小弟新手，在看著教程寫scrapy爬蟲時使用xpath().extract()[0]的方法獲取內(nèi)容，報IndexError: list index out of range錯誤，求問大神怎么解決，急求答案在線等。（試過去掉.extract()[0]，會報出TypeError: Request url must be str or unicode錯誤）。代碼如下：

cnblog_spider.py

# -*- coding:utf-8 -*-
# !/usr/bin/env python
import scrapy
from bs4 import BeautifulSoup
from scrapy import Selector

from p1.items import CnblogsSpiderItem


class CnblogsSpider(scrapy.spiders.Spider):
    name = "cnblogs" # 爬蟲的名稱
    allowed_domains = ["cnblogs.com"]# 允許的域名
    start_urls = [
        "http://www.cnblogs.com/qiyeboy/default.html? page=1"
    ]
    def parse(self,response):
        # 實現(xiàn)網(wǎng)頁的解析
        # 首先抽取所有的文章
        papers = response.xpath(".//*[@class='day']")#.extract()
        # 從每篇文章中抽取數(shù)據(jù)
        #soup = BeautifulSoup(papers, "html.parser", from_encoding="utf-8")
        # print papers
        for paper in papers:
            url = paper.xpath(".//*[@class='pastTitle']/a/@href").extract()[0]
            title = paper.xpath(".//*[@class='pastTitle']/a").extract()[0]
            time = paper.xpath(".//*[@class='dayTitle']/a").extract()[0]
            content = paper.xpath(".//*[@class='postCon']/a").extract()[0]
            # print url, title, time, content
            item = CnblogsSpiderItem(url=url, title=title, time=time, content=content)
            request = scrapy.Request(url=url, callback=self.parse_body)
            request.meta['item'] = item  # 將item暫存
            yield request
            #yield item
        next_page = Selector(response).re(u'<a href="(\S*)">下一頁</a>')
        if next_page:
            yield scrapy.Request(url=next_page[0], callback=self.parse)

    def parse_body(self, response):
        item = response.meta['item']
        body = response.xpath(".//*[@class='postBody']")
        item['cimage_urls'] = body.xpath('.//img//@src').extract()
        yield item