def getPostings(jobQuery, nURLs=1, start=0):
"""
return: jobkeys | list[string] | list of job postings unique ID
allterms | list[list[string]] | list of list of words from job postings
params:
jobQuery: string | default empty string (generic job search)
nJobs: int | number of job postings to search (default=499 (500 max allowed))
start: int | index to begin api url search
"""
# retrieve list of URL's for jobQuery
urls = indeed.getJobURLs(jobQuery, nURLs=nURLs, start=start)
# initialize lists for all terms and jobkeys
allwords, jobkeys = [], []
# loop over urls
for url in urls:
# retrieve information from URL's job posting
jobkey, position, company, location, words = indeed.parseJobPosting(
url)
# append current job posting info to allwords and jobkeys
jobkeys.append(jobkey)
allwords.append(words)
# only care about the jobkey and terms list for skillrank database
return jobkeys, allwords
def getPostings(jobQuery, nURLs=1, start=0):
"""
return: jobkeys | list[string] | list of job postings unique ID
allterms | list[list[string]] | list of list of words from job postings
params:
jobQuery: string | default empty string (generic job search)
nJobs: int | number of job postings to search (default=499 (500 max allowed))
start: int | index to begin api url search
"""
# retrieve list of URL's for jobQuery
urls = indeed.getJobURLs(jobQuery, nURLs=nURLs, start=start)
# initialize lists for all terms and jobkeys
allwords, jobkeys = [], []
# loop over urls
for url in urls:
# retrieve information from URL's job posting
jobkey, position, company, location, words = indeed.parseJobPosting(url)
# append current job posting info to allwords and jobkeys
jobkeys.append(jobkey)
allwords.append(words)
# only care about the jobkey and terms list for skillrank database
return jobkeys, allwords
def getResults(jobQuery, nJobs, start=0):
"""
return: list[tuple(term,relevance,count)] | "results"
params:
jobQuery: string | job query from user form
nJobs: int | number of jobs to consider
start: int | index to start indeed.com api search
"""
# connect to the skillrank database and create cursor
con = mdb.connect(host='localhost', user='******', db='skillrank')
cur = con.cursor()
# initialize list for all terms for jobQuery
terms = []
# retrieve URL's for jobQuery
urls = indeed.getJobURLs(jobQuery, nURLs=nJobs, start=start)
# if no URL's matched for jobQuery
if not urls: return [], [], ''
# get indeed job postings using threads for boosted efficieny
documents = indeed.threadResults(urls, nThreads=8)
# words lists are the 5th/last item in each
# tuple returned from threaded documents
for d in documents:
terms += d[-1]
# retrieve ranked results
results, biResults = analyze(cur, jobQuery, terms, x=0.6, nReturn=100, threshold=1)
# create the results string
resultsString = 'Based on '+str(len(terms))+' words scraped from '
resultsString += str(len(urls))+' job postings for "'+jobQuery+'"'
# close the database cursor and connection
if cur: cur.close()
if con: con.close()
return results, biResults, resultsString
