1
|
from Utilities.Database import database_loader
|
2
|
|
3
|
# mongodb collection with with already downloaded links
|
4
|
MONGODB_DATASET_LINK_COLLECTION = "LINKS"
|
5
|
# mongodb collection with with already processed files
|
6
|
MONGODB_DATASET_PROCESSED_COLLECTION = "PROCESSED"
|
7
|
# mongodb collection with with already loaded links
|
8
|
MONGODB_DATASET_LOADED_COLLECTION = "LOADED"
|
9
|
# mongodb collection with aviable datasets with number of days from last update
|
10
|
MONGODB_DATASET_COLLECTION = "DATASETS"
|
11
|
|
12
|
|
13
|
def load_ignore_set_links(dataset_name):
|
14
|
"""
|
15
|
Loades from database links of already downloaded files by crawler
|
16
|
|
17
|
Returns:
|
18
|
dataset_name name of dataset that has existing configuration file
|
19
|
"""
|
20
|
|
21
|
ignore_set = set()
|
22
|
|
23
|
connection = database_loader.create_database_connection()
|
24
|
|
25
|
my_col = connection[dataset_name + MONGODB_DATASET_LINK_COLLECTION]
|
26
|
|
27
|
data = my_col.find()
|
28
|
|
29
|
for part in data:
|
30
|
ignore_set.add(part['name'])
|
31
|
|
32
|
return ignore_set
|
33
|
|
34
|
|
35
|
def update_ignore_set_links(dataset_name,link):
|
36
|
"""
|
37
|
Adds links of newly crawled files to the database
|
38
|
|
39
|
Returns:
|
40
|
dataset_name name of dataset that has existing configuration file
|
41
|
"""
|
42
|
|
43
|
connection = database_loader.create_database_connection()
|
44
|
|
45
|
my_col = connection[dataset_name + MONGODB_DATASET_LINK_COLLECTION]
|
46
|
|
47
|
my_col.insert({ "name": link})
|
48
|
|
49
|
|
50
|
def reset_ignore_set_links(dataset_name):
|
51
|
"""
|
52
|
Drops collection of already downloaded links
|
53
|
|
54
|
Returns:
|
55
|
dataset_name name of dataset that has existing configuration file
|
56
|
"""
|
57
|
|
58
|
connection = database_loader.create_database_connection()
|
59
|
|
60
|
my_col = connection[dataset_name + MONGODB_DATASET_LINK_COLLECTION]
|
61
|
|
62
|
my_col.drop()
|
63
|
|
64
|
|
65
|
|
66
|
def load_ignore_set_processed(dataset_name):
|
67
|
"""
|
68
|
Loads from database set of already processed files
|
69
|
|
70
|
Returns:
|
71
|
dataset_name name of dataset that has existing configuration file
|
72
|
"""
|
73
|
|
74
|
ignore_set = set()
|
75
|
|
76
|
connection = database_loader.create_database_connection()
|
77
|
|
78
|
my_col = connection[dataset_name + MONGODB_DATASET_PROCESSED_COLLECTION]
|
79
|
|
80
|
data = my_col.find()
|
81
|
|
82
|
for part in data:
|
83
|
ignore_set.add(part['name'])
|
84
|
|
85
|
return ignore_set
|
86
|
|
87
|
|
88
|
def update_ignore_set_processed(dataset_name,filename):
|
89
|
"""
|
90
|
Adds files of newly processed files to the database
|
91
|
|
92
|
Returns:
|
93
|
dataset_name name of dataset that has existing configuration file
|
94
|
"""
|
95
|
|
96
|
connection = database_loader.create_database_connection()
|
97
|
|
98
|
my_col = connection[dataset_name + MONGODB_DATASET_PROCESSED_COLLECTION]
|
99
|
|
100
|
my_col.insert({ "name": filename})
|
101
|
|
102
|
|
103
|
|
104
|
def reset_ignore_set_processed(dataset_name):
|
105
|
"""
|
106
|
Drops collection of already processed files
|
107
|
|
108
|
Returns:
|
109
|
dataset_name name of dataset that has existing configuration file
|
110
|
"""
|
111
|
|
112
|
connection = database_loader.create_database_connection()
|
113
|
|
114
|
my_col = connection[dataset_name + MONGODB_DATASET_PROCESSED_COLLECTION]
|
115
|
|
116
|
my_col.drop()
|
117
|
|
118
|
|
119
|
|
120
|
def load_ignore_set_loaded(dataset_name):
|
121
|
"""
|
122
|
Loads from database set of already loaded files in database
|
123
|
|
124
|
Returns:
|
125
|
dataset_name name of dataset that has existing configuration file
|
126
|
"""
|
127
|
|
128
|
ignore_set = set()
|
129
|
|
130
|
connection = database_loader.create_database_connection()
|
131
|
|
132
|
my_col = connection[dataset_name + MONGODB_DATASET_LOADED_COLLECTION]
|
133
|
|
134
|
data = my_col.find()
|
135
|
|
136
|
for part in data:
|
137
|
ignore_set.add(part['name'])
|
138
|
|
139
|
return ignore_set
|
140
|
|
141
|
|
142
|
|
143
|
def update_ignore_set_loaded(dataset_name,filename):
|
144
|
"""
|
145
|
Adds files of newly loaded files to the database
|
146
|
|
147
|
Returns:
|
148
|
dataset_name name of dataset that has existing configuration file
|
149
|
"""
|
150
|
|
151
|
connection = database_loader.create_database_connection()
|
152
|
|
153
|
my_col = connection[dataset_name + MONGODB_DATASET_LOADED_COLLECTION]
|
154
|
|
155
|
my_col.insert({ "name": filename})
|
156
|
|
157
|
|
158
|
def reset_ignore_set_loaded(dataset_name):
|
159
|
"""
|
160
|
Drops collection of already loaded files
|
161
|
|
162
|
Returns:
|
163
|
dataset_name name of dataset that has existing configuration file
|
164
|
"""
|
165
|
|
166
|
connection = database_loader.create_database_connection()
|
167
|
|
168
|
my_col = connection[dataset_name + MONGODB_DATASET_LOADED_COLLECTION]
|
169
|
|
170
|
my_col.drop()
|
171
|
|
172
|
|
173
|
def load_updated(dataset_name):
|
174
|
"""
|
175
|
Loads value of (days from last update) from db
|
176
|
|
177
|
Returns:
|
178
|
dataset_name name of dataset that has existing configuration file
|
179
|
"""
|
180
|
|
181
|
updated = 0
|
182
|
|
183
|
connection = database_loader.create_database_connection()
|
184
|
|
185
|
my_col = connection[MONGODB_DATASET_COLLECTION]
|
186
|
|
187
|
data = my_col.find_one({'key-name': dataset_name},{'updated'})
|
188
|
|
189
|
updated = int(data['updated'])
|
190
|
|
191
|
return updated
|
192
|
|
193
|
|
194
|
def update_updated(dataset_name,value):
|
195
|
"""
|
196
|
Updates value of (days from last update) in db
|
197
|
|
198
|
Returns:
|
199
|
dataset_name name of dataset that has existing configuration file
|
200
|
"""
|
201
|
|
202
|
connection = database_loader.create_database_connection()
|
203
|
|
204
|
my_col = connection[MONGODB_DATASET_COLLECTION]
|
205
|
|
206
|
myquery = { 'key-name': dataset_name }
|
207
|
new_values = { "$set": { "updated": value } }
|
208
|
|
209
|
my_col.update_one(myquery,new_values)
|