五.scrapy CSVFeedSpider

一.何时用到

数据格式为csv时，抓取数据需要用到 如http://yum.iqianyue.com/weisuenbook/pyspd/part12/mydata.csv

二.如何玩

打开网站是csv下载文件，下载后为

用记事本打开后

三.上代码

scrapy startproject csvspider

cd csvspider

scrapy genspider -t csvfeed mycsvspider iqianyue.com

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


class MycsvspiderSpider(CSVFeedSpider):
    name = 'mycsvspider'
    allowed_domains = ['iqianyue.com']
    start_urls = ['http://yum.iqianyue.com/weisuenbook/pyspd/part12/mydata.csv']
    headers = ['name', 'sex', 'addr', 'email']
    delimiter = ','

    # Do any adaptations you need here
    #def adapt_response(self, response):
    #    return response
    def parse_row(self, response, row):
        i = {}
        i['name'] = row['name']
        i['sex'] = row['sex']
        print u'名字是：'+ i['name']
        print u'性别是：'+ i['sex']
        print '--'*8
        return i

headers为csv的表头信息

delimiter为每行的分隔符“,”