小编Phi*_*lip的帖子

我试图从子站点中抓取详细信息并与通过 site 抓取的详细信息合并。我一直在研究 stackoverflow 以及文档。但是，我仍然无法让我的代码工作。似乎我从子站点提取其他详细信息的功能不起作用。如果有人能看一下，我将不胜感激。

# -*- coding: utf-8 -*-
from scrapy.spiders import Spider
from scrapy.selector import Selector
from scrapeInfo.items import infoItem
import pyodbc


class scrapeInfo(Spider):
    name = "info"
    allowed_domains = ["http://www.nevermind.com"]
    start_urls = []

    def start_requests(self):

        #Get infoID and Type from database
        self.conn = pyodbc.connect('DRIVER={SQL Server};SERVER=server;DATABASE=dbname;UID=user;PWD=password')
        self.cursor = self.conn.cursor()
        self.cursor.execute("SELECT InfoID, category FROM dbo.StageItem")

        rows = self.cursor.fetchall()

        for row in rows:
            url = 'http://www.nevermind.com/info/'
            InfoID = row[0]
            category = row[1]
            yield self.make_requests_from_url(url+InfoID, InfoID, category, self.parse)

    def make_requests_from_url(self, …