我有一块带有Scrapy代码的Python,
cv::rectangle()
现在,即使import scrapy
import scrapy.crawler as crawler
from multiprocessing import Process, Queue
from twisted.internet import reactor
# your spider
class QuotesSpider(scrapy.Spider):
name = "quotes"
start_urls = ['http://quotes.toscrape.com/tag/humor/']
def parse(self, response):
for quote in response.css('div.quote'):
print(quote.css('span.text::text').extract_first())
# the wrapper to make it run more times
def run_spider():
def f(q):
try:
runner = crawler.CrawlerRunner()
deferred = runner.crawl(QuotesSpider)
deferred.addBoth(lambda _: reactor.stop())
reactor.run()
q.put(None)
except Exception as e:
q.put(e)
q = Queue()
p = Process(target=f, args=(q,))
p.start()
result = q.get()
p.join()
if result is not None:
raise result
print('first run:')
run_spider()
print('\nsecond run:')
run_spider()
返回空白或错误,run_spider仍在运行。
当QuotesSpider()错误或为空白时,如何使run_spider()不执行/排队?
谢谢