Python 刮擦式爬行器无法爬行所需页面

这是我试图抓取的网站链接。 下面是我的刮刀，因为这是第一次尝试刮刀，所以请原谅愚蠢的错误。请看一看，并建议任何修改，这将使我的代码运行

Items.py

import scrapy


class EpfoCrawl2Item(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    from scrapy.item import Item, Field
    S_No = Field()
    Old_region_code = Field()
    Region_code = Field()
    Name = Field()
    Address = Field()
    Pin = Field()
    Epfo_office = Field()
    Under_Ro = Field()
    Under_Acc = Field()
    Payment = Field()
    pass

import scrapy
from scrapy.selector import HtmlXPathSelector


class EpfoCrawlSpider(scrapy.Spider):
"""Spider for regularly updated search.epfoservices.in"""
name = "PfData"
allowed_domains = ["search.epfoservices.in"]
starturls = ["http://search.epfoservices.in/est_search_display_result.php?pageNum_search=1&totalRows_search=72045&old_rg_id=AP&office_name=&pincode=&estb_code=&estb_name=&paging=paging"]

def parse(self,response):
    hxs = HtmlXPathSelector(response)
    rows = hxs.select('//tr"]')
    items = []
    for val in rows:
        item = Val()
        item['S_no'] = val.select('/td[0]/text()').extract()
        item['Old_region_code'] = val.select('/td[1]/text').extract()
        item['Region_code'] = val.select('/td[2]/text()').extract()
        item['Name'] = val.select('/td[3]/text()').extract()
        item['Address'] = val.select('/td[4]/text()').extract()
        item['Pin'] = val.select('/td[5]/text()').extract()
        item['Epfo_office'] = val.select('/td[6]/text()').extract()
        item['Under_ro'] = val.select('/td[7]/text()').extract()
        item['Under_Acc'] = val.select('/td[8]/text()').extract()
        item['Payment'] = val.select('a/@href').extract()
        items.append(item)
        yield items

epfocrawl1\u spider.py

import scrapy


class EpfoCrawl2Item(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    from scrapy.item import Item, Field
    S_No = Field()
    Old_region_code = Field()
    Region_code = Field()
    Name = Field()
    Address = Field()
    Pin = Field()
    Epfo_office = Field()
    Under_Ro = Field()
    Under_Acc = Field()
    Payment = Field()
    pass

import scrapy
from scrapy.selector import HtmlXPathSelector


class EpfoCrawlSpider(scrapy.Spider):
"""Spider for regularly updated search.epfoservices.in"""
name = "PfData"
allowed_domains = ["search.epfoservices.in"]
starturls = ["http://search.epfoservices.in/est_search_display_result.php?pageNum_search=1&totalRows_search=72045&old_rg_id=AP&office_name=&pincode=&estb_code=&estb_name=&paging=paging"]

def parse(self,response):
    hxs = HtmlXPathSelector(response)
    rows = hxs.select('//tr"]')
    items = []
    for val in rows:
        item = Val()
        item['S_no'] = val.select('/td[0]/text()').extract()
        item['Old_region_code'] = val.select('/td[1]/text').extract()
        item['Region_code'] = val.select('/td[2]/text()').extract()
        item['Name'] = val.select('/td[3]/text()').extract()
        item['Address'] = val.select('/td[4]/text()').extract()
        item['Pin'] = val.select('/td[5]/text()').extract()
        item['Epfo_office'] = val.select('/td[6]/text()').extract()
        item['Under_ro'] = val.select('/td[7]/text()').extract()
        item['Under_Acc'] = val.select('/td[8]/text()').extract()
        item['Payment'] = val.select('a/@href').extract()
        items.append(item)
        yield items

下面是运行“scrapy crawl PfData”后的日志

---

请提供建议。

开始URL列表必须是

开始URL

，而不是

开始URL

@abukaj No！代码审查需要工作代码。此代码无法正常工作。

类EpfoCrawlSpider（scrapy.Spider）：

之后缺少缩进也永远不会起作用。缩进在Python中很重要。@Mast不是检查源代码来调试它，而是检查代码？@abukaj也许这是检查代码的一个版本，但它是针对codereview.se的。如果您不熟悉SE站点的范围，请不要推荐它们。@Mast谢谢。我只检查了codereview.se的描述，它相当简短，而不是主题外策略。