Delete WarOnline_Chat_test.py
Browse files- WarOnline_Chat_test.py +0 -254
WarOnline_Chat_test.py
DELETED
@@ -1,254 +0,0 @@
|
|
1 |
-
# This is an quote and post library for a specific thread in the WarOnline forum.
|
2 |
-
|
3 |
-
import WarClient
|
4 |
-
import requests
|
5 |
-
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
|
15 |
-
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'
|
25 |
-
|
26 |
-
# Start a session to persist the login cookie across requests
|
27 |
-
session = requests.Session()
|
28 |
-
|
29 |
-
def compare_pages(url1, url2):
|
30 |
-
#Compares 2 pages and returns True if they are the same
|
31 |
-
return urllib.urlopen(url1).geturl() == urllib.urlopen(url2).geturl()
|
32 |
-
|
33 |
-
def remove_non_english_russian_chars(s):
|
34 |
-
# Regular expression to match all characters that are not in English or Russian
|
35 |
-
pattern = '[^0-9A-Za-zА-Яа-яЁё(),.:!;"\s-]'
|
36 |
-
# Replace all matched characters with an empty string
|
37 |
-
return re.sub(pattern, '', s)
|
38 |
-
def login(username=username, password=password, thread_url=thread_url):
|
39 |
-
# Log-In to the forum and redirect to thread
|
40 |
-
|
41 |
-
# Retrieve the login page HTML to get the CSRF token
|
42 |
-
login_page_response = session.get(login_url)
|
43 |
-
soup = BeautifulSoup(login_page_response.text, 'html.parser')
|
44 |
-
csrf_token = soup.find('input', {'name': '_xfToken'})['value']
|
45 |
-
|
46 |
-
# Login to the website
|
47 |
-
login_data = {
|
48 |
-
'login': username,
|
49 |
-
'password': password,
|
50 |
-
'remember': '1',
|
51 |
-
'_xfRedirect': thread_url,
|
52 |
-
'_xfToken': csrf_token
|
53 |
-
}
|
54 |
-
response = session.post(login_url, data=login_data)
|
55 |
-
|
56 |
-
# Check if the login was successful
|
57 |
-
if 'Invalid login' in response.text:
|
58 |
-
print('Login failed!')
|
59 |
-
exit()
|
60 |
-
|
61 |
-
def post(message=message, thread_url=thread_url, post_url=post_url, quoted_by="",quote_text="",quote_source=""):
|
62 |
-
#Post a message to the forum (with or without the quote
|
63 |
-
#quote_source is in format 'post-3920992'
|
64 |
-
quote_source = quote_source.split('-')[-1] # Take the numbers only
|
65 |
-
|
66 |
-
if quoted_by:
|
67 |
-
message = f'[QUOTE="{quoted_by}, post: {quote_source}"]{quote_text}[/QUOTE]{message}'
|
68 |
-
#message = f'[QUOTE="{quoted_by}, data-source=post: {quote_source}"]{quote_text}[/QUOTE]{message}'
|
69 |
-
# optionally add @{quoted_by} to indent the quoter
|
70 |
-
|
71 |
-
# Retrieve the thread page HTML
|
72 |
-
response = session.get(thread_url)
|
73 |
-
|
74 |
-
# Parse the HTML with BeautifulSoup
|
75 |
-
soup = BeautifulSoup(response.text, 'html.parser')
|
76 |
-
|
77 |
-
# Extract the _xfToken value from the hidden form field
|
78 |
-
xf_token = soup.find('input', {'name': '_xfToken'}).get('value')
|
79 |
-
|
80 |
-
# Construct the message data for the POST request
|
81 |
-
message_data = {
|
82 |
-
'_xfToken': xf_token,
|
83 |
-
'message': message,
|
84 |
-
'attachment_hash': '',
|
85 |
-
'last_date': '',
|
86 |
-
'_xfRequestUri': post_url,
|
87 |
-
'_xfWithData': '1',
|
88 |
-
'_xfResponseType': 'json'
|
89 |
-
}
|
90 |
-
|
91 |
-
response = session.post(post_url, data=message_data)
|
92 |
-
|
93 |
-
# Check if the post was successful
|
94 |
-
if not response.ok:
|
95 |
-
print('Post failed!')
|
96 |
-
exit()
|
97 |
-
|
98 |
-
print('Post submitted successfully.')
|
99 |
-
|
100 |
-
def getMessages(thread_url=thread_url, quotedUser="", startingPage=1):
|
101 |
-
# Returns all the quotes for #username in the specific multi-page thread url
|
102 |
-
allquotes =[]
|
103 |
-
|
104 |
-
page = startingPage # Counter
|
105 |
-
lastPage = False
|
106 |
-
|
107 |
-
# Initial values for messangerName and the message ID
|
108 |
-
messengerName = ""
|
109 |
-
messageID = ""
|
110 |
-
quotedID = ""
|
111 |
-
|
112 |
-
# Patterns to search in the last quote.
|
113 |
-
namePattern = re.compile('data-lb-caption-desc="(.*?) ·')
|
114 |
-
messageIDPattern = re.compile('data-lb-id="(.*?)"')
|
115 |
-
quotedIDPattern = re.compile('data-source="(.*?)"')
|
116 |
-
quotedNamePattern = re.compile('data-quote="(.*?)"')
|
117 |
-
|
118 |
-
while not lastPage:
|
119 |
-
response = requests.get(thread_url + 'page-' + str(page))
|
120 |
-
if response.status_code == 200:
|
121 |
-
|
122 |
-
# Core of the function
|
123 |
-
html_content = response.content
|
124 |
-
|
125 |
-
# Parse the HTML content using BeautifulSoup
|
126 |
-
soup = BeautifulSoup(html_content, 'html.parser')
|
127 |
-
|
128 |
-
# Find all the message in the thread page
|
129 |
-
messageData = soup.find_all('div', {'class': 'message-userContent lbContainer js-lbContainer'})
|
130 |
-
|
131 |
-
for data in messageData:
|
132 |
-
try:
|
133 |
-
# Get the messager username
|
134 |
-
matchName = namePattern.search(str(data))
|
135 |
-
if matchName:
|
136 |
-
messengerName = matchName.group(1)
|
137 |
-
|
138 |
-
# Get the quoted ID
|
139 |
-
matchID = quotedIDPattern.search(str(data))
|
140 |
-
if matchID:
|
141 |
-
quotedID = matchID.group(1)
|
142 |
-
|
143 |
-
# Get the message ID
|
144 |
-
matchID = messageIDPattern.search(str(data))
|
145 |
-
if matchID:
|
146 |
-
messageID = matchID.group(1)
|
147 |
-
|
148 |
-
matchQuotedName = quotedNamePattern.search(str(data))
|
149 |
-
if matchQuotedName:
|
150 |
-
quotedName = matchQuotedName.group(1)
|
151 |
-
if quotedUser and (quotedUser != quotedName):
|
152 |
-
continue
|
153 |
-
|
154 |
-
# Make sure that the messages have a quote inside
|
155 |
-
blockquote = data.find('blockquote')
|
156 |
-
if blockquote:
|
157 |
-
# Extract the text
|
158 |
-
text = data.find('div', {'class': 'bbWrapper'})
|
159 |
-
for bq in text.find_all('blockquote'):
|
160 |
-
bq.extract()
|
161 |
-
reply = text.get_text().replace('\n', ' ').strip()
|
162 |
-
|
163 |
-
allquotes.append({'reply': reply, 'messengerName': messengerName, 'messageID': messageID, 'quotedID': quotedID})
|
164 |
-
|
165 |
-
except:
|
166 |
-
continue # There was no text in quote, move next
|
167 |
-
|
168 |
-
#check if that is not a last page
|
169 |
-
if not compare_pages(thread_url + 'page-' + str(page), thread_url + 'page-' + str(page + 1)):
|
170 |
-
page += 1
|
171 |
-
else:
|
172 |
-
lastPage = True
|
173 |
-
else:
|
174 |
-
lastPage = True
|
175 |
-
|
176 |
-
return allquotes
|
177 |
-
|
178 |
-
# Core Engine of the Client
|
179 |
-
def WarOnlineBot():
|
180 |
-
|
181 |
-
login(username=username, password=password, thread_url=thread_url)
|
182 |
-
#print("logged in")
|
183 |
-
|
184 |
-
# All messages (with quotes) by ALL users:
|
185 |
-
allMessages = getMessages(thread_url=thread_url, quotedUser='', startingPage=1)
|
186 |
-
|
187 |
-
# IDs of the quoted messages, for messages posted by bot:
|
188 |
-
messages_by_bot_IDs = []
|
189 |
-
|
190 |
-
for msg in allMessages:
|
191 |
-
# Set a list of replied IDs
|
192 |
-
if msg['messengerName'] == username:
|
193 |
-
messages_by_bot_IDs.append(msg['quotedID'].split(': ')[-1])
|
194 |
-
# remove empty elements
|
195 |
-
messages_by_bot_IDs = [elem for elem in messages_by_bot_IDs if elem]
|
196 |
-
|
197 |
-
# All messages (with quotes) sent _FOR_ the Bot:
|
198 |
-
messagesForBot = getMessages(thread_url=thread_url, quotedUser=username, startingPage=1)
|
199 |
-
|
200 |
-
# IDs of the messages, quoting the bot:
|
201 |
-
messages_for_bot_IDs = []
|
202 |
-
|
203 |
-
for msg in messagesForBot:
|
204 |
-
# Set a list of posted message IDs
|
205 |
-
messages_for_bot_IDs.append(msg['messageID'].split('-')[-1])
|
206 |
-
# remove empty elements
|
207 |
-
messages_for_bot_IDs = [elem for elem in messages_for_bot_IDs if elem]
|
208 |
-
|
209 |
-
# Filter the unanswered messages
|
210 |
-
for msgID in messages_for_bot_IDs:
|
211 |
-
if msgID in messages_by_bot_IDs:
|
212 |
-
messages_for_bot_IDs.remove(msgID)
|
213 |
-
|
214 |
-
# print unanswered messages
|
215 |
-
for msg in messagesForBot:
|
216 |
-
if msg['messageID'].split('-')[-1] in messages_for_bot_IDs:
|
217 |
-
|
218 |
-
quote = remove_non_english_russian_chars(msg['reply'])
|
219 |
-
message = ""
|
220 |
-
|
221 |
-
while not message:
|
222 |
-
message = WarClient.getReply(message=quote)
|
223 |
-
|
224 |
-
print('Quote: ', quote)
|
225 |
-
print('Reply: ', message)
|
226 |
-
|
227 |
-
login(username=username, password=password, thread_url=thread_url)
|
228 |
-
time.sleep(1)
|
229 |
-
post(message=message, thread_url=thread_url, post_url=post_url, quoted_by=msg['messengerName'], quote_text=quote, quote_source=msg['messageID'])
|
230 |
-
|
231 |
-
time.sleep(5) # Standby time for server load release
|
232 |
-
|
233 |
-
if __name__ == '__main__':
|
234 |
-
timeout = 2 # min
|
235 |
-
|
236 |
-
WarOnlineBot()
|
237 |
-
|
238 |
-
#login(username=username, password=password, thread_url=thread_url)
|
239 |
-
#post(message=message, thread_url=thread_url, post_url=post_url, quoted_by='WarBot', quote_text='quoted message', quote_source='12345')
|
240 |
-
|
241 |
-
|
242 |
-
"""
|
243 |
-
# Start the scheduler
|
244 |
-
while True:
|
245 |
-
login(username=username, password=password, thread_url=thread_url)
|
246 |
-
print("logged in")
|
247 |
-
WarOnlineBot()
|
248 |
-
p_bar = tqdm(range(60 * timeout))
|
249 |
-
|
250 |
-
for i in p_bar:
|
251 |
-
p_bar.update(1)
|
252 |
-
p_bar.refresh()
|
253 |
-
time.sleep(1)
|
254 |
-
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|