Completed and tested all parsers fro Cardingleaks forum

Forums/Altenens/crawler_selenium.py

@@ -30,18 +30,18 @@ baseURL = 'https://altenens.is/'
 
 # Opens Tor Browser, crawls the website
 def startCrawling():
-    # opentor()
+    opentor()
     forumName = getForumName()
-    # driver = getAccess()
-    #
-    # if driver != 'down':
-    #     try:
-    #         login(driver)
-    #         crawlForum(driver)
-    #     except Exception as e:
-    #         print(driver.current_url, e)
-    #     closetor(driver)
-    #
+    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)
 
 

Forums/Cardingleaks/crawler_selenium.py

@@ -29,17 +29,17 @@ baseURL = 'https://cardingleaks.ws/'
 
 # Opens Tor Browser, crawls the website
 def startCrawling():
-    opentor()
+    # opentor()
     forumName = getForumName()
-    driver = getAccess()
+    # driver = getAccess()
     
-    if driver != 'down':
-        try:
-            login(driver)
-            crawlForum(driver)
-        except Exception as e:
-            print(driver.current_url, e)
-        closetor(driver)
+    # if driver != 'down':
+    #     try:
+    #         login(driver)
+    #         crawlForum(driver)
+    #     except Exception as e:
+    #         print(driver.current_url, e)
+    #     closetor(driver)
 
     new_parse(forumName, baseURL, False)
 
@@ -242,7 +242,7 @@ def crawlForum(driver):
                         savePage(driver.page_source, topic + f"page{counter}")  # very important
 
                         # comment out
-                        if counter == 2:
+                        if counter == 5:
                             break
 
                         try:
@@ -261,7 +261,7 @@ def crawlForum(driver):
                     break
 
                 # comment out
-                if count == 1:
+                if count == 10:
                     break
 
                 try:

Forums/Cardingleaks/parser.py

@@ -7,12 +7,12 @@ from datetime import timedelta
 import re
 
 # Here, we are importing BeautifulSoup to search through the HTML tree
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup, ResultSet, Tag
 
 # This is the method to parse the Description Pages (one page to each topic in the Listing Pages)
 
 
-def cryptBB_description_parser(soup):
+def cardingleaks_description_parser(soup: Tag):
 
     # Fields to be parsed
 
@@ -26,135 +26,44 @@ def cryptBB_description_parser(soup):
     feedback = []           # 7 all feedbacks of each vendor (this was found in just one Forum and with a number format)
     addDate = []            # 8 all dates of each post
 
-    # Finding the topic (should be just one coming from the Listing Page)
-
-    li = soup.find("td", {"class": "thead"}).find('strong')
-    topic = li.text
-    topic = re.sub("\[\w*\]", '', topic)
-
-    topic = topic.replace(",","")
-    topic = topic.replace("\n","")
-    topic = cleanString(topic.strip())
-
-    # Finding the repeated tag that corresponds to the listing of posts
-
-    # try:
-    posts = soup.find('table', {"class": "tborder tfixed clear"}).find('td', {"id": "posts_container"}).find_all(
-        'div', {"class": "post"})
-
-    # For each message (post), get all the fields we are interested to:
-
-    for ipost in posts:
-
-        # Finding a first level of the HTML page
-
-        post_wrapper = ipost.find('span', {"class": "largetext"})
-
-        # Finding the author (user) of the post
-
-        author = post_wrapper.text.strip()
-        user.append(cleanString(author))  # Remember to clean the problematic characters
-
-        # Finding the status of the author
-
-        smalltext = ipost.find('div', {"class": "post_author"})
-
-        '''
-        # Testing here two possibilities to find this status and combine them
-        if ipost.find('div', {"class": "deleted_post_author"}):
-            status.append(-1)
-            interest.append(-1)
-            reputation.append(-1)
-            addDate.append(-1)
-            post.append("THIS POST HAS BEEN REMOVED!")
-            sign.append(-1)
-            feedback.append(-1)
-            continue
-        '''
-
-        # CryptBB does have membergroup and postgroup
-
-        membergroup = smalltext.find('div', {"class": "profile-rank"})
-        postgroup = smalltext.find('div', {"class": "postgroup"})
-        if membergroup != None:
-            membergroup = membergroup.text.strip()
-            if postgroup != None:
-                postgroup = postgroup.text.strip()
-                membergroup = membergroup + " - " + postgroup
-        else:
-            if postgroup != None:
-                membergroup = postgroup.text.strip()
-            else:
-                membergroup = "-1"
-        status.append(cleanString(membergroup))
-
-        # Finding the interest of the author
-        # CryptBB does not have blurb
-        blurb = smalltext.find('li', {"class": "blurb"})
-        if blurb != None:
-            blurb = blurb.text.strip()
-        else:
-            blurb = "-1"
-        interest.append(cleanString(blurb))
-
-        # Finding the reputation of the user
-        # CryptBB does have reputation
-        author_stats = smalltext.find('div', {"class": "author_statistics"})
-        karma = author_stats.find('strong')
-        if karma != None:
-            karma = karma.text
-            karma = karma.replace("Community Rating: ", "")
-            karma = karma.replace("Karma: ", "")
-            karma = karma.strip()
-        else:
-            karma = "-1"
-        reputation.append(cleanString(karma))
-
-        # Getting here another good tag to find the post date, post content and users' signature
-
-        postarea = ipost.find('div', {"class": "post_content"})
-
-        dt = postarea.find('span', {"class": "post_date"}).text
-        # dt = dt.strip().split()
-        dt = dt.strip()
-        day=date.today()
-        if "Yesterday" in dt:
-            yesterday = day - timedelta(days=1)
-            yesterday = yesterday.strftime('%m-%d-%Y')
-            stime = dt.replace('Yesterday,','').strip()
-            date_time_obj = yesterday+ ', '+stime
-            date_time_obj = datetime.strptime(date_time_obj,'%m-%d-%Y, %I:%M %p')
-        elif "hours ago" in dt:
-            day = day.strftime('%m-%d-%Y')
-            date_time_obj = postarea.find('span', {"class": "post_date"}).find('span')['title']
-            date_time_obj = datetime.strptime(date_time_obj, '%m-%d-%Y, %I:%M %p')
-        else:
-            date_time_obj = datetime.strptime(dt, '%m-%d-%Y, %I:%M %p')
-            stime = date_time_obj.strftime('%b %d, %Y')
-            sdate = date_time_obj.strftime('%I:%M %p')
-        addDate.append(date_time_obj)
-
-        # Finding the post
-
-        inner = postarea.find('div', {"class": "post_body scaleimages"})
-        inner = inner.text.strip()
-        post.append(cleanString(inner))
-
-        # Finding the user's signature
-
-        # signature = ipost.find('div', {"class": "post_wrapper"}).find('div', {"class": "moderatorbar"}).find('div', {"class": "signature"})
-        signature = ipost.find('div', {"class": "signature scaleimages"})
-        if signature != None:
-            signature = signature.text.strip()
-            # print(signature)
-        else:
-            signature = "-1"
-        sign.append(cleanString(signature))
-
-        # As no information about user's feedback was found, just assign "-1" to the variable
-
+    li = soup.find("h1", {"class": "p-title-value"})
+    topic = cleanString(li.text.strip())
+
+    post_list: ResultSet[Tag] = soup.find("div", {"class": "block-body js-replyNewMessageContainer"}).find_all("article", {"data-author": True})
+
+    for ipost in post_list:
+        username = ipost.get('data-author')
+        user.append(username)
+        
+        user_status = ipost.find("h5", {"class": "userTitle message-userTitle"}).text
+        status.append(cleanString(user_status.strip()))
+        
+        user_statistics: ResultSet[Tag] = ipost.find("div", {"class": "message-userExtras"}).find_all("dl", {"class": "pairs pairs--justified"})
+        
+        user_reputation = "-1"
+        
+        for stat in user_statistics:
+            data_type = stat.find("span").get("data-original-title")
+            if data_type == "Points":
+                user_reputation = stat.find("dd").text
+                break
+            
+        reputation.append(cleanString(user_reputation.strip()))
+        
+        interest.append("-1")
+        
+        sign.append("-1")
+        
+        user_post = ipost.find("div", {"class": "message-content js-messageContent"}).text
+        post.append(cleanString(user_post.strip()))
+        
         feedback.append("-1")
-
+        
+        datetime_text = ipost.find("ul", {"class": "message-attribution-main listInline"}).find("time").get("datetime")
+        datetime_obj = datetime.strptime(datetime_text, "%Y-%m-%dT%H:%M:%S%z")
+        addDate.append(datetime_obj)
+        
+        
     # Populate the final variable (this should be a list with all fields scraped)
 
     row = (topic, user, status, reputation, interest, sign, post, feedback, addDate)
@@ -165,10 +74,10 @@ def cryptBB_description_parser(soup):
 
 # This is the method to parse the Listing Pages (one page with many posts)
 
-def cryptBB_listing_parser(soup):
+def cardingleaks_listing_parser(soup: Tag):
 
     nm = 0              # *this variable should receive the number of topics
-    forum = "OnniForums"   # 0 *forum name
+    forum = "Cardingleaks"   # 0 *forum name
     board = "-1"        # 1 *board name (the previous level of the topic in the Forum categorization tree.
                         # For instance: Security/Malware/Tools to hack Facebook. The board here should be Malware)
     author = []         # 2 *all authors of each topic
@@ -181,55 +90,35 @@ def cryptBB_listing_parser(soup):
 
     # Finding the board (should be just one)
 
-    board = soup.find('span', {"class": "active"}).text
-    board = cleanString(board.strip())
-
-    # Finding the repeated tag that corresponds to the listing of topics
-
-    itopics = soup.find_all('tr',{"class": "inline_row"})
-
-    for itopic in itopics:
-
-        # For each topic found, the structure to get the rest of the information can be of two types. Testing all of them
-        # to don't miss any topic
-
-        # Adding the topic to the topic list
-        try:
-            topics = itopic.find('span', {"class": "subject_old"}).find('a').text
-        except:
-            topics = itopic.find('span', {"class": "subject_new"}).find('a').text
-        topics = re.sub("\[\w*\]", '', topics)
-        topic.append(cleanString(topics))
-
-        # Counting how many topics we have found so far
-
-        nm = len(topic)
-
-        # Adding the url to the list of urls
-        try:
-            link = itopic.find('span', {"class": "subject_old"}).find('a').get('href')
-        except:
-            link = itopic.find('span',{"class": "subject_new"}).find('a').get('href')
-        href.append(link)
-
-        # Finding the author of the topic
-        ps = itopic.find('div', {"class":"author smalltext"}).find('a').text
-        user = ps.strip()
-        author.append(cleanString(user))
-
-        # Finding the number of replies
-        columns = itopic.findChildren('td',recursive=False)
-        replies = columns[3].text
-
-        posts.append(cleanString(replies))
-
-        # Finding the number of Views
-        tview = columns[4].text
-        views.append(cleanString(tview))
-
-        # If no information about when the topic was added, just assign "-1" to the variable
-
-        addDate.append("-1")
+    li = soup.find("h1", {"class": "p-title-value"})
+    board = cleanString(li.text.strip())
+
+    thread_list: ResultSet[Tag] = soup.find("div", {"class": "structItemContainer-group js-threadList"}).find_all("div", {"data-author": True})
+    
+    nm = len(thread_list)
+    
+    for thread in thread_list:
+        thread_author = thread.get("data-author")
+        author.append(thread_author)
+        
+        thread_topic = thread.find("div", {"class": "structItem-title"}).text
+        topic.append(cleanString(thread_topic.strip()))
+        
+        thread_view = thread.find("dl", {"class": "pairs pairs--justified structItem-minor"}).find("dd").text
+        # Context text view count (i.e., 8.8K) to numerical (i.e., 8800)
+        if thread_view.find("K") > 0:
+            thread_view = str(int(float(thread_view.replace("K", "")) * 1000))
+        views.append(thread_view)
+        
+        thread_posts = thread.find("dl", {"class": "pairs pairs--justified"}).find("dd").text
+        posts.append(cleanString(thread_posts.strip()))
+        
+        thread_href = thread.find("div", {"class": "structItem-title"}).find("a").get("href")
+        href.append(thread_href)
+        
+        thread_date = thread.find("li", {"class": "structItem-startDate"}).find("time").get("datetime")
+        datetime_obj = datetime.strptime(thread_date, "%Y-%m-%dT%H:%M:%S%z")
+        addDate.append(datetime_obj)
 
     return organizeTopics(forum, nm, board, author, topic, views, posts, href, addDate)
 

Forums/CryptBB/crawler_selenium.py

@@ -273,7 +273,7 @@ def crawlForum(driver):
                         savePage(driver.page_source, topic + f"page{counter}")  # very important
 
                         # comment out
-                        if counter == 2:
+                        if counter == 10:
                             break
 
                         try:
@@ -291,10 +291,10 @@ def crawlForum(driver):
                         driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
-                if count == 1:
+                if count == 20:
                     break
 
                 try:

Forums/Initialization/forumsList.txt

@@ -1 +1 @@
-Altenens
+Cardingleaks

Forums/Initialization/geckodriver.log

@@ -14894,29 +14894,23 @@ JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: Type
 JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
 JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
 JavaScript error: moz-extension://ea77c2e9-b8db-4689-b4a8-30cbf0652171/content/staticNS.js, line 162: TypeError: can't access dead object
-1689787519066	geckodriver	INFO	Listening on 127.0.0.1:50232
-1689787522517	mozrunner::runner	INFO	Running command: "C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50233" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\MINHKH~1\\AppData\\Local\\Temp\\rust_mozprofileVprPHA"
-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"
-1689787522977	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:50233/devtools/browser/d02a6124-5f75-45d7-9517-a98b7d46eeea
-1689787524053	Marionette	INFO	Listening on port 50238
-1689787524078	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\minhkhoitran\AppData\Local\Temp\rust_mozprofileux3rvG\thumbnails) because it does not exist
 JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
 JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
+1689792192254	Marionette	INFO	Stopped listening on port 50161
+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\minhkhoitran\AppData\Local\Temp\rust_mozprofileux3rvG\thumbnails) because it does not exist
+[Parent 3988, IPC I/O Parent] WARNING: file /var/tmp/build/firefox-b6010b1466c9/ipc/chromium/src/base/process_util_win.cc:167
+1689792192665	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
+avaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
+JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
 JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
 JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
 JavaScript error: https://altenens.is/js/xenmake/headroom.min.js, line 155: TypeError: this.elem is null
@@ -14987,3 +14981,40 @@ unwatchForTargets()@TargetList.jsm:37
 destructor()@TargetList.jsm:109
 stop()@CDP.jsm:104
 close()@RemoteAgent.jsm:138
+1689790072936	geckodriver	INFO	Listening on 127.0.0.1:50011
+1689790078108	mozrunner::runner	INFO	Running command: "C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50012" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\MINHKH~1\\AppData\\Local\\Temp\\rust_mozprofile7s5IYY"
+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"
+1689790078736	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:50012/devtools/browser/d82f5bb0-7a3f-46d2-83b0-9451c01d88b2
+1689790080352	Marionette	INFO	Listening on port 50017
+1689790080437	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\minhkhoitran\AppData\Local\Temp\rust_mozprofile7s5IYY\thumbnails) because it does not exist
+JavaScript error: https://cardingleaks.ws/js/xenconcept/hidebbcode/message.min.js?_v=516cdbc2, line 1: TypeError: XF.QuickReply is undefined
+1689790828818	Marionette	INFO	Stopped listening on port 50017
+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\minhkhoitran\AppData\Local\Temp\rust_mozprofile7s5IYY\thumbnails) because it does not exist
+
+###!!! [Parent][MessageChannel] Error: (msgtype=0x390076,name=PContent::Msg_DestroyBrowsingContextGroup) Closed channel: cannot send/recv
+
+1689790829319	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

Forums/Initialization/prepare_parser.py

@@ -6,6 +6,7 @@ import os, re
 import shutil
 from Forums.DB_Connection.db_connection import *
 from Forums.BestCardingWorld.parser import *
+from Forums.Cardingleaks.parser import *
 from Forums.CryptBB.parser import *
 from Forums.OnniForums.parser import *
 from Forums.Altenens.parser import *
@@ -149,6 +150,8 @@ def new_parse(forum, url, createLog):
 
             if forum == "BestCardingWorld":
                 rmm = bestcardingworld_description_parser(soup)
+            elif forum == "Cardingleaks":
+                rmm = cardingleaks_description_parser(soup)
             elif forum == "CryptBB":
                 rmm = cryptBB_description_parser(soup)
             elif forum == "OnniForums":
@@ -230,6 +233,8 @@ def new_parse(forum, url, createLog):
 
                 if forum == "BestCardingWorld":
                     rw = bestcardingworld_listing_parser(soup)
+                elif forum == "Cardingleaks":
+                    rw = cardingleaks_listing_parser(soup)
                 elif forum == "CryptBB":
                     rw = cryptBB_listing_parser(soup)
                 elif forum == "OnniForums":

Forums/Procrax/parser.py

@@ -110,7 +110,7 @@ def procrax_listing_parser(soup: Tag):
         datetime_obj = datetime.strptime(thread_date, "%Y-%m-%dT%H:%M:%S%z")
         addDate.append(datetime_obj)
         
-        thread_link = thread.find("div", {"class": "structItem-title"}).find('a').get('href')
+        thread_link: str = thread.find("div", {"class": "structItem-title"}).find('a').get('href')
         href.append(thread_link)
     
     

setup.ini

@@ -1,11 +1,11 @@
 
 [TOR]
-firefox_binary_path = C:\Users\Helium\Desktop\Tor Browser\Browser\firefox.exe
-firefox_profile_path = C:\Users\Helium\Desktop\Tor Browser\Browser\TorBrowser\Data\Browser\profile.default
-geckodriver_path = C:\Users\Helium\PycharmProjects\dw_pipeline_test\selenium\geckodriver.exe
+firefox_binary_path = C:\Users\minhkhoitran\Desktop\Tor Browser\Browser\firefox.exe
+firefox_profile_path = C:\Users\minhkhoitran\Desktop\Tor Browser\Browser\TorBrowser\Data\Browser\profile.default
+geckodriver_path = C:\nsf-reu\dw_pipeline_test\selenium\geckodriver.exe
 
 [Project]
-project_directory = C:\Users\Helium\PycharmProjects\dw_pipeline_test
+project_directory = C:\nsf-reu\dw_pipeline_test
 shared_folder = \\VBoxSvr\\Shared
 
 [PostgreSQL]