-
Notifications
You must be signed in to change notification settings - Fork 8
/
Copy pathglRepos.py
executable file
·216 lines (183 loc) · 7.52 KB
/
glRepos.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
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
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
# #!/usr/bin/env python3
# import sys
# import re
# import pymongo
# import json
# import time
# import datetime
# import requests
# begin = sys.argv[1] # beginning page index from first arg
# # DB info
# client = pymongo.MongoClient()
# dbname = sys.argv[2] # expects db name as second arg
# collName = sys.argv[3] # expects collection name as third arg
# db = client[dbname]
# coll = db[collName]
# beginurl = "https://gitlab.com/api/v4/projects?archived=false&membership=false&order_by=created_at&owned=false&page={}&per_page=99&simple=false&sort=desc&starred=false&statistics=false&with_custom_attributes=false&with_issues_enabled=false&with_merge_requests_enabled=false"
# gleft = 0
# success = "Successfully loaded page {}. Got {} repos, current total is {}"
# header = {'per_page': str(99)}
# # check remaining query chances for rate-limit restriction
# def wait(left):
# global header
# while (left < 20):
# l = requests.get('https://gitlab.com/api/v4/projects', headers=header)
# if (l.ok):
# left = int(l.headers.get('RateLimit-Remaining'))
# print("Waiting for rate limit...")
# time.sleep(60)
# return left
# # send queries and extract urls
# def get(url, coll):
# global gleft
# global header
# global bginnum
# gleft = wait(gleft)
# total = 0
# try:
# r = requests .get(url, headers=header)
# time.sleep(0.5)
# # got blocked
# if r.status_code == 403:
# return "got blocked", str(bginnum)
# if (r.ok):
# gleft = int(r.headers.get('RateLimit-Remaining'))
# # get total number of pages (i.e. get last possible page)
# lll = r.headers.get('Link')
# ll = lll.replace(';', ',').split(',')
# url = ll[ll.index(' rel="next"') -
# 1].replace('<', '').replace('>', '').lstrip()
# last = re.findall(r'&page=(\d+)&', url)
# if (len(last) == 1):
# last = int(last[0])
# t = r.text
# array = json.loads(t)
# total += len(array)
# print(success.format(begin, len(array), total))
# for el in array:
# el['page_number'] = begin
# coll.insert(el)
# pageNum = int(r.headers.get('X-Next-Page'))
# consecutiveEmpty = 0
# while (pageNum):
# gleft = int(r.headers.get('RateLimit-Remaining'))
# gleft = wait(gleft)
# # extract next page url
# url = beginurl.format(pageNum)
# # try:
# r = requests .get(url, headers=header)
# if r.status_code == 403:
# return "got blocked", str(bginnum)
# if (r.ok):
# lll = r.headers.get('Link')
# t = r.text
# array1 = json.loads(t)
# total += len(array1)
# print(success.format(pageNum, len(array1), total))
# for el in array1:
# el['page_number'] = pageNum
# coll.insert(el)
# if (r.headers.get('X-Next-Page')):
# pageNum = int(r.headers.get('X-Next-Page'))
# consecutiveEmpty = 0
# else:
# sys.stderr.write("Can't find next page from:{}{}{}".format('\n', url, '\n'))
# pageNum += 1
# consecutiveEmpty += 1
# if consecutiveEmpty > 4:
# sys.stderr.write("Page {} is 5 consecutive empty pages. Exiting".format(pageNum))
# return
# continue
# else:
# sys.stderr.write("url can not found:\n" + url + '\n')
# return
# except requests.exceptions.ConnectionError:
# sys.stderr.write('could not get ' + url + '\n')
# except Exception as e:
# sys.stderr.write(url + ';' + str(e) + '\n')
# #start retrieving
# get(beginurl.format(begin),coll)
#!/usr/bin/env python3
import sys
import re
import pymongo
import json
import time
import requests
begin = sys.argv[1] # beginning page index from first arg
# DB info
client = pymongo.MongoClient()
dbname = sys.argv[2] # expects db name as second arg
collName = sys.argv[3] # expects collection name as third arg
db = client[dbname]
coll = db[collName]
beginurl = "https://gitlab.com/api/v4/projects?archived=false&membership=false&order_by=created_at&owned=false&page={}&per_page=99&simple=false&sort=desc&starred=false&statistics=false&with_custom_attributes=false&with_issues_enabled=false&with_merge_requests_enabled=false"
success = "Successfully loaded page {}. Got {} repos, current total is {}"
header = {'per_page': str(99)}
# Function to handle rate limiting
def wait():
print("Waiting for rate limit...")
time.sleep(60)
# Function to send queries and extract URLs
def get(url, coll):
total = 0
try:
r = requests.get(url, headers=header)
time.sleep(0.5)
# got blocked
if r.status_code == 403:
return "got blocked", str(begin)
if r.ok:
# get total number of pages (i.e. get last possible page)
lll = r.headers.get('Link')
if lll:
ll = lll.replace(';', ',').split(',')
url = ll[ll.index(' rel="next"') - 1].replace('<', '').replace('>', '').lstrip()
last = re.findall(r'&page=(\d+)&', url)
if len(last) == 1:
last = int(last[0])
t = r.text
array = json.loads(t)
total += len(array)
print(success.format(begin, len(array), total))
for el in array:
el['page_number'] = begin
coll.insert_one(el)
pageNum = int(r.headers.get('X-Next-Page', 0))
consecutiveEmpty = 0
while pageNum:
wait()
# extract next page url
url = beginurl.format(pageNum)
r = requests.get(url, headers=header)
if r.status_code == 403:
return "got blocked", str(begin)
if r.ok:
lll = r.headers.get('Link')
t = r.text
array1 = json.loads(t)
total += len(array1)
print(success.format(pageNum, len(array1), total))
for el in array1:
el['page_number'] = pageNum
coll.insert_one(el)
if r.headers.get('X-Next-Page'):
pageNum = int(r.headers.get('X-Next-Page'))
consecutiveEmpty = 0
else:
sys.stderr.write("Can't find next page from:{}{}{}".format('\n', url, '\n'))
pageNum += 1
consecutiveEmpty += 1
if consecutiveEmpty > 4:
sys.stderr.write("Page {} is 5 consecutive empty pages. Exiting".format(pageNum))
return
continue
else:
sys.stderr.write("url cannot be found:\n" + url + '\n')
return
except requests.exceptions.ConnectionError:
sys.stderr.write('could not get ' + url + '\n')
except Exception as e:
sys.stderr.write(url + ';' + str(e) + '\n')
# start retrieving
get(beginurl.format(begin), coll)