38 lines
1.1 KiB
Python
38 lines
1.1 KiB
Python
#!/home/nonroot/event_scrapy/venv/bin/python3
|
|
|
|
from scrapy.crawler import CrawlerRunner
|
|
from scrapy.utils.project import get_project_settings
|
|
from twisted.internet import reactor, defer
|
|
from scrape_event import unloze_spider
|
|
|
|
@defer.inlineCallbacks
|
|
def handle_urls(result, runner, reactor):
|
|
for item in result:
|
|
yield runner.crawl(unloze_spider, item = item)
|
|
#this finishes the reactor.run()
|
|
reactor.stop()
|
|
|
|
def main():
|
|
result = []
|
|
urls = []
|
|
#mg
|
|
urls.append("https://unloze.com/forums/events.79/")
|
|
#ze
|
|
urls.append("https://unloze.com/forums/events.76/")
|
|
#zr
|
|
urls.append("https://unloze.com/forums/events.80/")
|
|
#jb but there are no events yet
|
|
#urls.append("https://unloze.com/forums/events.90/")
|
|
|
|
for url in urls:
|
|
d = {"event_title" : None, "event_server": None, "event_maps": None, "event_date": None, "event_time": None, "event_reward": None, "url": url}
|
|
result.append(d)
|
|
|
|
runner = CrawlerRunner(get_project_settings())
|
|
handle_urls(result, runner, reactor)
|
|
reactor.run()
|
|
print("reactor finish")
|
|
|
|
if __name__ == '__main__':
|
|
main()
|