Upload WarOnline_Chat.py
Browse files- WarOnline_Chat.py +101 -60
WarOnline_Chat.py
CHANGED
@@ -6,9 +6,9 @@ import re
|
|
6 |
from bs4 import BeautifulSoup
|
7 |
import urllib.request as urllib
|
8 |
import warnings
|
9 |
-
import schedule
|
10 |
import time
|
11 |
-
from tqdm import tqdm
|
12 |
warnings.filterwarnings("ignore")
|
13 |
|
14 |
# Define the login URL and the thread URL
|
@@ -16,9 +16,6 @@ login_url = 'https://waronline.org/fora/index.php?login/login'
|
|
16 |
thread_url = 'https://waronline.org/fora/index.php?threads/warbot-playground.17636/'
|
17 |
post_url = "https://waronline.org/fora/index.php?threads/warbot-playground.17636/add-reply"
|
18 |
|
19 |
-
# Sending the message (change that!)
|
20 |
-
message = "Test"
|
21 |
-
|
22 |
# Define the login credentials
|
23 |
username = 'WarBot'
|
24 |
password = 'naP2tion'
|
@@ -26,11 +23,15 @@ password = 'naP2tion'
|
|
26 |
# Start a session to persist the login cookie across requests
|
27 |
session = requests.Session()
|
28 |
|
29 |
-
|
30 |
def compare_pages(url1, url2):
|
31 |
#Compares 2 pages and returns True if they are the same
|
32 |
return urllib.urlopen(url1).geturl() == urllib.urlopen(url2).geturl()
|
33 |
|
|
|
|
|
|
|
|
|
|
|
34 |
def login(username=username, password=password, thread_url=thread_url):
|
35 |
# Log-In to the forum and redirect to thread
|
36 |
|
@@ -61,6 +62,7 @@ def post(message=message, thread_url=thread_url, post_url=post_url, quoted_by=""
|
|
61 |
|
62 |
if quoted_by:
|
63 |
message = f'[QUOTE="{quoted_by}, post: {quote_source}"]{quote_text}[/QUOTE]{message}'
|
|
|
64 |
# optionally add @{quoted_by} to indent the quoter
|
65 |
|
66 |
# Retrieve the thread page HTML
|
@@ -92,7 +94,7 @@ def post(message=message, thread_url=thread_url, post_url=post_url, quoted_by=""
|
|
92 |
|
93 |
print('Post submitted successfully.')
|
94 |
|
95 |
-
def
|
96 |
# Returns all the quotes for #username in the specific multi-page thread url
|
97 |
allquotes =[]
|
98 |
|
@@ -102,10 +104,13 @@ def allQuotesFor(thread_url=thread_url, username=username, startingPage=1):
|
|
102 |
# Initial values for messangerName and the message ID
|
103 |
messengerName = ""
|
104 |
messageID = ""
|
|
|
105 |
|
106 |
# Patterns to search in the last quote.
|
107 |
namePattern = re.compile('data-lb-caption-desc="(.*?) ·')
|
108 |
messageIDPattern = re.compile('data-lb-id="(.*?)"')
|
|
|
|
|
109 |
|
110 |
while not lastPage:
|
111 |
response = requests.get(thread_url + 'page-' + str(page))
|
@@ -118,30 +123,44 @@ def allQuotesFor(thread_url=thread_url, username=username, startingPage=1):
|
|
118 |
soup = BeautifulSoup(html_content, 'html.parser')
|
119 |
|
120 |
# Find all the message in the thread page
|
121 |
-
messageData = soup.find_all('div', {'class': 'message-userContent'})
|
122 |
|
123 |
for data in messageData:
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
continue
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
145 |
|
146 |
#check if that is not a last page
|
147 |
if not compare_pages(thread_url + 'page-' + str(page), thread_url + 'page-' + str(page + 1)):
|
@@ -153,45 +172,67 @@ def allQuotesFor(thread_url=thread_url, username=username, startingPage=1):
|
|
153 |
|
154 |
return allquotes
|
155 |
|
|
|
156 |
def WarOnlineBot():
|
157 |
-
# Get All Quotes
|
158 |
-
quotes = allQuotesFor(thread_url=thread_url, username=username, startingPage=1)
|
159 |
-
repliedMessageIDs = []
|
160 |
-
for quote in quotes:
|
161 |
-
replies = allQuotesFor(thread_url=thread_url, username=quote['messengerName'], startingPage=1)
|
162 |
-
for reply in replies: # Remove all non-relevant and previously answered replies
|
163 |
-
|
164 |
-
if reply['messengerName']!=username or reply['messageID'] in repliedMessageIDs:
|
165 |
-
replies.remove(reply)
|
166 |
-
else:
|
167 |
-
repliedMessageIDs.append(reply['messageID'])
|
168 |
-
repliedMessageIDs = list(set(repliedMessageIDs))
|
169 |
-
# There is still some strange error. Will take a look later
|
170 |
|
171 |
-
|
172 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
173 |
while not message:
|
174 |
-
message = WarClient.getReply(message=quote
|
175 |
-
|
176 |
-
print('
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
time.sleep(
|
|
|
|
|
|
|
181 |
|
182 |
|
183 |
if __name__ == '__main__':
|
184 |
-
timeout =
|
185 |
-
#post(message=message, thread_url=thread_url, post_url=post_url,quoted_by='Василий Пупкин',quote_text='Testing the XenForo response mechanism')
|
186 |
|
187 |
# Start the scheduler
|
188 |
while True:
|
189 |
-
login(username=username, password=password, thread_url=thread_url)
|
190 |
-
print("logged in")
|
191 |
WarOnlineBot()
|
192 |
-
p_bar = tqdm(range(60 * timeout))
|
193 |
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
time.sleep(1)
|
|
|
6 |
from bs4 import BeautifulSoup
|
7 |
import urllib.request as urllib
|
8 |
import warnings
|
9 |
+
#import schedule
|
10 |
import time
|
11 |
+
#from tqdm import tqdm
|
12 |
warnings.filterwarnings("ignore")
|
13 |
|
14 |
# Define the login URL and the thread URL
|
|
|
16 |
thread_url = 'https://waronline.org/fora/index.php?threads/warbot-playground.17636/'
|
17 |
post_url = "https://waronline.org/fora/index.php?threads/warbot-playground.17636/add-reply"
|
18 |
|
|
|
|
|
|
|
19 |
# Define the login credentials
|
20 |
username = 'WarBot'
|
21 |
password = 'naP2tion'
|
|
|
23 |
# Start a session to persist the login cookie across requests
|
24 |
session = requests.Session()
|
25 |
|
|
|
26 |
def compare_pages(url1, url2):
|
27 |
#Compares 2 pages and returns True if they are the same
|
28 |
return urllib.urlopen(url1).geturl() == urllib.urlopen(url2).geturl()
|
29 |
|
30 |
+
def remove_non_english_russian_chars(s):
|
31 |
+
# Regular expression to match all characters that are not in English or Russian
|
32 |
+
pattern = '[^0-9A-Za-zА-Яа-яЁё(),.!?"\s-]'
|
33 |
+
# Replace all matched characters with an empty string
|
34 |
+
return re.sub(pattern, '', s)
|
35 |
def login(username=username, password=password, thread_url=thread_url):
|
36 |
# Log-In to the forum and redirect to thread
|
37 |
|
|
|
62 |
|
63 |
if quoted_by:
|
64 |
message = f'[QUOTE="{quoted_by}, post: {quote_source}"]{quote_text}[/QUOTE]{message}'
|
65 |
+
#message = f'[QUOTE="{quoted_by}, data-source=post: {quote_source}"]{quote_text}[/QUOTE]{message}'
|
66 |
# optionally add @{quoted_by} to indent the quoter
|
67 |
|
68 |
# Retrieve the thread page HTML
|
|
|
94 |
|
95 |
print('Post submitted successfully.')
|
96 |
|
97 |
+
def getMessages(thread_url=thread_url, quotedUser="", startingPage=1):
|
98 |
# Returns all the quotes for #username in the specific multi-page thread url
|
99 |
allquotes =[]
|
100 |
|
|
|
104 |
# Initial values for messangerName and the message ID
|
105 |
messengerName = ""
|
106 |
messageID = ""
|
107 |
+
quotedID = ""
|
108 |
|
109 |
# Patterns to search in the last quote.
|
110 |
namePattern = re.compile('data-lb-caption-desc="(.*?) ·')
|
111 |
messageIDPattern = re.compile('data-lb-id="(.*?)"')
|
112 |
+
quotedIDPattern = re.compile('data-source="(.*?)"')
|
113 |
+
quotedNamePattern = re.compile('data-quote="(.*?)"')
|
114 |
|
115 |
while not lastPage:
|
116 |
response = requests.get(thread_url + 'page-' + str(page))
|
|
|
123 |
soup = BeautifulSoup(html_content, 'html.parser')
|
124 |
|
125 |
# Find all the message in the thread page
|
126 |
+
messageData = soup.find_all('div', {'class': 'message-userContent lbContainer js-lbContainer'})
|
127 |
|
128 |
for data in messageData:
|
129 |
+
try:
|
130 |
+
# Get the messager username
|
131 |
+
matchName = namePattern.search(str(data))
|
132 |
+
if matchName:
|
133 |
+
messengerName = matchName.group(1)
|
134 |
+
|
135 |
+
# Get the quoted ID
|
136 |
+
matchID = quotedIDPattern.search(str(data))
|
137 |
+
if matchID:
|
138 |
+
quotedID = matchID.group(1)
|
139 |
+
|
140 |
+
# Get the message ID
|
141 |
+
matchID = messageIDPattern.search(str(data))
|
142 |
+
if matchID:
|
143 |
+
messageID = matchID.group(1)
|
144 |
+
|
145 |
+
matchQuotedName = quotedNamePattern.search(str(data))
|
146 |
+
if matchQuotedName:
|
147 |
+
quotedName = matchQuotedName.group(1)
|
148 |
+
if quotedUser and (quotedUser != quotedName):
|
149 |
+
continue
|
150 |
+
|
151 |
+
# Make sure that the messages have a quote inside
|
152 |
+
blockquote = data.find('blockquote')
|
153 |
+
if blockquote:
|
154 |
+
# Extract the text
|
155 |
+
text = data.find('div', {'class': 'bbWrapper'})
|
156 |
+
for bq in text.find_all('blockquote'):
|
157 |
+
bq.extract()
|
158 |
+
reply = text.get_text().replace('\n', ' ').strip()
|
159 |
+
|
160 |
+
allquotes.append({'reply': reply, 'messengerName': messengerName, 'messageID': messageID, 'quotedID': quotedID})
|
161 |
+
|
162 |
+
except:
|
163 |
+
continue # There was no text in quote, move next
|
164 |
|
165 |
#check if that is not a last page
|
166 |
if not compare_pages(thread_url + 'page-' + str(page), thread_url + 'page-' + str(page + 1)):
|
|
|
172 |
|
173 |
return allquotes
|
174 |
|
175 |
+
# Core Engine of the Client
|
176 |
def WarOnlineBot():
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
177 |
|
178 |
+
login(username=username, password=password, thread_url=thread_url)
|
179 |
+
#print("logged in")
|
180 |
+
|
181 |
+
# All messages (with quotes) by ALL users:
|
182 |
+
allMessages = getMessages(thread_url=thread_url, quotedUser='', startingPage=1)
|
183 |
+
|
184 |
+
# IDs of the quoted messages, replied by the bot:
|
185 |
+
messages_by_bot_IDs = []
|
186 |
+
|
187 |
+
for msg in allMessages:
|
188 |
+
# Set a list of replied messages IDs
|
189 |
+
if msg['messengerName'] == username: #message posted by the WarBot
|
190 |
+
messages_by_bot_IDs.append(msg['quotedID'].split(': ')[-1])
|
191 |
+
# remove empty and repeated elements
|
192 |
+
messages_by_bot_IDs = list(set([elem for elem in messages_by_bot_IDs if elem]))
|
193 |
+
|
194 |
+
# All messages (with quotes) sent _FOR_ the Bot:
|
195 |
+
messagesForBot = getMessages(thread_url=thread_url, quotedUser=username, startingPage=1)
|
196 |
+
|
197 |
+
# IDs of the messages, quoting the bot:
|
198 |
+
messages_for_bot_IDs = []
|
199 |
+
|
200 |
+
for msg in messagesForBot:
|
201 |
+
# Set a list of posted message IDs
|
202 |
+
messages_for_bot_IDs.append(msg['messageID'].split('-')[-1])
|
203 |
+
# remove empty elements
|
204 |
+
messages_for_bot_IDs = [elem for elem in messages_for_bot_IDs if elem]
|
205 |
+
|
206 |
+
# Filter to leave just the unanswered messages IDs:
|
207 |
+
messages_for_bot_IDs = [ID for ID in messages_for_bot_IDs if ID not in messages_by_bot_IDs]
|
208 |
+
|
209 |
+
# Reply the unanswered messages:
|
210 |
+
for msg in messagesForBot:
|
211 |
+
if msg['messageID'].split('-')[-1] in messages_for_bot_IDs:
|
212 |
+
|
213 |
+
quote = remove_non_english_russian_chars(msg['reply'])
|
214 |
+
message = ""
|
215 |
+
|
216 |
while not message:
|
217 |
+
message = WarClient.getReply(message=quote)
|
218 |
+
|
219 |
+
print('Quote: ', quote)
|
220 |
+
print('Reply: ', message)
|
221 |
+
|
222 |
+
login(username=username, password=password, thread_url=thread_url)
|
223 |
+
time.sleep(1)
|
224 |
+
post(message=message, thread_url=thread_url, post_url=post_url, quoted_by=msg['messengerName'], quote_text=quote, quote_source=msg['messageID'])
|
225 |
+
|
226 |
+
time.sleep(10) # Standby time for server load release
|
227 |
|
228 |
|
229 |
if __name__ == '__main__':
|
230 |
+
timeout = 5 # min
|
|
|
231 |
|
232 |
# Start the scheduler
|
233 |
while True:
|
|
|
|
|
234 |
WarOnlineBot()
|
|
|
235 |
|
236 |
+
timer = range(60 * timeout)
|
237 |
+
for t in timer:
|
238 |
+
time.sleep(1)
|
|