sudo apt-get install python-pip
sudo apt-get install python-dev
sudo pip install scrapy
$sudo scrapy startproject store_name
$sudo ls –lR store_name
import scrapy
class StoreNameItem(scrapy.Item):
name = scrapy.Field() # 取出卡片商店的名称
from scrapy.selector import Selector
from scrapy.spider import BaseSpider
from scrapy.http import Request
from scrapy.http import FormRequest
import re
class StoreNameItem(BaseSpider):
name = "storename"
allowed_domains = ["fatwallet.com"]
start_urls = ["http://fatwallet.com/cash-back-shopping/"]
def parse(self,response):
output = open('StoreName.txt','w')
resp = Selector(response)
tags = resp.xpath('//tr[@class="storeListRow"]|\
//tr[@class="storeListRow even"]|\
//tr[@class="storeListRow even last"]|\
//tr[@class="storeListRow last"]').extract()
for i in tags:
i = i.encode('utf-8', 'ignore').strip()
store_name = ''
if re.search(r"class=\"storeListStoreName\">.*?<",i,re.I|re.S):
store_name = re.search(r"class=\"storeListStoreName\">.*?<",i,re.I|re.S).group()
store_name = re.search(r">.*?<",store_name,re.I|re.S).group()
store_name = re.sub(r'>',"",re.sub(r'<',"",store_name,re.I))
store_name = re.sub(r'&',"&",re.sub(r'&',"&",store_name,re.I))
#print store_name
output.write(store_name+""+"\n")
机械节能产品生产企业官网模板...
大气智能家居家具装修装饰类企业通用网站模板...
礼品公司网站模板
宽屏简约大气婚纱摄影影楼模板...
蓝白WAP手机综合医院类整站源码(独立后台)...苏ICP备2024110244号-2 苏公网安备32050702011978号 增值电信业务经营许可证编号:苏B2-20251499 | Copyright 2018 - 2025 源码网商城 (www.ymwmall.com) 版权所有