mirror of
https://github.com/scrapy/scrapy.git
synced 2025-02-24 01:23:57 +00:00
* multiple projects * uploading scrapy projects as Python eggs * scheduling spiders using a JSON API Documentation is added along with the code. Closes #218. --HG-- rename : debian/scrapy-service.default => debian/scrapyd.default rename : debian/scrapy-service.dirs => debian/scrapyd.dirs rename : debian/scrapy-service.install => debian/scrapyd.install rename : debian/scrapy-service.lintian-overrides => debian/scrapyd.lintian-overrides rename : debian/scrapy-service.postinst => debian/scrapyd.postinst rename : debian/scrapy-service.postrm => debian/scrapyd.postrm rename : debian/scrapy-service.upstart => debian/scrapyd.upstart rename : extras/scrapy.tac => extras/scrapyd.tac
28 lines
677 B
Python
28 lines
677 B
Python
"""
|
|
This module can be used to run a Scrapy project contained in an egg file
|
|
|
|
To see all spiders in a project:
|
|
|
|
python -m scrapyd.eggrunner myproject.egg list
|
|
|
|
To crawl a spider:
|
|
|
|
python -m scrapyd.eggrunner myproject.egg crawl somespider
|
|
"""
|
|
|
|
import sys
|
|
|
|
from scrapyd.eggutils import activate_egg
|
|
|
|
def main(eggpath, args):
|
|
"""Run scrapy for the settings module name passed"""
|
|
activate_egg(eggpath)
|
|
from scrapy.cmdline import execute
|
|
execute(['scrapy'] + list(args))
|
|
|
|
if __name__ == '__main__':
|
|
if len(sys.argv) < 2:
|
|
print "usage: %s <eggfile> [scrapy_command args ...]" % sys.argv[0]
|
|
sys.exit(1)
|
|
main(sys.argv[1], sys.argv[2:])
|