GitHub-Language-Prediction/gitHubCrawler.py at main · BressettJ21/GitHub-Language-Prediction · 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
139
import requests
from bs4 import BeautifulSoup
import time
import numpy
import pandas as pd

def emojiDecode(description):
    output = (description
      .encode('utf-16', 'surrogatepass')
      .decode('utf-16')
      .encode("raw_unicode_escape")
      .decode("latin_1")
    )
    return output

def get_page_repo_list(URL,page):
    page = str(page)
    url_to_call = URL.format(page)

    response = requests.get(url_to_call, headers = {'User-Agent': "Mozilla/5.0"})
    if response.status_code != 200:
        print('connection failed')
        return
    html_content = response.content
    dom = BeautifulSoup(html_content, 'html.parser')
    repoList = dom.select("ul.repo-list li")
    return repoList


def is_int(temp):
    try:
        int(temp)
        return 1
    except:
        return 0

def is_Star(temp):
    if "." in temp or is_int(temp):
        return 1
    else:
        return 0


def is_lang(temp):
    langs = ['Jupyter Notebook','Python','R','HTML','JavaScript','Java','CSS','Rebol','TeX','Shell']
    return temp in langs

def is_license(temp):
    return "Updated" not in temp

def get_elements(section):
    al = section.find_all("div", {"class" : "mr-3"})
    if len(al) == 4:
        return [div.get_text().replace("\n", "").strip() for div in al]
    result = [0,0,0,0]
    for div in al:
        temp = div.get_text().replace("\n", "").strip()
        if is_Star(temp):
            result[0] = temp
            pass

        elif is_lang(temp):
            result[1] = temp
            pass

        elif is_license(temp):
            result[2] = temp
            pass
        else:
            result[3] = temp

    return result

def clean_stars(stars):
    stars = str(stars)
    if '.' in stars:
        stars = stars.replace(".", "").replace("k", "00")
    stars = stars.replace("k", "000")
    return stars

def clean_elements(elements):

    elements[0] = clean_stars(elements[0])

    elements[3] = elements[3].replace("Updated", "").strip()
    return elements

def extractData(repo):
    name = repo.a.attrs["href"]
    try:
        description = repo.p.get_text().replace("\n", "").strip()
    except:
        description = "NA"
    description = emojiDecode(description)
    section = repo.find("div", {"class" : ""})
    features = get_elements(section)
    features =  clean_elements(features)
    features.insert(0,name)
    features.insert(1,description)
    return features


def get_URLs():
    f = open("tempURLS.txt", "r")
    listURLs = [x for x in f]
    return listURLs

def save_data(data,URLCOUNT,count):
    a = numpy.asarray(data)
    cols = ["URLCODE","Name", "Descr","Stars","MajLang","License","LastUpdated"]
    pd.DataFrame(a).to_csv("GitHub_DS_Repos{}-{}.csv".format(URLCOUNT,count), header=cols)


def driver():
    URLCOUNT = 1

    for URL in get_URLs():
        data = []
        count = 0
        for page in range(1,101):
            time.sleep(20)
            repoList = get_page_repo_list(URL,page)
            for repo in repoList:
                temp = extractData(repo)
                temp.insert(0,URLCOUNT)
                data.append(temp)

            print(URLCOUNT,page)
            if page % 5 == 0:
                count += 1
                save_data(data,URLCOUNT,count)
        URLCOUNT += 1

if __name__ == "__main__":
    driver()