Web Scrapping

Author: larymak

WebScraping/README.md

@@ -0,0 +1 @@
+# WebScraping-Local-Website

WebScraping/posts/0.txt

@@ -0,0 +1,8 @@
+Company Name: Python Developer Trainees at Smart Data Analytical 
+Required Skills: About You
+Must Have:
+Good understanding of Python Demonstration of a python project will be required during the interview
+SQL, MySQL, Postgresql
+Web Experience UI and API development
+Un 
+More Info: /job/python-developer-trainees-smart-data-analytical 

WebScraping/posts/1.txt

@@ -0,0 +1,4 @@
+Company Name: Senior Python / Django Back - end Engineer at R4Kenya 
+Required Skills: The Position
+Our client is a fast growing, technology venture based in Nairobi, Kenya seeking to hire� �hands-on Senior Python/Django Back-end Engineer to join our Product team based in N 
+More Info: /job/senior-python-django-back-end-engineer-r4kenya 

WebScraping/posts/Capture.PNG

@@ -0,0 +1,28 @@
+from bs4 import BeautifulSoup
+import requests
+import time
+
+print('Please Enter Skills You are not familiar with')
+unfamiliar_skill = input(' > ')
+print(f'Filtering Out {unfamiliar_skill}')
+
+def find_jobs():
+     html_text = requests.get(' https://www.myjobmag.co.ke/search/jobs?q=python ').text
+     soup = BeautifulSoup( html_text, 'lxml' )
+     jobs = soup.find_all('li', class_ = 'job-list-li')
+     for index, job in enumerate(jobs):
+          published_date = job.find('li', class_ = 'job-item')
+          company_name = job.find('h2').text.replace('  ', '  ')
+          skills = job.find('li', class_ = 'job-desc').text.replace('  ', '  ')
+          more_info = job.h2.a['href']
+          if unfamiliar_skill not in skills:
+               with open(f'posts/{index}.txt', 'w') as f:
+                    f.write(f"Company Name: {company_name.strip()} \n")
+                    f.write(f"Required Skills: {skills.strip()} \n")
+                    f.write(f"More Info: {more_info} \n")
+               print('File Save Succesfully: {index}')
+
+if __name__ == "__main__":
+     while True:
+          find_jobs()
+          time.sleep(600)