Since scrapy is asynchronious you need to chain your requests manually. For transfering data between requests you can use Request's meta
attribute:
def parse(self, response):
item = dict()
item['name'] = 'foobar'
yield request('http://someurl.com', self.parse2,
meta={'item': item})
def parse2(self, response):
print(response.meta['item'])
# {'name': 'foobar'}
In your case you end up with a split chain when you should have one continuous chain.
Your code should look something like this:
def parse_companies(self, response):
data = json.loads(response.body)
if not data:
return
for company in data:
item = ThalamusItem()
comp_id = company["id"]
url = self.request_details_URL + str(comp_id) + ".json"
url2 = self.request_contacts + str(comp_id)
request = Request(url, callback=self.parse_details,
meta={'url2': url2, 'item': item})
yield request
def parse_details(self, response):
item = response.meta['item']
url2 = response.meta['url2']
item['details'] = '' # add details
yield Request(url2, callback=self.parse_contacts, meta={'item': item})
def parse_contacts(self, response):
item = response.meta['item']
item['contacts'] = '' # add details
yield item
与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…