roomInfo

main.py

@@ -1,4 +1,5 @@
 import sys
+import threading
 from urllib.parse import urlparse
 
 from scripts import watcher, webdriver
@@ -9,7 +10,9 @@ if __name__ == '__main__':
         print('Invalid url provided, please check...')
         sys.exit(1)
 
-    webdriver.go(sys.argv[1])
+    t = threading.Thread(target=webdriver.go, args=(sys.argv[1],))
+    t.start()
 
     w = watcher.Watcher(directory=config()['watchdog']['dir'])
     w.run()
+    

messages/utils.py

@@ -1,3 +1,4 @@
+import os
 from protobuf import message_pb2
 
 from messages.member import MemberMessage
@@ -29,6 +30,8 @@ def unpackMsgBin(filepath):
             decodeMsg(response.messages)
     except Exception as e:
         pass
+    finally:
+        os.remove(filepath)
 
 def decodeMsg(messages):
     for message in messages:

scripts/watcher.py

@@ -39,5 +39,6 @@ class Handler(FileSystemEventHandler):
             return None
 
         elif event.event_type == 'created':
+            print('here')
             q.put(event.src_path)
 

scripts/webdriver.py

@@ -1,15 +1,21 @@
+import requests
+import json
+
 from selenium import webdriver
 from selenium.webdriver.chrome.options import Options
 from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
 from selenium.webdriver.common.proxy import Proxy, ProxyType
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support.expected_conditions import presence_of_element_located
 
 from config.helper import config
+from store.mongo import MongoStore
 
 def go(url):
     chrome_options = Options()
     chrome_options.add_argument('--proxy-server=%s' % config()['webdriver']['proxy'])
     # chrome_options.add_argument('--headless')
-    chrome_options.add_experimental_option('detach', True)
 
     proxy = Proxy()
     proxy.proxy_type = ProxyType.MANUAL
@@ -19,6 +25,33 @@ def go(url):
     capabilities = DesiredCapabilities.CHROME
     proxy.add_to_capabilities(capabilities)
 
-    driver = webdriver.Chrome(options=chrome_options, desired_capabilities=capabilities, executable_path=config()['webdriver']['bin'])
+    with webdriver.Chrome(options=chrome_options,
+                            desired_capabilities=capabilities,
+                            executable_path=config()['webdriver']['bin']
+                            ) as driver:
+        wait = WebDriverWait(driver, 10)
+
+        driver.implicitly_wait(24 * 60 * 60)
+
+        driver.get(url)
+
+        first_result = wait.until(presence_of_element_located((By.ID, "RENDER_DATA")))
+        json_str = requests.utils.unquote(first_result.get_attribute("textContent"))
+        json_obj = json.loads(json_str)
+
+        roomInfo = json_obj['initialState']['roomStore']['roomInfo']
+
+        store = MongoStore()
+        store.set_collection('room')
+        store.insert_one({
+            'roomId': roomInfo['roomId'],
+            'web_rid': roomInfo['web_rid'],
+            'title': roomInfo['room']['title'],
+            'user_count_str': roomInfo['room']['user_count_str'],
+            'cover': roomInfo['room']['cover']['url_list'][0],
+            'admin_user_ids': roomInfo['room']['admin_user_ids'],
+            'owner': roomInfo['room']['owner']
+        })
+
+        wait.until(presence_of_element_located((By.CLASS_NAME, "oSu9Aw19")))
         
-    driver.get(url)