js, line 670: Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/9d56152f-51c2-42be-9fbd-fe4e215c085c'
+JavaScript error: resource://devtools/shared/DevToolsUtils.js, line 670: Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/861a57ef-0b59-4882-b8a4-f722933956f0'
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+console.warn: "Resource  of root-node was not found."
+SourceActor threw an exception: [Exception... "Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/b31f8585-55eb-4fae-993e-0637e6545dd7'"  nsresult: "0x805303f4 (<unknown>)"  location: "JS frame :: resource://devtools/shared/DevToolsUtils.js :: mainThreadFetch/< :: line 670"  data: yes]
+Stack: mainThreadFetch/<@resource://devtools/shared/DevToolsUtils.js:670:15
+mainThreadFetch@resource://devtools/shared/DevToolsUtils.js:516:10
+_fetchURLContents@resource://devtools/server/actors/utils/sources-manager.js:442:22
+urlContents@resource://devtools/server/actors/utils/sources-manager.js:406:17
+_resurrectSource@resource://devtools/server/actors/thread.js:2142:35
+addAllSources@resource://devtools/server/actors/thread.js:1509:14
+_onWindowReady@resource://devtools/server/actors/thread.js:1818:12
+_emit@resource://devtools/shared/event-emitter.js:226:34
+emit@resource://devtools/shared/event-emitter.js:172:18
+emit@resource://devtools/shared/event-emitter.js:324:18
+_windowReady@resource://devtools/server/actors/targets/browsing-context.js:1406:10
+DebuggerProgressListener.prototype.onWindowCreated<@resource://devtools/server/actors/targets/browsing-context.js:1761:23
+exports.makeInfallible/<@resource://devtools/shared/ThreadSafeDevToolsUtils.js:103:22
+Line: 670, column: 0
+console.error: ({})
+SourceActor threw an exception: [Exception... "Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/703518f2-0e44-4fa7-8fda-056e24dfc731'"  nsresult: "0x805303f4 (<unknown>)"  location: "JS frame :: resource://devtools/shared/DevToolsUtils.js :: mainThreadFetch/< :: line 670"  data: yes]
+Stack: mainThreadFetch/<@resource://devtools/shared/DevToolsUtils.js:670:15
+mainThreadFetch@resource://devtools/shared/DevToolsUtils.js:516:10
+_fetchURLContents@resource://devtools/server/actors/utils/sources-manager.js:442:22
+urlContents@resource://devtools/server/actors/utils/sources-manager.js:406:17
+_resurrectSource@resource://devtools/server/actors/thread.js:2142:35
+addAllSources@resource://devtools/server/actors/thread.js:1509:14
+_onWindowReady@resource://devtools/server/actors/thread.js:1818:12
+_emit@resource://devtools/shared/event-emitter.js:226:34
+emit@resource://devtools/shared/event-emitter.js:172:18
+emit@resource://devtools/shared/event-emitter.js:324:18
+_windowReady@resource://devtools/server/actors/targets/browsing-context.js:1406:10
+DebuggerProgressListener.prototype.onWindowCreated<@resource://devtools/server/actors/targets/browsing-context.js:1761:23
+exports.makeInfallible/<@resource://devtools/shared/ThreadSafeDevToolsUtils.js:103:22
+Line: 670, column: 0
+console.error: ({})
+JavaScript error: resource://devtools/shared/DevToolsUtils.js, line 670: Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/b31f8585-55eb-4fae-993e-0637e6545dd7'
+JavaScript error: resource://devtools/shared/DevToolsUtils.js, line 670: Failed to open input source 'blob:moz-extension://3064b8c5-bffd-4bf8-b2f1-210b12185538/703518f2-0e44-4fa7-8fda-056e24dfc731'
+console.warn: "Async method failed in safeAsyncMethod" (new Error("Connection closed, pending request to server0.conn0.child4/domwalker24, type cancelPick fail1687450492998	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51115" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileXamevd"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687450493482	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51115/devtools/browser/44be2243-5f4e-4b1a-9b9e-793f909eb5b6
+1687450494706	Marionette	INFO	Listening on port 51123
+1687450494734	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1687450804355	Marionette	INFO	Stopped listening on port 51123
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\Helium\AppData\Local\Temp\rust_mozprofileXamevd\thumbnails) because it does not exist
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+1687450804629	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51188/devtools/browser/a3878037-b0ca-4217-a088-f448c2fcb69d
+1687450681407	Marionette	INFO	Listening on port 51193
+1687450681628	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1687450806179	Marionette	INFO	Stopped listening on port 51193
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PageThumbs.jsm, line 709: AbortError: IOUtils.profileBeforeChange getter: IOUtils: profileBeforeChange phase has already finished
+[Parent 8520, IPC I/O Parent] WARNING: file /var/tmp/build/firefox-b6010b1466c9/ipc/chromium/src/base/process_util_win.cc:167
+1687450806439	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1687452282130	geckodriver	INFO	Listening on 127.0.0.1:51476
+1687452286160	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51477" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofileZ1gqjQ"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687452286803	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51477/devtools/browser/d96c7e14-7dc2-46f0-b4cd-35743e71c63f
+1687452288663	Marionette	INFO	Listening on port 51482
+1687452288955	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: key "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID" was already initialized
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 109: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS", key: ""
+JavaScript error: resource://gre/modules/ExtensionTelemetry.jsm, line 113: Error: TelemetryStopwatch: finishing nonexisting stopwatch. Histogram: "WEBEXT_CONTENT_SCRIPT_INJECTION_MS_BY_ADDONID", key: "{73a6fe31-595d-460b-a920-fcc0f8843232}"
+1687452391476	Marionette	INFO	Stopped listening on port 51482
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PageThumbs.jsm, line 709: AbortError: IOUtils.profileBeforeChange getter: IOUtils: profileBeforeChange phase has already finished
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+1687452391783	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1687453361999	geckodriver	INFO	Listening on 127.0.0.1:51726
+1687453364756	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51727" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofilemnOa7V"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687453365268	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51727/devtools/browser/cd3d5b10-01ee-4fb9-9982-649fadd5a624
+1687453366340	Marionette	INFO	Listening on port 51732
+1687453366698	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+1687453449959	Marionette	INFO	Stopped listening on port 51732
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PageThumbs.jsm, line 709: AbortError: IOUtils.profileBeforeChange getter: IOUtils: profileBeforeChange phase has already finished
+1687453450550	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1687453473007	geckodriver	INFO	Listening on 127.0.0.1:51777
+1687453476313	mozrunner::runner	INFO	Running command: "C:\\Users\\\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51778" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\Helium\\AppData\\Local\\Temp\\rust_mozprofilewh57OX"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: init()"
+console.log: "TorConnect: Entering Initial state"
+console.log: "TorConnect: Observed profile-after-change"
+console.log: "TorConnect: Observing topic 'TorProcessExited'"
+console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: Observing topic 'torsettings:ready'"
+console.log: "TorSettings: Observed profile-after-change"
+1687453476948	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: Will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:51778/devtools/browser/74e919f9-8fdf-410c-8061-37137c444056
+1687453478140	Marionette	INFO	Listening on port 51783
+1687453478502	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+1687453663389	Marionette	INFO	Stopped listening on port 51783
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData]
+!!! error running onStopped callback: TypeError: callback is not a function
+JavaScript error: resource:///modules/sessionstore/SessionFile.jsm, line 375: Error: _initWorker called too early! Please read the session file from disk first.
+JavaScript error: resource://gre/modules/PageThumbs.jsm, line 709: AbortError: IOUtils.profileBeforeChange getter: IOUtils: profileBeforeChange phase has already finished
+[Parent 4800, IPC I/O Parent] WARNING: file /var/tmp/build/firefox-b6010b1466c9/ipc/chromium/src/base/process_util_win.cc:167
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+1687453663611	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138

MarketPlaces/Initialization/marketsList.txt

@@ -1 +1 @@
-MikesGrandStore
+AnonymousMarketplace

MarketPlaces/Initialization/markets_mining.py

@@ -13,6 +13,9 @@ from MarketPlaces.TorBay.crawler_selenium import crawler as crawlerTorBay
 from MarketPlaces.LionMarketplace.crawler_selenium import crawler as crawlerLionMarketplace
 from MarketPlaces.TorMarket.crawler_selenium import crawler as crawlerTorMarket
 from MarketPlaces.MikesGrandStore.crawler_selenium import crawler as crawlerMikesGrandStore
+from MarketPlaces.DarkTor.crawler_selenium import crawler as crawlerDarkTor
+from MarketPlaces.DigitalThriftShop.crawler_selenium import crawler as crawlerDigitalThriftShop
+from MarketPlaces.AnonymousMarketplace.crawler_selenium import crawler as crawlerAnonymousMarketplace
 
 
 import time
@@ -82,6 +85,12 @@ if __name__ == '__main__':
             crawlerTorMarket()
         elif mkt == "MikesGrandStore":
             crawlerMikesGrandStore()
+        elif mkt == "DarkTor":
+            crawlerDarkTor()
+        elif mkt == "DigitalThriftShop":
+            crawlerDigitalThriftShop()
+        elif mkt == "AnonymousMarketplace":
+            crawlerAnonymousMarketplace()