Indeed-Job-Search-Bot/test3.py at master · Python-Open-Source/Indeed-Job-Search-Bot · GitHub

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
129
130
131
132
133
134
135
136
137
138

__Author__ = "Soumil Nitin Shah"
__Version__ = '1.1.1'
__Email__ = "soushah@my.bridgeport.edu"


try:
    import requests
    import bs4
    from bs4 import BeautifulSoup
    import pandas as pd

except Exception as e:
    print("Some Modules are Missing {}".format(e))


class WebCrawler(object):

    def __init__(self, title = '',location = ""):

        self._url = "https://www.indeed.com/jobs"
        self._headers = {'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36"}
        self._title = title
        self._location = location
        self.params = {
            'q': 'Python',
            'l': 'Bridgeport, CT'}

    def get(self):

        try:

            r = requests.get(url=self._url,
                              headers=self._headers ,
                              params=self.params)
            return r.text

        except Exception as e:

            print("Failed to make response to Indeed")


class DataStructure():

    def __init__(self):
        self.data = {
            'title':[],
            'location':[],
            'summary':[],
            'date':[],
            'link':[]
        }


class DataCleaning(object):

    def __init__(self, title = '', location = ""):
        self._title = title
        self._location = location
        self._webcrawler = WebCrawler(self._title, self._location)
        self.data = self._webcrawler.get()
        self.datastructure = DataStructure()

    def getData(self):
        soup = BeautifulSoup(self.data, 'html.parser')

        for x in soup.findAll('div', class_="jobsearch-SerpJobCard unifiedRow row result"):

            title = x.find(class_="title").text.strip()
            self.datastructure.data["title"].append(title)


            location = x.find(class_="location accessible-contrast-color-location").text.strip()
            self.datastructure.data["location"].append(location)


            summary = x.find(class_="summary")
            self.datastructure.data["summary"].append(summary.text)

            date = x.find(class_="date")
            self.datastructure.data["date"].append(date)


            link = x.find('a', href=True)
            base_url = "https://www.indeed.com/"


            Final = base_url + link["href"]

            self.datastructure.data["link"].append(Final)


        data = list(zip(
            self.datastructure.data["title"],  self.datastructure.data["location"],
            self.datastructure.data["summary"],self.datastructure.data["date"],
            self.datastructure.data["link"]
        ))

        df = pd.DataFrame(data=data, columns=["title", "location", "summary", "date", "link" ])
        return df


class IndeedJobSearch(object):

    def __init__(self, title = '', location = ""):

        self.title = title
        self.location = location
        self.datacleaning = DataCleaning(title=self.title, location=self.location)

    def getJobs(self):
        data = self.datacleaning.getData()
        return data

    def saveCsv(self):

        data = self.datacleaning.getData()
        data.to_csv("Jobs.csv")

    def saveExcel(self):

        data = self.datacleaning.getData()
        data.to_excel("job.xls")


if __name__ == "__main__":

    jobsearch = IndeedJobSearch(title='Python', location="Bridgeport , CT")
    data  = jobsearch.getJobs()
    print(data)
    # jobsearch.saveExcel()
    #jobsearch.saveCsv()