github-issues-exporter/github-issues-exporter.py at main · sra405/github-issues-exporter · 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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
#!/usr/bin/python3
"""
Script used run GitHub API commands
"""
import requests
import json
import os
import sys
import argparse
import pandas as pd

"""
CLI Parameter Parser
"""
# Create the parser
github_parser = argparse.ArgumentParser(description='Github Organisation Issues Getter')
# Add the arguments
github_parser.add_argument('--github-token',
                           '-g',
                           dest='github_token',
                           help="Token for Github - if not present environment variable 'GITHUB_TOKEN' must be used",
                           required=False)
github_parser.add_argument('--filter', '-f',
                           dest='github_filter',
                           help='Filter used to obtain isses (typically username or organisation)',
                           required=True)
# get cli args
github_args = github_parser.parse_args()

"""
DEFINE KEY VARIABLES HERE
"""
if github_args.github_token:
  github_token = github_args.github_token
elif os.getenv('GITHUB_TOKEN'):
  github_token = os.getenv('GITHUB_TOKEN')
else:
  print("Github token required for extraction of issues.")
  sys.exit(999)

repo_key_param = 'full_name'
issue_key_param = 'number'
repo_key_filter = github_args.github_filter
csv_filename = 'issues.csv'
debug = False
info = True

# Github curl parameters
repo_url = 'https://api.github.com/user/repos'
issue_url = 'https://api.github.com/repos/{}/issues'

headers = {'Authorization': 'token {}'.format(github_token)}

class GitIt:
  def __init__(self,
               headers,
               key_repo_param,
               repo_url,
               issue_url,
               key_issue_param,
               repo_dict={},
               repo_key_filter=None,
               csv_filename='issues.csv',
               debug=True,
               info=True):
    self.headers = headers
    self.key_repo_param = key_repo_param
    self.key_issue_param = key_issue_param
    self.repo_url = repo_url
    self.issue_url = issue_url
    self.repo_dict = repo_dict
    self.issue_list = []
    self.repo_key_filter = repo_key_filter
    self.issue_df = pd.DataFrame()
    self.csv_filename = csv_filename
    self.info = info
    self.debug = debug
    # call some stuff
    if repo_url:
      self.get_repo_list()
    if issue_url and self.repo_dict:
      self.get_issue_list()

  def make_github_call(self, page_number, url, headers, key_param):
    params = {'page': page_number,
              'per_page': 100}
    res = requests.get(url, params=params, headers=headers)

    if self.debug:
      print(res)
      print(dir(res))
      print(res.json())

    return res

  def get_repo_list(self):
    page_number = 1
    returning_stuff = True

    while returning_stuff:
      res = self.make_github_call(page_number,
                                  self.repo_url,
                                  self.headers,
                                  self.key_repo_param)
      # iterate page
      page_number += 1
      # check we have some stuff returned
      if len(res.json()) == 0:
        returning_stuff = False
        break

      # loop over returned json
      for i in range(len(res.json())):
        if self.repo_key_filter and self.repo_key_filter.lower() in res.json()[i][self.key_repo_param].lower():
          self.repo_dict[res.json()[i][self.key_repo_param]] = res.json()[i]

    if self.debug: print('\n'.join(self.repo_dict.keys()))
    if self.info: print('Total Repos Found: {}'.format(len(self.repo_dict.keys())))

  def get_issue_list(self):
    for repo in self.repo_dict.keys():
      if self.info: print("Getting Issues for {}".format(repo))

      page_number = 1
      returning_stuff = True

      while returning_stuff:
        res = self.make_github_call(page_number,
                                    self.issue_url.format(repo),
                                    self.headers,
                                    self.key_repo_param)
        # iterate page
        page_number += 1
        # check we have some stuff returned
        if len(res.json()) == 0:
          returning_stuff = False
          break

        if self.info: print("--- {} issues found".format(len(res.json())))

        # loop over returned json
        for i in range(0, len(res.json())):
          self.issue_list.append(res.json()[i])
        if self.info: print("--- {} total issues found".format(len(self.issue_list)))
        if self.debug: print(pd.DataFrame(self.issue_list))

      if self.debug: input("Press Anything")
      if self.debug: pd.DataFrame(self.issue_list).to_csv(self.csv_filename)
    pd.DataFrame(self.issue_list).to_csv(self.csv_filename)

if __name__ == "__main__":
  GitIt(headers=headers,
        key_repo_param=repo_key_param,
        repo_url=repo_url,
        issue_url=issue_url,
        key_issue_param=issue_key_param,
        repo_key_filter=repo_key_filter,
        csv_filename=csv_filename,
        debug=debug,
        info=info)