tangled
alpha
login
or
join now
dekker.one
/
Fourmi
0
fork
atom
A web scraper build to search specific information for a given compound (and its pseudonyms)
0
fork
atom
overview
issues
pulls
pipelines
Another name change to accommodate an executable script
Jip J. Dekker
12 years ago
b1840d3a
4f5b66ff
+6
-6
8 changed files
expand all
collapse all
unified
split
FourmiCrawler
__init__.py
items.py
pipelines.py
settings.py
spiders
Chemspider.py
Wikipedia.py
__init__.py
scrapy.cfg
Fourmi/__init__.py
FourmiCrawler/__init__.py
Fourmi/items.py
FourmiCrawler/items.py
Fourmi/pipelines.py
FourmiCrawler/pipelines.py
+5
-5
Fourmi/settings.py
FourmiCrawler/settings.py
···
6
6
# http://doc.scrapy.org/en/latest/topics/settings.html
7
7
#
8
8
9
9
-
BOT_NAME = 'Fourmi'
9
9
+
BOT_NAME = 'FourmiCrawler'
10
10
11
11
-
SPIDER_MODULES = ['Fourmi.spiders']
12
12
-
NEWSPIDER_MODULE = 'Fourmi.spiders'
11
11
+
SPIDER_MODULES = ['FourmiCrawler.spiders']
12
12
+
NEWSPIDER_MODULE = 'FourmiCrawler.spiders'
13
13
ITEM_PIPELINES = {
14
14
-
'Fourmi.pipelines.FourmiPipeline': 100
14
14
+
'FourmiCrawler.pipelines.FourmiPipeline': 100
15
15
}
16
16
17
17
# Crawl responsibly by identifying yourself (and your website) on the user-agent
18
18
-
#USER_AGENT = 'Fourmi (+http://www.yourdomain.com)'
18
18
+
#USER_AGENT = 'FourmiCrawler (+http://www.yourdomain.com)'
Fourmi/spiders/Chemspider.py
FourmiCrawler/spiders/Chemspider.py
Fourmi/spiders/Wikipedia.py
FourmiCrawler/spiders/Wikipedia.py
Fourmi/spiders/__init__.py
FourmiCrawler/spiders/__init__.py
+1
-1
scrapy.cfg
···
4
4
# http://doc.scrapy.org/en/latest/topics/scrapyd.html
5
5
6
6
[settings]
7
7
-
default = Scrapy.settings
7
7
+
default = FourmiCrawler.settings
8
8
9
9
[deploy]
10
10
#url = http://localhost:6800/