Indeed-job-data-mining-classification

This project was made to mine all the jobs on the website Indeed.com, related to software engineering, data engineering, data scientist:
1 - Collect at least 5,000 Job Ads for Data Scientists from Indeed.com. 2 - Collect at least 5,000 Job Ads for Software Engineers from Indeed.com. 3 - Collect at least 5,000 Job Ads for Data Engineers from Indeed.com. 4 - Get the html for each Ad. 5 - Extract the text from the html and create a csv with 1 Ad per line and 2 columns: , 6- Train a classification model that can predict whether a given Ad is for a Data Scientist, Software Engineer or Data Engineer.
Notes: For Steps 1,2,3 we had to focus on Ads from specific cities. As many cities as you need to get to 5000 for all 3 types. Each team will work on a different set of cities, so please send me your preferences as soon as possible. Your trained model will be evaluated on a separate test set that you will not have access to before the deadline. The deliverables include: The scraping script(s) The classification script(s) Instructions on how to run the 2 scripts A zip with the raw html of each Ad The csv from step 5