Scrapy 爬虫模板--CSVFeedSpider

# -*- coding: utf-8 -*-
from scrapy.spiders import CSVFeedSpider
from ..items import CsvfeedspiderItem


class CsvdataSpider(CSVFeedSpider):
    name = 'csvdata'
    allowed_domains = ['gzdata.gov.cn']
    start_urls = ['http://gzopen.oss-cn-guizhou-a.aliyuncs.com/科技特派员.csv']
    headers = ['name', 'SearchField', 'Service', 'Specialty']
    delimiter = ','
    quotechar = '\n'

    def parse_row(self, response, row):
        i = CsvfeedspiderItem()
        i["name"] = row["name"]
        i["searchField"] = row["SearchField"]
        i["service"] = row["Service"]
        i["specialty"] = row["Specialty"]
        return i

    def adapt_response(self, response):
        return response.body.decode('gb18030')

import scrapy


class CsvfeedspiderItem(scrapy.Item):
    name = scrapy.Field()
    searchField = scrapy.Field()
    service = scrapy.Field()
    specialty = scrapy.Field()