dekker.one
A web scraper build to search specific information for a given compound (and its pseudonyms)
Merge branch 'feature/sourcescfg_fixes' into develop
+24
-2
+19
sources.cfg.sample
+19
sources.cfg.sample
···
1
+
[DEFAULT]
2
+
reliability = Unknown
3
+
4
+
#For each source listed in FourmiCrawler/sources there should be a section
5
+
#named exactly as the filename in here. If not present, the DEFAULT value is
6
+
#used for reliability of that source.
7
+
8
+
[ChemSpider]
9
+
reliability = High
10
+
#token=Paste ChemSpider API token here and remove the hashtag
11
+
12
+
[NIST]
13
+
reliability = High
14
+
15
+
[WikipediaParser]
16
+
reliability = Medium
17
+
18
+
[PubChem]
19
+
reliability = High
+5
-2
utils/configurator.py
+5
-2
utils/configurator.py
···
1
1
import ConfigParser
2
2
3
3
from scrapy.utils.project import get_project_settings
4
-
4
+
import os
5
5
6
6
class Configurator:
7
7
"""
···
66
66
variables for sources
67
67
:return a ConfigParser object of sources.cfg
68
68
"""
69
+
current_dir = os.path.dirname(os.path.abspath(__file__))
70
+
config_path = current_dir + '\..\sources.cfg'
71
+
# [TODO]: location of sources.cfg should be softcoded eventually
69
72
config = ConfigParser.ConfigParser()
70
-
config.read('sources.cfg') # [TODO]: should be softcoded eventually
73
+
config.read(config_path)
71
74
return config
72
75
73
76
@staticmethod