Upload 2 files

app.py

@@ -7,12 +7,11 @@ from streamlit_extras.add_vertical_space import add_vertical_space
 from PyPDF2 import PdfReader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain_community.vectorstores import FAISS
-from langchain_community.chat_models import ChatOpenAI
+from langchain.vectorstores import FAISS
+from langchain.chat_models import ChatOpenAI
 from langchain.chains.question_answering import load_qa_chain
 from selenium import webdriver
 from selenium.webdriver.common.by import By
-from selenium.common.exceptions import NoSuchElementException
 import warnings
 warnings.filterwarnings('ignore')
 
@@ -244,43 +243,37 @@ class linkedin_scraper:
         website_url = df['Website URL'].tolist()
         
         # Scrap the Job Description
-        job_description = []
+        job_description, description_count = [], 0
         for i in range(0, len(website_url)):
             try:
                 # Open the URL
                 driver.get(website_url[i])
-                driver.implicitly_wait(10)
-                time.sleep(1)
-            
-                # Click on Show More Button
-                driver.find_element(by=By.CSS_SELECTOR, value='button[data-tracking-control-name="public_jobs_show-more-html-btn"]').click()
-                driver.implicitly_wait(10)
+                driver.implicitly_wait(5)
                 time.sleep(1)
 
                 # Click on Show More Button
                 driver.find_element(by=By.CSS_SELECTOR, value='button[data-tracking-control-name="public_jobs_show-more-html-btn"]').click()
-                driver.implicitly_wait(10)
+                driver.implicitly_wait(5)
                 time.sleep(1)
 
                 # Get Job Description
                 description = driver.find_elements(by=By.CSS_SELECTOR, value='div[class="show-more-less-html__markup relative overflow-hidden"]')
-                driver.implicitly_wait(10)
                 data = [i.text for i in description][0]
 
                 if len(data.strip()) > 0:
                     job_description.append(data)
+                    description_count += 1
                 else:
                     job_description.append('Description Not Available')
-                
-                # Check Description Count Meets User Job Count
-                if len([i for i in job_description if i != 'Description Not Available']) >= job_count:
-                    break
             
             # If URL cannot Loading Properly 
             except:
                 job_description.append('Description Not Available')
+            
+            # Check Description Count Meets User Job Count
+            if description_count == job_count:
+                break
 
-        
         # Filter the Job Description
         df = df.iloc[:len(job_description), :]
 

requirements.txt

@@ -5,8 +5,7 @@ streamlit_option_menu
 streamlit_extras
 PyPDF2
 langchain
-langchain-community
 openai
 tiktoken
 faiss-cpu
-selenium >=4.0.0, < 5.0.0
+selenium