monspo1/proj3_webscrape1.py

## proj3_webscrape1.py
# load the library
from bs4 import BeautifulSoup as Soup
import urllib, requests, re, pandas as pd

# indeed.com url
base_url = 'http://www.indeed.com/jobs?q=data+scientist&jt=fulltime&sort='
sort_by = 'date'          # sort by data
start_from = '&start='    # start page number

pd.set_option('max_colwidth',500)    # to remove column limit (Otherwise, we'll lose some info)
df = pd.DataFrame()   # create a new data frame
	# load the library
	from bs4 import BeautifulSoup as Soup
	import urllib, requests, re, pandas as pd

	# indeed.com url
	base_url = 'http://www.indeed.com/jobs?q=data+scientist&jt=fulltime&sort='
	sort_by = 'date' # sort by data
	start_from = '&start=' # start page number

	pd.set_option('max_colwidth',500) # to remove column limit (Otherwise, we'll lose some info)
	df = pd.DataFrame() # create a new data frame