我可以在start_urls中使用变量吗？请看下面的脚本:
这个脚本工作正常:
from scrapy.spider import Spider
from scrapy.selector import Selector
from example.items import ExampleItem
class ExampleSpider(Spider):
name = "example"
allowed_domains = ["example.com"]
start_urls = [
"http://www.example.com/search-keywords=['0750692995']",
"http://www.example.com/search-keywords=['0205343929']",
"http://www.example.com/search-keywords=['0874367379']",
]
def parse(self, response):
hxs = Selector(response)
item = ExampleItem()
item['url'] = response.url
item['price'] = hxs.select("//li[@class='mpbold']/a/text()").extract()
item['title'] = hxs.select("//span[@class='title L']/text()").extract()
return item
但我想这样:
from scrapy.spider import Spider
from scrapy.selector import Selector
from example.items import ExampleItem
class ExampleSpider(Spider):
name = "example"
allowed_domains = ["example.com"]
pro_id = ["0750692995", "0205343929", "0874367379"] ***(I added this line) …