Scrapy管道未启动

Question

我在使用Scrapy管道时遇到问题。 EnricherPipeline从未开始。我在process_item的第一行放了一个调试器，它从来没有得到控制权。 JsonPipeline不启动，但它接收到的第一个参数是generator object process_item型的，而不是MatchItem比如，它应该接受（当我禁用EnricherPipeline，JsonPipeline按预期工作。

class MatchSpider(CrawlSpider): 

    def parse(self, response): 
     browser = Browser(browser='Chrome') 
     browser.get(response.url) 
     browser.find_element_by_xpath('//a[contains(text(), "{l}") and @title="{c}"]'.format(l=self.league, c=self.country)).click() 
     browser.find_element_by_xpath('//select[@id="seasons"]/option[text()="{s}"]'.format(s=self.season.replace('-', '/'))).click() 
     browser.find_element_by_xpath('//a[contains(text(), "Fixture")]').click() 
     page_matches = browser.find_elements_by_xpath('//*[contains(@class, "result-1 rc")]') 
     matches.extend([m.get_attribute('href') for m in page_matches] 
     for m in matches[:1]: 
      yield Request(m, callback=self.process_match, dont_filter=True) 

    def process_match(self, response): 
     match_item = MatchItem() 
     match_item['url'] = response.url 
     match_item['project'] = self.settings.get('BOT_NAME') 
     match_item['spider'] = self.name 
     match_item['server'] = socket.gethostname() 
     match_item['date'] = datetime.datetime.now() 
     return match_item 

class EnricherPipeline: 
    def process_item(self, item, spider): 
     self.match = defaultdict(dict) 
     self.match['date'] = item['match']['startTime'] 
     self.match['referee'] = item['match']['refereeName'] 
     self.match['stadium'] = item['match']['venueName'] 
     self.match['exp_mins'] = item['match']['expandedMinutes'] 
     yield self.match 


class JsonPipeline: 

    def process_item(self, item, scraper): 
     output_dir = 'data/matches/{league}/{season}'.format(league=scraper.league, season=scraper.season) 
     if not os.path.exists(output_dir): 
      os.makedirs(output_dir) 
     file_name = "-".join([str(datetime.strptime(item['date'], '%Y-%m-%dT%H:%M:%S').date()), 
           item['home']['name'], item['away']['name']]) + '.json' 
     item_path = os.sep.join((output_dir, file_name)) 
     with open(item_path, 'w') as f: 
      f.write(json.dumps(item)) 



ITEM_PIPELINES = { 
    'scrapers.whoscored.whoscored.pipelines.EnricherPipeline': 300, 
    'scrapers.whoscored.whoscored.pipelines.JsonPipeline': 800, 
} 

Answer 1

好了，问题是，EnricherPipeline但是我仍然不明白为什么调试器不在第一个管道中工作