Skip to content

Instantly share code, notes, and snippets.

@serenamm
Created December 22, 2017 16:10
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save serenamm/fe6902610a629147a0aceeec341f1ddb to your computer and use it in GitHub Desktop.
Save serenamm/fe6902610a629147a0aceeec341f1ddb to your computer and use it in GitHub Desktop.
def scrapeGlassdoor():
import helper
# Load existing dictionary
# Initialize if empty
try:
job_dict = load_obj("C:/Users/Serena/Desktop/Projects/Glassdoor/job_dict")
desc_dict = load_obj("C:/Users/Serena/Desktop/Projects/Glassdoor/desc_dict")
except:
job_dict = {}
desc_dict = {}
# Initialize website, city, jobs
job_lst = ["Data Analyst", "Data Scientist"]
city_lst = ["Toronto", "Vancouver"]
# Search for jobs
for job_name in job_lst:
for city in city_lst:
try:
update_jdict, update_ddict = search_jobs(job_name, city, job_dict, desc_dict, num_pages = 1)
job_dict.update(update_jdict)
desc_dict.update(update_ddict)
except Exception as e:
print(e)
save_obj(job_dict, "job_dict")
save_obj(desc_dict, "desc_dict")
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment