def main():
DB = os.path.join('data', 'jobs.db')
create_sqlite_db(DB)
indeed_jobs = jobs_search(query=POS.replace(' ', '+'),
location=LOC.replace(' ', '+'),
days_ago=2)
insert_jobs(DB, indeed_jobs)
glassdoor_jobs = get_jobs(keyword=POS, location=LOC)
insert_jobs(DB, glassdoor_jobs)
# -*- coding: utf-8 -*-
"""
Created on Thu Aug 27 16:43:44 2020
@author: Xkfal
"""
import glassdoor_scraper as gs
import pandas as pd
path = "C:/Users/Xkfal/Documents/ds_salary_proj/chromedriver"
df1 = gs.get_jobs('data scientist', 300, False, path, 30)
df2 = gs.get_jobs('data scientist', 300, False, path, 30)
df3 = gs.get_jobs('data scientist', 300, False, path, 30)
df = pd.concat([df1, df2, df3])
df.to_csv('C:/Users/Xkfal/Documents/ds_salary_proj/job_data.csv')
df = pd.read_csv('C:/Users/Xkfal/Documents/ds_salary_proj/job_data.csv')
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Jul 25 11:04:43 2020
@author: pengcancan
"""
import glassdoor_scraper as gs
import pandas as pd
path = "/Users/pengcancan/Workspace/ds/ds_salary_proj/chromedriver"
df = gs.get_jobs("data_scientist", 5, False, path, 5)
import glassdoor_scraper as gs
import pandas as pd
path = "/home/vishnub/chromedriver"
df = gs.get_jobs('Data Scientist', 1000, False, path, 15)
df.head()
df.to_csv('glassdoor_jobs.csv', index=False)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat May 30 18:06:23 2020
@author: ibrahimbashir
"""
import glassdoor_scraper as gs
import pandas as pd
path = "/Users/ibrahimbashir/Documents/ds_salary_proj/chromedriver"
#df = gs.get_jobs(keyword, num_jobs, verbose, path, slp_time)
df = gs.get_jobs('data scientist', 80, False, path, 60)
df.to_csv('glassdoor_data.csv')
# -*- coding: utf-8 -*-
"""
Created on Thu Apr 8 17:13:35 2021
@author: Ahmad Abd Elhameed
"""
import glassdoor_scraper as gs
import pandas as pd
import sys
path = webdriver.Chrome("C:/Users/Ahmad Abd Elhameed/ds_salary_project/chromedriver.exe")
df = gs.get_jobs("Data Scientist",15,False,path,15)
import glassdoor_scraper as gs import pandas as pd keyword = 'data-scientist' num_jobs = 1000 verbose = False chromedriver = 'chromedriver.exe' output_file_name = 'glassdoor_data.csv' df = gs.get_jobs(keyword, num_jobs, verbose, chromedriver) df.to_csv(output_file_name, index=False)
# -*- coding: utf-8 -*-
"""
Created on Sun Jul 19 03:11:39 2020
@author: cumea
"""
#import scraper module
import glassdoor_scraper as gs
#define path on local machine
path = "C:/Users/cumea/Desktop/Projects/Glassdoor Salary Prediction/Glassdoor_Salary_Prediction/chromedriver"
#run scraper and store data into dataframe 'df
df = gs.get_jobs('Business Analyst', 500, False, path, 15)
#export data to .csv file
df.to_csv('glassdoor_jobs.csv', index=False)
# -*- coding: utf-8 -*-
"""
Created on Tue Jun 30 16:21:47 2020
@author: Ankit Chaudhari
"""
import glassdoor_scraper as gs
import pandas as pd
path = "E:/Data Science Projects/ds_salary_prediction/chromedriver"
jobs = gs.get_jobs("Data Scientist", 2000, False, path, 10)
jobs.to_csv('glassdoor_ds_jobs.csv', index = False)
# -*- coding: utf-8 -*-
"""
Created on Wed May 27 17:31:06 2020
@author: akinmade
"""
import glassdoor_scraper as gs
import pandas as pd
path = "C:/Users/Kinshade/Documents/ds_salary_proj/chromedriver"
df = gs.get_jobs('data science', 1010, False, path, 10)
df.to_csv('glassdoor_jobs.csv', index=False)
# -*- coding: utf-8 -*-
"""
Created on Sun May 16 13:55:32 2021
@author: Sumi
"""
import glassdoor_scraper as gs
import pandas as pd
path = "C:/Users/Sumi/Desktop/salary_proj/chromedriver"
df = gs.get_jobs('Data Science', 15, False, path, 5)
import glassdoor_scraper as gs
import pandas as pd
path = "/Users/imbuhira/ds_projects/chromedriver"
df = gs.get_jobs('software developer', 1000, False, path, 10)
df.to_csv('glassdoor_jobs.csv', index=False)
# -*- coding: utf-8 -*-
"""
Created on Fri Dec 11 17:49:19 2020
@author: koadu
"""
import glassdoor_scraper as gs
import pandas as pd
path = 'C:/Users/koadu/Documents/salary_proj/chromedriver.exe'
# df = gs.get_jobs('data scientist', 10, False, path, 0)
df = gs.get_jobs(1000, False, path, 10)
df.to_csv('glassdoor_jobs.csv', index=False)
import glassdoor_scraper as gs
import pandas as pd
path = r"C:/Users/praya/Documents/da_salary_proj/chromedriver.exe"
df = gs.get_jobs('data analyst', 1000, False, path, 15)
df.to_csv('glassdoor_jobs.csv', index=False)
# -*- coding: utf-8 -*-
"""
Created on Thu Apr 2 11:47:44 2020
@author: Ken
"""
import glassdoor_scraper as gs
import pandas as pd
#path = "C:/Users/Ken/Documents/ds_salary_proj/chromedriver"
path = "F:/ds_salary_project/chromedriver"
jobs = gs.get_jobs('data engineer', 100, False, path, 15)
df = pd.DataFrame(
jobs) #This line converts the dictionary object into a pandas DataFrame.
df.to_csv('glassdoor_jobs5.csv', index=False)
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Mon Jun 29 20:32:36 2020
@author: kershtheva
"""
import glassdoor_scraper as gs
import pandas as pd
path = "/Users/kershtheva/Desktop/Data Science Projects/chromedriver"
#glassdoorDB = gs.get_jobs('Molecular Biology', 400, False, path, 5)
#glassdoorDBnext400 = gs.get_jobs('Molecular Biology', 400, False, path, 5)
glassdoorDBlast400 = gs.get_jobs('Molecular Biology', 400, False, path, 5)
frames = [glassdoorDB, glassdoorDBnext400, glassdoorDBlast400]
result = pd.concat(frames)
from pandas import DataFrame
import glassdoor_scraper as gs
import pandas as pd
path = "C:/Users/44785/Documents/GitHub/ds_salary_proj/chromedriver"
df: DataFrame = gs.get_jobs('data scientist', 1000, False, path, 15)
df.to_csv('glassdoor_jobs.csv', index=False)
df
# -*- coding: utf-8 -*-
"""
Created on Sun Dec 6 02:02:33 2020
@author: pawangoon
"""
import glassdoor_scraper as gs
import pandas as pd
df = gs.get_jobs('data scientist', 500, False)
df.to_csv('glassdoor_jobs.csv', index=False)
# -*- coding: utf-8 -*-
"""
Created on Fri Jun 12 23:41:43 2020
@author: siddh
"""
import glassdoor_scraper as gs
import pandas as pd
path='C:/Users/siddh/ML/Project/chromedriver'
df= gs.get_jobs('data scientist', 0,False, path)
'''We obtain 1000 entries from glassdoor with jobs in different companies as datascientist'''
df.to_csv('glassdoor_jobs.csv')
# -*- coding: utf-8 -*-
"""
Created on Tue Jun 16 12:53:41 2020
@author: Cédric
"""
import glassdoor_scraper as gs
import pandas as pd
path = "D:/programmation/Data_Science/ds_skills_proj/chromedriver"
df = gs.get_jobs('data_scientist', 1000, False, path, 20)
df.to_csv('glassdoor_jobs.csv', index=False)
# %%
import glassdoor_scraper as gs
import pandas as pd
path = "C:/Users/<UserName>/Documents/GitHub/ds-salary-proj/drivers/geckodriver"
df = gs.get_jobs("data scientist", 25, False, path, 15)
# df
#%%
df.to_csv("glassdoor_jobs.csv", index=False)
# %%
df.columns
# %%
# -*- coding: utf-8 -*-
"""
Created on Sun Apr 26 22:28:18 2020
@author: Nik
"""
import glassdoor_scraper as gs
import pandas as pd
path = "C:/Users/nswor/OneDrive/Documents/ds_salary_proj/chromedriver"
df = gs.get_jobs('data scientist', 15, 'False', path, 15)
df
import glassdoor_scraper as gs
import pandas as pd
path = "/usr/local/share/chromedriver"
df = gs.get_jobs('India', 'data scientist', 50, False, path, 15)
df.to_csv('glassdoor_jobs.csv', index=False)
# -*- coding: utf-8 -*-
"""
Created on Tue Dec 22 17:30:36 2020
@author: Ritwick Joshi
"""
import glassdoor_scraper as gs
import pandas as pd
path = "C:/Users/DESKTOP/Desktop/Compiler/Pythonfiles/chromedriver_win32/chromedriver.exe"
profile = "data scientist"
num_jobs = 500
verbose_program = False
internet_connection_time = 20
df = gs.get_jobs(profile, num_jobs, verbose_program, path,
internet_connection_time)
df.to_csv('data_scientist_jobs_glassdoor_500.csv', index=False)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Jun 10 23:09:01 2020
@author: ryzary
"""
import glassdoor_scraper as gs
import pandas as pd
path = '/Users/ryzary/Desktop/projects/glassdoor/chromedriver'
df = gs.get_jobs('Software Engineer', 1000, False, path, 2)
df.to_csv('software_engineer.csv', index=False)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Apr 18 22:50:50 2020
@author: mcruzmbp2019
"""
import glassdoor_scraper as gs
import pandas as pd
path = "/Users/mcruzmbp2019/Documents/ds_salary_proj/chromedriver"
df = gs.get_jobs('data analyst', 5, False, path, 10)
df.to_csv('glassdoor_jobs.csv', index=False)
# -*- coding: utf-8 -*-
"""
Created on Wed Apr 7 11:48:21 2021
@author: im_chatterjee
"""
import glassdoor_scraper as gs
import pandas as pd
path = "C:/Users/hp/Desktop/Data analytics/Data Science Project/chromedriver"
df = gs.get_jobs('data scientist', 1000, False, path, 15)
'''
Data collector which scrapes data from Glassdoor using the glassdoor_scraper and stores it in a DataFrame for analysis
'''
import glassdoor_scraper as gs
import pandas as pd
path = "/Users/AkarshNagaraj/Desktop/Projects/Data_Scientist_Salaries/chromedriver"
df = gs.get_jobs('data', 1000, False, path, 15)
df.to_csv('glassdoor_jobs.csv', index=False)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Apr 21 11:40:49 2021
@author: gm
"""
import glassdoor_scraper as gs
import pandas as pd
path = "/Users/gm/documents/ds_salary_proj2/chromedriver"
df = gs.get_jobs('data scientist', 7, False, path, 10)
# -*- coding: utf-8 -*-
"""
Created on Sun Dec 6 02:02:33 2020
@author: pawangoon
"""
import glassdoor_scraper as gs
import pandas as pd
df = gs.get_jobs('data scientist', 15, False)
df