-
Notifications
You must be signed in to change notification settings - Fork 0
/
indeedApi.py
130 lines (108 loc) · 4.56 KB
/
indeedApi.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
from indeed import IndeedClient
import pandas as pd
import textSim
class indeed:
#jobDataFrame
def __init__(self):
# self.jobDataFrame= pd.DataFrame();
self.client = IndeedClient(8836246992678581);
def skill(self,l,city,jobtype):
#print l
#print " AND ".join(l)
print (jobtype)
if jobtype in ['intern','internship','Internship']:
jobtype = 'internship'
else:
jobtype = 'fulltime'
params = {
'q' : " AND ".join(l),
'l' : city,
'jt' : jobtype,
'userip' : "1.2.3.4",
'useragent' : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2)",
'limit' : "25",
'start' : 0,
'highlight' : 1
}
i = 25
search_response = self.client.search(**params)
results = []
if (len(search_response['results']) <= 0):
return results
while(i<100 and i<search_response['totalResults']):
results += search_response['results']
params['start'] += 25
search_response = self.client.search(**params)
results += search_response['results']
i+=25
print (params['start'])
self.jobDataFrame = pd.DataFrame(results).drop_duplicates('jobkey')
self.jobDataFrame.to_csv("sample.csv",encoding='UTF-8')
return results
def skillOR(self,l,city,jobtype):
#print l
#print " AND ".join(l)
print (jobtype)
if jobtype in ['intern','internship','Internship']:
jobtype = 'internship'
else:
jobtype = 'fulltime'
params = {
'q' : " OR ".join(l),
'l' : city,
'jt' : jobtype,
'userip' : "1.2.3.4",
'useragent' : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2)",
'limit' : "50"
}
i = 25
search_response = self.client.search(**params)
results = []
if (len(search_response['results']) <= 0):
return results
while(i<100 and i<search_response['totalResults']):
results += search_response['results']
params['start'] += 25
search_response = self.client.search(**params)
results += search_response['results']
i+=25
print (params['start'])
self.jobDataFrame = pd.DataFrame(results).drop_duplicates('jobkey')
self.jobDataFrame.to_csv("sample.csv",encoding='UTF-8')
return results
def similarJobs(self,job):
print ("the job is" + job)
sampledfo = pd.read_csv("sample.csv",encoding='UTF-8')
sampledf = sampledfo.copy()
del sampledf['stations']
del sampledf['Unnamed: 0']
del sampledf['source']
del sampledf['onmousedown']
del sampledf['formattedLocation']
del sampledf['formattedLocationFull']
del sampledf['url']
del sampledf['date']
del sampledf['formattedRelativeTime']
sampledf['indeedApply'] = [0 if x == 'false' else 1 for x in sampledf['indeedApply']]
sampledf['expired'] = [0 if x == 'false' else 1 for x in sampledf['expired']]
sampledf['sponsored'] = [0 if x == 'false' else 1 for x in sampledf['sponsored']]
jobNo = job
self.dataJob = sampledf.loc[sampledf['jobkey'] == jobNo]
df= sampledf[sampledf["jobkey"] != jobNo]
# df[''] = ['red' if x == 'Z' else 'green' for x in df['Set']]
df.ix[df.city == self.dataJob.city.iloc[0], ['city','country','state']] = 1
df.ix[df.city != 1, ['city','country','state']] = 0
df.ix[df.company == self.dataJob.company.iloc[0], ['company']] = 1
df.ix[df.company != 1, ['company']] = 0
# df[''] = df.apply(my_test2, axis=1)
df['snippet'] = [textSim.cosine_sim(x,self.dataJob.snippet.iloc[0]) for x in df['snippet']]
df['jobtitle'] = [textSim.cosine_sim(x,self.dataJob.jobtitle.iloc[0]) for x in df['jobtitle']]
df['variance'] = df['city'] + df['company'] + df['country'] + df['expired'] + df['indeedApply']+ 10*df['snippet']+5*df['jobtitle']
result = df.sort(['variance'], ascending=False)
#import pdb; pdb.set_trace()
simList = result['jobkey'][:10].tolist()
simDict = []
for x in simList:
s = sampledfo.loc[sampledfo['jobkey'] == x]
simDict.append(s.to_dict(orient = 'records')[0])
return simDict