Upload WarOnline_Chat_test.py

Fixed some bugs. This is a main file version candidate...

WarOnline_Chat_test.py

@@ -93,7 +93,7 @@ def post(message=message, thread_url=thread_url, post_url=post_url, quoted_by=""
 
     print('Post submitted successfully.')
 
-def messagesByUser(thread_url=thread_url, username="", startingPage=1):
+def getMessages(thread_url=thread_url, quotedUser="", startingPage=1):
     # Returns all the quotes for #username in the specific multi-page thread url
     allquotes =[]
 
@@ -109,6 +109,7 @@ def messagesByUser(thread_url=thread_url, username="", startingPage=1):
     namePattern = re.compile('data-lb-caption-desc="(.*?) ·')
     messageIDPattern = re.compile('data-lb-id="(.*?)"')
     quotedIDPattern = re.compile('data-source="(.*?)"')
+    quotedNamePattern = re.compile('data-quote="(.*?)"')
 
     while not lastPage:
         response = requests.get(thread_url + 'page-' + str(page))
@@ -124,37 +125,41 @@ def messagesByUser(thread_url=thread_url, username="", startingPage=1):
             messageData = soup.find_all('div', {'class': 'message-userContent lbContainer js-lbContainer'})
 
             for data in messageData:
-
-                if (username) in data.text:
-                    try:
-                        # Get the messager username
-                        matchName = namePattern.search(str(data))
-                        if matchName:
-                            messengerName = matchName.group(1)
-
-                        # Get the quoted ID
-                        matchID = quotedIDPattern.search(str(data))
-                        if matchID:
-                            quotedID = matchID.group(1)
-
-                        # Get the message ID
-                        matchID = messageIDPattern.search(str(data))
-                        if matchID:
-                            messageID = matchID.group(1)
-
-                        # Make sure that the messages have a quote inside
-                        blockquote = data.find('blockquote')
-                        if blockquote:
-                            # Extract the text
-                            text = data.find('div', {'class': 'bbWrapper'})
-                            for bq in text.find_all('blockquote'):
-                                bq.extract()
-                            reply = text.get_text().replace('\n', ' ').strip()
-
-                            allquotes.append({'reply': reply, 'messengerName': messengerName, 'messageID': messageID, 'quotedID': quotedID})
-
-                    except:
-                        continue # There was no text in quote, move next
+                try:
+                    # Get the messager username
+                    matchName = namePattern.search(str(data))
+                    if matchName:
+                        messengerName = matchName.group(1)
+
+                    # Get the quoted ID
+                    matchID = quotedIDPattern.search(str(data))
+                    if matchID:
+                        quotedID = matchID.group(1)
+
+                    # Get the message ID
+                    matchID = messageIDPattern.search(str(data))
+                    if matchID:
+                        messageID = matchID.group(1)
+
+                    matchQuotedName = quotedNamePattern.search(str(data))
+                    if matchQuotedName:
+                        quotedName = matchQuotedName.group(1)
+                    if quotedUser and (quotedUser != quotedName):
+                        continue
+
+                    # Make sure that the messages have a quote inside
+                    blockquote = data.find('blockquote')
+                    if blockquote:
+                        # Extract the text
+                        text = data.find('div', {'class': 'bbWrapper'})
+                        for bq in text.find_all('blockquote'):
+                            bq.extract()
+                        reply = text.get_text().replace('\n', ' ').strip()
+
+                        allquotes.append({'reply': reply, 'messengerName': messengerName, 'messageID': messageID, 'quotedID': quotedID})
+
+                except:
+                    continue # There was no text in quote, move next
 
             #check if that is not a last page
             if not compare_pages(thread_url + 'page-' + str(page), thread_url + 'page-' + str(page + 1)):
@@ -167,8 +172,12 @@ def messagesByUser(thread_url=thread_url, username="", startingPage=1):
     return allquotes
 def WarOnlineBot():
     # Get All Quotes by all users
-    allMessages = messagesByUser(thread_url=thread_url, username="", startingPage=1)
-    botMessages = messagesByUser(thread_url=thread_url, username=username, startingPage=1)
+    allMessages = getMessages(thread_url=thread_url,  startingPage=1)
+    unrepliedMessages = []
+    for msg in allMessages:
+        if msg['messageID'].strip('-')[-1] != msg['quotedID'].strip(': ')[-1]:
+            unrepliedMessages.append(msg)
+
     for quote in quotes:
         pass
 
@@ -189,13 +198,21 @@ if __name__ == '__main__':
     login(username=username, password=password, thread_url=thread_url)
     print("logged in")
 
-    ### Disabled. Will be enabled later on ###
+    ### Disabled ###
     #post(message=message, thread_url=thread_url, post_url=post_url, quoted_by='Василий Пупкин', quote_text='quoted message', quote_source='3926006')
 
-    quotes = messagesByUser(username=username)
-    for quote in quotes:
-        print(quote)
+    #messagedByBot = getMessages(thread_url=thread_url, quotedUser='WarBot', startingPage=1)
+    allMessages = getMessages(thread_url=thread_url, quotedUser='', startingPage=1)
+    repliedMessagesIDs = []
+
+    for msg in allMessages:
+        # Set a list of replied IDs
+        repliedMessagesIDs.append(msg['quotedID'].split(': ')[-1])
+        print(msg)
+    # remove empty elements
+    repliedMessagesIDs = [elem for elem in repliedMessagesIDs if elem]
 
+    print(repliedMessagesIDs)
     """
     # Start the scheduler
     while True: