Scrapy爬取照片

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import scrapy
import hashlib
from tutorial.items import JinLuoSiItem
from scrapy.http import Request
from scrapy.selector import HtmlXPathSelector


class JinLuoSiSpider(scrapy.spiders.Spider):
    count = 0
    url_set = set()

    name = "jluosi"
    domain = ‘http://www.jluosi.com‘
    allowed_domains = ["jluosi.com"]

    start_urls = [
        "http://www.jluosi.com:80/ec/goodsDetail.action?jls=QjRDNEIzMzAzOEZFNEE3NQ==",
    ]

    def parse(self, response):
        md5_obj = hashlib.md5()
        md5_obj.update(response.url)
        md5_url = md5_obj.hexdigest()
        if md5_url in JinLuoSiSpider.url_set:
            pass
        else:
            JinLuoSiSpider.url_set.add(md5_url)
            hxs = HtmlXPathSelector(response)
            if response.url.startswith(‘http://www.jluosi.com:80/ec/goodsDetail.action‘):
                item = JinLuoSiItem()
                item[‘company‘] = hxs.select(‘//div[@class="ShopAddress"]/ul/li[1]/text()‘).extract()
                item[‘link‘] = hxs.select(‘//div[@class="ShopAddress"]/ul/li[2]/text()‘).extract()
                item[‘qq‘] = hxs.select(‘//div[@class="ShopAddress"]//a/@href‘).re(‘.*uin=(?P<qq>\d*)&‘)
                item[‘address‘] = hxs.select(‘//div[@class="ShopAddress"]/ul/li[4]/text()‘).extract()

                item[‘title‘] = hxs.select(‘//h1[@class="goodsDetail_goodsName"]/text()‘).extract()

                item[‘unit‘] = hxs.select(‘//table[@class="R_WebDetail_content_tab"]//tr[1]//td[3]/text()‘).extract()
                product_list = []
                product_tr = hxs.select(‘//table[@class="R_WebDetail_content_tab"]//tr‘)
                for i in range(2,len(product_tr)):
                    temp = {
                        ‘standard‘:hxs.select(‘//table[@class="R_WebDetail_content_tab"]//tr[%d]//td[2]/text()‘ %i).extract()[0].strip(),
                        ‘price‘:hxs.select(‘//table[@class="R_WebDetail_content_tab"]//tr[%d]//td[3]/text()‘ %i).extract()[0].strip(),
                    }
                    product_list.append(temp)

                item[‘product_list‘] = product_list
                yield item

            current_page_urls = hxs.select(‘//a/@href‘).extract()
            for i in range(len(current_page_urls)):
                url = current_page_urls[i]
                if url.startswith(‘http://www.jluosi.com‘):
                    url_ab = url
                    yield Request(url_ab, callback=self.parse)

选择器规则Demo

def parse(self, response):
    from scrapy.http.cookies import CookieJar
    cookieJar = CookieJar()
    cookieJar.extract_cookies(response, response.request)
    print(cookieJar._cookies)

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import scrapy
import hashlib
from beauty.items import JieYiCaiItem
from scrapy.http import Request
from scrapy.selector import HtmlXPathSelector
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor


class JieYiCaiSpider(scrapy.spiders.Spider):
    count = 0
    url_set = set()

    name = "jieyicai"
    domain = ‘http://www.jieyicai.com‘
    allowed_domains = ["jieyicai.com"]

    start_urls = [
        "http://www.jieyicai.com",
    ]

    rules = [
        #下面是符合规则的网址,但是不抓取内容,只是提取该页的链接(这里网址是虚构的,实际使用时请替换)
        #Rule(SgmlLinkExtractor(allow=(r‘http://test_url/test?page_index=\d+‘))),
        #下面是符合规则的网址,提取内容,(这里网址是虚构的,实际使用时请替换)
        #Rule(LinkExtractor(allow=(r‘http://www.jieyicai.com/Product/Detail.aspx?pid=\d+‘)), callback="parse"),
    ]

    def parse(self, response):
        md5_obj = hashlib.md5()
        md5_obj.update(response.url)
        md5_url = md5_obj.hexdigest()
        if md5_url in JieYiCaiSpider.url_set:
            pass
        else:
            JieYiCaiSpider.url_set.add(md5_url)
            
            hxs = HtmlXPathSelector(response)
            if response.url.startswith(‘http://www.jieyicai.com/Product/Detail.aspx‘):
                item = JieYiCaiItem()
                item[‘company‘] = hxs.select(‘//span[@class="username g-fs-14"]/text()‘).extract()
                item[‘qq‘] = hxs.select(‘//span[@class="g-left bor1qq"]/a/@href‘).re(‘.*uin=(?P<qq>\d*)&‘)
                item[‘info‘] = hxs.select(‘//div[@class="padd20 bor1 comard"]/text()‘).extract()
                item[‘more‘] = hxs.select(‘//li[@class="style4"]/a/@href‘).extract()
                item[‘title‘] = hxs.select(‘//div[@class="g-left prodetail-text"]/h2/text()‘).extract()
                yield item

            current_page_urls = hxs.select(‘//a/@href‘).extract()
            for i in range(len(current_page_urls)):
                url = current_page_urls[i]
                if url.startswith(‘/‘):
                    url_ab = JieYiCaiSpider.domain + url
                    yield Request(url_ab, callback=self.parse)

spider

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html

import json
from twisted.enterprise import adbapi
import MySQLdb.cursors
import re

mobile_re = re.compile(r‘(13[0-9]|15[012356789]|17[678]|18[0-9]|14[57])[0-9]{8}‘)
phone_re = re.compile(r‘(\d+-\d+|\d+)‘)

class JsonPipeline(object):

    def __init__(self):
        self.file = open(‘/Users/wupeiqi/PycharmProjects/beauty/beauty/jieyicai.json‘, ‘wb‘)


    def process_item(self, item, spider):
        line = "%s  %s\n" % (item[‘company‘][0].encode(‘utf-8‘), item[‘title‘][0].encode(‘utf-8‘))
        self.file.write(line)
        return item

class DBPipeline(object):

    def __init__(self):
        self.db_pool = adbapi.ConnectionPool(‘MySQLdb‘,
                                             db=‘DbCenter‘,
                                             user=‘root‘,
                                             passwd=‘123‘,
                                             cursorclass=MySQLdb.cursors.DictCursor,
                                             use_unicode=True)

    def process_item(self, item, spider):
        query = self.db_pool.runInteraction(self._conditional_insert, item)
        query.addErrback(self.handle_error)
        return item

    def _conditional_insert(self, tx, item):
        tx.execute("select nid from company where company = %s", (item[‘company‘][0], ))
        result = tx.fetchone()
        if result:
            pass
        else:
            phone_obj = phone_re.search(item[‘info‘][0].strip())
            phone = phone_obj.group() if phone_obj else ‘ ‘

            mobile_obj = mobile_re.search(item[‘info‘][1].strip())
            mobile = mobile_obj.group() if mobile_obj else ‘ ‘

            values = (
                item[‘company‘][0],
                item[‘qq‘][0],
                phone,
                mobile,
                item[‘info‘][2].strip(),
                item[‘more‘][0])
            tx.execute("insert into company(company,qq,phone,mobile,address,more) values(%s,%s,%s,%s,%s,%s)", values)

    def handle_error(self, e):
        print ‘error‘,e

pipelines