def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath("//div[@class='productDetail product-detail-repair']/h1/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
def parse(self, response):
item = BaseItem()
details_list = []
pack_list = []
intro_list = []
speci_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath("//div[@class='breadcrumbs']/a[3]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_two = response.xpath("//div[@class='breadcrumbs']/a[4]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_three = response.xpath("//div[@class='breadcrumbs']/a[5]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' +classification_three
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath('//div[@class="tl-wrap-g"]/div[@class = "title"]/h3/b/text()').extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
def parse(self, response):
#filename = response.url.split("/")[-2]
#open(filename, 'wb').write(response.body)
#start browser
#self.driver.get(response.url)
#loading time interval
#time.sleep(5)
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath("//div[@class='textInfo']/form/div/h1/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
def parse(self, response):
item = BaseItem()
item = BaseItem()
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_two = response.xpath(
"//dd[@class='crumb_item'][1]/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='crumb']/dl/dd[@class='crumb_item'][2]/a/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
classification_one = response.xpath(
"//dd[@class='crumb_item'][13]/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//form[@id='form1']/ul/li[@class='tit']/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
list_brand = ''
for j in range(1, 20):
try:
list_brand = response.xpath(
"//form[@id='form1']/ul/li[%i]/label/text()" %
j).extract()[0].encode('utf-8').replace("\"",
"\'").strip()
if '品 牌:' == list_brand:
item['productBrand'] = response.xpath(
"//form[@id='form1']/ul/li[%i]/text()" %
j).extract()[0].encode('utf-8').replace("\"",
"\'").strip()
break
except:
pass
try:
item['productModel'] = response.xpath(
'//div[@class="m m1"]/div/ul/dt/li/text()').extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath(
"//strong[@class='orange price_tit']/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item['productImagePath'] = response.xpath(
"//div[@class='bd']/div/div/p/span/img/@src").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath(
"//form[@id='form1']/ul/li[4]/text()").extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath(
"//div[@class='Navigation']/span[3]/a/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='Navigation']/span[5]/a/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='Navigation']/span[7]/a/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//form[@class='goods-action']/h1[@class='goodsname']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
list_brand = ''
for j in range(1, 20):
try:
list_brand = response.xpath(
"//ul[@class='goodsprops clearfix']/li[%i]/span/text()" %
j).extract()[0].encode('utf-8').replace("\"",
"\'").strip()
if '品 牌：' in list_brand:
item['productBrand'] = response.xpath(
"//ul[@class='goodsprops clearfix']/li[%i]/a/text()" %
j).extract()[0].encode('utf-8').replace("\"",
"\'").strip()
break
except:
pass
try:
item['productModel'] = response.xpath(
"//ul[@class='goodsprops clearfix']/li/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath(
"//ul[@class='goods-price list']/li/span[@class='price1']/text()"
).extract()[0].encode('utf-8').replace("￥", "").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item['productImagePath'] = response.xpath(
"//div[@class='goodspic']/div[@class='goods-detail-pic']/a/img/@src"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath(
"//form[@id='form1']/ul/li[4]/text()").extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath(
"//div[@id='para']/table[1]/tbody[2]/tr/td/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = response.xpath("//span[@id='PDescriptiion']/text()").extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 1
for value_details in list_details:
value_details = value_details.encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\"", "").strip()
if num_one % 2 == 2:
num_one = 1
continue
if num_one % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one = 0
continue
if '型号' in value_details:
num_one = 0
continue
data2['attrkey'] = value_details
else:
if num_one == 0:
num_one = 1
continue
data2['keyname'] = value_details
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
product_intro = response.xpath(
"//span[@id='PDescription']/text()").extract()
product_pack = response.xpath(
"//td[@id='imgDiv']/div[@id='div3']/font/b/text()").extract()
product_details = response.xpath(
"//div[@id='goods-intro']/p/text()").extract()
filename = self.name + ".txt"
file = open("data/" + filename, 'a+')
file.write("\n" + "productUrl:" + response.url + "\n")
file.write("productDetails:" + "\n")
for details in product_details:
details = details.encode('utf-8').replace("\b", "").replace(
"<br/>", "").replace("<br>", "").strip()
file.write(details + "\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
print "PhantomJS is starting1..."
driver = webdriver.PhantomJS()
driver.get(response.url)
#time.sleep(3)
body = driver.page_source
#driver.close()
HtmlResponses = HtmlResponse(driver.current_url,
body=body,
encoding='utf-8',
request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//div[@id='product_information']/div[@class='product-titles']/h2/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath(
"//div[@class='product-concerns']/ul/li[@class='item'][3]/span[@class='detail']/i[@class='minor']/em[@class='action-mktprice']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productModel'] = response.xpath(
"//div[@class='product-concerns']/ul/li[@class='item'][4]/span[@class='detail']/i[@class='minor']/em[@class='action-mktprice']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@id='p_navbar']/a[2]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@id='p_navbar']/a[3]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@id='p_navbar']/a[4]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
item[
'productClassification'] = classification_one + '|||' + classification_two + '|||' + classification_three
except:
pass
try:
item['productPrice'] = HtmlResponses.xpath(
"//ins[@class='action-price']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
try:
ImagePath = response.xpath(
'//div[@class="product-album-pic"]/a/@href').extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
ImagePath = ImagePath.split('?')[-2]
item['productImagePath'] = ImagePath
except:
pass
try:
item['productAddres'] = response.xpath(
"//form[@id='form1']/ul/li[4]/text()").extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath(
"//div[@id='product_detail']/div[@class='product-attributes']/ul[@class='clearfix']/li/text()"
).extract()
details = response.xpath(
"//ul[@class='inLeft_attributes']/li/span/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
logging.info("-------details_len=%i" % len(details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = response.xpath("//span[@id='PDescription']/text()").extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 1
for value_details in list_details:
value_details = value_details.encode('utf-8').replace(
"\"", "\'").strip()
if '品牌' in value_details:
continue
else:
details = value_details.split('：')
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = details[0]
data2['keyname'] = details[1]
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath(
"//div[@class='layout']/div[@class='path']/a[2]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='layout']/div[@class='path']/a[3]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='layout']/div[@class='path']/a[4]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productUrl'] = response.url
try:
item['productName'] = response.xpath(
"//div[@class='prodetails']/h1[@class='protitle']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
list_brand = []
try:
list_brand = response.xpath(
"//ul[@class='list2 clf']/li[@class='itm']/span[@class='dt']/text()"
).extract()
for j in range(1, len(list_brand)):
brand = response.xpath(
"//ul[@class='list2 clf']/li[@class='itm'][%i]/span[@class='dt']/text()"
% j).extract()[0].encode('utf-8')
model = response.xpath(
"//ul[@class='list2 clf']/li[@class='itm'][%i]/span[@class='dt']/text()"
% j).extract()[0].encode('utf-8')
if '品牌' in brand:
item['productBrand'] = response.xpath(
"//ul[@class='list1 clf']/li[@class='itm'][%i]/span[@class='dd']/text()"
% j).extract()[0].encode('utf-8').replace(
"\"", "\'").strip()
if '型号' in model:
item['productModel'] = response.xpath(
"//ul[@class='list1 clf']/li[@class='itm'][%i]/span[@class='dd']/text()"
% j).extract()[0].encode('utf-8').replace(
"\"", "\'").strip()
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
price = response.xpath("//em[@class='prc']/b/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
if price == '':
price = '0.0'
except:
pass
try:
item['productPrice'] = str(
float(filter(lambda ch: ch in '0123456789.~', price)) * 100)
except:
pass
try:
item['productImagePath'] = "http:" + response.xpath(
"//li[@class='img-itm active']/div[@class='img-box']/img/@src"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
item['productAddres'] = ""
item['productCompany'] = ""
names = self.name + '.json'
item['fileName'] = names
list_details = response.xpath(
"//ul[@class='list1 clf']/li[@class='itm']/span/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = response.xpath("//span[@id='PDescriptiion']/text()").extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 1
for value_details in list_details:
value_details = value_details.encode('utf-8').replace(
":", "").replace("\n", "").replace("\"", "").strip()
if num_one % 2 == 2:
num_one = 1
continue
if num_one % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one = 0
continue
if '型号' in value_details:
num_one = 0
continue
data2['attrkey'] = value_details
else:
if num_one == 0:
num_one = 1
continue
data2['keyname'] = value_details
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
product_details = response.xpath(
"//div[@class='pro-main']/div[@class='con'][1]/text()").extract()
filename = self.name + ".txt"
file = open("data/" + filename, 'a+')
file.write("\n" + "productUrl:" + response.url + "\n")
file.write("productDetails:" + "\n")
for details in product_details:
details = details.encode('utf-8').replace("\b", "").replace(
"<br/>", "").replace("<br>", "").strip()
file.write(details + "\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
details_list = []
pack_list = []
intro_list = []
speci_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath("//h1[@class='prodbaseinfo_title']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()+"eoriutqirwe"
except:
pass
try:
item['productBrand'] = response.xpath("//ul[@class='ul_list']/li[@class='fg14'][1]/div[1]/a/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productModel'] = response.xpath("//ul[@class='ul_list']/li[@class='fg14'][2]/p/font/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
classification_one = response.xpath("//div[@class='location']/a[2]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_two = response.xpath("//div[@class='location']/a[3]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_three = response.xpath("//div[@class='location']/a[4]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
item['productClassification'] = classification_one + '|||' + classification_two + '|||' +classification_three
except:
pass
try:
item['productPrice'] = response.xpath("//ul[@class='ul_list']/li[@class='fg14'][3]/p/span[@id='attr_price']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productPrice'] = str(float(filter(lambda ch: ch in '0123456789.~', item['productPrice']))*100)
except:
pass
try:
item['productImagePath'] = response.xpath('//div[@id="wrap"]/a/@href').extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name+'.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath("//div[@id='para']/table[1]/tbody[2]/tr/td/text()").extract()
logging.info("-------list_details_len=%i" %len(list_details))
list_pack = response.xpath("//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()").extract()
intro = []
try:
intro_p = response.xpath("//li[@class='pb10p']/blockquote/table[2]/tbody/tr/td/p/text()").extract()
logging.info("-------intro_p_len=%i" %len(intro_p))
intro = response.xpath("//li[@class='pb10pppp']/blockquote/table[2]/tbody/tr/td/text()").extract()
logging.info("-------intro_len=%i" %len(intro))
except:
pass
speci = []
try:
speci_p = response.xpath("//li[@class='pb10p']/blockquote/table[2]/td/p/text()").extract()
logging.info("-------speci_p_len=%i" %len(speci_p))
speci = response.xpath("//li[@class='pb10pppp']/blockquote/table[2]/tbody/text()").extract()
logging.info("-------speci_len=%i" %len(speci))
except:
pass
num_one=1
for value_details in list_details :
value_details = value_details.encode('utf-8').replace(":","\/").replace("\n","").replace("\"","").strip()
if num_one%2==2 :
num_one = 1
continue
if num_one%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one=0
continue
if '型号' in value_details:
num_one=0
continue
data2['attrkey']=value_details
else:
if num_one ==0:
num_one = 1
continue
data2['keyname']=value_details
details_list.append(data2)
num_one+=1
num_two=1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n","").replace(":","").strip()
if num_two%2==1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '型号' in list_intro:
num_two +=1
continue
data2['attrkey']=list_intro
else:
if num_two == 3:
num_two +=1
continue
data2['keyname']=list_intro
if num_two == 4:
num_two =6
continue
intro_list.append(data2)
num_two +=1
num_three=1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n","").replace("\"","").strip()
if num_three%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in list_speci:
break
if '品牌' in list_speci:
break
data2['attrkey']=list_speci
else:
data2['keyname']=list_speci
speci_list.append(data2)
num_three+=1
intro_file = response.xpath("//li[@class='pb10p']/blockquote/table[2]/tbody/tr/td/text()").extract()
filename = self.name+".txt"
file = open("data/"+filename, 'a+')
file.write("\n"+"productUrl:"+response.url+"\n")
file.write("\n"+"productIntro:"+"\n")
for list_intro in intro_file:
list_intro = list_intro.encode('utf-8').replace("\n","").replace(":","").strip()
file.write(list_intro+"\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
details_list = []
pack_list = []
intro_list = []
speci_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
'//div[@class="goods_info"]/div/h1/text()').extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
brand = ''
try:
brand = response.xpath(
"//div[@id='con_goods_1']/ul[@class='detail-list']/li[3]/a/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
item['productBrand'] = brand
try:
item['productModel'] = response.xpath(
'//div[@class="m m1"]/div/ul/dt/li/text()').extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@class='breadcrumb']/a[2]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='breadcrumb']/a[3]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='breadcrumb']/a[4]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productClassification'] = classification
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath(
'//strong[@class="p-price"]/font/text()').extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item[
'productImagePath'] = "http://www.91yilong.com" + response.xpath(
'//div[@class="goods_img"]/a/@href').extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath(
"//div[@id='para']/table[1]/tbody[2]/tr/td/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = response.xpath(
"//div[@id='con_goods_1']/ul[@class='detail-list']/li/text()"
).extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath(
"//div[@id='con_goods_2']/ul/li/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 1
for value_details in list_details:
value_details = value_details.encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\"", "").strip()
if num_one % 2 == 2:
num_one = 1
continue
if num_one % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one = 0
continue
if '型号' in value_details:
num_one = 0
continue
data2['attrkey'] = value_details
else:
if num_one == 0:
num_one = 1
continue
data2['keyname'] = value_details
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
print "PhantomJS is starting..."
driver = webdriver.PhantomJS()
# driver = webdriver.Chrome()
driver.get(response.url)
time.sleep(3)
body = driver.page_source
#driver.close()
HtmlResponses = HtmlResponse(driver.current_url, body=body, encoding='utf-8', request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = HtmlResponses.xpath("//div[@class='detail-goods-right']/h1[@class='detail-goods-right-head ft18 J_title']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productBrand'] = HtmlResponses.xpath("//div[@class='main-width bread-top-main J_bread']/a[2]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
if '京东' in item['productBrand']:
item['productBrand'] = ''
except:
pass
try:
item['productModel'] = HtmlResponses.xpath("//div[@class='detail-goods-right']/div[@class='detail-goods-right-list m-top15 J_goods']/span[2]/label/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
classification_one = response.xpath("//div[@id='ur_here']/a[2]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_two = response.xpath("//div[@id='ur_here']/a[3]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_three = response.xpath("//div[@id='ur_here']/a[4]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
item['productClassification'] = classification_one + '|||' + classification_two + '|||' +classification_three
except:
pass
try:
#去空格 转分 去人民币符号
item['productPrice'] = HtmlResponses.xpath("//div[@class='detail-goods-right']/div[@class='detail-goods-price m-top15']/ul/li[1]/label[@class='ft24 a weight J_salePrice']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productPrice'] = str(float(filter(lambda ch: ch in '0123456789.~', item['productPrice']))*100)
except:
pass
#图片连接
try:
item['productImagePath'] = HtmlResponses.xpath('//div[@class="detail-goods-left"]/div[1]/img/@src').extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath("//form[@id='form1']/ul/li[4]/text()").extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name+'.json'
try:
item['fileName'] = names
except:
pass
list_details = HtmlResponses.xpath("//div[@class='J_shows']/table/tbody/tr/td/text()").extract()
logging.info("-------list_details_len=%i" %len(list_details))
list_pack = response.xpath("//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()").extract()
intro = response.xpath("//span[@id='PDescriptiion']/text()").extract()
logging.info("-------intr_len=%i" %len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" %len(speci))
num_one=1
for value_details in list_details :
value_details = value_details.encode('utf-8').replace(":","\/").replace("\n","").replace("\"","").strip()
if num_one%2==2 :
num_one = 1
continue
if num_one%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one=0
continue
if '型号' in value_details:
num_one=0
continue
data2['attrkey']=value_details
else:
if num_one ==0:
num_one = 1
continue
data2['keyname']=value_details
details_list.append(data2)
num_one+=1
num_two=1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n","").replace("\"","").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro :
if num_two%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey']=value_intro
else:
data2['keyname']=value_intro
intro_list.append(data2)
num_two+=1
num_three=1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n","").replace("\"","").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci :
if num_three%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey']=value_speci
else:
data2['keyname']=value_speci
speci_list.append(data2)
num_three+=1
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath("//div[@class='goods_content_a_l_r f_l']/div[@class='title']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath("//div[@class='goods_content_a_l_r f_l']/div[4]/span[@class='brand']/a/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productModel'] = response.xpath('//div[@class="m m1"]/div/ul/dt/li/text()').extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
classification_one = response.xpath("//div[@class='position w1000']/a[2]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_two = response.xpath("//div[@class='position w1000']/a[3]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_three = response.xpath("//div[@class='position w1000']/a[4]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' +classification_three
item['productClassification'] = classification
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath("//span[@class='goods_price weiruanyahei']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productPrice'] = str(float(filter(lambda ch: ch in '0123456789.~', item['productPrice']))*100)
except:
pass
#图片连接
try:
item['productImagePath'] = "http://www.deppre.cn/" + response.xpath('//div[@class="img_center_div"]/div/a/img/@src').extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath("//div[@class='goods_content_a_l_r f_l']/div[@class='score'][1]/span[@class='brand']/text()").extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name+'.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath("//div[@id='para']/table[1]/tbody[2]/tr/td/text()").extract()
logging.info("-------list_details_len=%i" %len(list_details))
list_pack = response.xpath("//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()").extract()
intro = response.xpath("//span[@id='PDescriptiion']/text()").extract()
logging.info("-------intr_len=%i" %len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" %len(speci))
num_one=1
for value_details in list_details :
value_details = value_details.encode('utf-8').replace(":","\/").replace("\n","").replace("\"","").strip()
if num_one%2==2 :
num_one = 1
continue
if num_one%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one=0
continue
if '型号' in value_details:
num_one=0
continue
data2['attrkey']=value_details
else:
if num_one ==0:
num_one = 1
continue
data2['keyname']=value_details
details_list.append(data2)
num_one+=1
num_two=1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n","").replace("\"","").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro :
if num_two%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey']=value_intro
else:
data2['keyname']=value_intro
intro_list.append(data2)
num_two+=1
num_three=1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n","").replace("\"","").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci :
if num_three%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey']=value_speci
else:
data2['keyname']=value_speci
speci_list.append(data2)
num_three+=1
product_intro = response.xpath("//div[@class='goods_content_c_r_b_b clearfix']/span/text()").extract()
product_pack = response.xpath("//td[@id='imgDiv']/div[@id='div3']/font/b/text()").extract()
filename = self.name+".txt"
file = open("data/"+filename, 'a+')
file.write("\n"+"productUrl:"+response.url+"\n")
file.write("productIntro:"+"\n")
for intro in product_intro:
intro = intro.encode('utf-8').replace("\b","").replace("<br/>","").replace("<br>","").strip()
file.write(intro+"\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
p = open('aa.html', 'a+')
p.write(response.body)
item = BaseItem()
details_list = []
pack_list = []
intro_list = []
speci_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
print "PhantomJS is starting1..."
driver = webdriver.PhantomJS()
driver.get(response.url)
#time.sleep(3)
body = driver.page_source
#driver.close()
HtmlResponses = HtmlResponse(driver.current_url,
body=body,
encoding='utf-8',
request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = HtmlResponses.xpath(
"//h1[@class='ware_title']/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
brand = ''
try:
brand = HtmlResponses.xpath("//div[@class='ware_text']/div/text()"
)[3].extract().encode('utf-8').replace(
"\r\n", "\'").strip()
except:
pass
item['productBrand'] = brand
model = ''
try:
model = HtmlResponses.xpath("//div[@class='ware_text']/div/text()"
).extract()[6].encode('utf-8').strip()
if '型号' in model:
item['productModel'] = HtmlResponses.xpath(
"//div[@class='ware_text']/div/text()").extract(
)[6].encode('utf-8').replace("型号:", "").strip()
else:
item['productModel'] = HtmlResponses.xpath(
"//div[@class='ware_text']/div/text()").extract(
)[5].encode('utf-8').replace("型号:", "").strip()
except:
pass
try:
classification_one = HtmlResponses.xpath(
"//div[@id='head']/div[@id='path']/a[2]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
classification_two = HtmlResponses.xpath(
"//div[@id='head']/div[@id='path']/a[3]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
classification_three = HtmlResponses.xpath(
"//div[@id='head']/div[@id='path']/a[4]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
if classification not in self.data1:
self.data1.append(classification)
item['productClassification'] = classification
try:
item['productPrice'] = response.xpath(
"//div[@class='rate']/span[@class='fontColor3'][2]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
try:
item['productImagePath'] = response.xpath(
'//span[@class="jqzoom"]/img/@src').extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_details = HtmlResponses.xpath(
"//div[@id='para']/table[1]/tbody[2]/tr/td/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
list_pack = HtmlResponses.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = HtmlResponses.xpath(
"//div[@id='para']/p[2]/font/text()").extract()
logging.info("-------intr_len=%i" % len(intro))
driver.close
num_one = 1
for value_details in list_details:
value_details = value_details.encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\"", "").strip()
if num_one % 2 == 2:
num_one = 1
continue
if num_one % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one = 0
continue
if '型号' in value_details:
num_one = 0
continue
data2['attrkey'] = value_details
else:
if num_one == 0:
num_one = 1
continue
data2['keyname'] = value_details
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace(":", "\/").replace(
"\n", "").replace("\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = intro_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//form[@id='ECS_FORMBUY']/ul/li[1]/dd/div/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath(
"//ul[@class='ul1']/li[@class='clearfix'][2]/dd/div[@class='f_r goos_news']/a/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productModel'] = response.xpath(
"//ul[@class='ul1']/li[@class='clearfix'][3]/dd/div[@class='f_l']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@id='ur_here']/a[2]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@id='ur_here']/a[3]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@id='ur_here']/a[4]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
item[
'productClassification'] = classification_one + '|||' + classification_two + '|||' + classification_three
except:
pass
try:
item['productPrice'] = response.xpath(
"//font[@id='ECS_SHOPPRICE']/text()").extract()[1].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#ͼƬÁ¬½Ó
try:
item[
'productImagePath'] = "http://www.sssmro.com/" + response.xpath(
'//div[@id="preview"]/div[@class="jqzoom"]/img/@src'
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
test_specis = response.xpath(
"//div[@id='main1']/blockquote[2]/div[@class='qyjstxt']/text()"
).extract()
logging.info("-------specis_len=%i" % len(test_specis))
test_details = response.xpath(
"//blockquote[@class='block']/div[@class='qyjstxt']/text()"
).extract()
logging.info("-------details_len=%i" % len(test_details))
specis = ''
try:
specis = response.xpath(
"//div[@id='main1']/blockquote[2]/div[@class='qyjst']/text()"
).extract()[0].encode('utf-8').replace("\n",
"").replace("\"",
"").strip()
except:
pass
list_speci = specis.split('£º')
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specisParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
num_one = 1
for speci in list_speci:
if num_one % 2 == 0:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = speci
else:
if num_one == 1:
num_one += 1
continue
data2['keyname'] = speci
speci_list.append(data2)
num_one += 1
num_two = 1
for value_pack in list_pack:
value_pack = value_pack.encode('utf-8').replace(":", "\/").replace(
"\n", "").replace("\"", "").strip()
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = value_pack
else:
data2['keyname'] = value_pack
pack_list.append(data2)
num_two += 1
product_intro = response.xpath(
"//div[@class='formwork_bt'][1]/p/text()").extract()
filename = self.name + ".txt"
file = open("data/" + filename, 'a+')
file.write("\n" + "productUrl:" + response.url + "\n")
file.write("productIntro:" + "\n")
for intro in product_intro:
intro = intro.encode('utf-8').replace("\"", "").strip()
file.write(intro + "\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = intro_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//div[@id='name']/h1/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath(
"//li[@id='summary-brand']/div[@class='dd']/a/em[@class='hl_red bold']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productModel'] = response.xpath(
'//div[@class="m m1"]/div/ul/dt/li/text()').extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@id='part_content']/div[@class='node_path']/a[3]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@id='part_content']/div[@class='node_path']/a[4]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@id='part_content']/div[@class='node_path']/a[5]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productClassification'] = classification
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath(
"//li[@id='summary-price']/div[@class='dd']/strong/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item['productImagePath'] = response.xpath(
'//div[@id="spec-n1"]/a/@href').extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath(
"//div[@class='goods_content_a_l_r f_l']/div[@class='score'][1]/span[@class='brand']/text()"
).extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
test_specis = response.xpath(
"//div[@id='main1']/blockquote[2]/div[@class='qyjstxt']/text()"
).extract()
logging.info("-------specis_len=%i" % len(test_specis))
test_details = response.xpath(
"//blockquote[@class='block']/div[@class='qyjstxt']/text()"
).extract()
logging.info("-------details_len=%i" % len(test_details))
specis = ''
try:
specis = response.xpath(
"//div[@id='main1']/blockquote[2]/div[@class='qyjst']/text()"
).extract()[0].encode('utf-8').replace("\n",
"").replace("\"",
"").strip()
except:
pass
list_speci = specis.split('：')
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specisParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
num_one = 1
for speci in list_speci:
if num_one % 2 == 0:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = speci
else:
if num_one == 1:
num_one += 1
continue
data2['keyname'] = speci
speci_list.append(data2)
num_one += 1
num_two = 1
for value_pack in list_pack:
value_pack = value_pack.encode('utf-8').replace(":", "\/").replace(
"\n", "").replace("\"", "").strip()
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = value_pack
else:
data2['keyname'] = value_pack
pack_list.append(data2)
num_two += 1
product_intro = response.xpath(
"//div[@id='content_product']/div[@class='property']/text()"
).extract()
filename = self.name + ".txt"
file = open("data/" + filename, 'a+')
file.write("\n" + "productUrl:" + response.url + "\n")
file.write("productIntro:" + "\n")
for intro in product_intro:
intro = intro.encode('utf-8').replace("\"", "").strip()
file.write(intro + "\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = intro_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
print "PhantomJS is starting1..."
#driver = webdriver.PhantomJS()
driver = webdriver.PhantomJS()
driver.get(response.url)
time.sleep(3)
body = driver.page_source
#driver.close()
HtmlResponses = HtmlResponse(driver.current_url,
body=body,
encoding='utf-8',
request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = HtmlResponses.xpath(
"//h1[@id='comTitle']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
list_brand = ''
for j in range(1, 20):
try:
list_brand = response.xpath(
"//div[@id='pdetail']/div/table/tr[%i]/th/h4/text()" %
j).extract()[0].encode('utf-8').replace("\"",
"\'").strip()
if '品牌：' in list_brand:
item['productBrand'] = response.xpath(
"//div[@id='pdetail']/div/table/tr[%i]/td/text()" %
j).extract()[0].encode('utf-8').replace("\"",
"\'").strip()
break
except:
pass
list_model = ''
for j in range(1, 20):
try:
list_model = response.xpath(
"//div[@id='pdetail']/div/table/tr[%i]/th/h4/text()" %
j).extract()[0].encode('utf-8').replace("\"",
"\'").strip()
if '型号：' in list_model:
item['productModel'] = response.xpath(
"//div[@id='pdetail']/div/table/tr[%i]/td/text()" %
j).extract()[0].encode('utf-8').replace("\"",
"\'").strip()
break
except:
pass
try:
classification_one = response.xpath(
"//div[@id='head']/div[@id='path']/a[2]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@id='head']/div[@id='path']/a[3]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@id='head']/div[@id='path']/a[4]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productClassification'] = classification
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath(
"//div[@id='oriPriceTop']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item['productImagePath'] = HtmlResponses.xpath(
"//a[@id='imgContainer']/@hrefs").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath(
"//div[@id='pdetail']/div[@class='d-vopy']/table/tbody/tr[4]/td/text()"
).extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
item['productAddres'] = ""
item['productCompany'] = ""
names = self.name + '.json'
item['fileName'] = names
list_details = response.xpath(
"//div[@class='d-vopy']/table/tr/th/h4/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
details = response.xpath(
"//div[@class='d-vopy']/table/tr/td/text()").extract()
logging.info("-------details_len=%i" % len(details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
list_intro = response.xpath(
"//table[@class='goods-items']/tr[1]/th/text()").extract()
logging.info("-------list_intro_len=%i" % len(list_intro))
intro = response.xpath(
"//div[@class='goods']/table[@class='goods-items']/tr[2]/td/text()"
).extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 0
for list_details_value in list_details:
list_details_value = list_details_value.encode('utf-8').replace(
"\n", "").replace("\"", "").strip()
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in list_details_value:
num_one += 1
continue
if '价格' in list_details_value:
num_one += 1
continue
if '供应商' in list_details_value:
num_one = 0
continue
if '保修期' in list_details_value:
break
data2['attrkey'] = list_details_value
data2['keyname'] = details[num_one]
details_list.append(data2)
num_one += 1
num_two = 0
for list_intro_value in list_intro:
list_intro_value = list_intro_value.encode('utf-8').replace(
"\n", "").replace("\"", "").strip()
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in list_intro_value:
num_two += 1
continue
if '价格' in list_intro_value:
num_two += 1
continue
if '供应商' in list_intro_value:
num_two = 0
continue
if '保修期' in list_intro_value:
break
data2['attrkey'] = list_intro_value
data2['keyname'] = intro[num_two]
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath("//div[@class='g_position']/a[2]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_two = response.xpath("//div[@class='g_position']/a[3]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_three = response.xpath("//div[@class='g_position']/a[4]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' +classification_three
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath('//div[@class="pd_l_cont clearfix"]/div[1]/a/h1/text()').extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
brand = ''
list_brand = []
for j in range(1,20):
try:
list_brand = response.xpath("//div[@class='pd_param clearfix']/ul/li[%i]/text()" %j).extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
if "品牌" in list_brand:
brand = response.xpath("//div[@class='pd_param clearfix']/ul/li[%i]/span/text()" %j).extract()[0].encode('utf-8').replace("\"","\'").strip()
break
item['productBrand'] = brand
try:
item['productModel'] = response.xpath("//div[@class='pd_param clearfix']/ul/li[2]/span/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath("//div[@class='pd_l clearfix']/div[@class='pd_l_cont clearfix'][1]/div[@class='pd_info']/ul[@class='pd_info_supplier']/li[4]//span[@class='f_red']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
if item['productPrice'] == '面议':
item['productPrice'] = 0.0
except:
pass
try:
item['productPrice'] = str(float(filter(lambda ch: ch in '0123456789.~', item['productPrice']))*100)
except:
pass
#图片连接
try:
item['productImagePath'] = response.xpath("//img[@id='show_big']/@src").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath("//span[@class='address_over']/a/text()").extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name+'.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath("//div[@class='pd_param clearfix']/ul/li/text()").extract()
details = response.xpath("//div[@class='pd_param clearfix']/ul/li/span/text()").extract()
logging.info("-------list_details_len=%i" %len(list_details))
list_pack = response.xpath("//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()").extract()
intro = response.xpath("//span[@id='PDescription']/text()").extract()
logging.info("-------intr_len=%i" %len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" %len(speci))
num_one=0
for value_details in list_details :
value_details = value_details.encode('utf-8').replace(":","\/").replace("\n","").replace("\"","").strip()
if '品牌' in value_details:
num_one+=1
continue
if '型号' in value_details:
num_one+=1
continue
else:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey']=value_details
data2['keyname']=details[num_one]
details_list.append(data2)
num_one+=1
num_two=1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n","").replace("\"","").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro :
if num_two%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey']=value_intro
else:
data2['keyname']=value_intro
intro_list.append(data2)
num_two+=1
num_three=1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n","").replace("\"","").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci :
if num_three%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey']=value_speci
else:
data2['keyname']=value_speci
speci_list.append(data2)
num_three+=1
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//h1[@class='lh40 col59 f18']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
list_brand = ''
try:
list_brand = response.xpath(
"//tr[@class='keyValue'][1]/td[1]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
if '涂层手套' not in list_brand:
brand = response.xpath(
"//div[@class='detailAndBuy']/div[@class='detail'][1]/span[@class='typeValue']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
item['productBrand'] = brand.split(' ')[0]
else:
item['productBrand'] = response.xpath(
"//tr[@class='keyValue'][1]/td[2]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
filter(str.isalnum, item['productBrand'])
except:
pass
try:
item['productModel'] = response.xpath(
"//div[@class='cpzstm']/b/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@class='crumbs']/span[2]/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='crumbs']/span[3]/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='crumbs']/span[4]/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productClassification'] = classification
try:
item['productPrice'] = response.xpath(
"//span[@id='show-price']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
try:
item[
'productImagePath'] = 'http://www.zhaogongye.cn' + response.xpath(
"//span[@class='jqzoom']/img/@src").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
test_specis = response.xpath(
"//div[@id='main1']/blockquote[2]/div[@class='qyjstxt']/text()"
).extract()
logging.info("-------specis_len=%i" % len(test_specis))
test_details = response.xpath(
"//blockquote[@class='block']/div[@class='qyjstxt']/text()"
).extract()
logging.info("-------details_len=%i" % len(test_details))
specis = ''
try:
specis = response.xpath(
"//div[@id='main1']/blockquote[2]/div[@class='qyjst']/text()"
).extract()[0].encode('utf-8').replace("\n",
"").replace("\"",
"").strip()
except:
pass
list_speci = specis.split('：')
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specisParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
num_one = 1
for speci in list_speci:
if num_one % 2 == 0:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = speci
else:
if num_one == 1:
num_one += 1
continue
data2['keyname'] = speci
speci_list.append(data2)
num_one += 1
num_two = 1
for value_pack in list_pack:
value_pack = value_pack.encode('utf-8').replace(":", "\/").replace(
"\n", "").replace("\"", "").strip()
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = value_pack
else:
data2['keyname'] = value_pack
pack_list.append(data2)
num_two += 1
product_details = response.xpath(
"//blockquote[@class='block']/div[@class='qyjstxt']/text()"
).extract()
product_speci = response.xpath(
"//div[@id='main1']/blockquote[2]/div[@class='qyjstxt']/text()"
).extract()
filename = self.name + ".txt"
file = open("data/" + filename, 'a+')
file.write("\n" + "productUrl:" + response.url + "\n")
file.write("productDetails:" + "\n")
for details in product_details:
details = details.encode('utf-8').replace("\b", "").replace(
"<br/>", "").replace("<br>", "").strip()
file.write(details + "\n")
file.write("productSpeci:" + "\n")
for speci in product_speci:
speci = speci.encode('utf-8').replace("\"", "").strip()
file.write(speci + "\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = intro_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath(
"//div[@class='breadth']/div/a[3]/text()").extract()[0].encode(
'utf-8').replace(".", "").strip()
classification_two = response.xpath(
"//div[@class='position w1000']/a[3]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='position w1000']/a[4]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
#print "PhantomJS is starting1..."
#driver = webdriver.PhantomJS()
#driver.get(response.url)
#time.sleep(3)
#body = driver.page_source
#driver.close()
#HtmlResponses = HtmlResponse(driver.current_url, body=body, encoding='utf-8', request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//div[@class='corpus_left']/div/h3/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath(
"//div[@class='intro']/table/tr[4]/td[2]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productModel'] = response.xpath(
"//div[@class='intro']/table/tr[1]/td[2]/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath(
"//div[@class='intro']/table/tr[3]/td[2]/b/text()").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item[
'productImagePath'] = "http://www.rolymro.com/" + response.xpath(
"//div[@class='sphoto']/a[@class='sphoto']/img/@src"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath(
"//div[@id='pdetail']/div[@class='d-vopy']/table/tbody/tr[4]/td/text()"
).extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath(
"//table[@class='table_pro_info']/tr/td[1]/text()").extract()
details = response.xpath(
"//table[@class='table_pro_info']/tr/td[2]/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
logging.info("-------details_len=%i" % len(details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = response.xpath("//span[@id='PDescription']/text()").extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 0
for value_details in list_details:
value_details = value_details.encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\t",
"").replace("\b",
"").strip()
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '产品单价' in value_details:
num_one += 2
continue
if '品牌' in value_details:
num_one += 1
continue
if '型号' in value_details:
num_one += 1
continue
data2['attrkey'] = value_details
data2['keyname'] = details[num_one].encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\t",
"").replace("\b",
"").strip()
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace(
"\r\n\t", "").replace("\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
product_intro = response.xpath(
"//span[@id='PDescription']/text()").extract()
product_pack = response.xpath(
"//td[@id='imgDiv']/div[@id='div3']/font/b/text()").extract()
filename = self.name + ".txt"
file = open("data/" + filename, 'a+')
file.write("\n" + "productUrl:" + response.url + "\n")
file.write("productIntro:" + "\n")
for intro in product_intro:
intro = intro.encode('utf-8').replace("\b", "").replace(
"<br/>", "").replace("<br>", "").strip()
file.write(intro + "\n")
file.write("productPack:" + "\n")
for pack in product_pack:
pack = pack.encode('utf-8').replace("\"", "").strip()
file.write(pack + "\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
#Analytical framework
sel = Selector(response)
#Loop body
speci_list = []
pack_list = []
intro_list = []
details_list = []
productClassification=""
productName=""
productBrand=""
productModel=""
productPrice=""
productImagePath=""
productAddres=""
productId=""
productCompany=""
productPack=""
price=""
fileName="www_ispek_cn_data_info.json"
#Instantiation CrawlertoolsItem object
item=BaseItem()
#Parse text
productImagePath=sel.xpath(".//*[@id='picshower']/img/@src").extract()[0]
if len(sel.xpath(".//div[@id='sample-table-2_wrapper']")) == 0:
try:
tempSel=sel.xpath(".//*[@id='main-container']/div/div[1]/div[1]/a")
i=1
classificationStr=""
while i < len(tempSel):
classificationStr=classificationStr+tempSel[i].xpath("text()").extract()[0].strip()+"|||"
i+=1
productClassification=classificationStr.rstrip("|||")
tempSel=sel.xpath(".//*[@id='main-container']/div/div[1]/div[2]/div[2]")
if len(tempSel.xpath("form")):
tempSel=tempSel.xpath("form")
temps=tempSel.xpath("div[1]/div[1]/span/text()")[0].extract()
productPrice=temps.split("/")[0].strip()
productPrice=filter(lambda ch: ch in '0123456789.', productPrice)
productCompany=temps.split("/")[1]
else:
temps=tempSel.xpath("div[1]/div[1]/text()")[0].extract().strip()
productPrice=filter(lambda ch: ch in '0123456789.~', temps).split("~")
productCompany=""
productName=tempSel.xpath("h2/text()").extract()[0]
productBrand=tempSel.xpath("div[2]/div/div[1]/a/text()").extract()[0]
tempSel=tempSel.xpath("div[2]/div/div")
i=2
while i<len(tempSel):
tempStr=""
tempStr=tempSel[i].xpath("text()").extract()[0].strip().split(u"：")
if tempStr[0]==u"型号":
productModel=tempStr[1]
if tempStr[0]==u"产地":
productAddres=tempStr[1]
if tempStr[0]==u"包装":
productPack=tempStr[1]
i+=1
prices=productPrice.encode('utf-8').replace("\"","\'").strip().split("~")
if len(prices) >1:
price=str(float(prices[0])*100)+"~"+str(float(prices[1])*100)
else:
price=str(float(prices[0])*100)
except Exception,e:
print "-----------------yichang--------------->",e
#Formatted data
item['productUrl']=response.url
item['productImagePath'] = "http://www.ispek.cn"+productImagePath.encode('utf-8').replace("\"","\'").strip()
item['productClassification'] =productClassification.encode('utf-8').replace("\"","\'").strip()
item['productName'] =productName.encode('utf-8').replace("\"","\'").strip()
item['productBrand'] =productBrand.encode('utf-8').replace("\"","\'").strip()
item['productModel'] =productModel.encode('utf-8').replace("\"","\'").strip()
item['productAddres'] =productAddres.encode('utf-8').replace("\"","\'").strip()
item['productCompany'] =productCompany.encode('utf-8').replace("\"","\'").strip()
item['productPrice'] =price
item['fileName']=fileName
item['productDetails']=""
item['productPack']=productPack.encode('utf-8').replace("\"","\'").strip()
item['productIntro']=""
item['productSpeci']=""
yield item
>>>>>>> 7235bd3b1c4452496ce81c35a74b003805fe6394
=======
>>>>>>> 7235bd3b1c4452496ce81c35a74b003805fe6394
productName=""
productBrand=""
productModel=""
productPrice=""
productImagePath=""
productId=""
productCompany=""
temps=""
productDetails=""
productPack=""
fileName="zc_mrobay_com_data_info.json"
#Instantiation CrawlertoolsItem object
item=BaseItem()
#Parse text
productImagePath=sel.xpath(".//*[@id='showPic']/@src").extract()[0]
try:
tempSel=sel.xpath(".//div[@class='Xh_xq']")
productName=tempSel.xpath("h1/text()").extract()[0]
productBrand=tempSel.xpath("div[2]/div[2]/ul/li[3]/text()").extract()[0]
temps=tempSel.xpath("div[2]/div[2]/ul/li[1]/span/b/text()")[0].extract()
productPrice=str(float(filter(lambda ch: ch in '0123456789.~', temps))*100)
productCompany=u"套"
productModel=tempSel.xpath("div[2]/div[2]/ul/li[4]/p[1]/text()")[0].extract()
except Exception,e:
print "-----------------yichang--------------->",e
try:
productPack=sel.xpath(".//div[5]/div/div[2]/div[2]/ul/li[9]/text()").extract()[0]
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
#print "PhantomJS is starting1..."
#driver = webdriver.PhantomJS()
#driver.get(response.url)
#time.sleep(3)
#body = driver.page_source
#HtmlResponses = HtmlResponse(driver.current_url, body=body, encoding='utf-8', request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//h1[@id='title']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@class='pos']/a[3]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='pos']/a[4]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='pos']/a[5]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productClassification'] = classification
try:
item['productPrice'] = response.xpath(
"//span[@class='f_price px16']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
try:
imagePath = response.xpath("//div[@id='mid_div']/img/@src"
).extract()[0].encode('utf-8').replace(
"\"", "\'").strip()
item['productImagePath'] = imagePath
except:
pass
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
print "PhantomJS is starting1..."
driver = webdriver.PhantomJS()
driver.get(response.url)
time.sleep(3)
body = driver.page_source
HtmlResponses = HtmlResponse(driver.current_url,
body=body,
encoding='utf-8',
request=response)
list_brand = HtmlResponses.xpath(
"//table/tbody/tr/td[2]/table/tbody/tr/td/table/tbody/tr/td[1]"
).extract()
list_speci_th = response.xpath(
"//div[@class='col-xs-12 nopadding border-ccc attrDiv']/div/p/text()"
).extract()
list_detail = response.xpath("//div[@id='content']").extract()
logging.info("----------list_detail_len=%i" % len(list_detail))
list_intro = response.xpath(
"//div[@id='tbc_13']/div[@class='intro_box']").extract()
logging.info("----------list_intro_len=%i" % len(list_intro))
for j in range(1, len(list_brand)):
brand = HtmlResponses.xpath(
"//table/tbody/tr/td[2]/table/tbody/tr/td/table/tbody/tr[%i]/td[1]/text()"
% j).extract()[0].encode('utf-8').replace(":", "\/").replace(
"\n", "").replace("\"", "").strip()
if "型号" in brand:
item['productModel'] = HtmlResponses.xpath(
"//table/tbody/tr[2]/td[3]/table/tbody/tr[%i]/td[2]/a[@class='b']/text()"
% j).extract()[0].encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\"", "").strip()
continue
if "品牌" in brand:
item['productBrand'] = HtmlResponses.xpath(
"//table/tbody/tr[2]/td[3]/table/tbody/tr[%i]/td[2]/a[@class='b']/text()"
% j).extract()[0].encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\"", "").strip()
break
driver.close()
#11.28
brand = ''
try:
brand = response.xpath(
"//dl[@class='pro-info-prop pro-info-brand']/dd[@class='pro-info-cons']/text()"
).extract()[0].encode('utf-8').replace("\t", "").replace(
"\n", "").replace("\b", "").replace("\r", "").strip()
item['productBrand'] = brand
except:
pass
model = ''
try:
model = response.xpath(
"//dl[@class='pro-info-prop pro-info-model']/dd[@class='pro-info-cons']/text()"
).extract()[0].encode('utf-8').replace("\t", "").replace(
"\n", "").replace("\b", "").strip()
item['productModel'] = model
except:
pass
#11.28
for value_detail in list_detail:
value_detail = value_detail.encode('utf-8').replace(
"\t", "").replace("\n", "").replace("\b", "").replace(
"<br>", "").replace("</br>", "").replace("\r", "").strip()
dr = re.compile(r'<[^>]+>', re.S)
dd_value_detail = dr.sub('', value_detail)
details_list.append(dd_value_detail)
cancel = ''
try:
cancel_l = response.xpath(
"//p[@class='link-detail']/text()").extract()
for cancel_s in cancel_l:
cancel_s = cancel_s.encode('utf-8').replace("\t", "").replace(
"\n", "").replace("\b", "").replace("<br>", "").replace(
"</br>", "").replace("\r", "").strip()
cancel += cancel_s
except:
pass
for value_intro in list_intro:
value_intro = value_intro.encode('utf-8').replace(
"\t", "").replace("\n", "").replace("\b", "").replace(
"<br>", "").replace("</br>", "").replace("\r", "").strip()
value_intro.replace(cancel, '')
dr = re.compile(r'<[^>]+>', re.S)
dd_value_intro = dr.sub('', value_intro)
intro_list.append(dd_value_intro)
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath("//div[@class='w-fly-cnt']/div[@class='position']/a[2]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_two = response.xpath("//div[@class='w-fly-cnt']/div[@class='position']/a[3]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
classification_three = response.xpath("//div[@class='w-fly-cnt']/div[@class='position']/a[4]/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' +classification_three
item['productUrl'] = response.url
try:
item['productName'] = response.xpath("//div[@class='prodetails']/h1[@class='protitle']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath('//ul[@class="list_pic"]/li/dl/dt/a/text()').extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productModel'] = response.xpath("//div[@class='fn-fr']/div[@class='add-to-basket']/dl[@class='fn-clearfix atb-dl-01']/dd/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
price=response.xpath("//font[@id='ECS_GOODS_AMOUNT']/text()").extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
try:
item['productPrice'] = str(float(filter(lambda ch: ch in '0123456789.~', price))*100)
except:
pass
try:
item['productImagePath'] = "http://www.isweek.cn/"+response.xpath('//a[@class="jqzoom"]/img/@src').extract()[0].encode('utf-8').replace("\"","\'").strip()
except:
pass
item['productAddres'] = ""
item['productCompany'] = ""
names = self.name+'.json'
item['fileName'] = names
list_details = response.xpath("//div[@id='para']/table[1]/tbody[2]/tr/td/text()").extract()
logging.info("-------list_details_len=%i" %len(list_details))
list_pack = response.xpath("//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()").extract()
intro = response.xpath("//span[@id='PDescriptiion']/text()").extract()
logging.info("-------intr_len=%i" %len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" %len(speci))
num_one=1
for value_details in list_details :
value_details = value_details.encode('utf-8').replace(":","\/").replace("\n","").replace("\"","").strip()
if num_one%2==2 :
num_one = 1
continue
if num_one%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one=0
continue
if '型号' in value_details:
num_one=0
continue
data2['attrkey']=value_details
else:
if num_one ==0:
num_one = 1
continue
data2['keyname']=value_details
details_list.append(data2)
num_one+=1
num_two=1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n","").replace("\"","").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro :
if num_two%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey']=value_intro
else:
data2['keyname']=value_intro
intro_list.append(data2)
num_two+=1
num_three=1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n","").replace("\"","").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci :
if num_three%2==1 :
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey']=value_speci
else:
data2['keyname']=value_speci
speci_list.append(data2)
num_three+=1
product_intro = response.xpath("//div[@class='prodesc']/p/span/text()").extract()
product_pack = response.xpath("//td[@id='imgDiv']/div[@id='div3']/font/b/text()").extract()
product_speci = response.xpath("//div[@class='fn-fr']/div[@class='info']/p/text()").extract()
filename = self.name+".txt"
file = open("data/"+filename, 'a+')
file.write("\n"+"productUrl:"+response.url+"\n")
file.write("productIntro:"+"\n")
for intro in product_intro:
intro = intro.encode('utf-8').replace("\b","").replace("<br/>","").replace("<br>","").strip()
file.write(intro+"\n")
file.write("productSpeci:"+"\n")
for speci in product_speci:
speci = speci.encode('utf-8').replace("\"","").strip()
file.write(speci+"\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath(
"//div[@id='Public_breadCrumb01-110']/a[@class='arrowbg1']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@id='Public_breadCrumb01-110']/a[@class='arrowbg2']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@id='Public_breadCrumb01-110']/a[@class='arrowbg3']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//div[@id='ProductDetail_basic01-101']/h1[@class='htmlinline']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath(
'//ul[@class="list_pic"]/li/dl/dt/a/text()').extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productModel'] = response.xpath(
"//li[@class='number']/em/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath(
"//li[@class='retailprice']/em/strong").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item[
'productImagePath'] = "http://www.ieou.com.cn" + response.xpath(
'//div[@class="jqzoom"]/img/@src').extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath(
"//div[@id='pdetail']/div[@class='d-vopy']/table/tbody/tr[4]/td/text()"
).extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath(
"//div[@class='extend']/ul/li/label/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
details = response.xpath(
"//div[@class='extend']/ul/li/span/text()").extract()
logging.info("-------details_len=%i" % len(details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = response.xpath(
"//div[@class='descreibe htmledit']/ul/li/span/span/text()"
).extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath(
"//div[@class='desceribe htmleit']/ul/li/span/span/span/text()"
).extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 0
for value_details in list_details:
value_details = value_details.encode('utf-8').replace(
":", "").replace("\n", "").replace("\"", "").strip()
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one += 1
continue
if '型号' in value_details:
num_one += 1
continue
data2['attrkey'] = value_details
data2['keyname'] = details[num_one].encode('utf-8').replace(
":", "").replace("\n", "").replace("\"", "").strip()
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
product_intro = response.xpath(
"//div[@class='describe htmledit']/ul/li/span/span/text()"
).extract()
product_details = response.xpath(
"//div[@class='describe htmledit']/p/span/text()").extract()
product_speci = response.xpath(
"//div[@class='describe htmledit']/p/span/strong/text()").extract(
)
if len(product_speci) == 0:
product_speci = response.xpath(
"//div[@class='describe htmledit']/p/strong/span/text()"
).extract()
product_pack = response.xpath(
"//td[@id='imgDiv']/div[@id='div3']/font/b/text()").extract()
filename = self.name + ".txt"
file = open("data/" + filename, 'a+')
file.write("\n" + "productUrl:" + response.url + "\n")
file.write("productIntro:" + "\n")
for intro in product_intro:
intro = intro.encode('utf-8').replace("\b", "").replace(
"<br/>", "").replace("<br>", "").strip()
file.write(intro + "\n")
file.write("productDetails:" + "\n")
for details in product_details:
details = details.encode('utf-8').replace("\"", "").strip()
file.write(details + "\n")
file.write("productSpeci:" + "\n")
for speci in product_speci:
speci = speci.encode('utf-8').replace("\"", "").strip()
file.write(speci + "\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
print "PhantomJS is starting1..."
driver = webdriver.PhantomJS()
driver.get(response.url)
time.sleep(3)
body = driver.page_source
HtmlResponses = HtmlResponse(driver.current_url,
body=body,
encoding='utf-8',
request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = HtmlResponses.xpath(
"//div[@class='panel-heading panel-heading-div']/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@class='crumbs']/span[2]/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='crumbs']/span[3]/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='crumbs']/span[4]/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productClassification'] = classification
try:
item['productPrice'] = HtmlResponses.xpath(
"//font[@class='price-font'][2]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
try:
item['productImagePath'] = HtmlResponses.xpath(
"//img[@id='zoomimg']/@src").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_speci_tr = HtmlResponses.xpath(
"//div[@class='col-xs-12 nopadding border-ccc attrDiv']/div/b/text()"
).extract()
list_speci_th = HtmlResponses.xpath(
"//div[@class='col-xs-12 nopadding border-ccc attrDiv']/div/p/text()"
).extract()
list_detail = HtmlResponses.xpath(
"//div[@id='prd-desc-mdeditor']/p/text()").extract()
driver.close()
num_one = 0
for value_speci in list_speci_tr:
data2 = {}
value_speci = value_speci.encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\"", "").strip()
if "型号" in value_speci:
item['productModel'] = list_speci_th[num_one]
num_one += 1
continue
if "品牌" in value_speci:
item['productBrand'] = list_speci_th[num_one]
num_one += 1
continue
data2['attrkey'] = value_speci
data2['keyname'] = list_speci_th[num_one]
speci_list.append(data2)
num_one += 1
#11.28
brand = ''
try:
brand = HtmlResponses.xpath(
"//div[@class='form-group margin-left_53 margin-bottom-0'][1]/div/p/font/text()"
).extract()[0].encode('utf-8').replace("\t", "").replace(
"\n", "").replace("\b", "").strip()
if '/' in brand and item['productBrand'] == '':
item['productBrand'] = brand.split('/')[0]
else:
item['productBrand'] = brand
except:
pass
model = ''
try:
model = HtmlResponses.xpath(
"//div[@class='form-group margin-left_53 margin-bottom-0'][1]/div/p/font/text()"
).extract()[0].encode('utf-8').replace("\t", "").replace(
"\n", "").replace("\b", "").strip()
if '/' in brand and item['productModel'] == '':
item['productModel'] = model.split('/')[1]
except:
pass
#11.28
detail = ' '
for value_detail in list_detail:
value_detail = value_detail.encode('utf-8').replace(
"\t",
"").replace("\n",
"").replace("\b",
"").replace("<br>",
"").replace("</br>",
"").strip()
detail += value_detail
details_list.append(detail)
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
#print "PhantomJS is starting1..."
#driver = webdriver.PhantomJS()
#driver.get(response.url)
#time.sleep(3)
#body = driver.page_source
#HtmlResponses = HtmlResponse(driver.current_url, body=body, encoding='utf-8', request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//span[@id='productMainName']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@class='bread-crumb']/a[2]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='bread-crumb']/a[3]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='bread-crumb']/a[4]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productClassification'] = classification
try:
item['productPrice'] = response.xpath(
"//strong[@class='prodet']/b/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
try:
imagePath = response.xpath("//img[@id='productImg']/@src").extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
item['productImagePath'] = 'http://mro.abiz.com' + imagePath
except:
pass
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_speci_tr = response.xpath(
"//div[@class='col-xs-12 nopadding border-ccc attrDiv']/div/b/text()"
).extract()
list_speci_th = response.xpath(
"//div[@class='col-xs-12 nopadding border-ccc attrDiv']/div/p/text()"
).extract()
list_detail = response.xpath(
"//div[@id='tbc_11']/div[@class='intro_box']").extract()
logging.info("----------list_detail_len=%i" % len(list_detail))
list_intro = response.xpath(
"//div[@id='tbc_13']/div[@class='intro_box']").extract()
logging.info("----------list_intro_len=%i" % len(list_intro))
num_one = 0
for value_speci in list_speci_tr:
data2 = {}
value_speci = value_speci.encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\"", "").strip()
if "型号" in value_speci:
item['productModel'] = list_speci_th[num_one]
num_one += 1
continue
if "品牌" in value_speci:
item['productBrand'] = list_speci_th[num_one]
num_one += 1
continue
data2['attrkey'] = value_speci
data2['keyname'] = list_speci_th[num_one]
speci_list.append(data2)
num_one += 1
#11.28
brand = ''
try:
brand = response.xpath(
"//dl[@class='pro-info-prop pro-info-brand']/dd[@class='pro-info-cons']/text()"
).extract()[0].encode('utf-8').replace("\t", "").replace(
"\n", "").replace("\b", "").replace("\r", "").strip()
item['productBrand'] = brand
except:
pass
model = ''
try:
model = response.xpath(
"//dl[@class='pro-info-prop pro-info-model']/dd[@class='pro-info-cons']/text()"
).extract()[0].encode('utf-8').replace("\t", "").replace(
"\n", "").replace("\b", "").strip()
item['productModel'] = model
except:
pass
#11.28
for value_detail in list_detail:
value_detail = value_detail.encode('utf-8').replace(
"\t", "").replace("\n", "").replace("\b", "").replace(
"<br>", "").replace("</br>", "").replace("\r", "").strip()
dr = re.compile(r'<[^>]+>', re.S)
dd_value_detail = dr.sub('', value_detail)
details_list.append(dd_value_detail)
cancel = ''
try:
cancel_l = response.xpath(
"//p[@class='link-detail']/text()").extract()
for cancel_s in cancel_l:
cancel_s = cancel_s.encode('utf-8').replace("\t", "").replace(
"\n", "").replace("\b", "").replace("<br>", "").replace(
"</br>", "").replace("\r", "").strip()
cancel += cancel_s
except:
pass
for value_intro in list_intro:
value_intro = value_intro.encode('utf-8').replace(
"\t", "").replace("\n", "").replace("\b", "").replace(
"<br>", "").replace("</br>", "").replace("\r", "").strip()
value_intro.replace(cancel, '')
dr = re.compile(r'<[^>]+>', re.S)
dd_value_intro = dr.sub('', value_intro)
intro_list.append(dd_value_intro)
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath(
"//div[@class='subNav']/a[3]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='subNav']/a[4]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='subNav']/a[5]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//div[@class='proDiv']/dl[@class='proDl']/dt/b/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath(
"//div[@class='proDiv']/dl[@class='proDl']/dd[3]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
item['productBrand'] = item['productBrand'].replace('产品品牌：', '')
except:
pass
try:
item['productModel'] = response.xpath(
"//div[@class='proDiv']/dl[@class='proDl']/dd[2]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
item['productModel'] = item['productModel'].replace('原始型号：', '')
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
#去空格 转分 去人民币符号
item['productPrice'] = response.xpath(
"//div[@class='proDiv']/dl[@class='proDl']/dd[4]/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
item['productPrice'] = item['productPrice'].replace('价格：', '')
if item['productPrice'] == '询价':
item['productPrice'] = 0.0
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item[
'productImagePath'] = "http://www.btone-mro.com" + response.xpath(
"//img[@id='ctl00_ContentPlaceHolder1_imgMain']/@src"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath(
"//form[@id='form1']/ul/li[4]/text()").extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath(
"//div[@id='para']/table[1]/tbody[2]/tr/td/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = response.xpath("//span[@id='PDescription']/text()").extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 1
for value_details in list_details:
value_details = value_details.encode('utf-8').replace(
":", "\/").replace("\n", "").replace("\"", "").strip()
if num_one % 2 == 2:
num_one = 1
continue
if num_one % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in value_details:
num_one = 0
continue
if '型号' in value_details:
num_one = 0
continue
data2['attrkey'] = value_details
else:
if num_one == 0:
num_one = 1
continue
data2['keyname'] = value_details
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
product_intro = response.xpath(
"//div[@class='proNavInfo proNav1']/p[2]/text()").extract()
product_pack = response.xpath(
"//div[@class='proNavInfo proNav3']/p/text()").extract()
product_speci = response.xpath(
"//div[@class='proNavInfo proNav2']/p/text()").extract()
filename = self.name + ".txt"
file = open("data/" + filename, 'a+')
file.write("\n" + "productUrl:" + response.url + "\n")
file.write("productIntro:" + "\n")
for intro in product_intro:
intro = intro.encode('utf-8').replace("\b", "").replace(
"<br/>", "").replace("<br>", "").strip()
file.write(intro + "\n")
file.write("productPack:" + "\n")
for pack in product_pack:
pack = pack.encode('utf-8').replace("\"", "").strip()
file.write(pack + "\n")
file.write("productSpeci:" + "\n")
for speci in product_speci:
speci = speci.encode('utf-8').replace("\"", "").strip()
file.write(speci + "\n")
file.close()
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = intro_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//div[@class='center_title']/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath(
"//form[@id='ECS_FORMBUY_P']/div[@class='detail_center']/div[@class='center_txt']/div[@class='center_text']/p[1]/a/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productModel'] = response.xpath(
'//div[@class="m m1"]/div/ul/dt/li/text()').extract(
)[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
classification_one = response.xpath(
"//div[@class='location']/a[2]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='location']/a[3]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='location']/a[4]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
item['productClassification'] = classification
try:
item['productPrice'] = response.xpath(
"//div[@class='center_text']/ul[@class='tm-fcs-panel']/li[1]/span[@id='ECS_GOODS_AMOUNT']/span/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
try:
item[
'productImagePath'] = "http://www.1ez.com.cn/" + response.xpath(
'//img[@id="J_prodImg"]/@src').extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productAddres'] = ""
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
list_details = response.xpath(
"//ul[@class='inLeft_attributes']/li/text()").extract()
details = response.xpath(
"//ul[@class='inLeft_attributes']/li/span/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
logging.info("-------details_len=%i" % len(details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
intro = response.xpath("//span[@id='PDescription']/text()").extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 0
value_details = ''
for j in range(1, len(list_details)):
try:
value_details = response.xpath(
"//ul[@class='inLeft_attributes']/li[%i]/text()" %
j).extract()[0].encode('utf-8').replace(":", "").replace(
"\"", "").replace("：", "").strip()
except:
break
if '品牌' in value_details:
num_one += 1
continue
if '商品名称' in value_details:
num_one += 1
continue
if '型号' in value_details:
num_one += 1
continue
else:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
data2['attrkey'] = value_details
data2['keyname'] = details[num_one]
details_list.append(data2)
num_one += 1
num_two = 1
for list_intro in intro:
list_intro = list_intro.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_intro = list_intro.split('：')
for value_intro in list_intro:
if num_two % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_intro:
break
if '品牌' in value_intro:
break
data2['attrkey'] = value_intro
else:
data2['keyname'] = value_intro
intro_list.append(data2)
num_two += 1
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
def parse(self, response):
item = BaseItem()
speci_list = []
pack_list = []
intro_list = []
details_list = []
item['productUrl'] = ''
item['productName'] = ''
item['productBrand'] = ''
item['productModel'] = ''
item['productClassification'] = ''
item['productPrice'] = ''
item['productImagePath'] = ''
item['productAddres'] = ""
item['productCompany'] = ''
item['fileName'] = ''
item['productDetails'] = ""
item['productPack'] = ""
item['productIntro'] = ""
item['productSpeci'] = ""
classification_one = ''
classification_two = ''
classification_three = ''
try:
classification_one = response.xpath(
"//div[@class='siteUrl']/a[2]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_two = response.xpath(
"//div[@class='siteUrl']/a[3]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
classification_three = response.xpath(
"//div[@class='siteUrl']/a[4]/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
classification = classification_one + '|||' + classification_two + '|||' + classification_three
print "PhantomJS is starting1..."
driver = webdriver.PhantomJS()
driver.get(response.url)
#time.sleep(3)
body = driver.page_source
#driver.close()
HtmlResponses = HtmlResponse(driver.current_url,
body=body,
encoding='utf-8',
request=response)
try:
item['productUrl'] = response.url
except:
pass
try:
item['productName'] = response.xpath(
"//div[@class='hd']/div/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productBrand'] = response.xpath(
"//div[@class='dd']/em/a/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productModel'] = response.xpath(
"//form[@id='ECS_FORMBUY']/div[@class='proInfo f_R']/div[@class='bd']/ul/li[2]/div[@class='dd']/em/text()"
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productClassification'] = classification
except:
pass
try:
#去空格 转分 去人民币符号
item['productPrice'] = HtmlResponses.xpath(
"//b[@id='ECS_GOODS_AMOUNT']/text()").extract()[0].encode(
'utf-8').replace("\"", "\'").strip()
except:
pass
try:
item['productPrice'] = str(
float(
filter(lambda ch: ch in '0123456789.~',
item['productPrice'])) * 100)
except:
pass
#图片连接
try:
item['productImagePath'] = "http://www.huaaomro.com/" + HtmlResponses.xpath(
'//div[@class="proSide f_L"]/div[@class="bd"]/img[@id="idImage2"]/@src'
).extract()[0].encode('utf-8').replace("\"", "\'").strip()
except:
pass
#print item['image_urls'],"777777"
try:
item['productAddres'] = response.xpath(
"//div[@id='pdetail']/div[@class='d-vopy']/table/tbody/tr[4]/td/text()"
).extract()[0]
except:
pass
try:
item['productCompany'] = ""
except:
pass
names = self.name + '.json'
try:
item['fileName'] = names
except:
pass
item['productAddres'] = ""
item['productCompany'] = ""
names = self.name + '.json'
item['fileName'] = names
list_details = response.xpath(
"//div[@class='d-vopy']/table/tr/th/h4/text()").extract()
logging.info("-------list_details_len=%i" % len(list_details))
details = response.xpath(
"//div[@class='d-vopy']/table/tr/td/text()").extract()
logging.info("-------details_len=%i" % len(details))
list_pack = response.xpath(
"//div[@class='packageParameter tabContent']/div[@class='specsParameter-wrap']/table[@class='standardTable']/tbody/tr[@class='keyValue']/td/text()"
).extract()
list_intro = response.xpath(
"//ul[@class='detail-list clearfix']/li/text()").extract()
logging.info("-------list_intro_len=%i" % len(list_intro))
intro = response.xpath(
"//div[@class='goods']/table[@class='goods-items']/tr[2]/td/text()"
).extract()
logging.info("-------intr_len=%i" % len(intro))
speci = response.xpath("//span[@id='techParam']/text()").extract()
logging.info("-------intr_len=%i" % len(speci))
num_one = 0
for list_details_value in list_details:
list_details_value = list_details_value.encode('utf-8').replace(
"\n", "").replace("\"", "").strip()
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '品牌' in list_details_value:
num_one += 1
continue
if '价格' in list_details_value:
num_one += 1
continue
if '供应商' in list_details_value:
num_one = 0
continue
if '保修期' in list_details_value:
break
data2['attrkey'] = list_details_value
data2['keyname'] = details[num_one]
details_list.append(data2)
num_one += 1
for list_intro_value in list_intro:
list_intro_value = list_intro_value.encode('utf-8').replace(
"\n", "").strip()
intro = list_intro_value.split('：')
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品品牌' in intro[0]:
continue
if '商品型号' in intro[0]:
continue
if '商品名称' in intro[0]:
continue
data2['attrkey'] = intro[0]
data2['keyname'] = intro[1]
intro_list.append(data2)
num_three = 1
for list_speci in speci:
list_speci = list_speci.encode('utf-8').replace("\n", "").replace(
"\"", "").strip()
list_speci = list_speci.split('：')
for value_speci in list_speci:
if num_three % 2 == 1:
data2 = {}
data2['attrkey'] = ''
data2['keyname'] = ''
if '商品名称' in value_speci:
break
if '品牌' in value_speci:
break
data2['attrkey'] = value_speci
else:
data2['keyname'] = value_speci
speci_list.append(data2)
num_three += 1
item['productSpeci'] = speci_list
item['productPack'] = pack_list
item['productIntro'] = intro_list
item['productDetails'] = details_list
yield item
